Choudhary et al. (2025) Assessment of Spatio-Temporal Dynamics of Drought Stress Anomalies UsingHyperspectral Imagery Fusion

Identification

• Journal: ISPRS annals of the photogrammetry, remote sensing and spatial information sciences
• Year: 2025
• Date: 2025-12-19
• Authors: Preetam Choudhary, Rajesh K. Dhumal, Soumyashree Kar
• DOI: 10.5194/isprs-annals-x-5-w2-2025-115-2025

Research Groups

• Symbiosis Institute of Geoinformatics, Pune, India
• Centre of Studies in Resources Engineering (CSRE), Indian Institute of Technology Bombay (IIT BOMBAY), Mumbai, India

Short Summary

This study assessed the spatio-temporal dynamics of drought stress anomalies in California's Sierra Nevada region from 2013 to 2025 using fused hyperspectral and multispectral imagery, revealing strengthening drought trends and forecasting further deterioration in 2026.

Objective

• To evaluate the spatio-temporal dynamics of drought stress anomalies in California's ecologically fragile Sierra Nevada region.

Study Configuration

• Spatial Scale: Sierra Nevada region, California, USA.
• Temporal Scale: 2013–2025 (analysis period), with a forecast for 2026.

Methodology and Data

• Models used: Analytic Hierarchy Process (AHP) framework for weighting spectral indices, Random Forest model for classification.
• Data sources: Hyperspectral imagery (AVIRIS Classic, 2013–2018), Multispectral imagery (Sentinel-2, 2019–2025). Eight spectral indices were combined, including Moisture Stress Index (MSI), Normalized Difference Drought Index (NDDI), and Normalised Burn Ratio (NBR).

Main Results

• The developed methodology, combining AHP and Random Forest, achieved high accuracy in drought severity classification, with an overall accuracy of 86.53% and a balanced accuracy of 86.37%.
• Analysis from 2013 to 2025 indicated varied but strengthening trends of drought, with an increased escalation in the spatial magnitude and severity of exceptional drought (D4) conditions, particularly in southern areas since 2019.
• A forecast for 2026 shows an increased deterioration in drought conditions.

Contributions

• Presents a powerful, scalable, and transferable paradigm for reliable drought monitoring through multi-sensor integration and a decision-theoretic weighting scheme.
• Offers valuable information for anticipatory resource management and mitigation plans in drought-prone mountain regions globally.
• Overcomes spectral limitations of multispectral data by fusing it with hyperspectral data.

Funding

• Not explicitly mentioned in the provided text.

Citation

@article{Choudhary2025Assessment,
  author = {Choudhary, Preetam and Dhumal, Rajesh K. and Kar, Soumyashree},
  title = {Assessment of Spatio-Temporal Dynamics of Drought Stress Anomalies UsingHyperspectral Imagery Fusion},
  journal = {ISPRS annals of the photogrammetry, remote sensing and spatial information sciences},
  year = {2025},
  doi = {10.5194/isprs-annals-x-5-w2-2025-115-2025},
  url = {https://doi.org/10.5194/isprs-annals-x-5-w2-2025-115-2025}
}