Deep Learning-Based Crop Drought Identification and Prediction Model

DOI

10.2991/978-94-6463-910-0_33How to use a DOI?

Keywords

Crop drought identification; Multi-source data fusion; Deep learning; Spatio-temporal features

Abstract

Drought, as a major global threat to agriculture, severely impacts food security. This study proposes a deep learning-based model for crop drought identification and prediction. It innovatively designs a multi-source data fusion architecture integrating remote sensing, meteorological, and soil characteristics, utilising a dual-stream network to extract spatio-temporal features. The model employs an adaptive attention mechanism to optimise feature fusion and incorporates spatio-temporal graph neural networks to achieve multi-scale prediction. Experiments demonstrate that this approach significantly outperforms traditional methods, providing a novel technical pathway for agricultural drought monitoring and early warning.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kang Yang
AU  - Huizhen Fan
PY  - 2025
DA  - 2025/12/15
TI  - Deep Learning-Based Crop Drought Identification and Prediction Model
BT  - Proceedings of the 2025 2nd International Symposium on Agricultural Engineering and Biology (ISAEB 2025)
PB  - Atlantis Press
SP  - 312
EP  - 318
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6463-910-0_33
DO  - 10.2991/978-94-6463-910-0_33
ID  - Yang2025
ER  -