Search

Timely and accurate crop yield information can ensure regional food security. In the field of predicting crop yields, deep learning techniques such as long short-term memory (LSTM) and convolutional neural networks (CNN) are frequently employed. Many studies have shown that the predictions of models combining the two are better than those of single models. Crop growth can be reflected by the vegetation index calculated using data from remote sensing. However, the use of pure remote sensing data alone ignores the spatial heterogeneity of different regions. In this paper, we tested a total of three models, CNN-LSTM, CNN and convolutional LSTM (ConvLSTM), for predicting the annual rice yield at the county level in Hubei Province, China. The model was trained by ERA5 temperature (AT) data, MODIS remote sensing data including the Enhanced Vegetation Index (EVI), Gross Primary Productivity (GPP) and Soil-Adapted Vegetation Index (SAVI), and a dummy variable representing spatial heterogeneity; rice yield data from 2000–2019 were employed as labels. Data download and processing were based on Google Earth Engine (GEE). The downloaded remote sensing images were processed into normalized histograms for the training and prediction of deep learning models. According to the experimental findings, the model that included a dummy variable to represent spatial heterogeneity had a stronger predictive ability than the model trained using just remote sensing data. The prediction performance of the CNN-LSTM model outperformed the CNN or ConvLSTM model. [ABSTRACT FROM AUTHOR]

Accurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an under-development of deep-learning frameworks. To tackle this issue, we integrated multi-source (remote sensing, weather, and soil properties) data into a dual-stream deep-learning neural network model for winter wheat in China's major planting regions. The model consists of two branches for robust feature learning: one for sequential data (remote sensing and weather series data) and the other for statical data (soil properties). The extracted features by both branches were aggregated through an adaptive fusion model to forecast the final wheat yield. We trained and tested the model by using official county-level statistics of historical winter wheat yields. The model achieved an average R2 of 0.79 and a root-mean-square error of 650.21 kg/ha, superior to the compared methods and outperforming traditional machine-learning methods. The dual-stream deep-learning neural network model provided decent in-season yield prediction, with an error of about 13% compared to official statistics about two months before harvest. By effectively extracting and aggregating features from multi-source datasets, the new approach provides a practical approach to predicting winter wheat yields at the county scale over large spatial regions. [ABSTRACT FROM AUTHOR]