EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Xiaohui Kuang, Xinyue Hou, Dawei Wang, Bohan Mao, Yafeng Li, Deshan Chen, Wanna Fu, Qian Cheng, Fuyi Duan, Hao Li, Zhen Chen

Remote Sensing · 07.02.2026 · 18 (4) · 538

DOI: 10.3390/rs18040538 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 07.02.2026. Verfasst von Xiaohui Kuang und 10 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Central Public-interest Scientific Institution Basal Research Fund, the Science and Technology Innovation Project of the Chinese Academy of Agricultural Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Key R&D Program of China
  • Central Public-interest Scientific Institution Basal Research Fund
  • the Science and Technology Innovation Project of the Chinese Academy of Agricultural Sciences

Zitieren

APA

Kuang, X., Hou, X., Wang, D., Mao, B., Li, Y., Chen, D., Fu, W., Cheng, Q., Duan, F., Li, H., & Chen, Z. (2026). A CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery. Remote Sensing, 18(4), 538. https://doi.org/10.3390/rs18040538

Vancouver

Kuang X, Hou X, Wang D, Mao B, Li Y, Chen D, et al. A CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery. Remote Sensing. 2026;18(4):538. doi:10.3390/rs18040538

BibTeX
@article{Kuang2026,
  author = {Kuang, Xiaohui and Hou, Xinyue and Wang, Dawei and Mao, Bohan and Li, Yafeng and Chen, Deshan and Fu, Wanna and Cheng, Qian and Duan, Fuyi and Li, Hao and Chen, Zhen},
  title = {A CNN-LSTM-XGBoost Hybrid Framework for Interpretable Nitrogen Stress Classification Using Multimodal UAV Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {4},
  pages = {538},
  doi = {10.3390/rs18040538}
}
Kostenlos starten →