Markov chain analysis to predict natural disasters in the Province of Bangka Belitung Islands as part of preventative measures to prevent environmental damage

Abstract

Bangka Belitung Islands Province is a province which is famous for its beauty and natural wealth. In addition to its natural beauty and wealth, this province has disaster-prone areas. Based on the results of the 2021 Indonesian Disaster Risk Index (IRBI) measurement, the Bangka Belitung Islands Province has the second highest risk class in Indonesia with a value of 160.98. Therefore, a study is needed that aims to determine the prediction of natural disasters in the Bangka Belitung Islands Province as a preventive measure to prevent environmental damage. The analytical method used in this research is the Markov Chain method. The data used in this study is secondary data obtained from the official website of the National Disaster Management Agency (BNPB) from 2017 to 2022 with several types of disasters, including floods, landslides, tornadoes, forest and land fires, and natural disasters others (missing persons, house fires, drowning persons, etc.). Based on the results of calculations using the Markov Chain concept, it can be concluded that the possibility of flooding in 2023 is 31.46%, landslides are 7.73%, tornadoes are 43.81%, forest and land fires are 14.32%, and other disasters of 2.69% with a Mean Absolute Error (MAE) of 0.356 and a Mean Square Error (MSE) of 0.17.