ConvLSTM–ViT: A Deep Neural Network for Crop Yield Prediction Using Earth Observations and Remotely Sensed Data

Abstract

This article introduces an approach for soybean yield prediction by integrating convolutional long short-term memory (ConvLSTM), three-dimensional convolutional neural network (3D-CNN), and vision transformer (ViT). By utilizing multispectral remote sensing data, our model leverages the spatial hierarchy of 3D-CNNs, the temporal sequencing capabilities of ConvLSTM, and the global context analysis of ViTs to capture complex patterns in agricultural datasets. The integration of these advanced methodologies allows for a comprehensive analysis of both spatial and temporal aspects of crop growth, enabling more accurate and robust predictions. Our experimental results demonstrate that the proposed model significantly outperforms existing methods, as evidenced by lower root mean square error and higher correlation coefficients. The 3D-CNN component effectively extracts spatial features from the multispectral images, while the ConvLSTM captures the temporal dynamics of crop development. The ViT further refines these features by focusing on the most relevant parts of the input data through self-attention mechanisms. The findings highlight the potential of this model in enhancing decision-making processes in crop management, particularly in precision agriculture. By providing more accurate yield predictions, the model can assist farmers in optimizing resource allocation, scheduling irrigation, and applying fertilizers more efficiently, thereby promoting sustainable farming practices. Furthermore, the model's robustness across various conditions underscores its applicability to different crops and geographic regions. This article contributes to the field of agricultural remote sensing by offering a robust solution to the complexities of analyzing large-scale, multispectral data. The proposed approach not only improves prediction accuracy but also provides timely and actionable insights for agricultural stakeholders.

Keywords

• Agricultural data processing
• convolutional long short-term memory (ConvLSTM)
• crop yield forecasting
• deep learning
• model generalization
• multispectral data analysis