Deep Learning in Remote Sensing for Disaster Management and Humanitarian Aid
Outlet Title
Deep Learning Applications in Remote Sensing for Climate Change Monitoring
Document Type
Book
Publication Date
2026
Abstract
Disaster management refers to the preparation, response, and recovery activities to mitigate or minimize the losses caused by a disaster. Remote sensing plays a crucial role in disaster management by gathering information about the affected areas through satellite and other aerial imagery platforms. This chapter explores the role of deep learning techniques in processing remote sensing data and supporting the decision-making process in disaster management. We explain how various deep learning architectures, such as convolutional neural networks, sequential models, transformers, and autoencoders, can be used in real-life disaster situations. The chapter details how multi-modal and multi-temporal data fusion integrates optical, synthetic-aperture radar, and light detection and ranging imagery into a single analytic pipeline. A discussion on datasets and benchmarking protocols is followed by model deployment and real-time considerations. The chapter concludes with limitations of the discussed techniques, open challenges, and future research directions.
Recommended Citation
Mehmood, Abid and Ilyas, Qazi Mudassar, "Deep Learning in Remote Sensing for Disaster Management and Humanitarian Aid" (2026). Research & Publications. 155.
https://scholar.dsu.edu/ccspapers/155