Pan et al. (2025) Multi-Scale Assessment and Prediction of Drought: A Case Study in the Arid Area of Northwest China

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

Identification

• Journal: Remote Sensing
• Year: 2025
• Date: 2025-12-10
• Authors: Tingting Pan, Yang Wang, Yaning Chen, Jiayou Wang, Meiqing Feng
• DOI: 10.3390/rs17243985

Research Groups

Not explicitly mentioned in the provided text.

Short Summary

This study analyzed multi-scale drought evolution in the Arid Area of Northwest China (AANC) from 1962–2021, revealing a shift from wetting to drying after 1997 due to warming-enhanced evapotranspiration. It developed a Stacking ensemble model that significantly improved meteorological drought prediction, projecting increasingly frequent and severe droughts in the AANC until 2035.

Objective

• To analyze the multi-scale drought evolution in the Arid Area of Northwest China (AANC) from 1962–2021, particularly focusing on the impact of climate change.
• To develop an improved predictive model for meteorological drought using an integrated Stacking ensemble framework.
• To project future drought trends in the AANC for the period 2022–2035.

Study Configuration

• Spatial Scale: Arid Area of Northwest China (AANC)
• Temporal Scale:
  • Analysis period: 1962–2021 (60 years)
  • Prediction period: 2022–2035 (14 years)

Methodology and Data

• Models used: Stacking ensemble framework integrating Elastic Network, Random Forest, and Prophet + XGBoost models.
• Data sources: 1962–2021 meteorological observations, used to derive the Standardized Precipitation Evapotranspiration Index (SPEI).

Main Results

• The Arid Area of Northwest China (AANC) experienced a distinct shift from a wetting to a drying trend after 1997.
• Rapid temperature rise significantly enhanced evapotranspiration, which offset the humidification effect of precipitation.
• The developed Stacking ensemble framework achieved superior predictive accuracy for meteorological drought (Nash-Sutcliffe Efficiency (NSE) = 0.886, Mean Absolute Error (MAE) = 0.236, Root Mean Square Error (RMSE) = 0.214) compared to single models (NSE ≤ 0.742).
• The integrated model's residuals followed a near-normal distribution, indicating high robustness.
• Future projections for 2022–2035 consistently show declines in SPEI1, SPEI3, SPEI6, SPEI12, and SPEI24, suggesting that the AANC will experience increasingly frequent and severe droughts.

Contributions

• Developed and validated an advanced Stacking ensemble framework that significantly enhances the predictability of meteorological drought.
• Provided quantitative evidence of a distinct shift from wetting to drying in the Arid Area of Northwest China post-1997, attributing it to warming-induced evapotranspiration.
• Offered theoretical support and a practical tool for climate risk assessment and adaptive water management strategies in arid environments.

Funding

Not explicitly mentioned in the provided text.

Citation

@article{Pan2025MultiScale,
  author = {Pan, Tingting and Wang, Yang and Chen, Yaning and Wang, Jiayou and Feng, Meiqing},
  title = {Multi-Scale Assessment and Prediction of Drought: A Case Study in the Arid Area of Northwest China},
  journal = {Remote Sensing},
  year = {2025},
  doi = {10.3390/rs17243985},
  url = {https://doi.org/10.3390/rs17243985}
}