Waseem et al. (2026) A time adaptive weighting framework for enhanced vegetation health index based drought monitoring

Identification

• Journal: Remote Sensing Applications Society and Environment
• Year: 2026
• Date: 2026-07-24
• Authors: Muhammad Waseem, Ali Hasan Jaffry, Mudassar Iqbal, Muhammad Ajmal, Jiaqing Xiao, Tao Yang, Pengfei Shi, Awais Naeem Sarwar
• DOI: 10.1016/j.rsase.2026.102155

Research Groups

• Centre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, Pakistan
• Yangtze Institute for Conservation and Development, Hohai University, China
• College of Hydrology and Water Resources, Hohai University, China
• The National Key Laboratory of Water Disaster Prevention, Hohai University, China
• School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, China
• Department of Agricultural Engineering, University of Engineering and Technology, Peshawar, Pakistan
• Department of Civil, Architectural and Environmental Engineering, University of Naples Federico II, Italy

Short Summary

The study introduces an Enhanced Vegetation Health Index (EVHI) that replaces static weights with time-adaptive weights for its components to improve agricultural drought monitoring. The framework demonstrates superior performance over traditional VHI in detecting droughts across Pakistan by better accounting for the temporal dominance of thermal and vegetation stress.

Objective

• To develop a time-adaptive weighting framework for the Vegetation Health Index (VHI) that captures temporal shifts in vegetation and climate interactions to enhance drought detection accuracy.

Study Configuration

• Spatial Scale: 141 districts of Pakistan.
• Temporal Scale: 2002–2024.

Methodology and Data

• Models used: Enhanced Vegetation Health Index (EVHI) utilizing a time-adaptive weighting framework (SoftMax), calibrated using the 3-month Standardized Precipitation Evapotranspiration Index (SPEI-3) and validated using the Standardized Soil Moisture Index (SSI).
• Data sources: Satellite-derived indices (Vegetation Condition Index - VCI and Temperature Condition Index - TCI).

Main Results

• Weight Dynamics: Temperature stress ($\betat$) consistently dominates over vegetation stress ($\alphat$) during pre-monsoon and drought onset periods.
• Quantitative Weights: The average weights across all districts and time steps were $\betat = 0.531$ (TCI) and $\alphat = 0.468$ (VCI).
• Performance: EVHI consistently outperformed traditional VHI by reducing the False Alarm Rate (FAR) and increasing the Probability of Detection (POD) and Critical Success Index (CSI) in both calibration (70% of data) and validation (30% of data) phases.

Contributions

• The research advances drought monitoring by replacing the traditional static weighting of VHI components with a learned, time-varying sequence, allowing the index to adapt to the evolving dominance of different stress factors across diverse climate zones.

Funding

• Not specified in the provided text.

Citation

@article{Waseem2026time,
  author = {Waseem, Muhammad and Jaffry, Ali Hasan and Iqbal, Mudassar and Ajmal, Muhammad and Xiao, Jiaqing and Yang, Tao and Shi, Pengfei and Sarwar, Awais Naeem},
  title = {A time adaptive weighting framework for enhanced vegetation health index based drought monitoring},
  journal = {Remote Sensing Applications Society and Environment},
  year = {2026},
  doi = {10.1016/j.rsase.2026.102155},
  url = {https://doi.org/10.1016/j.rsase.2026.102155}
}