Self-Learning Digital Twins for Sustainable Land Management
Lead Research Organisation:
University of Leicester
Department Name: Sch of Geog, Geol & the Environment
Abstract
Greenhouse gas emissions from agriculture and land use in the UK contribute to global climate change. The UK is committed to achieving net zero greenhouse gas emissions by 2050. Since 1990, greenhouse gas emissions from agriculture and land use have fallen, but in 2020 and 2021 they started rising again. 11% of UK GHG emissions stem from cattle and sheep grazing (7%) and degraded peatlands (4%).
This research project is developing an Artificial Intelligence algorithm called a 'Self-Learning Digital Twin' for sustainable land management. A Digital Twin applies computational modelling, environmental measurements and an Artificial Intelligence algorithm to provide new environmental insights into the functioning of a system. Farmers and land managers can ask questions that the Digital Twin can answer. In a nutshell, it is a digital model of the physical environment and is updated from real-time data, so that it mirrors the environment at all times. Digital Twins can support farmers and environmental managers to achieve better outcomes for their greenhouse gas emission reductions, ultimately saving time and resources.
The self-learning digital twin learns from real-time satellite images, greenhouse gas measurements from field instruments and other data. Its underlying model improves over time as new data are becoming available.
The project will promote sustainable cattle and sheep farming practices and peatland restoration. We will prepare the ground for an ethical and socially responsible application of artificial intelligence for achieving net zero greenhouse gas emissions. An important part of our work is to build a 'Community of Practice in AI for Net Zero' that brings together computer scientists with environmental, behavioural and social science researchers to develop a common approach. We will incorporate the social and ethical dimensions of digital twins, including who they may benefit or disadvantage.
This research project is developing an Artificial Intelligence algorithm called a 'Self-Learning Digital Twin' for sustainable land management. A Digital Twin applies computational modelling, environmental measurements and an Artificial Intelligence algorithm to provide new environmental insights into the functioning of a system. Farmers and land managers can ask questions that the Digital Twin can answer. In a nutshell, it is a digital model of the physical environment and is updated from real-time data, so that it mirrors the environment at all times. Digital Twins can support farmers and environmental managers to achieve better outcomes for their greenhouse gas emission reductions, ultimately saving time and resources.
The self-learning digital twin learns from real-time satellite images, greenhouse gas measurements from field instruments and other data. Its underlying model improves over time as new data are becoming available.
The project will promote sustainable cattle and sheep farming practices and peatland restoration. We will prepare the ground for an ethical and socially responsible application of artificial intelligence for achieving net zero greenhouse gas emissions. An important part of our work is to build a 'Community of Practice in AI for Net Zero' that brings together computer scientists with environmental, behavioural and social science researchers to develop a common approach. We will incorporate the social and ethical dimensions of digital twins, including who they may benefit or disadvantage.
Organisations
- University of Leicester (Lead Research Organisation)
- Cranfield University (Collaboration)
- OPEN UNIVERSITY (Collaboration)
- Glenfield Hospital (Collaboration)
- BT Group (Collaboration)
- CGI (Collaboration)
- UK CENTRE FOR ECOLOGY & HYDROLOGY (Collaboration)
- British Geological Survey (Collaboration)
- University of Warwick (Collaboration)
- Animal and Plant Health Agency (Collaboration)
- Alan Turing Institute (Collaboration)
- UNIVERSITY OF BIRMINGHAM (Collaboration)
- Rothamsted Research (Collaboration)
- FNK Designs (Project Partner)
- Silvasheep (Project Partner)
- Planet Labs (Project Partner)
- The Cattle Information Service (Project Partner)
- CGI Global (Project Partner)
- Maxar Technologies (Project Partner)
- Geospatial Insight Ltd (Project Partner)
- National Centre for Earth Observation (Project Partner)
Publications
Bashar Alhnaity
(2024)
A multi-head self-attention LSTM model for UK methane prediction
Davis U.
(2024)
Land: The Hidden Unknown of Food Waste
Fillola E
(2023)
A machine learning emulator for Lagrangian particle dispersion model footprints: a case study using NAME
in Geoscientific Model Development
Lloyd I
(2023)
State of Knowledge on UK Agricultural Peatlands for Food Production and the Net Zero Transition
in Sustainability
| Description | Based on the system model for a self-learning digital twin based on artificial intelligence that we developed in this project, we have implemented a suite of models that predict net ecosystem exchange. The individual models include an Earth Observation-based machine learning model that has validated rigorously with flux towers, a JULES-CROP land surface emulator model (validation in progress), and an integrated model that combines the best features from both component models. This prototype of the digital twin gives estimates of net ecosystem exchange from drained peatlands under agricultural land use at field scale for past climate data (CHESS-Met), ongoing weather predictions (OpenMeteo), and future climate scenarios (CHESS-SCAPE). The key findings have been presented to farmers in The Fens at the Fenland Soil conference 2025 in Ely in a participatory workshop. Loughborough University has developed AI predictive models for greenhouse gas emission prediction associated with ruminant farming. Built on farm-scale data, it incorporates pasture management, feeding strategies, and animal-specific insights. At its core, the digital twin highlights greenhouse gas emissions, focusing on methane, ammonia (a major air pollutant), and nitrous oxide. Additionally, methane emissions associated with land use are analysed using satellite observations at a national scale, integrating environmental and climate factors. The research highlights the increasing methane emissions in recent years and their strong association with agricultural land use and farming practices. The AI models and tools are integrated into a digital platform. Designed for usability, the AI-powered platform offers intuitive visualisations, predictive modelling, and easy-to- interfaces. Users can adjust parameters, explore different factors, and receive data-driven insights. The research demonstrates the potential of AI-driven predictive analytics to track and understand long-term greenhouse gas emission trends and emphasises the importance of substantial data in enhancing analytical accuracy. Key findings and insights have been presented and shared with stakeholders and researchers across multiple disciplines at international conferences and national events. Both digital twins are hosted on the Bloc Hub cloud platform, which provides a visualisation and user interface. To evaluate model fluxes at larger scales, new national methane emissions estimates have been made using concentration observations, and an improved approach for assimilating very large satellite methane data has been developed based on the machine learning emulation of atmospheric transport simulators. |
| Exploitation Route | The digital twin is intended to provide information, data, insights, and knowledge to farmers, land users, and policy-makers in order to reduce greenhouse gas emissions from land use. We will be presenting the digital twin to the Defra peatland team and have shown it to farmers. |
| Sectors | Agriculture Food and Drink Environment |
| Description | We demonstrated the current version of the digital twin to farmers in a workshop at the Fenland Soil Conference in Ely on 29 January 2025 and gathered their feedback. This raised awareness around the greenhouse gas emission potential on drained peatland fields by choosing different crop types. |
| First Year Of Impact | 2025 |
| Sector | Agriculture, Food and Drink,Environment |
| Impact Types | Cultural Societal |
| Description | Contribution to the CEOS working group on AI and Machine Learning with Earth Observation Data |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| Description | Gemini Call Live - invited presentation |
| Geographic Reach | Multiple continents/international |
| Policy Influence Type | Contribution to new or improved professional practice |
| URL | https://cp.catapult.org.uk/event/gemini-call-live/ |
| Description | Oral evidence to House of Lords Environment and Climate Change Select Committee inquiry on methane |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| URL | https://parliamentlive.tv/event/index/cfba1e9b-1fa6-4182-86b7-2b2a52e3b18b |
| Description | Resolving the Energy-Food-Nature Trilemma in Land Use: The Role of Digitalisation and EU Policies |
| Geographic Reach | Europe |
| Policy Influence Type | Participation in a guidance/advisory committee |
| Description | AI technology and automated inspector for the discovery of new generation safe and effective herbicides |
| Amount | £186,000 (GBP) |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 03/2023 |
| End | 03/2025 |
| Description | AI-Powered Action Analysis for Sports Talent Identification |
| Amount | £287,000 (GBP) |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 03/2025 |
| End | 10/2027 |
| Description | AI-embedded railway passenger counting and information system |
| Amount | £487,000 (GBP) |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 01/2024 |
| End | 08/2026 |
| Description | Accelerating digital twin technology to deliver a prosperous net zero |
| Amount | £640,000 (GBP) |
| Funding ID | APP56593 |
| Organisation | United Kingdom Research and Innovation |
| Sector | Public |
| Country | United Kingdom |
| Start | 03/2025 |
| End | 10/2026 |
| Description | Global Methane Flux Inference using Emulated Atmospheric Transport |
| Amount | £840,000 (GBP) |
| Funding ID | NE/Z504294/1 |
| Organisation | Natural Environment Research Council |
| Sector | Public |
| Country | United Kingdom |
| Start | 04/2025 |
| End | 10/2028 |
| Description | Land Use for Net Zero (LUNZ) Hub |
| Amount | £6,250,000 (GBP) |
| Funding ID | BB/Y008723/1 |
| Organisation | United Kingdom Research and Innovation |
| Sector | Public |
| Country | United Kingdom |
| Start | 11/2023 |
| End | 03/2027 |
| Description | Self-learning AI-based digital twins for accelerating clinical care in respiratory emergency admissions (SLAIDER) |
| Amount | £619,667 (GBP) |
| Funding ID | EP/Y018281/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 09/2023 |
| End | 04/2025 |
| Title | AI-NetZero Psychological Alignment Measure |
| Description | The AI-NetZero Psychological Alignment Measure is a questionnaire designed to gauge farmers' attitudes, preparedness, and self-directed motivation towards adopting AI technologies for Net Zero farming initiatives. Like other similar instruments, it employs a Likert-type scale (1 = Strongly Disagree to 5 = Strongly Agree) and is divided into three major dimensions: Motivational Alignment (Items 1-4) Focuses on how farmers' personal and professional aspirations intersect with AI-driven farming practices. Examines the extent to which using AI for Net Zero solutions resonates with a farmer's sense of satisfaction and overall attitude. Operational Preparedness (Items 5-8) Evaluates access to information, resources, and practical strategies required for adopting AI in farming. Assesses whether farmers have a clear plan and the necessary support structures to implement AI for Net Zero objectives. Independent Innovativeness (Items 9-12) Explores a farmer's willingness to self-direct decisions, adapt current practices, and integrate AI solutions in line with personal values. Highlights the role of autonomy and proactive problem-solving when choosing to embrace AI-based technologies. |
| Type Of Material | Model of mechanisms or symptoms - human |
| Year Produced | 2025 |
| Provided To Others? | Yes |
| Impact | Altogether, this measure aims to identify how confident, ready, and intrinsically motivated farmers are to leverage AI for more sustainable and carbon-reduced agricultural processes, thereby offering a structured perspective on potential enablers or obstacles to technology-driven Net Zero farming. |
| URL | https://osf.io/preprints/osf/jyw86_v1 |
| Title | Integrated Motivation Model for Sustainable Farming Scale |
| Description | The Integrated Motivation Model for Sustainable Farming Scale is a questionnaire designed to capture farmers' motivations, attitudes, and perceived capabilities regarding sustainable, Net Zero-aligned farming practices. It uses a Likert-type format (from 1 = Strongly Disagree to 5 = Strongly Agree) and covers key dimensions such as: • Commitment and Stewardship - The farmer's sense of identity, pride, and values tied to Net Zero goals. • Readiness and Confidence - The perceived preparedness and self-efficacy for adopting or modifying farming methods to reduce environmental impact. • Incentive Engagement - Attitudes towards financial or other external incentives designed to encourage sustainable practices. • Climate Adaptation Competence - Beliefs in one's own skills and understanding of climate adaptation strategies relevant to agriculture. • Accountability and Reporting - Level of dedication to measuring and disclosing farming practices in line with Net Zero targets. • Community Influence - Recognition of the role local farming networks play in shaping sustainable activities. • Innovation and Technological Competence - Willingness and ability to integrate novel technologies to further Net Zero objectives. |
| Type Of Material | Model of mechanisms or symptoms - human |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | Overall, this scale provides a structured way to assess farmers' motivational drivers and potential barriers to implementing environmentally friendly and climate-resilient approaches on their farms, making it useful for research, policy development, and programme evaluation. |
| URL | https://doi.org/10.1371/journal.pone.0301881 |
| Title | Patent with BT on digital twins |
| Description | We have submitted a patent application that will allow digital twins to be used in building and operating large network in situ |
| Type Of Material | Improvements to research infrastructure |
| Year Produced | 2024 |
| Provided To Others? | No |
| Impact | We have assimilated data and physics models to lay the foundations of next generation of digital twins |
| Title | AI model for milk yield prediction based on biological characteristics and feeding strategies. |
| Description | Knowing expected milk yield can help dairy farmers in better decision-making and management. The objective of this study was to build and compare predictive models to forecast daily milk yield over a long duration. A machine-learning pipeline was provided and five baseline models as well as a novel stacking model were developed for the prediction of milk yield. The results showed that the overall performance of predictive models improved after proper feature selection, with an R2 value increased to 0.811, and a root mean squared error (RMSE) decreased to 3.627. The stacking model achieved the best performance with an R2 value of 0.85, a mean absolute error (MAE) of 2.537 and an RMSE of 3.236. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | This research provides benchmark information for the prediction of milk yield on the CowNflow dataset and identifies useful factors such as dry matter intake and lactation month in long-term milk yield prediction. |
| URL | https://repository.lboro.ac.uk/articles/conference_contribution/Stacking_ensemble_machine_learning_m... |
| Title | ML models to Predict Methane Emissions in Livestock Farming and using Environmental and Biological Variables |
| Description | Cattle livestock contribute to climate change through enteric methane production, making it essential to identify and validate methods for reducing methane emissions. This research correlates GreenFeed cattle methane measurements with farm environment data using the North Wyke Farm Platform (NWFP), a heavily instrumented research facility in the UK. The disparate datasets are combined into a machine-learning-ready dataset capable of mapping methane emissions in grams per day and grams per kilogram of live weight gain. Predictive models are then developed and evaluated for methane prediction. Experimental results indicate that Gradient Boosting achieved the highest accuracy (g/day: r=0.619, RMSE=51.8; g/kg live weight gain: r=0.562, RMSE=65.9). Explainable AI methods are applied to quantify how a broad selection of farm and animal characteristics contribute to methanogenesis. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | This research provides valuable insights into methane reduction in livestock farming through machine learning and quantitative analytical methods. |
| URL | https://repository.lboro.ac.uk/articles/conference_contribution/Utilizing_machine_learning_to_unders... |
| Description | Animal and Plant Health Agency (APHA) |
| Organisation | Animal and Plant Health Agency |
| Country | United Kingdom |
| Sector | Public |
| PI Contribution | Requesting aggregated cattle data from APHA for the digital twin development. |
| Collaborator Contribution | n/a |
| Impact | Requested Cattle Tracing System data for England aggregated at County Scale. |
| Start Year | 2024 |
| Description | CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 |
| Organisation | British Geological Survey |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Prof. Pat Heslop-Harrison attended the CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 and taught a Module "Farm Carbon Budgets - Storage, Inputs and Outputs". Cheltenham Project X: Farm Carbon Budgets - Storage, Inputs and Outputs There is an imperative to reduce greenhouse gas emissions, with a global target for reaching 'net-zero' by 2050. Farming or agriculture is responsible for substantial emissions of greenhouse gasses, and also has the potential to sequester carbon, going beyond the net-zero target. Non-agricultural land use also has effects on greenhouse gas emissions. Greenhouse gas emissions from agriculture and forestry are estimated to account for about a quarter of the global emissions, with emissions including methane, carbon dioxide, and nitrogen compounds. An appreciation of the greenhouse gas sources and sinks, their volume, and changes in status due to land use and environmental change is of fundamental importance. Methods of estimation of farm greenhouse gas emissions within the global carbon cycle is controversial. Approaches to reduce farm emissions are even more controversial at a political level, with EU proposals causing major demonstrations in the first months of 2024 and controversy within the UK (eg https://www.bbc.co.uk/news/uk-northern-ireland-68241023, "Beef cattle carbon emissions scheme 'could disadvantage us'") The Managing Director of the agriculture advisory service, Climate and Sustainability Group, says "Calculating the carbon footprint of a farm is a complex problem. What are the current metrics that exist for doing this and what are their shortcomings? Is there a need for a standardised metric? What are the gaps in the current scientific understanding of agricultural emissions calculations?", while the agricultural consultant Simon Ward comments "There are a number of problems with a farm-based calculations of greenhouse gas emissions. For some of the calculations the inputs are complex and detail is not available." (see, for example, the 'featured farmer question" which covers some of this CENTA project: https://farmpep.net/group/1164). A major greenhouse gas generated in agriculture is methane. This gas causes 80 time more global warming than carbon dioxide, and is particularly generated by ruminant animals such as cattle and sheep, from digestion of grass by microbial flora during rumination. Globally, methane emissions may account for 10% of emissions, and are very high in tropical pastures, representing a third of global agricultural area. In this project, we will visit publicly accessible areas of contrasting agricultural farms. We will combine our ground-based observations with map-based studies and calculations to estimate greenhouse gas emissions and capture, and energy balances, from various farm types. During the 'field campaign' of your speed PhD you will need to estimate the emissions (and flows) of greenhouse gasses associated with contrasting land uses - in particular, a dairy farm, an arable farm, a forestry plantation, a 'solar farm', and potentially other sites of your own choosing (this could include, for example, roadside verges, golf-courses, or even urban environment). You will also examine food energy outputs from these farms, and consider the greenhouse gas footprint of producing the equivalent food elsewhere and importing. This might include clearing tropical rain forest and import of soybean and grain, or of meat. You could also consider intensification of production (as has been done, eg, for dairying in UK since 2000) in the UK, and use of irrigated/protected (plastic or greenhouses; and maybe imported) crops of Gloucestershire/Herefordshire. You could also consider associated food waste/co-products, and food security (cf energy security, or lack of). We will compare the measurements and estimates we make with methods such as those available on-line: https://www.fwi.co.uk/business/business-management/agricultural-transition/4-popular-carbon-calculators-for-farms-compared (there are limited number of articles you can read free in Farmers Weekly so copy the article!). We will consider the results and policy implications for reaching net-zero, and taking into consideration the requirement for food production. |
| Collaborator Contribution | n/a |
| Impact | Teaching PhD students from the CENTA cohort. |
| Start Year | 2024 |
| Description | CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 |
| Organisation | Cranfield University |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Prof. Pat Heslop-Harrison attended the CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 and taught a Module "Farm Carbon Budgets - Storage, Inputs and Outputs". Cheltenham Project X: Farm Carbon Budgets - Storage, Inputs and Outputs There is an imperative to reduce greenhouse gas emissions, with a global target for reaching 'net-zero' by 2050. Farming or agriculture is responsible for substantial emissions of greenhouse gasses, and also has the potential to sequester carbon, going beyond the net-zero target. Non-agricultural land use also has effects on greenhouse gas emissions. Greenhouse gas emissions from agriculture and forestry are estimated to account for about a quarter of the global emissions, with emissions including methane, carbon dioxide, and nitrogen compounds. An appreciation of the greenhouse gas sources and sinks, their volume, and changes in status due to land use and environmental change is of fundamental importance. Methods of estimation of farm greenhouse gas emissions within the global carbon cycle is controversial. Approaches to reduce farm emissions are even more controversial at a political level, with EU proposals causing major demonstrations in the first months of 2024 and controversy within the UK (eg https://www.bbc.co.uk/news/uk-northern-ireland-68241023, "Beef cattle carbon emissions scheme 'could disadvantage us'") The Managing Director of the agriculture advisory service, Climate and Sustainability Group, says "Calculating the carbon footprint of a farm is a complex problem. What are the current metrics that exist for doing this and what are their shortcomings? Is there a need for a standardised metric? What are the gaps in the current scientific understanding of agricultural emissions calculations?", while the agricultural consultant Simon Ward comments "There are a number of problems with a farm-based calculations of greenhouse gas emissions. For some of the calculations the inputs are complex and detail is not available." (see, for example, the 'featured farmer question" which covers some of this CENTA project: https://farmpep.net/group/1164). A major greenhouse gas generated in agriculture is methane. This gas causes 80 time more global warming than carbon dioxide, and is particularly generated by ruminant animals such as cattle and sheep, from digestion of grass by microbial flora during rumination. Globally, methane emissions may account for 10% of emissions, and are very high in tropical pastures, representing a third of global agricultural area. In this project, we will visit publicly accessible areas of contrasting agricultural farms. We will combine our ground-based observations with map-based studies and calculations to estimate greenhouse gas emissions and capture, and energy balances, from various farm types. During the 'field campaign' of your speed PhD you will need to estimate the emissions (and flows) of greenhouse gasses associated with contrasting land uses - in particular, a dairy farm, an arable farm, a forestry plantation, a 'solar farm', and potentially other sites of your own choosing (this could include, for example, roadside verges, golf-courses, or even urban environment). You will also examine food energy outputs from these farms, and consider the greenhouse gas footprint of producing the equivalent food elsewhere and importing. This might include clearing tropical rain forest and import of soybean and grain, or of meat. You could also consider intensification of production (as has been done, eg, for dairying in UK since 2000) in the UK, and use of irrigated/protected (plastic or greenhouses; and maybe imported) crops of Gloucestershire/Herefordshire. You could also consider associated food waste/co-products, and food security (cf energy security, or lack of). We will compare the measurements and estimates we make with methods such as those available on-line: https://www.fwi.co.uk/business/business-management/agricultural-transition/4-popular-carbon-calculators-for-farms-compared (there are limited number of articles you can read free in Farmers Weekly so copy the article!). We will consider the results and policy implications for reaching net-zero, and taking into consideration the requirement for food production. |
| Collaborator Contribution | n/a |
| Impact | Teaching PhD students from the CENTA cohort. |
| Start Year | 2024 |
| Description | CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 |
| Organisation | Open University |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Prof. Pat Heslop-Harrison attended the CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 and taught a Module "Farm Carbon Budgets - Storage, Inputs and Outputs". Cheltenham Project X: Farm Carbon Budgets - Storage, Inputs and Outputs There is an imperative to reduce greenhouse gas emissions, with a global target for reaching 'net-zero' by 2050. Farming or agriculture is responsible for substantial emissions of greenhouse gasses, and also has the potential to sequester carbon, going beyond the net-zero target. Non-agricultural land use also has effects on greenhouse gas emissions. Greenhouse gas emissions from agriculture and forestry are estimated to account for about a quarter of the global emissions, with emissions including methane, carbon dioxide, and nitrogen compounds. An appreciation of the greenhouse gas sources and sinks, their volume, and changes in status due to land use and environmental change is of fundamental importance. Methods of estimation of farm greenhouse gas emissions within the global carbon cycle is controversial. Approaches to reduce farm emissions are even more controversial at a political level, with EU proposals causing major demonstrations in the first months of 2024 and controversy within the UK (eg https://www.bbc.co.uk/news/uk-northern-ireland-68241023, "Beef cattle carbon emissions scheme 'could disadvantage us'") The Managing Director of the agriculture advisory service, Climate and Sustainability Group, says "Calculating the carbon footprint of a farm is a complex problem. What are the current metrics that exist for doing this and what are their shortcomings? Is there a need for a standardised metric? What are the gaps in the current scientific understanding of agricultural emissions calculations?", while the agricultural consultant Simon Ward comments "There are a number of problems with a farm-based calculations of greenhouse gas emissions. For some of the calculations the inputs are complex and detail is not available." (see, for example, the 'featured farmer question" which covers some of this CENTA project: https://farmpep.net/group/1164). A major greenhouse gas generated in agriculture is methane. This gas causes 80 time more global warming than carbon dioxide, and is particularly generated by ruminant animals such as cattle and sheep, from digestion of grass by microbial flora during rumination. Globally, methane emissions may account for 10% of emissions, and are very high in tropical pastures, representing a third of global agricultural area. In this project, we will visit publicly accessible areas of contrasting agricultural farms. We will combine our ground-based observations with map-based studies and calculations to estimate greenhouse gas emissions and capture, and energy balances, from various farm types. During the 'field campaign' of your speed PhD you will need to estimate the emissions (and flows) of greenhouse gasses associated with contrasting land uses - in particular, a dairy farm, an arable farm, a forestry plantation, a 'solar farm', and potentially other sites of your own choosing (this could include, for example, roadside verges, golf-courses, or even urban environment). You will also examine food energy outputs from these farms, and consider the greenhouse gas footprint of producing the equivalent food elsewhere and importing. This might include clearing tropical rain forest and import of soybean and grain, or of meat. You could also consider intensification of production (as has been done, eg, for dairying in UK since 2000) in the UK, and use of irrigated/protected (plastic or greenhouses; and maybe imported) crops of Gloucestershire/Herefordshire. You could also consider associated food waste/co-products, and food security (cf energy security, or lack of). We will compare the measurements and estimates we make with methods such as those available on-line: https://www.fwi.co.uk/business/business-management/agricultural-transition/4-popular-carbon-calculators-for-farms-compared (there are limited number of articles you can read free in Farmers Weekly so copy the article!). We will consider the results and policy implications for reaching net-zero, and taking into consideration the requirement for food production. |
| Collaborator Contribution | n/a |
| Impact | Teaching PhD students from the CENTA cohort. |
| Start Year | 2024 |
| Description | CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 |
| Organisation | UK Centre for Ecology & Hydrology |
| Country | United Kingdom |
| Sector | Public |
| PI Contribution | Prof. Pat Heslop-Harrison attended the CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 and taught a Module "Farm Carbon Budgets - Storage, Inputs and Outputs". Cheltenham Project X: Farm Carbon Budgets - Storage, Inputs and Outputs There is an imperative to reduce greenhouse gas emissions, with a global target for reaching 'net-zero' by 2050. Farming or agriculture is responsible for substantial emissions of greenhouse gasses, and also has the potential to sequester carbon, going beyond the net-zero target. Non-agricultural land use also has effects on greenhouse gas emissions. Greenhouse gas emissions from agriculture and forestry are estimated to account for about a quarter of the global emissions, with emissions including methane, carbon dioxide, and nitrogen compounds. An appreciation of the greenhouse gas sources and sinks, their volume, and changes in status due to land use and environmental change is of fundamental importance. Methods of estimation of farm greenhouse gas emissions within the global carbon cycle is controversial. Approaches to reduce farm emissions are even more controversial at a political level, with EU proposals causing major demonstrations in the first months of 2024 and controversy within the UK (eg https://www.bbc.co.uk/news/uk-northern-ireland-68241023, "Beef cattle carbon emissions scheme 'could disadvantage us'") The Managing Director of the agriculture advisory service, Climate and Sustainability Group, says "Calculating the carbon footprint of a farm is a complex problem. What are the current metrics that exist for doing this and what are their shortcomings? Is there a need for a standardised metric? What are the gaps in the current scientific understanding of agricultural emissions calculations?", while the agricultural consultant Simon Ward comments "There are a number of problems with a farm-based calculations of greenhouse gas emissions. For some of the calculations the inputs are complex and detail is not available." (see, for example, the 'featured farmer question" which covers some of this CENTA project: https://farmpep.net/group/1164). A major greenhouse gas generated in agriculture is methane. This gas causes 80 time more global warming than carbon dioxide, and is particularly generated by ruminant animals such as cattle and sheep, from digestion of grass by microbial flora during rumination. Globally, methane emissions may account for 10% of emissions, and are very high in tropical pastures, representing a third of global agricultural area. In this project, we will visit publicly accessible areas of contrasting agricultural farms. We will combine our ground-based observations with map-based studies and calculations to estimate greenhouse gas emissions and capture, and energy balances, from various farm types. During the 'field campaign' of your speed PhD you will need to estimate the emissions (and flows) of greenhouse gasses associated with contrasting land uses - in particular, a dairy farm, an arable farm, a forestry plantation, a 'solar farm', and potentially other sites of your own choosing (this could include, for example, roadside verges, golf-courses, or even urban environment). You will also examine food energy outputs from these farms, and consider the greenhouse gas footprint of producing the equivalent food elsewhere and importing. This might include clearing tropical rain forest and import of soybean and grain, or of meat. You could also consider intensification of production (as has been done, eg, for dairying in UK since 2000) in the UK, and use of irrigated/protected (plastic or greenhouses; and maybe imported) crops of Gloucestershire/Herefordshire. You could also consider associated food waste/co-products, and food security (cf energy security, or lack of). We will compare the measurements and estimates we make with methods such as those available on-line: https://www.fwi.co.uk/business/business-management/agricultural-transition/4-popular-carbon-calculators-for-farms-compared (there are limited number of articles you can read free in Farmers Weekly so copy the article!). We will consider the results and policy implications for reaching net-zero, and taking into consideration the requirement for food production. |
| Collaborator Contribution | n/a |
| Impact | Teaching PhD students from the CENTA cohort. |
| Start Year | 2024 |
| Description | CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 |
| Organisation | University of Birmingham |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Prof. Pat Heslop-Harrison attended the CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 and taught a Module "Farm Carbon Budgets - Storage, Inputs and Outputs". Cheltenham Project X: Farm Carbon Budgets - Storage, Inputs and Outputs There is an imperative to reduce greenhouse gas emissions, with a global target for reaching 'net-zero' by 2050. Farming or agriculture is responsible for substantial emissions of greenhouse gasses, and also has the potential to sequester carbon, going beyond the net-zero target. Non-agricultural land use also has effects on greenhouse gas emissions. Greenhouse gas emissions from agriculture and forestry are estimated to account for about a quarter of the global emissions, with emissions including methane, carbon dioxide, and nitrogen compounds. An appreciation of the greenhouse gas sources and sinks, their volume, and changes in status due to land use and environmental change is of fundamental importance. Methods of estimation of farm greenhouse gas emissions within the global carbon cycle is controversial. Approaches to reduce farm emissions are even more controversial at a political level, with EU proposals causing major demonstrations in the first months of 2024 and controversy within the UK (eg https://www.bbc.co.uk/news/uk-northern-ireland-68241023, "Beef cattle carbon emissions scheme 'could disadvantage us'") The Managing Director of the agriculture advisory service, Climate and Sustainability Group, says "Calculating the carbon footprint of a farm is a complex problem. What are the current metrics that exist for doing this and what are their shortcomings? Is there a need for a standardised metric? What are the gaps in the current scientific understanding of agricultural emissions calculations?", while the agricultural consultant Simon Ward comments "There are a number of problems with a farm-based calculations of greenhouse gas emissions. For some of the calculations the inputs are complex and detail is not available." (see, for example, the 'featured farmer question" which covers some of this CENTA project: https://farmpep.net/group/1164). A major greenhouse gas generated in agriculture is methane. This gas causes 80 time more global warming than carbon dioxide, and is particularly generated by ruminant animals such as cattle and sheep, from digestion of grass by microbial flora during rumination. Globally, methane emissions may account for 10% of emissions, and are very high in tropical pastures, representing a third of global agricultural area. In this project, we will visit publicly accessible areas of contrasting agricultural farms. We will combine our ground-based observations with map-based studies and calculations to estimate greenhouse gas emissions and capture, and energy balances, from various farm types. During the 'field campaign' of your speed PhD you will need to estimate the emissions (and flows) of greenhouse gasses associated with contrasting land uses - in particular, a dairy farm, an arable farm, a forestry plantation, a 'solar farm', and potentially other sites of your own choosing (this could include, for example, roadside verges, golf-courses, or even urban environment). You will also examine food energy outputs from these farms, and consider the greenhouse gas footprint of producing the equivalent food elsewhere and importing. This might include clearing tropical rain forest and import of soybean and grain, or of meat. You could also consider intensification of production (as has been done, eg, for dairying in UK since 2000) in the UK, and use of irrigated/protected (plastic or greenhouses; and maybe imported) crops of Gloucestershire/Herefordshire. You could also consider associated food waste/co-products, and food security (cf energy security, or lack of). We will compare the measurements and estimates we make with methods such as those available on-line: https://www.fwi.co.uk/business/business-management/agricultural-transition/4-popular-carbon-calculators-for-farms-compared (there are limited number of articles you can read free in Farmers Weekly so copy the article!). We will consider the results and policy implications for reaching net-zero, and taking into consideration the requirement for food production. |
| Collaborator Contribution | n/a |
| Impact | Teaching PhD students from the CENTA cohort. |
| Start Year | 2024 |
| Description | CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 |
| Organisation | University of Warwick |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Prof. Pat Heslop-Harrison attended the CENTA Speed PhD residential field trip to Cheltenham from 18-22 March 2024 and taught a Module "Farm Carbon Budgets - Storage, Inputs and Outputs". Cheltenham Project X: Farm Carbon Budgets - Storage, Inputs and Outputs There is an imperative to reduce greenhouse gas emissions, with a global target for reaching 'net-zero' by 2050. Farming or agriculture is responsible for substantial emissions of greenhouse gasses, and also has the potential to sequester carbon, going beyond the net-zero target. Non-agricultural land use also has effects on greenhouse gas emissions. Greenhouse gas emissions from agriculture and forestry are estimated to account for about a quarter of the global emissions, with emissions including methane, carbon dioxide, and nitrogen compounds. An appreciation of the greenhouse gas sources and sinks, their volume, and changes in status due to land use and environmental change is of fundamental importance. Methods of estimation of farm greenhouse gas emissions within the global carbon cycle is controversial. Approaches to reduce farm emissions are even more controversial at a political level, with EU proposals causing major demonstrations in the first months of 2024 and controversy within the UK (eg https://www.bbc.co.uk/news/uk-northern-ireland-68241023, "Beef cattle carbon emissions scheme 'could disadvantage us'") The Managing Director of the agriculture advisory service, Climate and Sustainability Group, says "Calculating the carbon footprint of a farm is a complex problem. What are the current metrics that exist for doing this and what are their shortcomings? Is there a need for a standardised metric? What are the gaps in the current scientific understanding of agricultural emissions calculations?", while the agricultural consultant Simon Ward comments "There are a number of problems with a farm-based calculations of greenhouse gas emissions. For some of the calculations the inputs are complex and detail is not available." (see, for example, the 'featured farmer question" which covers some of this CENTA project: https://farmpep.net/group/1164). A major greenhouse gas generated in agriculture is methane. This gas causes 80 time more global warming than carbon dioxide, and is particularly generated by ruminant animals such as cattle and sheep, from digestion of grass by microbial flora during rumination. Globally, methane emissions may account for 10% of emissions, and are very high in tropical pastures, representing a third of global agricultural area. In this project, we will visit publicly accessible areas of contrasting agricultural farms. We will combine our ground-based observations with map-based studies and calculations to estimate greenhouse gas emissions and capture, and energy balances, from various farm types. During the 'field campaign' of your speed PhD you will need to estimate the emissions (and flows) of greenhouse gasses associated with contrasting land uses - in particular, a dairy farm, an arable farm, a forestry plantation, a 'solar farm', and potentially other sites of your own choosing (this could include, for example, roadside verges, golf-courses, or even urban environment). You will also examine food energy outputs from these farms, and consider the greenhouse gas footprint of producing the equivalent food elsewhere and importing. This might include clearing tropical rain forest and import of soybean and grain, or of meat. You could also consider intensification of production (as has been done, eg, for dairying in UK since 2000) in the UK, and use of irrigated/protected (plastic or greenhouses; and maybe imported) crops of Gloucestershire/Herefordshire. You could also consider associated food waste/co-products, and food security (cf energy security, or lack of). We will compare the measurements and estimates we make with methods such as those available on-line: https://www.fwi.co.uk/business/business-management/agricultural-transition/4-popular-carbon-calculators-for-farms-compared (there are limited number of articles you can read free in Farmers Weekly so copy the article!). We will consider the results and policy implications for reaching net-zero, and taking into consideration the requirement for food production. |
| Collaborator Contribution | n/a |
| Impact | Teaching PhD students from the CENTA cohort. |
| Start Year | 2024 |
| Description | CGI Sustainability Digital twin |
| Organisation | CGI |
| Country | Canada |
| Sector | Private |
| PI Contribution | CGI has embarked on a journey to build digital twins and Prof Ashiq Anjum has been asked to support the effort by leading the research team. |
| Collaborator Contribution | Technical specification has been produced. A porotype is being developed |
| Impact | UN sustainable development goals on energy efficiency in data centres and food security by developing products that support these two areas. |
| Start Year | 2023 |
| Description | Leicester Glenfield Hospital |
| Organisation | Glenfield Hospital |
| Country | United Kingdom |
| Sector | Hospitals |
| PI Contribution | We have built a partnership with the Glenfield Hospital and submitted a proposal to EPSRC for a health digital twin. |
| Collaborator Contribution | Working on a health digital twin to reduce the queues for hospital addmissions. |
| Impact | Design of a health digital twin |
| Start Year | 2023 |
| Description | Network of Digital Twins with BT |
| Organisation | BT Group |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | We have formed a collaboration to build network of digital twins. This will develop a prototype of the network digital twin to support the network optimization and energy efficacy of the British telecom for media broadcast services. This will allow BT to cut down energy costs ad increase the reliability of their networks. BT is spending £1Million a day on energy and this is slowing them on wide scale deployment of their networks for new applications such as smart cars and smart homes. This work will lead to the submission of a patent application that will be used as evidence of the impact. |
| Collaborator Contribution | A patent has been submitted jointly. A research paper has been submitted to journal of machine learning. |
| Impact | This is a multidisciplinary collaboration involving software engineers, academics, telecom experts and electrical engineers. |
| Start Year | 2022 |
| Description | Predict methane emissions in cattle farming- North Wyke Farm Platform, Rothamsted Research |
| Organisation | Rothamsted Research |
| Department | North Wyke Farm Platform |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | develop machine learning technology to understand and predict methane emissions in cattle farming with farm-scale environmental and biological variables |
| Collaborator Contribution | farm data, and domain knowledge in data collection, cattle feeding and pasture management. |
| Impact | It is multi-disciplinary collaboration in ruminate farming, AI technology and agriculture NetZero. 1) publications 2) Workshops, network with stakeholders and farms 3) press release: Scientists develop AI tools to help reduce greenhouse gas emissions associated with livestock farming and land use. https://www.lboro.ac.uk/media-centre/press-releases/2025/february/ai-tool-reduce-greenhouse-gas-emissions/ |
| Start Year | 2024 |
| Description | Turing University Network |
| Organisation | Alan Turing Institute |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | The University of Leicester has joined the Turing University Network. Prof. Heiko Balzter has been invited to give a presentation on 22 March 2024 on self-learning digital twins and AI for sustainable land management as part of this network. |
| Collaborator Contribution | n/a |
| Impact | Presentation on 22 March 2024 to the network |
| Start Year | 2023 |
| Title | Machine learning models for GHG prediction and reduction for ruminant farming systems and sustainable land use management |
| Description | A range of ML models have been developed for GHG prediction and reduction for ruminant farming systems and sustainable land use management: Refer to publications below: 1. J. Cutler, B. Li*, B. Alhnaity, T. Partridge, M. Thompson, Q. Meng. AI for Sustainable Land Management and Greenhouse Gas Emission Forecasting: Advancing Climate Action. IEEE Conf. on Algorithms, Computing and Machine Learning (CACML 2025). 2. B. Li, M. Thompson, T. Partridge, R. Xing, J. Cutler, B. Alhnaity, Q. Meng (2024). AI-powered Digital Twin for Sustainable Agriculture and Greenhouse Gas Reduction. IEEE 21st Int. Conf. on Smart Communities: Improving Quality of Life using AI, Robotics and IoT, IEEE/HONET'24. Dec, 2024. Doha, Qatar 3. B. Alhnaity, B. Li, T. Partridge, Q. Meng (2024). A Multi-head Self-attention LSTM Model for UK Methane Prediction. 5th Int. Conf. on Computers and Artificial Intelligence Technology, IEEE/CAIT'24. Best paper of the conference and best presentation. Dec. 2024 in Huizhou, Guangzhou, China. 4. T. Partridge, B. Li, B. Alhnaity, Q. Meng (2024). Utilizing Machine Learning to Understand and Predict Methane Emissions in Cattle Farming with Farm-Scale Environmental and Biological Variables. IEEE Int. Conf. on Computer Applications, IEEE/ICCA'24. December 2024. Cairo, Egypt. 5. R. Xing, B. Li, S. Dora, M. Whittaker and J. Mathie (2024). Stacking Ensemble Machine Learning Modelling for Milk Yield Prediction Based on Biological Characteristics and Feeding Strategies. Int. Conf. Computer Science and Intelligence Systems, FedCSIS'24. September, 2024. Belgrade, Serbia. |
| Type Of Technology | Software |
| Year Produced | 2024 |
| Impact | Our mission is to bridge the gap between innovation and practicality, offering a platform that supports data-driven decisions to combat climate change, advance sustainable farming, and achieve global net-zero emissions goals. This initiative reimagines agriculture as a driver of environmental stewardship and resilience. The AI technology demonstrated in this project along with software and machine learning models will be used by policymakers, government bodies, and farming organisations to deepen understanding of how environmental factors influence emissions and enable data-backed decisions to be made to reduce emissions. |
| Description | AI HPC Conference in Leicester- 2023 |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | The HPC-AI Advisory Council's 5th Annual UK Conference, held on October 18-19, 2023, had an exciting agenda that delved into the intersection of high-performance computing (HPC), artificial intelligence (AI), and environmental responsibility. This had the following focus: Balancing the granularity of calculations in simulation and AI research to optimize efficiency without compromising research value can we mitigate the trend of higher resolution always meaning more compute power? Evaluating the carbon footprint associated with computational demands and exploring strategies to mitigate environmental impact Net zero data centre strategies Ethical and practical considerations about using AI to replace human work and/or traditional simulation techniques in real-world applications Case studies discussing the role of AI in addressing global challenges and improving quality of life, as well as risks involved in using AI in this context |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://www.hpcwire.com/off-the-wire/hpc-ai-advisory-council-gears-up-for-october-conference-in-uk-i... |
| Description | AI UK - The Alan Turing Institute 2025: AI and Digital Twins for sustbable agriculure and land use management |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | talks and demonstration "AI and digital twins for sustainable agriculture and land use management" |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://ai-uk.turing.ac.uk |
| Description | AI UK 2024 conference attendance |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | AI UK 2024 was a showcase of how data science and AI can be applied to society's biggest challenges, with a focus on The Alan Turing Institute's grand challenges, defence and security, environment and sustainability, and transformation of healthcare. Over 2000 people attended AI UK 2024 at QE II Conference Centre. A team of six AI for net zero team members attended the event on 19-20 March 2024 in London and networked with AI experts from the Turing Institute, researchers and industry leaders. We promoted self-learning digital twins for sustainable land management at the event and agreed with David Wagg (lead of the digital twin working group in Turing) to link into that activity. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.turing.ac.uk/events/ai-uk-2024 |
| Description | AZOAI- AI-driven platform empowers UK farmers with real-time insights to cut methane emissions, improve land use efficiency, and contribute to the nation's net zero goal |
| Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | press report on AI for livestock farming and GHG reduction |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.azoai.com/news/20250218/AI-Tools-Help-UK-Farmers-Cut-Livestock-Emissions-and-Boost-Susta... |
| Description | Agrifood for net zero Big Tent event in Sheffield, 13-14 March 2024 |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | The Big Tent event in Sheffield brought together about 150 attendees, about half of whom were academics and the others were from business and farms. I participated as a panel member in a panel discussion and in several working groups and breakouts and promoted the use of digital technologies such as self-learning digital twins for sustainable land management. This sparked a lot of interest. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.agrifood4netzero.net/big-tent-2024.html |
| Description | Agrifood for net zero network (AFN+) expert workshop on 23 January 2025 |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Policymakers/politicians |
| Results and Impact | I attended an invitation-only event in London by the Agrifood for net zero network where the AFN+ carbon calculator was presented and feedback was collected. I fed my views into the workshop outcomes. |
| Year(s) Of Engagement Activity | 2025 |
| Description | Attendance at the COP29 Climate Conference in Baku in November 2024 |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Policymakers/politicians |
| Results and Impact | I was a panellist at COP29 in Baku in the session 'Evaluating progress on forest, land use and agriculture emissions - from the Emirates Declaration to accounting for carbon sequestration' chaired by Nick Breeze. It was livestreamed as well. I advised on using digital technologies for making more informed land use decisions in order to accelerate the land use transition towards net zero and nature restoration. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://unfccc.int/cop29 |
| Description | BES Resilient Landscapes Symposium |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | I attended the BES Symposium on Resilient Landscapes from 24-25 June 2024 in Birmingham. About 200+ people from research, policy, NGOs and industry attended. I presented a poster on the Land Use for Net Zero Hub that led to many useful connections and interactions. There was also interest in the digital twin work my group is doing. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.britishecologicalsociety.org/events/resilient-landscapes-for-people-nature-and-climate/ |
| Description | Cereals 2023 |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Cereals is the key occasion in the arable calendar, offering unmissable networking and educational opportunities. A unique event, showcasing the latest in arable farming, Cereals will welcome over 17000 farmers, agronomists as well as service and product displays from nearly 400 arable-focussed exhibitors and sponsors. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://farmpep.net/event/cereals-2023 |
| Description | Collaboration network at Cereals Event UK (June 2023): leading technical event for arable farmers and agronomists |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | we attended the event to introduce our research and the project, build collaborations and partnership and network with stakeholders such as Department for Environment, Food & Rural Affairs (DEFRA), National Institute of Agricultural Botany (NIAB), Agriculture and Horticulture Development Board (AHDB) |
| Year(s) Of Engagement Activity | 2023 |
| Description | Community of Practice (every 2 months over life of project commencing Jan 2024) |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Postgraduate students |
| Results and Impact | These are events every 2 months on line. The core membership are PGRA's from institutions who are recipients of AI4NetZero grants in the first instance. Over time we will widen participation to policy makers, general AI practitioners, subject matter experts, or others that would have an interest in the topics. The first meeting had attendance of 50 participants |
| Year(s) Of Engagement Activity | 2024 |
| Description | Digital Twins in Industry at KFUPM |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | A workshop was arranged at KFUPM in Saudi Arabia in collaboration with Aramco where the talk was delivered on the physics of digital twins and its applications in energy and net zero. |
| Year(s) Of Engagement Activity | 2023 |
| Description | EO4PEAT Steering Committee |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | Heiko Balzter was appointed to the Steering Committee of the EO4PEAT Project, which is funded by the Belgian Space Office (STEREO IV programme, https://eo.belspo.be/en/stereo-iv-programme). It is a 5-year project in the research group of Gabrielle De Lannoy at KU Leuven, Belgium (Catholic University Louvain). The project is partnered by Patrick Willems (KU Leuven, Belgium), Frieke Van Coillie (U Gent, Belgium), Sebastien Lambot (UCL, Belgium), Raphael Tshimanga (CRREBaC, DRC), and Alex Cobb (MIT-Singapore Alliance). It is focused on tropical peatlands and the interaction between land use land cover change (LULCC) and hydrology. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://eo.belspo.be/en/stereo-iv-programme |
| Description | Farming UK |
| Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | press report |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.farminguk.com/news/researchers-develop-ai-to-track-uk-farm-emissions_66141.html |
| Description | Fenland Soil Conference 2025 |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Professional Practitioners |
| Results and Impact | At the Fenland Soil Conference 2025 in Ely, the University of Leicester ran a workshop for about 40 minutes on Digital technologies for sustainable land use, focusing on the estimation of carbon dioxide emissions from agriculture on drained peatland. The audience were mostly farmers, with some policy makers and other companies present. We demonstrated a machine learning model to estimate field-scale net ecosystem exchange from Earth observation and flux tower data. There was high interest in this technology. |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.fenlandsoil.org/conference-2025/ |
| Description | Fenland Soil Conference, Ely, Cambridgeshire |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Industry/Business |
| Results and Impact | Presentation of the Digital Twin to farmers and other practitioners |
| Year(s) Of Engagement Activity | 2024 |
| Description | Golden Hooves at Hooks Farm Open Day |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Public/other audiences |
| Results and Impact | Farm open day and milking robot demonstration |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://www.goldenhooves.co.uk/farm/hooks-farm-dairy/ |
| Description | Invited speaker at eFutures: Emerging Technologies for Net Zero (Belfast) |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Presentation outlining aims and approach for AI4NetZero: Sustainable Land Management, highlighting how Digital Twins can support NetZero objectives. including insights into hte technical solution. Networking developed future relationships and invitations to future conferences Speakers Dr Asima Khan and Dr Stephen Wright |
| Year(s) Of Engagement Activity | 2024 |
| Description | Invited talk at Digital Twins in Bioscience, Environmental and Medical Science Workshop: AI for Agriculture and Ruminant Farming |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | invited talk at Digital Twins in bioscience, environmental and medical science workshop: AI and Digital Twin Technologies for Agriculture and Ruminant Farming |
| Year(s) Of Engagement Activity | 2024 |
| Description | Land Use Summit 2024 at ZSL |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Policymakers/politicians |
| Results and Impact | Heiko Balzter gave an invited presentation at the Zoological Society of London (ZSL)'s and British Ecological Society (BES)'s Land Use Summit on 16 April 2024 about the Land Use for Net Zero (LUNZ) Hub. The summit was attended by around 200 people from Defra, Desnz, universities and other organisations. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.zsl.org/news-and-events/events/land-use-summit |
| Description | North Wyke Farm Platform and Rothamsted Research workshop on agriculture farm data |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Professional Practitioners |
| Results and Impact | workshop about farm data use, data collection, and cattle pasture management with researches and agriculture scientists from North Wyke Farm Platform and Rothamsted Research |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://repository.lboro.ac.uk/articles/conference_contribution/Utilizing_machine_learning_to_unders... |
| Description | Presentation at a public event - Pint of Science - Title: Digital Twins: What's the buzz about?". By Dr Asima Kahn and Dr Cristina R. Villena |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Public/other audiences |
| Results and Impact | Goal: Introduce the concepts of digital twins to a non-expert audience using our project as an example Content: Our talk covered the basics of AI, EO, and Digital Twins (definitions, examples, and architecture), followed by a description of our project and its applications and a small demo that was previously shared by Bloc Digital. Key takeaway: A lot of people were interested in the future of DTs and whether the general public will have access to them in the future. We received very positive feedback from the audience; they were engaged and appreciative of us using real-life examples to explain highly technical concepts. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://pintofscience.co.uk/event/look-into-my-AIs |
| Description | Presentation to DEFRA "AI for Net Zero: Digital Twins for Sustainable Land Management" - Event: DEFRA Earth Observation Centre of Excellence session on Digital Twins and Ground Truthing data (online), 23rd July, 2024 - by Dr Asima Khan |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Goal: Introducing our project and highlighting our understanding of a DT and the role EO is playing in its development Content: I talked about the DT solution we are developing, and the models we are using in the background, with more focus on the EO-based model (data sources, workflow, accuracy) and a brief overview of JULES and JULES surrogate model. Also showed the latest prototype video by Bloc. Key takeaway: Everyone agreed on a common definition of a DT with the key distinction being a 'transformation layer' that allows the flow of regular data and an updated system. More focus should be on the applicability and user-friendliness of the DT rather than trying to achieve a "perfect" DT. The audience showed interest in our project and was impressed with the level of feedback from end-users we use in our design, i.e., our focus on the applicability of our solution. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Public lecture: "Ways out of the climate crisis" |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Public/other audiences |
| Results and Impact | I gave a one-hour public lecture on 11 April 2024 on invitation by Harborough Climate Action, Market Harborough. The room was packed with over 60 attendees mainly from Market Harborough but with some having travelled from London and Northampton. The purpose was to discuss potential pathways and actions to get to net zero greenhouse gas emissions. I made contacts with the Council for the Protection of Rural England, environmental activists and community champions. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Quote in the Guardian article about global peatlands |
| Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | I was quoted in a Guardian article about the need for protecting global peatlands. |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.theguardian.com/environment/2025/feb/13/worlds-largely-unprotected-peatlands-are-ticking... |
| Description | Ruminant stakeholder workshop: AI, ML and digital twins for sustainable agriculture and livestock framing lture and livestock framing |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | LU team presented research findings at Ruminant stakeholder workshop: AI, Machine learning and digital twins for sustainable agriculture and livestock framing |
| Year(s) Of Engagement Activity | 2024 |
| Description | Scientists develop AI tools to help reduce greenhouse gas emissions associated with livestock farming and land use |
| Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | Scientists develop AI tools to help reduce greenhouse gas emissions associated with livestock farming and land use |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.lboro.ac.uk/media-centre/press-releases/2025/february/ai-tool-reduce-greenhouse-gas-emis... |
| Description | Space tech drives innovation in the food chain |
| Form Of Engagement Activity | Engagement focused website, blog or social media channel |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Public/other audiences |
| Results and Impact | Thought leadership interview |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://citizen.le.ac.uk/blog/space-tech-food-chain/ |
| Description | Talks and demonstarition at Accelerating the Net Zero Transition with AI |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Talks and demonstration at Accelerating the Net Zero Transition with AI, Dec 2024, Exeter UK. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://netzeroplus.ac.uk/ai-for-net-zero-conference |
| Description | Training and Workshops with Bahrain Government Ministries and National Space Science Agency |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Intended purpose was to inform ministries of environment and agriculture in Bahrain on how Earth Observation Activities can benefit strategic national projects. We included this project as an example of the developing area of Digital Twins using AI, and how value can be delivered at local, regional, and national levels from hybridizing a portfolio of data sources to explore solutions to environmental challenges |
| Year(s) Of Engagement Activity | 2024 |
| Description | Training and Workshops with Bahrain Government Ministries, Local Academics, and SMEs |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The training followed a similar event in 2024. Training and workshops were delivered to engage ministries and SME's (and a few local academics) with the potrential of EO data and AI to inform policy and delivery in the areas of climate change, environment, agriculture, and land use. Extensive discussions of the potential of Digital Twins. During the project development workshops many of the projects identified and developed included an Environmental Digital Twin at its core Speakers from AI4netZero project, Dr Asima Khan, Dr Cristina Ruiz Villena, Dr Matt Payne, Professor Kevin Tansey, Dr Stephen Wright |
| Year(s) Of Engagement Activity | 2025 |
| Description | Turing University Network presentations on 21/3/2024 |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Postgraduate students |
| Results and Impact | The Turing University Network Cafe in Leicester aims to connect University colleagues and students to share ideas and discussions around AI and data science in an informal setting and to hear about ongoing research and opportunities at the University which may be relevant to the Turing University Network and vice versa. Professor Heiko Balzter provided a short presentation on his work around using AI to develop a digital 'twin' of the UK that harnesses artificial intelligence and big data to meet its net zero target and Dr Rob Parker talked about his work on the UKRI Future Leaders Fellowship project "The First Environmental Digital Twin Dedicated to Understanding Tropical Wetland Methane Emissions for Improved Predictions of Climate Change" in front of an audience of about 25 attendees. |
| Year(s) Of Engagement Activity | 2024 |
| Description | UK Dairy Day, talk & demonstration "AI platform for Net Zero agriculture" |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | The Loughborough team introduced and demonstrated our AI platform for livestock farming and Net Zero agriculture, attracting a large audience and highlighting its significance in the UK's dairy industry. Uk Dairy Day is a national largest dairy trade event provided a platform for networking, knowledge sharing, and business opportunities within the dairy industry. The event featured over 280 trade stands, showcasing a wide range of products and services from feed manufacturers, animal health suppliers, vets, milk buyers, and dairy equipment providers. The cattle show included six dairy breeds, hosting National Shows for Ayrshire, Brown Swiss, and Holstein breeds, judged by a panel of esteemed professionals. The seminar program covered topics such as opportunities in dairy farming, carbon management, and cost strategies, offering valuable insights to attendees. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://ukdairyday.co.uk |
| Description | Webinar: Self-learning digital twins for sustainable land management |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | 120 people attended a webinar in the AI for Net Zero webinar series on 18 June 2024. In the discussion after the presentation and in follow-up emails I received, several participants thanked me for the talk and said they were farmers and found my talk very refreshing. There were also attendees from policy, e.g. Natural England. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.youtube.com/live/AOxZCVuQi80 |
| Description | Workshop at GIK and BZU on Digital Twins |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | A workshop was arranged at GIKI/BZU in Pakistan in collaboration with local universities where the talks were delivered on the physics of digital twins and its applications in industry, energy and net zero. |
| Year(s) Of Engagement Activity | 2023 |
| Description | demonstration and publicity at Hooks Farm Open Day events (2023, 2024) |
| Form Of Engagement Activity | Participation in an open day or visit at my research institution |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Professional Practitioners |
| Results and Impact | June 2023, Hooks Farm onsite Visit, collaboration and network with farmers and stakeholders. June 2024 presentation and demonstration at Hooks Fram Open Day, demonstrate research and technology of AI and DT in ruminate farming, publicity and network with farms, general public and diary industry. |
| Year(s) Of Engagement Activity | 2023,2024 |
| Description | eFutures presentation on line - Land Use Net Zero Hub - topic advisory group - seminar - "Case Studies of Digital Technologies in Land Use Net Zero" |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Policymakers/politicians |
| Results and Impact | Presentation on case study of Digital Twinning. Explain how Digital Twinning can inform Land Use Decisions |
| Year(s) Of Engagement Activity | 2025 |
| Description | invited talk at AI for NetZero Webinar: AI-powered Digital Twins for Sustainable Agriculture |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | invited talk at AI for NetZero Webinar, title: AI-powered Digital Twins for Sustainable Agriculture https://www.youtube.com/watch?v=UEEOaTkEUUg 240 subscribers, 123 views by 22nd Feb 2025 |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.youtube.com/watch?v=UEEOaTkEUUg |
| Description | research presentation and lab visit at Cattle Information Service (Sept.2023) |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Professional Practitioners |
| Results and Impact | research presentation, discussion and lab visit at Cattle Information Service. |
| Year(s) Of Engagement Activity | 2023 |
| Description | workshop with MerLin Fullwood for farm data collection using robotic technology |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Professional Practitioners |
| Results and Impact | workshop with MerLin Fullwood for farm data collection using robotic technology |
| Year(s) Of Engagement Activity | 2024 |