Target-Aware Yield Prediction (TAYP) Model Used to Improve Agriculture Crop Productivity

Because rice is the most important food crop, its yield prediction has a critical impact on the food policy and farmer income. In this article, we propose a new yield prediction model for rice, called target-aware yield prediction (TAYP) model that can effectively improve the accuracy of yield prediction. The proposed TAYP model is a long short-term memory (LSTM)-based network, in which we modify the loss function by introducing the target yield. Unlike the traditional loss function that is independent of the target yield, our design can make the prediction model sensitive to the target yield such that the accuracy of yield prediction is increased. To test the TAYP model, we use a rice dataset from Taiwan Agricultural Research Institute, which consists of multispectral vegetation indexes collected by drones. The experimental results show that the TAYP model performs better than the related works on various evaluation criteria. Compared to the traditional LSTM model, the TAYP model improves the root-mean-squared error (RMSE) and
$R$
-squared by 6.1% and 13.0%, respectively, while increasing accuracy from 89% to 95%. In particular, the Kappa value of TAYP is 0.82, which is almost perfect agreement with the real measurement. It is clear that the proposed TAYP model can make significant accuracy improvement to the rice yield prediction and has the potential to be a useful tool for improving agricultural productivity.