カネミツ　ヒデヒロ   Hidehiro Kanemitsu   金光　永煥    所属   コンピュータサイエンス学部 コンピュータサイエンス学科    職種   専任講師
言語種別	英語
発行・発表の年月	2019/03
形態種別	国際会議論文
査読	査読あり
標題	Evaluation of Inundation Area for 16 Years in Bangladesh by MODIS Data
執筆形態	共著
掲載誌名	Proc. NCSP 2019
掲載区分	国外
出版社・発行元	RISP
巻・号・頁	pp.343-346
総ページ数	4 pages
著者・共著者	JongGeol Park, Masaki Hanada, and Hidehiro Kanemitsu
概要	The near real-time flood map obtained from satellite datais essential data for government measures and flooddamage monitoring and efficient rescue activities. It isnecessary to distinguish between standing water and floodwater from the damage map. Bangladesh is considered tobe among the countries most vulnerable to a variety ofnatural disasters. The major natural hazards whichBangladesh has to confront regularly include floods,cyclones and accompanying storm surge. Flooding fromriver waters overflowing the banks, particularly duringmonsoon, is an annual phenomenon. Flash floods, whichare caused by heavy or excessive rainfall in a short periodover a relatively small area. In this study, spatial-temporalpatterns of continuous water area were examined usingthe patterns observed in metrics calculated for 15-year ofModerate Resolution Imaging Spectrometer (MODIS).Four analytical approached were used; calculation oftemporal Red, Blue, Near Infrared, Short Wave Infraredlayers for selected water area.First, the annual time-series data of MODIS were used tomainly detect floodwaters in the case of the 15-year (from2001 to 2016) flood. Five training samples (water, forest,cultivated area, urban, snow) and a number of differentattributes were tested with sample areas. Three machinelearning methods were used to find the most influentialindex which compose the model for classification offlooded areas.