The Mars method approach in the analysis of earthquake hazard predictions in Sumbawa

Sumbawa Island is part of the territory of Indonesia which is in the position of three active earth plates which of course will have an impact on frequent earthquakes and the risk of earthquake hazards. Research on earthquakes in general has been done a lot, but especially on the island of Sumbawa there are still few who do research on the dangers of earthquakes. Earthquake research has uncertain parameters and to obtain optimal results an appropriate method is needed. In general, some predictive data mining methods are grouped into two categories, namely Parametric and Non-Parametric. This study uses a non-parametric method with MARS. There are two stages of MARS completion, namely Forward Stepwise and Backward Stepwise algorithms. The results of this study after testing the parameters and analysis obtained a mathematical model with 11 basis functions (BF) that contribute to the response variable, namely the basis function (BF) 1,2,3,4,5,7,9, and 11. not contributing are BF 6.8, and 10. The predictor variables that have the greatest influence are 100 % Epicenter Distance and 73.8% Magnitude. It can be concluded that the results of the prediction analysis of the areas in Sumbawa that have the highest earthquake hazard are Mapin Kebak, Mapin Rea, Panjang Island and Saringi Island.