Research Article | Open Access

Volume 2026 |Article ID 100144 | https://doi.org/10.1016/j.plaphe.2025.100144

WPDSI: A deep learning method for wheat phenology detection from single-temporal images

Yan Li,^1,2 Yucheng Cai,^1,2 Xuerui Qi,^1,2 Suyi Liu,^1,2 Xiangxin Zhuang,^1,2 Hengbiao Zheng,^1,2 Yongchao Tian,^1,3 Yan Zhu,^1,2 Weixing Cao,^1,2 Xiaohu Zhang ^1,2,3

¹National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing, 211800, China
²Key Laboratory for Crop System Analysis and Decision Making, Ministry of Agriculture and Rural Affairs, Nanjing, 211800, China
³Jiangsu Collaborative Innovation Center for Modern Crop Production, Nanjing, 211800, China

Abstract

Accurate monitoring of wheat phenology is critical for ensuring wheat production. Recent advances in deep learning have enabled the automated detection of wheat phenology in the field. In particular, deep learning models using multi-temporal image series have addressed the challenge of low accuracy in models that only use spatial features by incorporating dynamic aspects of the wheat growth process. However, utilizing multi-temporal image series introduces challenges such as model parameter redundancy, complex inference processes, and difficulties in real-time deployment. To address these issues, this study presents an optimization method for deriving wheat phenology from single-temporal images (WPDSI) that combines knowledge distillation and multi-layer attention transfer. The proposed approach employs knowledge distillation. In this framework, a teacher model extracts spatiotemporal features from multi-temporal image-series and generates soft labels to guide a student model trained on single-temporal images. This reduces model complexity and input data requirements. Multi-layer attention transfer allows the student model to inherit feature representations from multiple layers of the teacher model. This enhances its ability to capture key phenological characteristics and supports interpretability through attention mechanisms. The proposed method achieves an overall accuracy (OA) of 0.927, comparable to models trained on multi-temporal image series. Furthermore, the model demonstrates strong generalization on unseen datasets, enhancing real-time performance and computational efficiency while maintaining high accuracy, providing a practical solution for deriving wheat phenology in the field. The dataset is available at https://github.com/phenology-detection/WPDSI.