Soybean phenological stage identification based on multimodal data and a dynamic gating fusion model

Accurate, near real-time soybean phenology information is critical for crop management and breeding. Previous approaches relying on satellite remote sensing time-series data suffer from temporal delays, limiting their usefulness for in-season decision-making. To overcome this limitation, this study reframes phenology identification as a near real-time classification task using single-timepoint Unmanned Aerial Vehicle (UAV) imagery collected from 420 soybean germplasm resources across three experimental sites, and proposes an innovative multi-modal dynamic Gating Fusion Model that integrates two optimized pathways. one based on machine learning (ML) and the other on deep learning (DP). In the ML branch, systematic benchmarking of tabular-feature models identified the Soft Voting ensemble as the best classifier. In the DL branch, an enhanced BC-ConvNeXt model equipped with BiFPN and CBAM modules was developed to strengthen visual feature extraction. Building on these two optimal classifiers, the dynamic gating fusion model achieved the highest F1-score of 94.3% across seven key growth stages (V1, V2, R1, R2, R6, R7, R8). This result represents a significant improvement of 1.5% and 10.6% over the best performing ML and DL models, respectively. The superior performance arises from the intelligent arbitration of complementary strengths, with gating-weight analysis revealing a strategy that prioritizes ML predictions while leveraging DL for error correction. This work establishes a complete framework for near real-time crop phenology detection and demonstrates the strong potential of intelligent multi-modal fusion in high-throughput phenotyping.