Wheat Yield Robust Prediction in the Huang-Huai-Hai Plain by Coupling Multi-Source Data with Ensemble Model under Different Irrigation and Extreme Weather Events
Open Access
- 2 April 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (7) , 1259
Abstract
The timely and robust prediction of wheat yield is very significant for grain trade and food security. In this study, the yield prediction model was developed by coupling an ensemble model with multi-source data, including vegetation indices (VIs) and meteorological data. The results showed that green chlorophyll vegetation index (GCVI) is the optimal remote sensing (RS) variable for predicting wheat yield compared with other VIs. The accuracy of the adaptive boosting- long short-term memory (AdaBoost-LSTM) ensemble model was higher than the LSTM model. AdaBoost-LSTM coupled with optimal input data had the best performance. The AdaBoost-LSTM model had strong robustness for predicting wheat yield under different irrigation and extreme weather events in general. Additionally, the accuracy of AdaBoost-LSTM for rainfed counties was higher than that for irrigation counties in most years except extreme years. The yield prediction model developed with the characteristic variables of the window from February to April had higher accuracy and smaller data requirements, which was the best prediction window. Therefore, wheat yield can be accurately predicted by the AdaBoost-LSTM model one to two months of lead time before maturity in the HHHP. Overall, the AdaBoost-LSTM model can achieve accurate and robust yield prediction in large-scale regions.Keywords
Funding Information
- National Natural Science Foundation of China (32371990, 32021004, BE2023368)
- Innovative Research Group Project of the National Natural Science Foundation of China (32371990, 32021004, BE2023368)
- Jiangsu Provincial Key R&D plan (32371990, 32021004, BE2023368)
This publication has 86 references indexed in Scilit:
- Dynamic wheat yield forecasts are improved by a hybrid approach using a biophysical model and machine learning techniqueAgricultural and Forest Meteorology, 2020
- Mapping sub-field maize yields in Nebraska, USA by combining remote sensing imagery, crop simulation models, and machine learningPrecision Agriculture, 2019
- Incorporating machine learning with biophysical model can improve the evaluation of climate extremes impacts on wheat yield in south-eastern AustraliaAgricultural and Forest Meteorology, 2019
- Integrating satellite and climate data to predict wheat yield in Australia using machine learning approachesAgricultural and Forest Meteorology, 2019
- Mapping the agricultural land use of the North China Plain in 2002 and 2012Journal of Geographical Sciences, 2019
- Improving the accuracy of satellite-based high-resolution yield estimation: A test of multiple scalable approachesAgricultural and Forest Meteorology, 2017
- Development of an in-season estimate of yield potential utilizing optical crop sensors and soil moisture data for winter wheatPrecision Agriculture, 2016
- A comparative analysis of multitemporal MODIS EVI and NDVI data for large-scale rice yield estimationAgricultural and Forest Meteorology, 2014
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Red and photographic infrared linear combinations for monitoring vegetationRemote Sensing of Environment, 1979