Artificial Intelligence Enabling Future Optimal Flexible Biogas Production for Net-Zero
Lead Research Organisation:
University of Surrey
Department Name: Chemical Engineering
Abstract
Anaerobic digestion (AD) is a technology where microorganisms break down organic matter to produce biogas, thereby generating renewable energy from waste. Biogas can be combusted to produce electricity or purified and used as a substitute for natural gas (NG). Because it provides a carbon-neutral substitute for fossil fuels, while also preventing methane emissions at landfills by processing organic waste, AD is noted as an important part of the UK Net Zero Strategy: Build Back Greener.
This project aims to develop artificial intelligence (AI) tools to enable radical efficiency improvements in AD biogas production. Currently, there are about 650 operational AD sites in the UK, which reduce UK greenhouse gas emissions by an estimated 1%. This contribution is meaningful, but modest in comparison to AD's potential. The fundamental roadblock at present is a lack of flexibility. Due to the complexities of predicting how different waste feedstocks and different microbial communities will interact under varying operating conditions, AD biogas producers must minimise risk by purchasing only the highest-quality, consistent feedstock, which may also be seasonal; any errors could result in long and costly downtimes. Thus, available waste streams are vastly under-utilised; feedstock prices are driven up, weakening the economic viability of AD biogas production; and limited feedstocks may need to be transported longer distances, increasing carbon emissions.
AI holds crucial promise for the optimisation and future expansion of AD biogas production. As an industry that does not have the central research capabilities of other large energy sectors, it furthermore presents exceptional challenges due to the complexities and inherent uncertainties across interacting chemical, biological, and - if reductions in total life-cycle emissions are to be achieved - environmental systems. The project team therefore unites expertise in AI, process optimisation, systems microbiology, and life-cycle assessment to develop whole-systems decision-making tools informed by detailed sub-system modelling.
The outputs will include decision-making tools, specifically: A) a hybrid machine-learning digital twin of the biodigesters, based on novel mechanistic modelling approaches combined with process data from industrial partners and new experimental data from the project; and B) optimisation-based system models of other components of a site, to perform site-wide real-time optimisation through a multi-layer digital twin that includes economic and environmental indicators. By linking the digital twin of the biodigester to feedstock procurement and downstream processes, it will be possible to quickly determine the impact of different feedstocks, their combinations, and their prices on biogas quality, while also tracking quantified environmental impacts across AD value chains in real-time and assessing negative emissions potential in future.
Increasing the flexibility of UK AD industry will expand waste markets and lower prices to grow the sector with more capacity, boost profits and productivity, and enhance the overall attractiveness of AD as an investment. Increasing biogas output will help lower UK dependence on foreign NG sources and lower overall emissions from the energy system. The project is supported by partners from across the UK to ensure the aims and objectives can be met, to result in a step-change in the AD industry and position the UK as a global AD leader. The knowledge, tools, and methods developed will be applicable in wastewater treatment, where AD is also used. Beyond that, our AI approaches to systems biology will have potential for widespread application in bioprocessing sectors more generally, such as biopharmaceuticals, biofuels, food, and fermentation. With our network of partners, we will explore potential commercialisation and licencing of our digital techniques to maximise impact and work across sectors toward the common goal of Net Zero.
This project aims to develop artificial intelligence (AI) tools to enable radical efficiency improvements in AD biogas production. Currently, there are about 650 operational AD sites in the UK, which reduce UK greenhouse gas emissions by an estimated 1%. This contribution is meaningful, but modest in comparison to AD's potential. The fundamental roadblock at present is a lack of flexibility. Due to the complexities of predicting how different waste feedstocks and different microbial communities will interact under varying operating conditions, AD biogas producers must minimise risk by purchasing only the highest-quality, consistent feedstock, which may also be seasonal; any errors could result in long and costly downtimes. Thus, available waste streams are vastly under-utilised; feedstock prices are driven up, weakening the economic viability of AD biogas production; and limited feedstocks may need to be transported longer distances, increasing carbon emissions.
AI holds crucial promise for the optimisation and future expansion of AD biogas production. As an industry that does not have the central research capabilities of other large energy sectors, it furthermore presents exceptional challenges due to the complexities and inherent uncertainties across interacting chemical, biological, and - if reductions in total life-cycle emissions are to be achieved - environmental systems. The project team therefore unites expertise in AI, process optimisation, systems microbiology, and life-cycle assessment to develop whole-systems decision-making tools informed by detailed sub-system modelling.
The outputs will include decision-making tools, specifically: A) a hybrid machine-learning digital twin of the biodigesters, based on novel mechanistic modelling approaches combined with process data from industrial partners and new experimental data from the project; and B) optimisation-based system models of other components of a site, to perform site-wide real-time optimisation through a multi-layer digital twin that includes economic and environmental indicators. By linking the digital twin of the biodigester to feedstock procurement and downstream processes, it will be possible to quickly determine the impact of different feedstocks, their combinations, and their prices on biogas quality, while also tracking quantified environmental impacts across AD value chains in real-time and assessing negative emissions potential in future.
Increasing the flexibility of UK AD industry will expand waste markets and lower prices to grow the sector with more capacity, boost profits and productivity, and enhance the overall attractiveness of AD as an investment. Increasing biogas output will help lower UK dependence on foreign NG sources and lower overall emissions from the energy system. The project is supported by partners from across the UK to ensure the aims and objectives can be met, to result in a step-change in the AD industry and position the UK as a global AD leader. The knowledge, tools, and methods developed will be applicable in wastewater treatment, where AD is also used. Beyond that, our AI approaches to systems biology will have potential for widespread application in bioprocessing sectors more generally, such as biopharmaceuticals, biofuels, food, and fermentation. With our network of partners, we will explore potential commercialisation and licencing of our digital techniques to maximise impact and work across sectors toward the common goal of Net Zero.
Organisations
- University of Surrey (Collaboration, Lead Research Organisation)
- Council of Scientific and Industrial Research (CSIR) (Collaboration)
- AgriSA (Collaboration)
- Engie (Collaboration)
- Green Giraffe (Collaboration)
- Kenyatta University (Collaboration)
- Rolls Royce Group Plc (Collaboration)
- Universidade de São Paulo (Collaboration)
- Sanergy, Inc. (Collaboration)
- Alps Ecoscience (Collaboration)
- Scotish Gas Networks (Collaboration)
- Future Biogas (Collaboration, Project Partner)
- African Sun Holdings (Collaboration)
- SLR Consulting Limited (UK) (Project Partner)
- Ixora Energy Ltd (Project Partner)
- Siemens plc (UK) (Project Partner)
- Anaerobic Digestion & Bioresources Ass (Project Partner)
Publications
Dolat M
(2024)
Dynamic feed scheduling for optimised anaerobic digestion: An optimisation approach for better decision-making to enhance revenue and environmental benefits
in Digital Chemical Engineering
Fisher O
(2025)
Breaking barriers to modelling biotechnologies with machine learning
in Resources, Conservation and Recycling
Kay S
(2025)
A novel approach to identify optimal and flexible operational spaces for product quality control
in Chemical Engineering Science
Zhang D
(2025)
Carbon credits monetary value for anaerobic digestion systems and energy policy implication in the UK
in The Innovation Energy
| Description | What were the most significant achievements from the award? There are several major achievements so far from the award, including: 1. a suite of models of different kinds for prediction of biogas yields from a variety of feedstocks across different conditions. These models include: -mechanistic models modified from other applications to be applicable to agricultural anaerobic digestion, found to be effective across a range of conditions -Purely data-driven models based on recurrent neural network architectures that far outperform existing machine learning approaches -Sets of hybrid models with uncertainty quantification to give trustworthy modelling results in regions with less data 2. Embedding these models within whole-site optimisation algorithms based on model predictive control and real-time optimisation techniques to provide decision support 3. Techniques for optimisation of bioprocesses under uncertainty to guarantee performance, even when model parameters are uncertain. 4. Technoeconomic and life cycle assessment models for biogas sites with carbon capture and storage. We showed the economic and environmental benefits and issue areas within the processes and embedded these indicators within the real-time optimisation model for real-time economic decision-making 5. Developing methods for incorporating crop yield uncertainty within biogas site decision-making and feedstock acquisition. 6. Detailed microbial community analysis to start to understand the shifts in community relative species abundance during transient operation. 7. Contributed to building a UK AI net-zero community through participation in events, giving of talks and training, etc. To what extent were the award objectives met? If you can, briefly explain why any key objectives were not met. From the award, objectives 1, 2, 3, and 5 (out of 5) were fully delivered. However, objective 4, related to on-site partner site implementation has been agreed but is delayed. The partner and team are confident of delivering the prototype, however, there were severe delays in key positions being appointed, amounting to well over 18 months in human resources delays across the project (due to visas, recruiting, etc.). This meant that we focused on delivering technical contributions. Site demonstrations are planned (and a no-cost extension requested) for April and May 2025 with Future Biogas. How might the findings be taken forward and by whom? We are in the process of spinning out a company to commercialise the software platform with support from commercial partners Future Biogas and ALPS EcoScience. We will take this to market after the validation on site. We anticipate the uptake of these tools in many other biogas sites. |
| Exploitation Route | We are actively seeking investment to take the products developed to market as a software as a service model for the biogas sector. We are working with our existing partners in the biogas sector (Engie, Future Biogas, ALPS EcoScience, etc.) to validate on-site and explore the best market proposition to get this to market. Beyond the software for real-time optimisation, which is the major output, we will also be publishing the work on microbial community dynamics, detailed kinetic models incorporating community dynamics, and the methods for bioprocess modelling and control under uncertainty in the near future to allow for others to access the knowledge created. |
| Sectors | Agriculture Food and Drink Chemicals Digital/Communication/Information Technologies (including Software) Energy |
| Description | Our work has already seen use in industry to, for example, quantify process changes on economic outcomes of a biogas plant with a commercial partner. We have received significant external interest in the software we have developed and have begun the spinout process to deliver the product on biogas sites to enhance decision-making for economic and environmental benefit. We expect these benefits to be quantifiable in the next submission once trials are underway. Beyond this, we have given significant training to a wider audience on the role of AI in bioenergy, giving talks across the world and encouraging a paradigm shift in terms of encouraging data-driven decisions in what is one of the least data-driven industries. |
| First Year Of Impact | 2024 |
| Sector | Energy |
| Impact Types | Economic |
| Description | Interview with Open Innovation from the government |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| Description | Interview with Open Innovation from the government on biomass |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| Description | Life Cycle Assessment for the EBNet Industrial Community: Goal and Scope Definition |
| Geographic Reach | National |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Impact | With the worldwide concerns of the living environment, it is highly important to investigate and understand the environmental impacts of each technology and feedstock, for decision-makers to develop the future energy management plan. This understanding is crucial for decision-makers in formulating strategies for managing these organic materials using circular economy principles. AD is assisted by hydrothermal treatment and nutrient recovery, with this framework seen as a promising circular economy concept for food waste valorization, while reducing the carbon footprint. Developing an LCI and gathering data stand as a pivotal phase in any LCA investigation. Our novel standard anaerobic digestion (AD) / biogas / biomethane / bio-electricity GWP calculation equation follows the format for GWP measurements, regulations, and reporting of the EU directive, consisting of GWP from individual life cycle stages, i.e., resource acquisition or cultivation, transportation including feedstock and digestate, AD plant operation, CHP systems, and digestate application. Further, avoided GWP includes GWP from natural gas production (displaced by cradle-to-gate AD systems), or GWP from grid electricity and heat, and conventional fossil-based fertilizer (displaced by cradle-to-grave AD systems). The net GWP saving by AD systems is the difference between avoided GWP and GWP impacts. Commendably, our novel model provides the formulation in a format similar to the EU Directive of the European Parliament and of the Council by establishing a minimum threshold for greenhouse gas emissions savings. |
| Description | Meetings with Mayoral committee of Garden route |
| Geographic Reach | Africa |
| Policy Influence Type | Participation in a guidance/advisory committee |
| Description | Workshop with Malaysian industry and government |
| Geographic Reach | Asia |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Description | Workshops with Philippines government officials |
| Geographic Reach | National |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Description | African Agriculture KTP:23-24 Part 2 |
| Amount | £241,337 (GBP) |
| Funding ID | 10097617 |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 07/2024 |
| End | 07/2026 |
| Description | Biomethane Islands |
| Amount | £514,656 (GBP) |
| Funding ID | https://portal.futureenergynetworks.org.uk/content/projects/NIA2_SGN0072 |
| Organisation | Ofgem Office of Gas and Electricity Markets |
| Sector | Public |
| Country | United Kingdom |
| Start | 03/2025 |
| End | 08/2025 |
| Description | Digitalisation of the biogas industry to deliver net-zero using artificial intelligence |
| Amount | £18,000 (GBP) |
| Funding ID | FEPS HEIF Allocation 2024/25 - 46 |
| Organisation | Higher Education Innovation Funding (HEIF) |
| Sector | Public |
| Country | United Kingdom |
| Start | 03/2025 |
| End | 06/2025 |
| Description | Global Alliance Africa Sebenzisa Tembisa Waste Challenge |
| Amount | £10,000 (GBP) |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 05/2024 |
| End | 11/2024 |
| Description | Research and Innovation for Development in ASEAN (RIDA) |
| Amount | £60,000 (GBP) |
| Organisation | Foreign Commonwealth and Development Office (FCDO) |
| Sector | Public |
| Country | United Kingdom |
| Start | 01/2024 |
| End | 06/2024 |
| Description | Supergen Bioenergy Impact Hub 2023 |
| Amount | £5,295,845 (GBP) |
| Funding ID | EP/Y016300/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 11/2023 |
| End | 10/2027 |
| Title | Novel Algebraic Equation-based Models for Global Warming Standardization in Anaerobic Digestion Systems with Critical Life Cycle Analyses |
| Description | There is renewed interest in biogas due to the Green Gas Support Scheme to create Net-Zero UK. It is crucial to develop a universally robust LCA model to conduct structured and reliable evaluations of LCA, ensuring the results remain comparable with those from LCI databases. Thus, our approach results in two sets of algebraic equations for standard GWP estimation, one based on published literature and the other based on the Ecoinvent LCI database. The predictions between the two models are compared, so that the former set of algebraic equations based on published literature can be easily applied in other studies to calculate the GWP of biogas in various contexts (biomethane and bio-electricity). Our approach emphasizes ease of updating and can be used in long-term or short-term scheduling and control optimization models, achieving the same quality of results as the LCI database. In this study, we pursued several objectives: (i) a comprehensive analysis of LCA results for various feedstocks used in AD systems worldwide; (ii) an exploration of the impact of different AD system variabilities on LCA through sensitivity analysis; (iii) the development of LCA-based algebraic formulae to evaluate the environmental footprint of cradle-to-grave (literature-based) and cradle-to-gate (both literature-based and Ecoinvent LCI-based) AD systems across different scenarios, feedstocks, geographic locations, etc.; and (iv) a comparison between the two approaches. It can be noted that Ecoinvent LCI data for cradle-to-grave AD systems are aggregated and indivisible by life cycle stage or activity. Consequently, Ecoinvent LCI-based formulae are limited to cradle-to-gate up to biomethane production systems. In contrast, literature-based formulae cover holistic cradle-to-grave systems with contributions of individual life cycle stages or activities. Furthermore, comparisons of the literature-based model with the Ecoinvent-based predictions are conducted to reveal closely aligned results, affirming their robustness. |
| Type Of Material | Technology assay or reagent |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | The organic waste processors can easily access this research tool and method to calculate the GWP saving through their waste treatment process. This result will help them to comply with the regulations. Biogas or anaerobic digestion (AD) systems can mitigate global warming potential (GWP), but carbon trading is complex. Successful carbon offsetting requires AD systems to adhere to key carbon crediting or offsetting programs, such as Verra's Verified Carbon Standard (VCS), Gold Standard (GS), Climate Action Reserve (CAR) and American Carbon Registry (ACR) by standardizing life cycle GWP reporting. For example, there are 147 ongoing VCS carbon offsetting projects with biogas estimated to reduce 16.93 Mt (million tonnes) CO2e. There are 322 ongoing GS carbon offsetting projects with biogas estimated to reduce 22.88 Mt (million tonnes) CO2e. This study focuses on creating algebraic equations for calculating the GWP of biogas, crucial for carbon crediting or offsetting programs and net-zero goals, which balance carbon emissions and sequestration. Biogas, derived from carbon-neutral organic waste and used as a substitute for natural gas, contributes to reducing greenhouse gas (GHG) emissions. With increases in carbon markets and the value of selling carbon offsets, it is important to predict GWP savings from replacing fossil fuels, and a comprehensive life cycle assessment (LCA) is thus necessary. The study develops two novel methods for GWP calculation based on published literature and the Ecoinvent life cycle inventory (LCI) database. These methods, which differ in how they group life cycle activities, are compared to assess their predictive accuracy. The methods conduct a rigorous and significant modular synthesis approach, assigning a distinct GWP to the life cycle stages or activities in the system. This study's models are thus essential for an effective and thorough life cycle GWP assessment in AD systems. The tool will be applied by waste processors to calculate the carbon offset or saving or reduction by their system enabling them to apply for the various carbon offsetting schemes as well as qualifying them for the Green Gas Support Scheme. An example is the 50 g CO2e per kWh biomethane production rate requirement by 2030 for gas grid injection of biomethane in the UK's net-zero electricity carbon intensity requirements. |
| Title | Dataset from 18 months of continuous biogas production from 8 biodigesters fed with industrial agricultural feedstocks |
| Description | This dataset is a detailed dataset of feeding rates, feedstock characteristics, biodigester performance (VFAs, gas yields, etc.) at daily intervals. The data uses industrial recipes to mimic the dynamics of real sites. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2025 |
| Provided To Others? | No |
| Impact | These datasets have been used to create highly accurate models of digester operation for optimisation. |
| Title | Digital whole-site decision-making models for Anaerobic Digestion |
| Description | We have developed optimisation models for whole-site decision-making (feedstock acquisition, storage, digester performance prediction with co-digestion, and downstream gas cleaning and storage). |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | No |
| Impact | We are in the early stages of implementing this on partner sites. Hence, no quantified impacts to report as of yet. We have arranged for the trials and are in process of arranging IP for a potential spinout. |
| Title | Life cycle global warming potential of biogas, biomethane and bio-electricity |
| Description | Amidst rising interest in biogas as a sustainable alternative to traditional energy vectors like natural gas, this study focuses on its role in achieving net-zero targets-where carbon emissions are balanced with sequestration. Biogas, derived from carbon-neutral organic waste, offers significant greenhouse gas (GHG) emission reductions. Life cycle assessments (LCA) are crucial for evaluating the global warming potential (GWP) of biogas, ensuring its effectiveness in offsetting fossil fuel equivalents. However, current GWP calculations lack transparency and standardization, necessitating new robust easily calculable algebraic equations. Our study introduces two complementary sets of equations, grounded in published literature and LCA databases. Despite their differing structures due to distinctive specific activities across life cycles, both sets yield closely aligned estimations, reinforcing confidence in these models. The GWP is sensitive to the feedstock type, electricity and heat consumption, and fugitive emissions. The statistical distributions show the mean GWP of 0.54 per m3 biogas, 0.09 per kWh biomethane and 0.73 per kWh electricity production rates of cradle-to-grave systems with all plausible technologies available in the database. The lowest GWP meets the UK's 50 g CO2e per kWh biomethane target by 2030 for gas grid injection. The GWP in g CO2e per kg AD feedstock is 93-104 (manure), 16-26 (sludge), and 273 (grass silage), etc. The biowaste AD system reduces at 0.5-0.7 kg CO2e per kWh of electricity generated, requiring 1.5 MWh of minimum threshold electricity generation to reduce 1 tonne of CO2e. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | There has been an upsurge of renewed interest in the comparative LCA of biogas/AD as a mechanism to standardize climate change impact reduction potential. This study offers a fresh perspective on calculating the GWP performance of AD setups utilizing data from literature and the Ecoinvent LCI database. First, based on detailed comprehensive literature review, a GWP prediction model with equations focused on GWP of each activity in the AD system has been developed. Second, Ecoinvent 3.6 LCI data of all AD-related systems are assimilated to create another GWP prediction model. Both models are then tested to see how they compare. They show good agreement, despite some distinguishing characteristics. In the process of detailed exploration of the possibility of open-source models based on literature and the Ecoinvent database, some scopes are identified, e.g., Swiss (or alternatively rest of the world) data availability in Ecoinvent. The published literature-based model shows more inclusivity in terms of global contexts, allowing LCA stage-specific GWP factors updating based on geographic contexts. Both models capture sensitivity of feedstock variations in GWP prediction and energy related GWP variations, demonstrating robust comprehensive GWP calculations. Furthermore, the Ecoinvent 3.6 LCI database allowed analysis of GWP due to variations in biomethane purification or pre-combustion upgrading technologies (amino washing, membrane, and pressure swing adsorption) and CHP technologies (micro gas turbine (MGT), polymer electrolyte membrane fuel cell, solid oxide fuel cell (SOFC) and SOFC-MGT). Our modular synthesis approach demonstrates distinguishable GWP from each feedstock and technology type, allowing a statistical analysis that shows GWP variations, 25th, 50th and 75th percentile values, and mean values in transferable units, per unit volume of biogas and biomethane, and per unit energetic value of biomethane and electricity, for the cradle-to-grave systems. Some key quantitative GWP measures are as follows. The cradle-to-grave AD system's GWP (kg CO2e/m3 biogas) from the literature-based and Ecoinvent data-based models is manure: 1.33 and 0.9-0.97, sludge: 0.5 and 0.42-0.48, food waste or biowaste 0.34 and 0.29-0.35, and grass silage 1.2 and 0.5-0.58. The GWP in g CO2e per kg AD feedstock is 93-104 (manure), 16-26 (sludge), 245-618 (UCO), and 273 (grass silage). The intended recipients of this study encompass governmental agencies, environmental engineers, the scientific community, feedstock community and energy companies, informing emerging policies on net-zero. |
| Title | Technoeconomic models for biogas plants with carbon capture and storage |
| Description | The model is in the form of a Python-based model with technoeconomic parameters for the design and costing of an agricultural biogas plant, along with different technologies, including torrefaction, carbon capture via different technologies, and liquefaction of CO2. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2025 |
| Provided To Others? | No |
| Impact | The model is to be used in a project with Scottish Gas Networks, and in future work with industrial partners. The model will be released after peer review. |
| Description | African Sun Holdings partnership |
| Organisation | African Sun Holdings |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | We are providing advice on their operations in Africa, linking them with our network, and exploring funding mechanisms. |
| Collaborator Contribution | They often email for advice and ad hoc meetings. They have provided information to us on technologies and African context of bioenergy. |
| Impact | None so far. |
| Start Year | 2024 |
| Description | Carbon credits and life cycle assessment for biogas CHPs |
| Organisation | Rolls Royce Group Plc |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | We have developed Life Cycle Assessment models for biogas with Rolls-Royce for their internal use. We have also provided them with guidance on carbon credits for increasing plant profitability. |
| Collaborator Contribution | Using their expertise and data, they have helped us to develop LCA models for environmental performance monitoring of AD. Through several meetings jointly held with them, they have helped us to better understand the process for carbon credit verification. They have also attended our workshops. |
| Impact | Internal models of LCA for Rolls-Royce use. We have an output under review. |
| Start Year | 2023 |
| Description | Commercial partnerships with ALPS EcoScience |
| Organisation | Alps Ecoscience |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | ALPS EcoScience, working in collaboration with Engie and Biogest, sought help with modelling their unique biogas pretreatment unit. we have provided modelling advice and have now entered talks to work together as commercial partners. |
| Collaborator Contribution | They have provided data, commercial advice for our potential spinout and offered a member of staff as CEO of a potential spinout. |
| Impact | Models of novel bioreactors, performance modelling of biodigesters. Multidisciplinary as it is combination of AI, modelling, and biology. |
| Start Year | 2024 |
| Description | Engie biogas decision-amking tools |
| Organisation | Engie |
| Country | Global |
| Sector | Private |
| PI Contribution | We have developed models of their biodigesters at 2 sites and have applied optimisation algorithms over these for enhanced decision-making. |
| Collaborator Contribution | They have provided data, advice and steer on direction of research, co-developing the tools. |
| Impact | Models, decision-support tools. Plan for trials in next few months. |
| Start Year | 2023 |
| Description | Increasing Biogas in South Africa |
| Organisation | AgriSA |
| Country | South Africa |
| Sector | Private |
| PI Contribution | After this award, I was invited to give work with South Cape TVET College on a waste-to-energy project in George, South Africa. We are meeting with the Mayors in the area and doing research on feedstocks and carbon financing for these projects. |
| Collaborator Contribution | They have been finding local partners on the ground and liaising between myself and the municipalities and local stakeholders to find interest and funding. They have also been handling questionnaires for local waste collection and landfills. |
| Impact | None |
| Start Year | 2023 |
| Description | Increasing Biogas in South Africa |
| Organisation | Council of Scientific and Industrial Research (CSIR) |
| Country | South Africa |
| Sector | Academic/University |
| PI Contribution | After this award, I was invited to give work with South Cape TVET College on a waste-to-energy project in George, South Africa. We are meeting with the Mayors in the area and doing research on feedstocks and carbon financing for these projects. |
| Collaborator Contribution | They have been finding local partners on the ground and liaising between myself and the municipalities and local stakeholders to find interest and funding. They have also been handling questionnaires for local waste collection and landfills. |
| Impact | None |
| Start Year | 2023 |
| Description | Innovate UK African Agriculture Knowledge Transfer Partnership |
| Organisation | Kenyatta University |
| Country | Kenya |
| Sector | Academic/University |
| PI Contribution | Working to model and digitalise a black soldier fly from human waste business delivering sanitation to townships. |
| Collaborator Contribution | Working to model and digitalise a black soldier fly from human waste business delivering sanitation to townships. |
| Impact | Not yet. |
| Start Year | 2024 |
| Description | Innovate UK African Agriculture Knowledge Transfer Partnership |
| Organisation | Sanergy, Inc. |
| Country | Kenya |
| Sector | Private |
| PI Contribution | Working to model and digitalise a black soldier fly from human waste business delivering sanitation to townships. |
| Collaborator Contribution | Working to model and digitalise a black soldier fly from human waste business delivering sanitation to townships. |
| Impact | Not yet. |
| Start Year | 2024 |
| Description | Innovate UK African Agriculture Knowledge Transfer Partnership |
| Organisation | University of Surrey |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Working to model and digitalise a black soldier fly from human waste business delivering sanitation to townships. |
| Collaborator Contribution | Working to model and digitalise a black soldier fly from human waste business delivering sanitation to townships. |
| Impact | Not yet. |
| Start Year | 2024 |
| Description | New partnerships in Brazilian biogas |
| Organisation | Universidade de São Paulo |
| Country | Brazil |
| Sector | Academic/University |
| PI Contribution | We hosted research visits at Surrey of undergraduate and Professors working in this space to share ideas and data. We provided modelling insights and techniques for their work in mapping biomass potentials in Brazil. |
| Collaborator Contribution | We hosted an undergraduate research assistant, sponsored by FAPESP, at Surrey. The researcher worked with the Surrey team to develop new models and visualisation tools for mapping biogas potential in the UK. They also invited Dr Short to give a presentation in Sao Paulo to partners, CopaEnergia. This partnership is still developing. |
| Impact | Under review |
| Start Year | 2023 |
| Description | Scottish Gas Networks OFGEM NIA |
| Organisation | Green Giraffe |
| Country | United States |
| Sector | Private |
| PI Contribution | We are funded by the Network Innovation Allowance to study biomethane in the natural gas grid. We are performing optimisation and technoeconomic analysis and design of biomethane sites. |
| Collaborator Contribution | Partners provide data for gas demands and locations, as well as feedstock availability. They also perform financial modelling to deliver the project. |
| Impact | None. |
| Start Year | 2025 |
| Description | Scottish Gas Networks OFGEM NIA |
| Organisation | Scotish Gas Networks |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | We are funded by the Network Innovation Allowance to study biomethane in the natural gas grid. We are performing optimisation and technoeconomic analysis and design of biomethane sites. |
| Collaborator Contribution | Partners provide data for gas demands and locations, as well as feedstock availability. They also perform financial modelling to deliver the project. |
| Impact | None. |
| Start Year | 2025 |
| Description | Secondment with Future Biogas |
| Organisation | Future Biogas |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | An employee of Future Biogas was seconded into the AI for Net Zero research group to help the team to develop industrially-relevant and informed tools, one of which is to be trialed in their operations, while also training the employee in Future Biogas to leverage AI in the business. |
| Collaborator Contribution | Future Biogas helped the team to develop industrially-relevant and informed tools. |
| Impact | Secondment and training. Software more industrially-relevant. Trial of tool agreed. |
| Start Year | 2024 |
| Title | A Techno-Economic Analysis (TEA) model has been developed to evaluate the economic feasibility of an anaerobic digestion plant with integrated carbon capture. |
| Description | The technoeconomic model can be used to cost and perform business model assessment for anaerobic digestion sites with carbon capture and storage (CCS) to develop bioenergy with CCS (BECCS). It can be used with a variety of feedstocks and gas usage. |
| Type Of Technology | Webtool/Application |
| Year Produced | 2025 |
| Impact | We will be using this model in a Future Energy Networks-funded project led by Scottish Gas Networks. |
| Title | Model predictive real-time optimisation model for whole-site optimisation |
| Description | The software is used for model predictive decision-making on-site for scheduling and optimising the feeding rates, dilution rates, etc. and is intended for use by site managers and planners for feedstock acquisition. |
| Type Of Technology | Software |
| Year Produced | 2025 |
| Impact | We are in the process of licencing, validating and potentially spinning out this model as a software as a service product. Our partners in Future Biogas have begun using the tool recently, but we do not have details on the impacts as of yet. |
| Title | Spreadsheet or dataset about calculation of GWP for AD available on Github |
| Description | The spreadsheet allows an easy-to-use and open method for accounting for the emissions across a biogas chain. Its open-source nature makes it replicable and means that you can estimate emissions without the need for expensive LCA software licences |
| Type Of Technology | Webtool/Application |
| Year Produced | 2023 |
| Impact | This is incorporated into a new spinout's software and has also been used in Rolls-Royce Germany's own internal calculator to estimate the benefits of biogas for clients within their sales team. |
| Description | 3 talks at University of Sao Paulo campuses |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Undergraduate students |
| Results and Impact | Delivered 3 talks at University of Sao Paulo campuses in Sao Carlos and Ribeirao Preto for academics, undergraduates and postgraduate students in December 2024 |
| Year(s) Of Engagement Activity | 2024 |
| Description | ADBA National Conference 2024 engagement |
| 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 | Meshkat Dolat and Angela Bywater (both research assistants on the project) attended the Anaerobic Digestion & Bioresources Association National Conference 2024 at Westminster. Participated in industrial outreach, engaging in networking and presenting our group's work in AI for AD. |
| Year(s) Of Engagement Activity | 2024 |
| Description | EBNet Webinar: Unlocking AI and Machine Learning's Potential for Environmental Biotechnology |
| 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 | Dr Short and Dr Zhang were invited to the webinar as it featured prominent academics discussing the application of AI and machine learning to improve bioremediation, resource recovery, and environmental protection. The audience asked questions after presentations on the use of AI in AD and it sparked discussions and new collaborations. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://ebnet.ac.uk/wgai-ebml-240221/ |
| Description | Interview on BBC Surrey radio |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Media (as a channel to the public) |
| Results and Impact | 5 minute interview on BBC Surrey radio to discuss the award of the project (15-06-2024). The interview was played as a small snippet throughout the day and then the full interview at around 17h30. We discussed AI and biogas generally |
| Year(s) Of Engagement Activity | 2023 |
| Description | Invited talk and engagement at the EBNet Sludge Modelling workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Industry/Business |
| Results and Impact | Sponsored by the Environmental Biotechnology Network and falling within the remit of its Engineering / Biology theme which considers interactions between microbial and engineering factors, this two-day workshop brought together sludge flow modellers with microbiologists and end users to discuss best practice, challenges and opportunities in sludge predictive behaviour from both a flow and biogas generation perspective. Dr Short delivered an invited talk on the AI for Net Zero project. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://ebnet.ac.uk/wp-content/uploads/sites/343/2025/03/EBNet-Sludge-Modelling-Workshop-Report.pdf |
| Description | Invited talk at webinar on AD modelling |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Media (as a channel to the public) |
| Results and Impact | Webinar AD Modelling Demystified: Essential Fundamentals and Hands-on Applications In this webinar, we will describe the modelling fundamentals and highlight the benefits associated with its practice. We will break down the two main approaches to modelling anaerobic digestion, mechanistic and data-driven alternatives, along with their pros and cons. Towards the end, we will introduce two useful web modules that are freely available for modelling, showcasing the added value of modelling. Our ultimate goal is to demonstrate the significant role that modelling should play in the context of climate change, industrial automation and digitalisation for both academia and industrial partners. Dr Short presented on the AI for Net Zero project. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.youtube.com/watch?v=aYumR1agTXU&ab_channel=ProCycla |
| Description | Invited talks/panel at African Summit on Entrepreneurship and Innovation |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Dr Short invited to attend the African Summit on Entrepreneurship and Innovation by the Department for Business and Trade. Dr Short presented this project to delegates from across Africa in academia, government and industry. The simple explanations on what AI is and how it can be applied, as well as the potential for bioenergy sparked debate and new partnerships in South Africa. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://www.facebook.com/ASENTIKE/ |
| Description | Joint Research Symposium Webinar with BioMass Canada |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Meshkat Dolat presented his work on 'Anaerobic digestion feedstock acquisition under uncertainty and scheduling optimisation with dynamic demand' to a group of researchers and industry practitioners interested in stoking collaboration between the UK and Canada. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Keynote talk |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Gave a keynote talk at the Carnegie Mellon University Centre for Advanced Process Decision-making (CAPD) Fall Enterprise-Wide Optimisation conference (Oct 2024). |
| Year(s) Of Engagement Activity | 2024 |
| Description | Life Cycle Assessment (LCA) for the EBNet Industrial AD Community-Goal and Scope Definition |
| 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 | We co-hosted an industrial workshop, which attracted 25 industrial practitioners from as far as Germany and Chile to interact in a workshop discussing AD life cycle assessment, challenges and future directions.. This sparked a lot of discussion and has also resulted in new partnerships with some of the companies that attended. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://ebnet.ac.uk/wg-lca-231030-scope/ |
| Description | Magazine article on the project |
| Form Of Engagement Activity | A magazine, newsletter or online publication |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Bywater, A. 'Get Ready for the AI Boost'. AD & Bioresources News, Issue 58, Winter 2024*: 15-17. (https://adbioresources.org/newsroom/ad-bioresources-news-winter-2024/). |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://adbioresources.org/newsroom/ad-bioresources-news-winter-2024/ |
| Description | Media attention related to project announcement |
| 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 | Media (as a channel to the public) |
| Results and Impact | We have been the subject of a fair amount of media attention, with the press release picked up by national and international trade media, including EnviroTech Magazine, AzoRobotics, Green Business Journal, and Biofuels Digest. |
| Year(s) Of Engagement Activity | 2023,2024 |
| URL | https://envirotecmagazine.com/2023/06/14/ai-plus-microbes-could-unlock-higher-biogas-production-for-... |
| Description | Presentation for the AI for Net Zero Youtube Webinar Series |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | A webinar series to engage and inform the AI and NetZero research communities about the ongoing research and development in utilising AI technologies to meet NetZero targets. Dr Michael Short (PI) gave a talk on 'Mathematical optimisation with surrogates and data-driven modelling for sustainable systems: from efficient process synthesis to biogas control and optimisation'. Viewed by over 100 people. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.youtube.com/watch?v=o6JMRJOWG-M&t=5s&ab_channel=AIforNetZeroWebinars |
| Description | Presented at Energy Systems Catapult South Africa Industrial Decarbonisation workshop |
| 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 | Dr Short invited by Energy Systems Catapult to support the FCDO-funded UK-SA Industrial Decarbonisation project. Dr Short presented this project and resulting discussions for engagement with large South African companies, government and academia in future. |
| Year(s) Of Engagement Activity | 2024 |
| Description | TV interview on BBC South |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Media (as a channel to the public) |
| Results and Impact | I was interviewed related to an explosion on an anaerobic digester site in Oxfordshire. |
| Year(s) Of Engagement Activity | 2023 |
| Description | Talk at the AI for Net Zero Youtube Webinar series |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Media (as a channel to the public) |
| Results and Impact | A webinar series to engage and inform the AI and NetZero research communities about the ongoing research and development in utilising AI technologies to meet NetZero targets. Meshkat Dolat, a Research Assistant on the project, gave a talk on 'Anaerobic digestion feedstock acquisition under uncertainty and scheduling optimisation with dynamic demand' |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.youtube.com/watch?v=KoQheBklPR0&ab_channel=AIforNetZeroWebinars |
| Description | Talk at the AI for Net Zero Youtube Webinar series |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Media (as a channel to the public) |
| Results and Impact | o AI for NetZero Webinars ? Video: https://www.youtube.com/watch?v=tTYoxVmPXPc ? Optimization-based operational space design for effective bioprocess performance under uncertainty Presented by PDRA on the project, Dr Mengjia Zhu |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.youtube.com/watch?v=tTYoxVmPXPc |
| Description | Talk at the ECO-AI Workshop: AI-Driven Solutions for Carbon Capture and Storage |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | As part of building the AI for Net Zero Community, I was invited to deliver a talk at the workshop hosted by another project, ECO-AI. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Talk by Industrial Partners to undergraduate and Master's students |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Postgraduate students |
| Results and Impact | Future Biogas colleagues came to University of Surrey to give a talk on the biogas industry to students. Many students have since enquired about the graduate programme at Future Biogas and have shown interest in bioenergy as a career. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Talk on energy systems and role of bioenergy |
| 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 | Gave talk on energy systems and role of bioenergy 3 venues to industry, government and academic audience in March 2024 in Manila (90 delegates, mostly from government), Kuala Lumpur (30 delegates, mostly industry) and Kuching (20 delegates, mostly academic). |
| Year(s) Of Engagement Activity | 2024 |
| Description | Webinar for BioMass Canada |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | PhD Research Presented in Webinar for BioMass Canada and Supergen Bioenergy Hub to show the research in the UK in bioenergy. Attended by around 60 people from Canada and the UK. Has resulted in new research collaborations with University of British Columbia. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Webinar on AD Modelling Demystified: Essential Fundamentals and Hands-on Applications |
| 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 | In this webinar, Dr Short was invited by EBNet and Modela PTY to participate in describing the modelling fundamentals and highlight the benefits associated with its practice. The goal was to demonstrate the significant role that modelling should play in the context of climate change, industrial automation and digitalisation for both academia and industrial partners. We had around 50 people live and the Youtube video has been viewed over 100 times. This has led to follow-up work. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://ebnet.ac.uk/ad-modela-ai-240208/ |
| Description | Webinar on the AI for Net Zero webinar series on Youtube |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | A webinar series to engage and inform the AI and NetZero research communities about the ongoing research and development in utilising AI technologies to meet NetZero targets. Postdoc on the project, Dr Amin Zarei gave a talk on 'A model-based dynamic optimization strategy for co-digestion and CHP-based biogas production. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.youtube.com/watch?v=ishbcSEHoas&ab_channel=AIforNetZeroWebinars |