Development of a method for flood detection based on Sentinel‐1 images and classifier algorithms

• Published in: Water and environment journal : WEJ Vol. 35; no. 3; pp. 924 - 929
• Main Author: Sharifi, Alireza
• Format: Journal Article
• Language: English
• Published: London Wiley Subscription Services, Inc 01.08.2021
• Subjects: Algorithms; Baseline studies; classifiers; Damage; Disaster management; Disasters; Economic activities; Ecosystem services; ecosystems; environment; Environmental risk; flood detection; Flooded areas; Floods; human health; Hydrologic data; Hydrology; ICA algorithm; infrastructure; Learning algorithms; Machine learning; Monitoring systems; Natural disasters; Risk management; Risk reduction; Sentinel‐1; water; Water management
• ISSN: 1747-6585; 1747-6593
• DOI: 10.1111/wej.12681

Floods are one of the most devastating natural disasters in the world, displacing millions of people each year and causing severe damage to people's lives and infrastructure. It is the most widespread hydrological hazard worldwide that affects water management, nature protection, economic activities, hydromorphological alterations on ecosystem services and human health. Real‐time monitoring systems play a key role in flood risk reduction and disaster response decisions. Studies have shown that using earth observation data for flood monitoring and timely actions based on good quality information reduces damages. In this paper, after thresholding, a machine learning algorithm and an object‐based classification method were used to classify the SAR data. Thresholding helps detect regions in the flooded areas. A comparison of the results showed that the machine learning algorithm obtained significant results. Because of the results obtained, the usefulness of Sentinel‐1 images as a baseline data for the improvement of the methodological guide is appreciated and should be used as a new source to monitor the flood risks.