Khotele et al. (2026) Disaster Detection Based on Synthetic Aperture Radar (SAR) Images

Identification

• Journal: INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
• Year: 2026
• Date: 2026-04-09
• Authors: Priya R Khotele, Rushikesh Lohe, Himanshu Raut, Humendra Harinkhede, Rajhans Khatik, Kaushik Dhande
• DOI: 10.55041/ijsrem59554

Research Groups

• Department of Computer Technology, Priyadarshini College of Engineering, Nagpur, India

Short Summary

This paper proposes an AI-driven remote sensing system utilizing Synthetic Aperture Radar (SAR) images and Convolutional Neural Networks (CNN) for efficient and scalable multi-disaster detection, addressing limitations of traditional monitoring methods. The experimental analysis demonstrates the model's high accuracy and potential for real-time disaster monitoring.

Objective

• To develop an efficient and scalable AI-driven remote sensing technology for multi-disaster detection and management using Synthetic Aperture Radar (SAR) images.

Study Configuration

• Spatial Scale: Global applicability, as SAR satellites provide wide coverage for multi-disaster detection.
• Temporal Scale: Designed for real-time monitoring of disasters.

Methodology and Data

• Models used: Convolutional Neural Network (CNN)-based classification techniques.
• Data sources: Data acquired from SAR satellites such as Sentinel-1 and Terra SAR-X. Preprocessing techniques include speckle noise reduction and feature extraction.

Main Results

• Experimental analysis clearly indicates the efficiency and potency of the proposed model in achieving high accuracy in the detection of disasters.
• The system demonstrates immense potential for real-time monitoring of disasters, enabling authorities to optimize early warning systems, resources, and response strategies.

Contributions

• Development of an AI-driven remote sensing technology that offers an efficient and scalable solution for multi-disaster detection and management.
• Overcomes limitations of traditional disaster monitoring approaches, such as adverse weather conditions, lack of real-time data, and terrain complexity, by leveraging SAR's all-weather, day-and-night operational capability.

Funding

• No specific funding projects or grants were mentioned in the provided text.

Citation

@article{Khotele2026Disaster,
  author = {Khotele, Priya R and Lohe, Rushikesh and Raut, Himanshu and Harinkhede, Humendra and Khatik, Rajhans and Dhande, Kaushik},
  title = {Disaster Detection Based on Synthetic Aperture Radar (SAR) Images},
  journal = {INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
  year = {2026},
  doi = {10.55041/ijsrem59554},
  url = {https://doi.org/10.55041/ijsrem59554}
}