Pengelompokkan Data Bencana Alam Berdasarkan Wilayah, Waktu, Jumlah Korban dan Kerusakan Fasilitas Dengan Algoritma K-Means

Abstract

Indonesia has fertile soil, natural resources and abundant marine resources. However, Indonesia is also not immune to the risk of natural disasters which are a series of events that disturb and threaten life safety and cause material and non-material losses. Indonesia's strategic geological location causes Indonesia to be frequently hit by earthquakes, volcanic eruptions and other natural disasters. From the data collected, natural disasters that occurred in Indonesia consisted of several categories, namely earthquakes, volcanic eruptions, floods, landslides, tornados, and tsunamis. Many natural disasters in Indonesia have caused casualties, both fatalities and injuries, destroying the surrounding area and destroying infrastructure and causing property losses. The trend of increasing incidence of natural disasters needs to be further investigated to prevent the number of victims from increasing. This information can be obtained through a data mining approach given the large amount of data available. In relation to natural disaster data, clustering techniques in data mining are very useful for grouping natural disaster data based on the same characteristics so that the data can be adopted as a groundwork for predicting natural disaster events in the future. Thus, this research is supposed to group natural disaster data using clustering techniques using the k-means algorithm into several groups, in terms of natural disaster types, time of disaster, number of victims, and damage to various facilities as a result of natural disasters