Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience
The potential for operations research with farmer supplied data coupled with machine learning to improve crop management is explored through a series of case studies from developing countries. The information provided by the farmers ranged from solely yield to a description of the management of the...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Language: | Inglés |
| Published: |
Elsevier
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/129905 |
| _version_ | 1855542537125625856 |
|---|---|
| author | Cock, James H. Jiménez, Daniel Dorado, Hugo Oberthür, Thomas |
| author_browse | Cock, James H. Dorado, Hugo Jiménez, Daniel Oberthür, Thomas |
| author_facet | Cock, James H. Jiménez, Daniel Dorado, Hugo Oberthür, Thomas |
| author_sort | Cock, James H. |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | The potential for operations research with farmer supplied data coupled with machine learning to improve crop management is explored through a series of case studies from developing countries. The information provided by the farmers ranged from solely yield to a description of the management of the crop and some details of the growth environment. The climate or weather conditions of the georeferenced farms were estimated from publicly available data bases. Two principle analytical approaches were used. The first benchmarks crop performance against farmers practices and the second establishes relatively Homogenous Environmental Conditions (HECs) in which the variation in crop response is due to variation in management practices and not to spatiotemporal variation in biophysical factors. Both approaches depend on large amounts of data which can only realistically be obtained from records of on farm experiences using an operations research focus. Machine learning effectively defined HECs for crops with limited prior knowledge on the biophysical factors that influence crop response. The definition of HECs facilitated the identification of either individual farmers who managed their crops well within individual HECs or combinations of management practices well suited to the specific spatiotemporal environmental conditions. This opens the way for farmers to learn better agricultural practices from others in the same HEC. Variation in yield and fertilizer response was associated with variation in the El Niño Southern Oscillation (ENSO) patterns up to 24 months before the harvest: this offers the opportunity for farmers to minimizes risk, based on ENSO predictions, even when they have no information on how ENSO influences their weather patterns. Despite concerns about the quality of farmer data, the consistency of the analyses suggests that even relatively crude production data from individual farms analysed with machine learning can provide useful guidelines for crop management. Limited variation in management on farmers’ fields may limit the ability to identify optimal practices, however, this constraint can be partially obviated by superimposing varied management practices on farmers’ fields. The use of operations research combined with machine learning complements, rather than replaces, traditional research methodologies. Furthermore, the approach must be used carefully with emphasis on the dangers of extrapolation to circumstances that are not encompassed by the original data sets. |
| format | Journal Article |
| id | CGSpace129905 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| record_format | dspace |
| spelling | CGSpace1299052025-11-11T19:09:14Z Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience Cock, James H. Jiménez, Daniel Dorado, Hugo Oberthür, Thomas risk management machine learning agricultural practices operations research crop production crop management The potential for operations research with farmer supplied data coupled with machine learning to improve crop management is explored through a series of case studies from developing countries. The information provided by the farmers ranged from solely yield to a description of the management of the crop and some details of the growth environment. The climate or weather conditions of the georeferenced farms were estimated from publicly available data bases. Two principle analytical approaches were used. The first benchmarks crop performance against farmers practices and the second establishes relatively Homogenous Environmental Conditions (HECs) in which the variation in crop response is due to variation in management practices and not to spatiotemporal variation in biophysical factors. Both approaches depend on large amounts of data which can only realistically be obtained from records of on farm experiences using an operations research focus. Machine learning effectively defined HECs for crops with limited prior knowledge on the biophysical factors that influence crop response. The definition of HECs facilitated the identification of either individual farmers who managed their crops well within individual HECs or combinations of management practices well suited to the specific spatiotemporal environmental conditions. This opens the way for farmers to learn better agricultural practices from others in the same HEC. Variation in yield and fertilizer response was associated with variation in the El Niño Southern Oscillation (ENSO) patterns up to 24 months before the harvest: this offers the opportunity for farmers to minimizes risk, based on ENSO predictions, even when they have no information on how ENSO influences their weather patterns. Despite concerns about the quality of farmer data, the consistency of the analyses suggests that even relatively crude production data from individual farms analysed with machine learning can provide useful guidelines for crop management. Limited variation in management on farmers’ fields may limit the ability to identify optimal practices, however, this constraint can be partially obviated by superimposing varied management practices on farmers’ fields. The use of operations research combined with machine learning complements, rather than replaces, traditional research methodologies. Furthermore, the approach must be used carefully with emphasis on the dangers of extrapolation to circumstances that are not encompassed by the original data sets. 2023-06 2023-04-05T14:24:44Z 2023-04-05T14:24:44Z Journal Article https://hdl.handle.net/10568/129905 en Open Access application/pdf Elsevier Cock, J.; Jiménez, D.; Dorado, H.; Oberthur, T. (2023) Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience. Current Opinion in Environmental Sustainability 62: 101278. ISSN: 1877-3435 |
| spellingShingle | risk management machine learning agricultural practices operations research crop production crop management Cock, James H. Jiménez, Daniel Dorado, Hugo Oberthür, Thomas Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience |
| title | Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience |
| title_full | Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience |
| title_fullStr | Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience |
| title_full_unstemmed | Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience |
| title_short | Operations research and machine learning to manage risk and optimize production practices in agriculture: good and bad experience |
| title_sort | operations research and machine learning to manage risk and optimize production practices in agriculture good and bad experience |
| topic | risk management machine learning agricultural practices operations research crop production crop management |
| url | https://hdl.handle.net/10568/129905 |
| work_keys_str_mv | AT cockjamesh operationsresearchandmachinelearningtomanageriskandoptimizeproductionpracticesinagriculturegoodandbadexperience AT jimenezdaniel operationsresearchandmachinelearningtomanageriskandoptimizeproductionpracticesinagriculturegoodandbadexperience AT doradohugo operationsresearchandmachinelearningtomanageriskandoptimizeproductionpracticesinagriculturegoodandbadexperience AT oberthurthomas operationsresearchandmachinelearningtomanageriskandoptimizeproductionpracticesinagriculturegoodandbadexperience |