Flood susceptibility mapping using extremely randomized trees for Assam 2020 floods

The year 2020 proved disastrous for the north eastern state of India, Assam. The state witnessed terrible floods in the midst of the pandemic. The current study aims to better understand the role played by various factors that contributed to the deluge. To this end, the current study undertakes a flood susceptibility mapping using a seldom employed decision tree based ensemble machine learning technique of extremely randomized trees (ERT). The model was trained and tested on a flood inventory superimposed with 14 flood influencing factors, namely slope, elevation, aspect, normalized difference vegetation index (NDVI), topographic wetness index (TWI), slope length, land use, geology, soil type, topographic roughness index (TRI), rainfall, distance from rivers, plan and profile curvature. The model was compared against other mapping techniques and produced an area under the receiver operating characteristic curve (AUC) of 0.901 outperforming others. The generated susceptibility map deduced the presence of low elevation, high rainfall and close proximity to rivers as major factors leading up to the disaster. It prophesizes a very high flood risk for approximately 18.32% of the study area concentrated in the northern and western part of the study region. •ERT model employed for ascertaining the flood susceptibility in Hojai, Assam, India.•ERT performs better than other tree based ensembles such as RF, GBDT.•Elevation, rainfall, proximity to rivers found to be the major influencing factors.•Smaller sized dataset increases risk of over-fitting models.•Northern and western part of the region found to be most susceptible.