Guan et al. (2025) Study of the Correlation Between Water Resource Changes and Drought Indices in the Yinchuan Plain Based on Multi-Source Remote Sensing and Deep Learning

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Water
• Year: 2025
• Date: 2025-09-16
• Authors: Huanhuan Guan, Zhicheng Jiang, Jing Lu, Yukuai Wan
• DOI: 10.3390/w17182740

Research Groups

[Not explicitly stated in the provided text.]

Short Summary

This study integrates multi-source remote sensing data with deep learning to model water resource dynamics and their relationship with drought indices in the Yinchuan Plain, China, finding strong correlations with SPEI and superior performance of LSTM for predictions, offering a robust foundation for water management.

Objective

• To examine the intricate relationship between water resource dynamics and drought indices (SPI, SPEI, PDSI) in the Yinchuan Plain, China, using multi-source remote sensing data and deep learning techniques.

Study Configuration

• Spatial Scale: Yinchuan Plain, China
• Temporal Scale: 2002 to 2022 (21 years)

Methodology and Data

• Models used: Long Short-Term Memory (LSTM) networks, Wavelet coherence analysis
• Data sources: Multi-source remote sensing data, Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI), Palmer Drought Severity Index (PDSI)

Main Results

• A strong correlation was found between total water resources and the Standardized Precipitation Evapotranspiration Index (SPEI) (r = 0.81, p < 0.001), highlighting the significant role of evapotranspiration.
• The LSTM model outperformed traditional statistical methods, achieving a Root Mean Square Error (RMSE) of 0.142 for water resource predictions and 0.118 for drought index forecasts.
• Spatial analysis revealed stronger correlations in the northern Yinchuan Plain, influenced by proximity to the Yellow River and regional water management.
• Wavelet coherence analysis identified significant coherence at the 6–12-month scale, emphasizing the importance of seasonal to inter-annual strategies for water resource management.

Contributions

• Provides a robust foundation for developing effective water management policies and drought mitigation strategies in arid and semi-arid regions.
• Introduces methodologies broadly applicable to similar water-scarce regions, contributing to global efforts in sustainable water resource management under changing climatic conditions.
• Demonstrates the superior performance of deep learning (LSTM) in modeling water resource dynamics and drought indices compared to traditional statistical methods.

Funding

[Not explicitly stated in the provided text.]

Citation

@article{Guan2025Study,
  author = {Guan, Huanhuan and Jiang, Zhicheng and Lu, Jing and Wan, Yukuai},
  title = {Study of the Correlation Between Water Resource Changes and Drought Indices in the Yinchuan Plain Based on Multi-Source Remote Sensing and Deep Learning},
  journal = {Water},
  year = {2025},
  doi = {10.3390/w17182740},
  url = {https://doi.org/10.3390/w17182740}
}