Tsunami Vulnerability and Risk Assessment in Banyuwangi District using machine learning and Landsat 8 image data

Abstract

The tsunami is a disaster that often occurs in Indonesia, there are no valid indicators to assess and monitor coastal areas based on functional land use and based on land cover which refers to the biophysical characteristics of the earth's surface. One of the recommended methods is the vegetation index. Vegetation index is a method from LULC that can be used to provide information on how severe the impact of the tsunami was on the area.In this study, an increase in the vegetation index was carried out using machine learning. The purpose of this study was to develop a tsunami vulnerability assessment model using the Vegetation Index extracted from Landsat 8 satellite imagery optimized with KNN, Random Forest and SVM. The stages of study, are: 1)extraction Landsat 8 images using algorithms NDVI, NDBI, NDWI, MSAVI, and MNDWI; 2) prediction of vegetation indices using KNN, Random Forest, and SVM algorithms. 3) accuracy testing using the MSE, RMSE, and MAE,4) spatial prediction using the Kriging function and 5) tsunami modelling vulnerability indicators. The results of this study indicate that the NDVI interpolation value is 0 - 0.1 which is defined as vegetation density, biomass growth, and moderate to low vegetation health. the NDWI value is 0.02 - 0.08 and the MNDWI value is 0.02 - 0.09 which is interpreted as the presence of surface water along the coast. MSAVI is a value of 0.1 – 0 which is defined as the absence of vegetation. The NDBI interpolation value is -0.05 - (-0.08) which is interpreted as the existence of built-up land with social and economic activities. From the results of research on the 10 areas studied, there are 3 areas with conditions that have a high level of tsunami vulnerability. 2 areas with medium vulnerability and 5 areas with low vulnerability to tsunami.

Optimizing the Amount of Production Using Hybrid Fuzzy Logic and Census II

“…The amount of error from forecasting results and determining the amount of production is calculated using MAE. The equation used to calculate the MAE can be seen in Equation ( 24) [26]. While the accuracy of the forecasting results and determining the amount of production is calculated using Equation (25).…”