AUTOMATIC FLOOD DETECTION USING SENTINEL-1 IMAGES IN GOOGLE EARTH ENGINE

Abstract

The paper presents a method to detect flooded areas based on the classification of superpixels from Sentinel-1 satellite image data. The automatic thresholding method based on the Simple Non-Iterative Clustering and the OTSU algorithm extracts flooded areas from Sentinel-1 images on the Google Earth Engine platform. Experimental results in Quang Binh province in October 2016 show the efficiency of the proposed method (Simple Non-Iterative Clustering algorithm combined with the OTSU algorithm). The proposed method accuracy is 91% higher than the OTSU algorithm, with about 86% in classifying flooded areas in SAR images. The results obtained in the study area can provide timely information about the flooded area, contributing to effective response and reduction of damage caused by floods. The study also shows the power of the Google Earth Engine platform. Google Earth Engine has supported rapid data analysis and processing thanks to rich data sources, multi-time, diverse data, and various algorithms.