Next-Generation Drought Forecasting: Hybrid AI Models for Climate Resilience
Remote Sensing · 10.10.2025 · 17 (20) · 3402
DOI: 10.3390/rs17203402 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.10.2025. Verfasst von Jinping Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, MNR, Henan Provincial Science and Technology Research, Henan Province Joint Fund Project of Science and Technology.
Abstract (Originalsprache)
Droughts are increasingly threatening ecological balance, agricultural productivity, and socio-economic resilience—especially in semi-arid regions like the Inner Mongolia segment of China’s Yellow River Basin. This study presents a hybrid drought forecasting framework integrating machine learning (ML) and deep learning (DL) models with high-resolution historical and downscaled future climate data. TerraClimate observations (1985–2014) and bias-corrected CMIP6 projections (2030–2050) under SSP2-4.5 and SSP5-8.5 scenarios were utilized to develop and evaluate the models. Among the tested ML algorithms, Random Forest (RF) demonstrated the best trade-off between accuracy and interpretability and was selected for feature importance analysis. The top-ranked predictors—precipitation, solar radiation, and maximum temperature—were used to train a Long Short-Term Memory (LSTM) network. The LSTM outperformed all ML models, achieving high predictive skill (R2 = 0.766, CC = 0.880, RMSE = 0.885). Scenario-based projections revealed increasing drought severity and variability under SSP5-8.5, with mean PDSI values dropping below −3 after 2040 and deepening toward −4 by 2049. The high-emission scenario also exhibited broader uncertainty bands and amplified interannual anomalies. These findings highlight the value of hybrid AI–climate modeling approaches in capturing complex drought dynamics and supporting anticipatory water resource planning in vulnerable dryland environments.
Förderung
- Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, MNR
- Henan Provincial Science and Technology Research
- Henan Province Joint Fund Project of Science and Technology
- Henan Science Foundation for Distinguished Young Scholars of China
- Henan Key Research and Development Program of China
- Ningxia Natural Science Foundation
- Key Research and Development Project of Ningxia Hui Autonomous Region
Zitieren
APA
Liu, J., Liu, T., Huang, L., Ren, Y., & He, P. (2025). Next-Generation Drought Forecasting: Hybrid AI Models for Climate Resilience. Remote Sensing, 17(20), 3402. https://doi.org/10.3390/rs17203402
Vancouver
Liu J, Liu T, Huang L, Ren Y, He P. Next-Generation Drought Forecasting: Hybrid AI Models for Climate Resilience. Remote Sensing. 2025;17(20):3402. doi:10.3390/rs17203402
BibTeX
@article{Liu2025,
author = {Liu, Jinping and Liu, Tie and Huang, Lei and Ren, Yanqun and He, Panxing},
title = {Next-Generation Drought Forecasting: Hybrid AI Models for Climate Resilience},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {20},
pages = {3402},
doi = {10.3390/rs17203402}
}
EUVIMED