Dynamic gating-enhanced deep learning model with multi-source remote sensing synergy for optimizing wheat yield estimation

Dynamic gating-enhanced deep learning model with multi-source remote sensing synergy for optimizing wheat yield estimation

IntroductionAccurate wheat yield estimation is crucial for efficient crop management. This study introduces the Spatio–Temporal Fusion Mixture of Experts (STF-MoE) model, an innovative deep learning framework built upon an LSTM-Transformer architecture.MethodsThe STF-MoE model incorporates a heterog...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Li, Junrui Kang, Jian Lu, Hongkun Fu, Zheng Li, Baoqi Liu, Xinglei Lin, Jiawei Zhao, Hengxu Guan, He Liu, Zhihan Liu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Plant Science
Subjects:
multi-source remote sensing
deep learning
wheat yield estimation
transformer
MoE module
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1640806/full
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:IntroductionAccurate wheat yield estimation is crucial for efficient crop management. This study introduces the Spatio–Temporal Fusion Mixture of Experts (STF-MoE) model, an innovative deep learning framework built upon an LSTM-Transformer architecture.MethodsThe STF-MoE model incorporates a heterogeneous Mixture of Experts (MoE) mechanism with an adaptive gating network. This design dynamically processes fused multi-source remote sensing features (e.g., near-infrared vegetation reflectance, NIRv; fraction of photosynthetically active radiation absorption, Fpar) and environmental variables (e.g., relative humidity, digital elevation model) across multiple expert networks. The model was applied to estimate wheat yield in six major Chinese provinces.ResultsThe STF-MoE model demonstrated exceptional accuracy in the most recent estimation year (R² = 0.827, RMSE = 547.7 kg/ha) and exhibited robust performance across historical years and extreme climatic events, outperforming baseline models. Relative humidity and digital elevation model were identified as the most critical yield-influencing factors. Furthermore, the model accurately estimated yield 1-2 months before harvest by identifying key phenological stages (March to June).DiscussionSTF-MoE effectively handles multi-source spatiotemporal complexity via its dynamic gating and expert specialization. While underestimation persists in extreme-yield regions, the model provides a scalable solution for pre-harvest yield estimation. Future work will optimize computational efficiency and integrate higher-resolution data.
ISSN:1664-462X

Similar Items