TY - JOUR ID - 3770 TI - Developing a Decision Tree based on Data Mining Method for Detecting the Influential Parameters on the Power of Flood Destruction JO - Amirkabir Journal of Civil Engineering JA - CEEJ LA - en SN - 2588-297X AU - Farhadi, Hadi AU - Esmaeily, Ali AU - Najafzadeh, Mohammad AD - M.Sc. Student in Remote Sensing Engineering, Department of Surveying Engineering, Faculty of civil and surveying Engineering, Graduate University of Advanced Technology, Kerman AD - Assistant Professor, Department of Surveying Engineering, Faculty of civil and surveying Engineering, Graduate University of Advanced Technology, Kerman AD - Department of Water Engineering, Faculty of Civil and Survey Engineering, Graduate University of Advanced Technology, Kerman Y1 - 2021 PY - 2021 VL - 53 IS - 5 SP - 1763 EP - 1780 KW - Flood KW - Decision Tree KW - Data Mining KW - Change Detection KW - Landsat-7 DO - 10.22060/ceej.2020.17119.6465 N2 - Floods, as one of the natural disasters, cause irreparable damages to the urban infrastructures, agricultural lands, and natural resources. Therefore, access to comprehensive information on influential factors the extent of flood damage can be useful in estimating the extent of the damage. In this way, this study investigates the creation of a database of effective parameters on flood destruction power using a case study of Landsat-7 satellite images with ETM+ sensor and ASTER DEM data using a decision tree. In the current research, environmental parameters such as canopy, natural slope, and slope direction were considered to evaluate flood degradation power in the study area and the decision tree model was created using these criteria. Ultimately, based on these parameters, the number of changed pixels (after the flood) in the study area is 692361 which indicates 62312.49 hectares of degraded land in the study area. According to the findings of the present study, lands with low canopy characteristics, namely normalized differential vegetation index (NDVI) between 0.2 and 0.4, low slope 0 to 45 degrees, and Southern slope direction caused the most damage caused by floods. Also, areas with dense NDVI, high slope, and northern slope orientation have a preventative influence on floods-caused damages. Overall, it can be found that the decision tree, as a data mining method, is capable of yielding better accuracy and quality in determining the effective parameters in estimating flood destruction power by increasing the input variables. UR - https://ceej.aut.ac.ir/article_3770.html L1 - https://ceej.aut.ac.ir/article_3770_419aa492110e7796ee2a8dcb8ab07734.pdf ER -