PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction

2026-05-22

AI Summary

Existing single-crop yield prediction methods struggle to generalize to multi-crop scenarios and often fail to model crop-specific phenological responses under complex meteorological conditions. To address these limitations, this work proposes PhenoYieldNet, a novel framework that introduces a Crop Phenology Bank (CPB) and a Crop Phenology Attention (CPA) module. By leveraging learnable phenological embeddings and a multi-scale temporal attention mechanism, PhenoYieldNet dynamically captures crop-specific phenological dynamics. The framework further integrates a pretrained foundation model with a self-supervised temporal contrastive adaptation strategy to achieve strong cross-crop and cross-region generalization. Experimental results demonstrate that PhenoYieldNet significantly outperforms state-of-the-art models on multi-crop datasets, delivering both high prediction accuracy and exceptional generalization capability.

Abstract

Accurate crop yield prediction is crucial for sustainable agriculture and global food security. While existing methods are predominantly developed for single-crop prediction, they often struggle to generalize across diverse crop types, without addressing the unique crop phenological responses that are dynamically modulated by complex weather patterns. In this paper, we propose PhenoYieldNet, a multi-crop yield prediction framework that learns crop-specific phenology by explicitly modeling their responses with temporal drivers. Specifically, we develop a crop-aware temporal decoder consisting of a Crop Phenology Bank (CPB) and a Crop Phenology Attention (CPA) module. The CPB integrates a set of learnable embeddings, which leverage a query to guide the CPA module to learn the most relevant phenology patterns for the specific crop. And the CPA module explicitly captures multi-scale trend and variation components to construct temporal contexts, enabling the model to dynamically adjust the attention across different phenological stages. To learn robust and generalizable features for multi-crop prediction, the encoder is initialized with a pre-trained foundation model, and further adapted via a self-supervised Temporal Contrastive Adaptation strategy to align with agricultural temporal dynamics. Extensive experiments conducted on multi-crop datasets indicate that our proposed method significantly outperforms state-of-the-art methods, exhibiting strong generalization capabilities across different regions and crops.

Problem

• crop yield prediction
• multi-crop
• phenological responses
• weather patterns
• generalization

Innovation

• crop-aware phenology
• multi-crop yield prediction
• temporal attention
• self-supervised adaptation
• foundation model