Prabhu et al. (2026) Smart disaster management: Leveraging machine learning and remote sensing for informed decision-making

Identification

• Journal: Elsevier eBooks
• Year: 2026
• Date: 2026-01-01
• Authors: Ruta Prabhu, Anupama Jawale, Hiral Patel, Disha Gandhi, Shivwani Nadar, Riddhi Lonandkar
• DOI: 10.1016/b978-0-443-32878-7.00023-7

Research Groups

Department of Information Technology, Narsee Monjee College of Commerce and Economics, Mumbai, Maharashtra, India

Short Summary

This paper presents a review of machine learning (ML) and deep learning (DL) techniques applied across various domains of natural disaster management to enhance operational efficiency and support informed decision-making.

Objective

• To review and synthesize the applications of machine learning and deep learning techniques in diverse natural disaster management domains, aiming to assist and improve disaster management operations.

Study Configuration

• Spatial Scale: Global (covering various disaster types like typhoons, floods, earthquakes, landslides).
• Temporal Scale: Continuous (covering pre-disaster preparedness, real-time monitoring during events, and post-disaster response and assessment).

Methodology and Data

• Models used: Review of existing literature discussing Machine Learning (ML), Deep Learning (DL), Convolutional Neural Networks (CNN), Genetic Algorithms (GA), and Multilayer Perceptron (MLP) neural networks.
• Data sources: Existing scientific literature and case studies on disaster management. Discusses the use of aerial images and real-time data for ML/DL applications.

Main Results

• ML and DL techniques are widely applicable across disaster management tasks, including physical and social exposure/vulnerability assessment, risk mapping, damage prediction, post-disaster event mapping, early warning systems, forecasting, monitoring, and detection.
• These technologies enable quick and effective damage assessment (e.g., via aerial imagery) and facilitate real-time data-driven decision-making.
• ML/DL can optimize resource allocation and improve coordination among volunteers and rescuers during disaster events.
• Specific applications include managing typhoons, hurricanes, floods, lava flows, earthquakes, and landslides.
• One cited study demonstrated 85% classification accuracy for landslide prediction using a combination of Genetic Algorithm and Multilayer Perceptron neural network.

Contributions

• Provides a comprehensive overview of the current state and potential of ML and DL in enhancing natural disaster management.
• Synthesizes diverse applications and techniques, offering a valuable resource for researchers and practitioners in the field.
• Highlights the innovative strategies that ML and AI can offer for improving societal resilience, particularly for vulnerable communities.

Funding

Not specified in the provided text.

Citation

@article{Prabhu2026Smart,
  author = {Prabhu, Ruta and Jawale, Anupama and Patel, Hiral and Gandhi, Disha and Nadar, Shivwani and Lonandkar, Riddhi},
  title = {Smart disaster management: Leveraging machine learning and remote sensing for informed decision-making},
  journal = {Elsevier eBooks},
  year = {2026},
  doi = {10.1016/b978-0-443-32878-7.00023-7},
  url = {https://doi.org/10.1016/b978-0-443-32878-7.00023-7}
}