Multi-scale spatial-temporal remote sensing fusion for phenology identification in rice germplasm resources.

Abstract

Crop phenology is a critical determinant for yield prediction and germplasm evaluation. However, precise phenological monitoring in large-scale rice breeding trials faces significant challenges due to the inherent phenological asynchrony among hundreds of cultivars and the trade-off between spatial resolution and temporal continuity in unmanned aerial vehicle (UAV) remote sensing. To address these issues, this study proposes a multi-scale temporal deep learning framework that integrates high-frequency medium-resolution (MR) images as temporal anchor with sparse high-resolution (HR) images as spatial enhancement. We introduce a Missing Aware Gated Fusion (MAGF) mechanism to dynamically integrate multi-resolution features on non-aligned timelines, enabling robust modeling under irregular sampling conditions. Validated on a massive dataset covering approximately 500 rice cultivars and over 100,000 images across 2023 and 2024 growing seasons, the proposed method significantly outperformed single-temporal-scale baselines despite multiple growth stages coexisting within the same dates. The integration of multi-spatial-scale fusion with LSTM temporal modeling yielded superior performance considering efficiency, achieving an Overall Accuracy (OA) and F1-score of 0.873, with a Kappa coefficient of 0.84. A hybrid sampling strategy (daily MR image combined with weekly HR image) demonstrates that weekly flight time can be reduced from 28 h to approximately 6 h while maintaining high accuracy. Notably, even when HR acquisition was reduced to a once every 14 days frequency, the fusion performance remained significantly superior to that of daily MR monitoring alone. The model exhibited strong generalization capabilities. When directly applying the model trained on 2024 data to the 2023 dataset, it maintained an OA of 0.774 and an F1-score of 0.738 under a 3-day error tolerance, with recall for the maturity stage consistently exceeding 0.96. This framework offers a flexible, scalable, and cost-effective solution for high-throughput phenotyping in precision breeding.

Plant phenotyping relevance

UAVリモートセンシング画像と深層学習によるイネの生育ステージ（フェノロジー）推定手法を開発・検証し、大規模育種データで性能評価しているため、フェノタイピング手法が中心である。

Code and data availability

The article explicitly states that the authors' source code and test samples for the rice phenology identification framework are publicly available on GitHub, matching an allowed URL. No public dataset deposit is stated; additional data is only on request.