Flood Mapping Using Relevance Vector Machine and SAR Data: A Case Study from Aqqala, Iran
- PDF / 1,793,320 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 65 Downloads / 205 Views
RESEARCH ARTICLE
Flood Mapping Using Relevance Vector Machine and SAR Data: A Case Study from Aqqala, Iran Alireza Sharifi1 Received: 15 October 2019 / Accepted: 24 August 2020 Ó Indian Society of Remote Sensing 2020
Abstract The use of satellite imagery to monitor flood areas is essential to determine the damage and prevent related problems in the future. This paper examines thresholding and unsupervised classification for flood mapping using Sentinel-1 SAR image. Thresholding helps us to determine over-detection and under-detection regions in the flooded areas, and so, gamma distribution is used to select the thresholds. Also, the relevance vector machine (RVM) and the object-based classification method have been used for classification. The RVM algorithm obtained better results with overall accuracy = 0.89 and k = 0.95, while for the object-based classification method, these values were 0.87 and 0.91, respectively. According to the results, over- and under-detection occurred in flat areas and man-made structures, respectively. The results demonstrate a great potential of radar imagery for operational detection and delimitation of water in flood risk areas. The automation of satellite radar data processing operation has been tested, and it shows a potential for optimising the system of monitoring and early detection of flood risk. Keywords Flood mapping SAR Remote sensing Machine learning Classification
Introduction The floods are one of the world’s most devastating natural disasters, killing thousands of people each year and causing extensive damage to infrastructure. Anthropogenic activity in several cases increases the likelihood of flood events. These include construction activities in the flood plain that requires the occupation of parts of the river and reduces the natural capacity of the river. Urbanisation and removal of vegetation reduces water infiltration and thus increases water levels after floods (Sharifi and Hosseingholizadeh 2019). Large volumes of water can increase flooding and erosion, creating sediments that reduce the capacity of the main riverbed (Sunar et al. 2019). Dangerous water overflows in residential areas are a common occurrence in Iran after the earthquake, and catastrophic floods occur annually in the provinces of & Alireza Sharifi [email protected] 1
Department of Surveying Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, 16785-136 Tehran, Iran
Mazandaran, Gilan, and Golestan in northern Iran (Sharifi 2020a). Due to the high frequency of floods in this area, in order to prevent loss of life and property damage, areas that are at high risk of flooding should be identified according to the potential flood plans. In the last decade, the occurrence of frequent floods in the northern part of Iran has reached its historical peak, and amount of damage is increasing every year. Recent floods in northern Iran, which have caused more than half a million dollars in damage and destroyed more than 100 hectares of agricultural land, include the
Data Loading...
