Fertiliser Use Efficiency with AI
Lead Research Organisation:
University of Southampton
Department Name: Sch of Engineering
Abstract
One of the biggest challenges facing the agricultural industry is achieving high yields with the use of fertilisers while simultaneously minimising the environmental side effects of the fertiliser application and production. In this highly weather-reliant industry, developing weather-dependent fertilisation strategies will help maintain crop production and reduce the greenhouse gas (GHG) emissions in the face of climate change. This is particularly important for phosphorus and nitrogen (P&N) fertilisers, which have a high environmental footprint in terms of GHG emissions and pollution. One approach to achieving this goal is by harnessing new computational technologies within a precision agriculture framework.
In the first six months of 2022, fertiliser prices have significantly increased and in some cases tripled. These prices are likely to remain volatile; the increases are largely driven by disruptions to the production due to climate change (warming, droughts etc) and geopolitics (energy/gas supply, war in Ukraine etc). In addition, the Haber-Bosch process for nitrogen fertiliser production is at best of times a highly energy consuming process responsible for 1.2% of the global energy usage. While there are worldwide efforts to deal with climate change, the climate is expected to remain volatile for the foreseeable future. Computer simulations are a valuable tool for considering climate volatility, as they allow for the testing of different soil/crop management approaches under different climate scenarios. Computer simulations/models for fertiliser use efficiency (FUE) allow for fast and cheap testing of different scenarios as part of the multifaceted decision making process for fertilisation applications. Approaches to enhance FUE address at least one of the 4R's of FUE: right type of fertiliser, right rate, right time and right place of application. My ERC Consolidator Grant (CoG) DIMR-646809 created new mathematical models, which now allow us to start tackling these issues.
In the first six months of 2022, fertiliser prices have significantly increased and in some cases tripled. These prices are likely to remain volatile; the increases are largely driven by disruptions to the production due to climate change (warming, droughts etc) and geopolitics (energy/gas supply, war in Ukraine etc). In addition, the Haber-Bosch process for nitrogen fertiliser production is at best of times a highly energy consuming process responsible for 1.2% of the global energy usage. While there are worldwide efforts to deal with climate change, the climate is expected to remain volatile for the foreseeable future. Computer simulations are a valuable tool for considering climate volatility, as they allow for the testing of different soil/crop management approaches under different climate scenarios. Computer simulations/models for fertiliser use efficiency (FUE) allow for fast and cheap testing of different scenarios as part of the multifaceted decision making process for fertilisation applications. Approaches to enhance FUE address at least one of the 4R's of FUE: right type of fertiliser, right rate, right time and right place of application. My ERC Consolidator Grant (CoG) DIMR-646809 created new mathematical models, which now allow us to start tackling these issues.
Organisations
People |
ORCID iD |
Tiina Roose (Principal Investigator) |
Description | One of the biggest challenges facing the agricultural industry is achieving high yields with the use of fertilisers while simultaneously minimising the environmental side effects of the fertiliser application and production. In this highly weather-reliant industry, developing weather-dependent fertilisation strategies will help maintain crop production and reduce the greenhouse gas (GHG) emissions in the face of climate change. This is particularly important for phosphorus and nitrogen (P&N) fertilisers, which have a high environmental footprint for production and pollution (P&N), and direct GHG emission during use (N). One approach to achieving this goal is by harnessing new computational technologies within a precision agriculture framework. In the first six months of 2022, fertiliser prices have significantly increased and in some cases tripled. These prices are likely to remain volatile; the increases are largely driven by disruptions to the production due to climate change (warming, droughts etc) and geopolitics (energy/gas supply, war in Ukraine etc). In addition, the Haber-Bosch process for nitrogen fertiliser production is at best of times a highly energy consuming process responsible for 1.2% of the global energy usage. While there are some worldwide efforts to deal with climate change, the climate is expected to remain volatile for the foreseeable future. Computer simulations are a valuable tool for considering climate volatility, as they allow for the testing of different soil/crop management approaches under different climate scenarios. Computer simulations/models for fertiliser use efficiency (FUE) allow for fast and cheap testing of different scenarios as part of the multifaceted decision making process for fertiliser applications. Approaches to enhance FUE address at least one of the 4R's of FUE: right type of fertiliser, right rate, right time and right place of application. My ERC Consolidator Grant (CoG) DIMR-646809 created new mathematical models, which now allow us to start tackling the right time and place issues of the 4Rs in the changing climate. The solution: Development of AI and machine learning tools for time optimised fertilisation applications. Currently, the new models based on the state of the art ERC CoG work are research tools that have produced new scientific knowledge about processes influencing plant P&N uptake. We now want to integrate these models with historical weather data (e.g. rainfall, temperature, etc.) and climate prediction models to assess the general trends and impacts that climate change would have on fertiliser use practices. We also plan to demonstrate that these models can be integrated with artificial intelligence approaches to develop decision support tools for agriculture, which can help determine optimal fertilisation times based on short term weather forecasts. Findings: We found as part of this project that consolidating data from multiple fertiliser field trials is hard. Whilst lots of data is created and stored the sparsity of metadata is often limiting for modelling. The best data for modelling was found from the James Hutton Institute due to the institute's systematic approach to data science. EU wide efforts to use data were less successful as far too often the data science part of projects was underfunded hence impeding the re-use of the data for modelling. |
Exploitation Route | The key outcome is the need to work across countries and jurisdiction towards standardized data and metadata formats for soil and crop fertiliser trials as to maximize public benefit from the investments by reuse for modelling and AI enabled agriculture. |
Sectors | Agriculture Food and Drink Manufacturing including Industrial Biotechology |
Description | We have used the project results to engage with fertiliser and farming industry about their needs for optimizing fertiliser use efficiency whilst maximizing food production. Please see the other sections of this report. |
First Year Of Impact | 2024 |
Sector | Agriculture, Food and Drink,Environment,Manufacturing, including Industrial Biotechology |
Impact Types | Societal Economic |
Description | FERT-TIME app demonstration at the International Fertilizer Society Conference in Dec 2024 in Cambridge |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Software demo and poster presentation at the International Fertilizer Society meeting in Cambridge Dec 2024. Title: FERT-TIME Optimum Fertiliser Timin App Authors: Nic Fair, Tiina Roose, Dan McKay Fletches, Siul Ruiz, Nancy Walker, Stefano Modafferi, Jakub Dylag |
Year(s) Of Engagement Activity | 2024 |
URL | https://fertiliser-society.org/ifs-events/2024-ifs-conference/ |
Description | Presentation at the International Fertilizer Society meeting in Cambridge Dec 2023 to gauge fertilizer app user needs |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Presentation at the Fertilizer Society meeting in Cambridge Dec 2023 to gauge user needs for optimal fertilizer application mobile app Title: The AI-optimised fertiliser use efficiency app Authors: Nic Fair, Dan McKay Fletches, Stefano Modafferi, Siul Ruiz, Tiina Roose |
Year(s) Of Engagement Activity | 2023 |
URL | https://fertiliser-society.org/ifs-events/2023-ifs-conference/ |