Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction
Subseasonal-to-seasonal (S2S) prediction of winter wheat yields is crucial for farmers and decision-makers to reduce yield losses and ensure food security. Recently, numerous researchers have utilized machine learning (ML) methods to predict crop yield, using observational climate variables and sate...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/7/1707 |
| _version_ | 1827622588199731200 |
|---|---|
| author | Junjun Cao Huijing Wang Jinxiao Li Qun Tian Dev Niyogi |
| author_facet | Junjun Cao Huijing Wang Jinxiao Li Qun Tian Dev Niyogi |
| author_sort | Junjun Cao |
| collection | DOAJ |
| description | Subseasonal-to-seasonal (S2S) prediction of winter wheat yields is crucial for farmers and decision-makers to reduce yield losses and ensure food security. Recently, numerous researchers have utilized machine learning (ML) methods to predict crop yield, using observational climate variables and satellite data. Meanwhile, some studies also illustrated the potential of state-of-the-art dynamical atmospheric prediction in crop yield forecasting. However, the potential of coupling both methods has not been fully explored. Herein, we aimed to establish a skilled ML–dynamical hybrid model for crop yield forecasting (MHCF v1.0), which hybridizes ML and a global dynamical atmospheric prediction system, and applied it to northern China at the S2S time scale. In this study, we adopted three mainstream machining learning algorithms (XGBoost, RF, and SVR) and the multiple linear regression (MLR) model, and three major datasets, including satellite data from MOD13C1, observational climate data from CRU, and S2S atmospheric prediction data from IAP CAS, used to predict winter wheat yield from 2005 to 2014, at the grid level. We found that, among the four models examined in this work, XGBoost reached the highest skill with the S2S prediction as inputs, scoring R<sup>2</sup> of 0.85 and RMSE of 0.78 t/ha 3–4 months, leading the winter wheat harvest. Moreover, the results demonstrated that crop yield forecasting with S2S dynamical predictions generally outperforms that with observational climate data. Our findings highlighted that the coupling of ML and S2S dynamical atmospheric prediction provided a useful tool for yield forecasting, which could guide agricultural practices, policy-making and agricultural insurance. |
| first_indexed | 2024-03-09T11:28:37Z |
| format | Article |
| id | doaj.art-942f8b1c0d1a474dbc6ae095756b0af2 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:28:37Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-942f8b1c0d1a474dbc6ae095756b0af22023-11-30T23:57:48ZengMDPI AGRemote Sensing2072-42922022-04-01147170710.3390/rs14071707Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble PredictionJunjun Cao0Huijing Wang1Jinxiao Li2Qun Tian3Dev Niyogi4Key Laboratory of Geographical Process Analysis & Simulation of Hubei Province, College of Urban and Environmental Sciences, Central China Normal University, Wuhan 430079, ChinaKey Laboratory of Geographical Process Analysis & Simulation of Hubei Province, College of Urban and Environmental Sciences, Central China Normal University, Wuhan 430079, ChinaState Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, ChinaGuangdong Provincial Key Laboratory of Regional Numerical Weather Prediction, Guangzhou Institute of Tropical and Marine Meteorology, CMA, Guangzhou 510641, ChinaDepartment of Geological Sciences, Jackson School of Geosciences, University of Texas at Austin, Austin, TX 78712, USASubseasonal-to-seasonal (S2S) prediction of winter wheat yields is crucial for farmers and decision-makers to reduce yield losses and ensure food security. Recently, numerous researchers have utilized machine learning (ML) methods to predict crop yield, using observational climate variables and satellite data. Meanwhile, some studies also illustrated the potential of state-of-the-art dynamical atmospheric prediction in crop yield forecasting. However, the potential of coupling both methods has not been fully explored. Herein, we aimed to establish a skilled ML–dynamical hybrid model for crop yield forecasting (MHCF v1.0), which hybridizes ML and a global dynamical atmospheric prediction system, and applied it to northern China at the S2S time scale. In this study, we adopted three mainstream machining learning algorithms (XGBoost, RF, and SVR) and the multiple linear regression (MLR) model, and three major datasets, including satellite data from MOD13C1, observational climate data from CRU, and S2S atmospheric prediction data from IAP CAS, used to predict winter wheat yield from 2005 to 2014, at the grid level. We found that, among the four models examined in this work, XGBoost reached the highest skill with the S2S prediction as inputs, scoring R<sup>2</sup> of 0.85 and RMSE of 0.78 t/ha 3–4 months, leading the winter wheat harvest. Moreover, the results demonstrated that crop yield forecasting with S2S dynamical predictions generally outperforms that with observational climate data. Our findings highlighted that the coupling of ML and S2S dynamical atmospheric prediction provided a useful tool for yield forecasting, which could guide agricultural practices, policy-making and agricultural insurance.https://www.mdpi.com/2072-4292/14/7/1707yield forecastingclimate variablessubseasonal-to-seasonal predictionmachine learningwinter wheat |
| spellingShingle | Junjun Cao Huijing Wang Jinxiao Li Qun Tian Dev Niyogi Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction Remote Sensing yield forecasting climate variables subseasonal-to-seasonal prediction machine learning winter wheat |
| title | Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction |
| title_full | Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction |
| title_fullStr | Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction |
| title_full_unstemmed | Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction |
| title_short | Improving the Forecasting of Winter Wheat Yields in Northern China with Machine Learning–Dynamical Hybrid Subseasonal-to-Seasonal Ensemble Prediction |
| title_sort | improving the forecasting of winter wheat yields in northern china with machine learning dynamical hybrid subseasonal to seasonal ensemble prediction |
| topic | yield forecasting climate variables subseasonal-to-seasonal prediction machine learning winter wheat |
| url | https://www.mdpi.com/2072-4292/14/7/1707 |
| work_keys_str_mv | AT junjuncao improvingtheforecastingofwinterwheatyieldsinnorthernchinawithmachinelearningdynamicalhybridsubseasonaltoseasonalensembleprediction AT huijingwang improvingtheforecastingofwinterwheatyieldsinnorthernchinawithmachinelearningdynamicalhybridsubseasonaltoseasonalensembleprediction AT jinxiaoli improvingtheforecastingofwinterwheatyieldsinnorthernchinawithmachinelearningdynamicalhybridsubseasonaltoseasonalensembleprediction AT quntian improvingtheforecastingofwinterwheatyieldsinnorthernchinawithmachinelearningdynamicalhybridsubseasonaltoseasonalensembleprediction AT devniyogi improvingtheforecastingofwinterwheatyieldsinnorthernchinawithmachinelearningdynamicalhybridsubseasonaltoseasonalensembleprediction |