What question did this study set out to answer?

The aim is to develop a hybrid framework for accurate nitrogen stress classification in winter wheat using UAV imagery.

February 10, 20260 citationsOpen Access

A CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery

XKXiaohui Kuang DWDawei Wang BMBohan Mao

Key Points

The aim is to develop a hybrid framework for accurate nitrogen stress classification in winter wheat using UAV imagery.
Hybrid CNN-LSTM-XGBoost model developed for classification
Implemented a randomized block design with multiple cultivars and nitrogen levels
Multispectral and TIR imagery captured at different growth stages
Integration of manual and temporal statistical features for enhanced analysis
Achieved 89.38% accuracy with CNN-LSTM on multimodal features
XGBoost F1macro improved to 0.9131 with multi-temporal features
Hybrid model reached highest performance: 0.9208 accuracy, 0.9212 F1macro, 0.9879 AUCmacro, 0.8944 Kappa
Key indicator identified as TIR × NDRE reflecting nitrogen deficiency effects

Abstract

Accurate diagnosis of nitrogen status is essential for precision fertilization in winter wheat. Single-modal or single-temporal remote sensing often fails to capture the multidimensional crop responses to nitrogen stress. In this study, we propose a hybrid framework based on CNN-LSTM-XGBoost for interpretable classification of wheat nitrogen stress gradients using multimodal unmanned aerial vehicle (UAV) multispectral and thermal infrared (TIR) imagery. Field experiments were conducted at the Xinxiang base in Henan Province during the 2023–2024, following a randomized block design involving 10 cultivars, four nitrogen levels, and four water treatments. Multisource UAV images acquired at jointing, heading, and filling stages were used to construct a multimodal feature set consisting of manual features (spectral bands, vegetation indices (VIs), TIR, and their interaction terms) and seven temporal statistical features. A deep learning model (CNN-LSTM) was utilized to further extract deep spatiotemporal features, and its performance was systematically compared with traditional machine learning models. The results show that multimodal feature fusion significantly enhanced classification performance. The CNN-LSTM model achieved an accuracy of 89.38% with fused multimodal features, outperforming all traditional machine learning models. Incorporating multi-temporal features improved the F1macro of the XGBoost model to 0.9131, a 9.42 percentage-point increase over using the single heading stage alone. The hybrid model (CNN-LSTM-XGBoost) achieved the highest overall performance (Accuracy = 0.9208; F1macro = 0.9212; AUCmacro = 0.9879; Kappa = 0.8944). SHAP analysis identified TIR × NDRE as the most influential indicator, reflecting the coupled physiological response of reduced chlorophyll content and increased canopy temperature under nitrogen deficiency. The proposed multimodal, multi-temporal, and interpretable framework provides a robust technical foundation for UAV-assisted precision nitrogen management.

问 AI

Bookmark

View Full Paper

Cite This Study

Kuang et al. (Sat,) studied this question.

synapsesocial.com/papers/698acac07c832249c30ba179 https://doi.org/https://doi.org/10.3390/rs18040538

问 AI

Bookmark

View Full Paper