Computer model for tsunami vulnerability using sentinel 2A and SRTM images optimized by machine learning

This study aims to develop a software framework for modeling of tsunami vulnerability using DEM and Sentinel 2 images. The stages study, are: 1) extraction images algorithms NDVI, NDBI, NDWI, MSAVI, MNDWI; 2) prediction vegetation indices machine learning algorithms. 3) accuracy testing the MSE, ME, RMSE, MAE, MPE, MAPE; 4) spatial Kriging function 5) indicators. results show that in 2021 area was dominated by density between (-0.1-0.3) with moderate high risk land use as result decreasing vegetation. low canopy degree surface slope. Based on 2021, mostly shows existence built-up lands (more than 0.1). Vegetation population had decreased 67% from original areas 2017 an 135 km2. Forest 45% 116 km2 2017. Land fisheries increased 86 24