Computer model of Tsunami vulnerability using machine learning and multispectral satellite imagery

This research aims to develop a tsunami vulnerability assessment model on land use and cover using information NDVI, NDWI, MDWI, MSAVI, NDBI extracted from sentinel 2 A ASTER satellite images. The optimization algorithms LASSO linear regression. validation test is MSE, ME, RMSE MAE which show that the regression has higher accuracy than LASSO. NDWI interpolation values are 0.00 - (-0.35) MNDWI (-0.40) interpreted as presence of water surfaces along coast. MSAVI (-0.20) no vegetation. 0.15-0.20 built-up lands with social economic activities. While NDVI 0.20-0.30 vegetation densities, biomass growths photosynthesis process, moderate low levels health. digital elevation analysis shows all areas high socioeconomic activities, NDWI/MDWI, in (10 meters) so they have waves.