Kumar et al. (2026) Multi-Temporal Satellite Observations and Machine Learning-Based Flood Susceptibility Assessment of the 2025 Punjab Flood

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

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-17
• Authors: Ankush Kumar, Ashwani Raju, Saraah Imran, Ramesh P. Singh
• DOI: 10.3390/rs18183204

Research Groups

• Indian Institute of Technology (IIT) Delhi
• National Centre for Medium Range Weather Forecasting (NCMRWF)
• Punjab Agricultural University (PAU)

Short Summary

This study integrates multi-sensor satellite observations and machine learning frameworks to assess flood susceptibility in the Punjab plains, identifying rainfall, soil moisture, runoff, and elevation as dominant contributors.

Objective

• Investigate the role of hydroclimatic variability, land use changes, and geomorphic parameters on flood events in the Punjab plains

Study Configuration

• Spatial Scale: Regional (Punjab plains, Northern India)
• Temporal Scale: Decadal (2023-2025)

Methodology and Data

• Models used:
  • Random Forest
  • Extreme Gradient Boosting
  • Artificial Neural Network
• Data sources:
  • Multi-sensor satellite observations (Sentinel-1 backscatter signals)
  • Local climate zones data
  • Land cover, soil type, and infiltration characteristics

Main Results

• Balanced classification performance of Random Forest and Extreme Gradient Boosting compared to Artificial Neural Network
• Greater class separability of 2023 flood events than for 2025
• Probability distributions demonstrate model-dependent threshold behavior
• SHAP analysis identifies rainfall, soil moisture, runoff, and elevation as dominant contributors

Contributions

• Provides a comprehensive understanding of the complex interactions between hydrological, topographical, and land use factors controlling flood susceptibility in the Punjab plains
• Demonstrates the effectiveness of machine learning frameworks in predicting flood events with high accuracy

Funding

• This research was supported by the Ministry of Earth Sciences (MoES), Government of India (Grant No. MoES/16-17/2019)
• Funded under the National Monsoon Mission (NMM) program

Citation

@article{Kumar2026MultiTemporal,
  author = {Kumar, Ankush and Raju, Ashwani and Imran, Saraah and Singh, Ramesh P.},
  title = {Multi-Temporal Satellite Observations and Machine Learning-Based Flood Susceptibility Assessment of the 2025 Punjab Flood},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18183204},
  url = {https://doi.org/10.3390/rs18183204}
}