Crossformer-Based Model for Predicting and Interpreting Crop Yield Variations Under Diverse Climatic and Agricultural Conditions

Crop yield prediction is critical for agricultural decision making and food security. Traditional models struggle to capture the complex interactions among meteorological, soil, and agricultural factors. This study introduces Crossformer, a Transformer-based model with a Local Perception Unit (LPU) for local dependencies and a Cross-Window Attention Mechanism for global dependencies. Experiments on winter wheat, rice, and corn datasets show that Crossformer outperforms CNN, LSTM, and Transformer in Test Loss, R2, MSE, and MAE. For instance, on the corn dataset, Crossformer achieves a Test Loss of 0.0271 and an R2 of 0.9863, compared to 0.7999 and 0.1634 for LSTM, respectively, demonstrating a substantial improvement in predictive performance. Interpretability analysis highlights the importance of temperature and precipitation in yield prediction, aligning with agricultural insights. The results demonstrate Crossformer’s potential for precision agriculture.