Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments
Context Accurately projecting crop yields under climate change is essential for understanding potential impacts and planning of agricultural adaptation in sub-Saharan Africa (SSA). Crop growth models and machine learning (ML) are often used, but their effectiveness is limited by data availability,...
| Autores principales: | , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
Elsevier
2025
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/178106 |
| _version_ | 1855542895377907712 |
|---|---|
| author | Alimagham, Seyyedmajid van Loon, Marloes P Ramirez Villegas, Julian Berghuijs, Herman N.C. Rosenstock, Todd Stuart van Ittersum, Martin K. |
| author_browse | Alimagham, Seyyedmajid Berghuijs, Herman N.C. Ramirez Villegas, Julian Rosenstock, Todd Stuart van Ittersum, Martin K. van Loon, Marloes P |
| author_facet | Alimagham, Seyyedmajid van Loon, Marloes P Ramirez Villegas, Julian Berghuijs, Herman N.C. Rosenstock, Todd Stuart van Ittersum, Martin K. |
| author_sort | Alimagham, Seyyedmajid |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Context
Accurately projecting crop yields under climate change is essential for understanding potential impacts and planning of agricultural adaptation in sub-Saharan Africa (SSA). Crop growth models and machine learning (ML) are often used, but their effectiveness is limited by data availability, precision, and geographic coverage in SSA.
Objective
This study aimed to integrate ML with a process-based crop model to produce geographically continuous gridded crop yield projections while reducing uncertainties associated with standalone ML or crop growth models. As a case study, we implemented it to project the climate change impact on water-limited potential yield of maize across SSA.
Methods
We developed an integrated system that combines ML with eco-physiological processes to estimate sowing dates and thermal times, ensuring that crop phenology is accounted for, thus improving potential rainfed yield simulations under varying environmental conditions. Random Forest and crop model-based algorithms are integrated in three steps: (i) RF1, a Random Forest model integrated with a sowing algorithm, designed to estimate the sowing window and sowing date; (ii) RF2, a Random Forest model combined with a crop model algorithm to estimate cumulative thermal time during the growing season, used to determine the timing of phenological stages; and (iii) RF3, another Random Forest model, trained based on eco-physiological principles applied in phases (i) and (ii), employed to simulate water-limited potential yield. The outcomes of the different steps of the framework under historical conditions were tested against reported data across SSA.
Results and conclusions
For maize and historical climatic conditions, the framework delivers yields which differ less than 20 % of those simulated with a crop model with high-quality inputs, in 95 % of the cases. Our approach thus shows value for generating crop yield projections in data-scarce regions under historical climate, and under future climatic conditions which already feature today somewhere in SSA and for which the framework has been trained.
Significance
Our approach can also be applied to other major food crops in SSA, under both current and climate change conditions. It allows testing the effect of adaptation of crop cultivars in terms of maturity group. Thus, it can be used for different crops and with far less data requirements compared to process-based crop models. It has the potential for significant applications in assessing climate change impacts, guiding adaptation strategies, and supporting crop breeding programes and policymaking efforts in SSA. |
| format | Journal Article |
| id | CGSpace178106 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| record_format | dspace |
| spelling | CGSpace1781062025-12-08T10:29:22Z Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments Alimagham, Seyyedmajid van Loon, Marloes P Ramirez Villegas, Julian Berghuijs, Herman N.C. Rosenstock, Todd Stuart van Ittersum, Martin K. machine learning adaptation crop modelling climate change impacts sowing date phenology maximum sustainable yield Context Accurately projecting crop yields under climate change is essential for understanding potential impacts and planning of agricultural adaptation in sub-Saharan Africa (SSA). Crop growth models and machine learning (ML) are often used, but their effectiveness is limited by data availability, precision, and geographic coverage in SSA. Objective This study aimed to integrate ML with a process-based crop model to produce geographically continuous gridded crop yield projections while reducing uncertainties associated with standalone ML or crop growth models. As a case study, we implemented it to project the climate change impact on water-limited potential yield of maize across SSA. Methods We developed an integrated system that combines ML with eco-physiological processes to estimate sowing dates and thermal times, ensuring that crop phenology is accounted for, thus improving potential rainfed yield simulations under varying environmental conditions. Random Forest and crop model-based algorithms are integrated in three steps: (i) RF1, a Random Forest model integrated with a sowing algorithm, designed to estimate the sowing window and sowing date; (ii) RF2, a Random Forest model combined with a crop model algorithm to estimate cumulative thermal time during the growing season, used to determine the timing of phenological stages; and (iii) RF3, another Random Forest model, trained based on eco-physiological principles applied in phases (i) and (ii), employed to simulate water-limited potential yield. The outcomes of the different steps of the framework under historical conditions were tested against reported data across SSA. Results and conclusions For maize and historical climatic conditions, the framework delivers yields which differ less than 20 % of those simulated with a crop model with high-quality inputs, in 95 % of the cases. Our approach thus shows value for generating crop yield projections in data-scarce regions under historical climate, and under future climatic conditions which already feature today somewhere in SSA and for which the framework has been trained. Significance Our approach can also be applied to other major food crops in SSA, under both current and climate change conditions. It allows testing the effect of adaptation of crop cultivars in terms of maturity group. Thus, it can be used for different crops and with far less data requirements compared to process-based crop models. It has the potential for significant applications in assessing climate change impacts, guiding adaptation strategies, and supporting crop breeding programes and policymaking efforts in SSA. 2025-08-01 2025-11-24T10:31:52Z 2025-11-24T10:31:52Z Journal Article https://hdl.handle.net/10568/178106 en Open Access application/pdf Elsevier Alimagham, S.; van Loon, M.P.; Ramirez Villegas, J.; Berghuijs, H.N.; Rosenstock, T.S.; van Ittersum, M.K. (2025) Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments. Agricultural Systems 228: 104367. ISSN: 0308-521X |
| spellingShingle | machine learning adaptation crop modelling climate change impacts sowing date phenology maximum sustainable yield Alimagham, Seyyedmajid van Loon, Marloes P Ramirez Villegas, Julian Berghuijs, Herman N.C. Rosenstock, Todd Stuart van Ittersum, Martin K. Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments |
| title | Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments |
| title_full | Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments |
| title_fullStr | Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments |
| title_full_unstemmed | Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments |
| title_short | Integrating crop models and machine learning for projecting climate change impacts on crops in data-limited environments |
| title_sort | integrating crop models and machine learning for projecting climate change impacts on crops in data limited environments |
| topic | machine learning adaptation crop modelling climate change impacts sowing date phenology maximum sustainable yield |
| url | https://hdl.handle.net/10568/178106 |
| work_keys_str_mv | AT alimaghamseyyedmajid integratingcropmodelsandmachinelearningforprojectingclimatechangeimpactsoncropsindatalimitedenvironments AT vanloonmarloesp integratingcropmodelsandmachinelearningforprojectingclimatechangeimpactsoncropsindatalimitedenvironments AT ramirezvillegasjulian integratingcropmodelsandmachinelearningforprojectingclimatechangeimpactsoncropsindatalimitedenvironments AT berghuijshermannc integratingcropmodelsandmachinelearningforprojectingclimatechangeimpactsoncropsindatalimitedenvironments AT rosenstocktoddstuart integratingcropmodelsandmachinelearningforprojectingclimatechangeimpactsoncropsindatalimitedenvironments AT vanittersummartink integratingcropmodelsandmachinelearningforprojectingclimatechangeimpactsoncropsindatalimitedenvironments |