Machine learning for yield prediction in Fergana valley, Central Asia
Accurate yield prediction is essential for growers, researchers, governments, the farming industry, and policymakers for social peace, food safety, security, and sustainable development. The results of earlier techniques of data collecting and analysis for yield forecasts were typically delayed, exp...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-02-01
|
| Series: | Journal of the Saudi Society of Agricultural Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1658077X22000777 |
| _version_ | 1811161838621032448 |
|---|---|
| author | Mukesh Singh Boori Komal Choudhary Rustam Paringer Alexander Kupriyanov |
| author_facet | Mukesh Singh Boori Komal Choudhary Rustam Paringer Alexander Kupriyanov |
| author_sort | Mukesh Singh Boori |
| collection | DOAJ |
| description | Accurate yield prediction is essential for growers, researchers, governments, the farming industry, and policymakers for social peace, food safety, security, and sustainable development. The results of earlier techniques of data collecting and analysis for yield forecasts were typically delayed, expensive, time-consuming, site-specific, and riddled with errors and uncertainties. This study is a novel approach to using high-resolution satellite data in conjunction with environmental and topographic data to predict wheat yield variability at the farm scale using machine learning. In this research, winter wheat yield prediction was based on 36 indicators in machine learning using correlation and different regression models. Winter wheat yield was predicted using linear regression (LR), decision tree (DT), and random forest (RF) regression models with scikit-learn in machine learning. More than 10,000 data points from 45 farms were trained and validated in Fergana valley, Central Asia. Results indicate that at 10 m resolution using Sentinel-2 and other secondary data such as topographic, soil, environmental, and filed data can generate an accurate wheat yield prediction map. The accuracy of all regressions is lowest for LR (R2:95, RMSE: 2.31), highest for RF (R2:98, RMSE: 1.40), and intermediate for DT regression (R2:97, RMSE: 1.85). Results also indicate that prediction in the early stage of the crop is less accurate in comparison to harvesting time as LR (R2:85, RMSE: 2.66), DT (R2:95, RMSE: 2.06), RF (R2:97, RMSE: 1.54) have different R2 and RMSE values. Appling the RF model, the winter wheat prediction is 3.29 to 4.30 t/ha therefore the total wheat production is approximately 100 t in the study area. Thus this study will demonstrate the capability of high-resolution satellite imagery and secondary data for highly accurate real-time crop yield prediction at the field scale, which can be used to assist precision agriculture and will provide a point of reference for crop area extraction, mapping, monitoring, and sustainable development with food security. |
| first_indexed | 2024-04-10T06:21:41Z |
| format | Article |
| id | doaj.art-6ecf94aa77214498a4697e61832c80b4 |
| institution | Directory Open Access Journal |
| issn | 1658-077X |
| language | English |
| last_indexed | 2024-04-10T06:21:41Z |
| publishDate | 2023-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of the Saudi Society of Agricultural Sciences |
| spelling | doaj.art-6ecf94aa77214498a4697e61832c80b42023-03-02T04:59:02ZengElsevierJournal of the Saudi Society of Agricultural Sciences1658-077X2023-02-01222107120Machine learning for yield prediction in Fergana valley, Central AsiaMukesh Singh Boori0Komal Choudhary1Rustam Paringer2Alexander Kupriyanov3Scientific Research Laboratory of Automated Systems of Scientific Research (SRL-35), Samara National Research University, Samara, Russia; Corresponding authors.Scientific Research Laboratory of Automated Systems of Scientific Research (SRL-35), Samara National Research University, Samara, Russia; Department of Land Surveying and Geo- Informatics, Smart Cities Research Institute, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China; Corresponding authors.Scientific Research Laboratory of Automated Systems of Scientific Research (SRL-35), Samara National Research University, Samara, Russia; Image Processing Systems Institute of the RAS–Branch of the FSRC “Crystallography and Photonics”, Samara, RussiaScientific Research Laboratory of Automated Systems of Scientific Research (SRL-35), Samara National Research University, Samara, Russia; Image Processing Systems Institute of the RAS–Branch of the FSRC “Crystallography and Photonics”, Samara, RussiaAccurate yield prediction is essential for growers, researchers, governments, the farming industry, and policymakers for social peace, food safety, security, and sustainable development. The results of earlier techniques of data collecting and analysis for yield forecasts were typically delayed, expensive, time-consuming, site-specific, and riddled with errors and uncertainties. This study is a novel approach to using high-resolution satellite data in conjunction with environmental and topographic data to predict wheat yield variability at the farm scale using machine learning. In this research, winter wheat yield prediction was based on 36 indicators in machine learning using correlation and different regression models. Winter wheat yield was predicted using linear regression (LR), decision tree (DT), and random forest (RF) regression models with scikit-learn in machine learning. More than 10,000 data points from 45 farms were trained and validated in Fergana valley, Central Asia. Results indicate that at 10 m resolution using Sentinel-2 and other secondary data such as topographic, soil, environmental, and filed data can generate an accurate wheat yield prediction map. The accuracy of all regressions is lowest for LR (R2:95, RMSE: 2.31), highest for RF (R2:98, RMSE: 1.40), and intermediate for DT regression (R2:97, RMSE: 1.85). Results also indicate that prediction in the early stage of the crop is less accurate in comparison to harvesting time as LR (R2:85, RMSE: 2.66), DT (R2:95, RMSE: 2.06), RF (R2:97, RMSE: 1.54) have different R2 and RMSE values. Appling the RF model, the winter wheat prediction is 3.29 to 4.30 t/ha therefore the total wheat production is approximately 100 t in the study area. Thus this study will demonstrate the capability of high-resolution satellite imagery and secondary data for highly accurate real-time crop yield prediction at the field scale, which can be used to assist precision agriculture and will provide a point of reference for crop area extraction, mapping, monitoring, and sustainable development with food security.http://www.sciencedirect.com/science/article/pii/S1658077X22000777Yield predictionRegressionSentinel-2Spectral-indicesMachine learningPhenology |
| spellingShingle | Mukesh Singh Boori Komal Choudhary Rustam Paringer Alexander Kupriyanov Machine learning for yield prediction in Fergana valley, Central Asia Journal of the Saudi Society of Agricultural Sciences Yield prediction Regression Sentinel-2 Spectral-indices Machine learning Phenology |
| title | Machine learning for yield prediction in Fergana valley, Central Asia |
| title_full | Machine learning for yield prediction in Fergana valley, Central Asia |
| title_fullStr | Machine learning for yield prediction in Fergana valley, Central Asia |
| title_full_unstemmed | Machine learning for yield prediction in Fergana valley, Central Asia |
| title_short | Machine learning for yield prediction in Fergana valley, Central Asia |
| title_sort | machine learning for yield prediction in fergana valley central asia |
| topic | Yield prediction Regression Sentinel-2 Spectral-indices Machine learning Phenology |
| url | http://www.sciencedirect.com/science/article/pii/S1658077X22000777 |
| work_keys_str_mv | AT mukeshsinghboori machinelearningforyieldpredictioninferganavalleycentralasia AT komalchoudhary machinelearningforyieldpredictioninferganavalleycentralasia AT rustamparinger machinelearningforyieldpredictioninferganavalleycentralasia AT alexanderkupriyanov machinelearningforyieldpredictioninferganavalleycentralasia |