Abstract
Crop yield prediction is extremely challenging due to its dependence on multiple factors such as crop genotype, environmental factors, management practices, and their interactions. This paper presents a deep learning framework using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for crop yield prediction based on environmental data and management practices. The proposed CNN-RNN model, along with other popular methods such as random forest (RF), deep fully connected neural networks (DFNN), and LASSO, was used to forecast corn and soybean yield across the entire Corn Belt (including 13 states) in the United States for years 2016, 2017, and 2018 using historical data. The new model achieved a root-mean-square-error (RMSE) 9% and 8% of their respective average yields, substantially outperforming all other methods that were tested. The CNN-RNN has three salient features that make it a potentially useful method for other crop yield prediction studies. (1) The CNN-RNN model was designed to capture the time dependencies of environmental factors and the genetic improvement of seeds over time without having their genotype information. (2) The model demonstrated the capability to generalize the yield prediction to untested environments without significant drop in the prediction accuracy. (3) Coupled with the backpropagation method, the model could reveal the extent to which weather conditions, accuracy of weather predictions, soil conditions, and management practices were able to explain the variation in the crop yields.
Highlights
Crop yield is affected by many factors such as crop genotype, environment, and management practices
The W-convolutional neural networks (CNNs) model used one-dimensional convolution to capture the temporal dependencies of weather data, whereas the S-CNN model used one-dimensional convolution to capture the spatial dependencies of soil data measured at different depths underground
The reasons for the outstanding performance of the CNNRNN model are as follows: (1) the recurrent neural networks (RNNs) part of the CNN-RNN model considered the genetic improvements of the seeds by capturing the yearly time dependencies of the yield, (2) the WCNN part of the CNN-RNN model captured the internal time dependencies of the weather data, (3) the S-CNN part of the CNN-RNN model considered the spatial dependencies of soil data measured at different depths underground, and (4) the CNN-RNN model took into account the nonlinear effects of environmental components
Summary
Crop yield is affected by many factors such as crop genotype, environment, and management practices. Crop genotype has improved significantly over years by seed companies. Environments, changing spatially and temporally, have huge effects on year-to-year and location-to-location variations in crop yield (Horie et al, 1992). Under such circumstances, accurate yield prediction is very beneficial to global food production. Import and export decisions can be made based on accurate predictions. Farmers can utilize the yield prediction to make knowledgeable management and financial decisions. Successful crop yield prediction is very difficult due to many complex factors. Genotype and environmental factors often have interactions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
