Indonesian forest fire data clustering using spatiotemporal data using grid density-based clustering algorithm

Fitrianah, Devi ORCID: https://orcid.org/0000-0001-5029-8149, Fahmi, Hisyam ORCID: https://orcid.org/0000-0002-2665-1536, Kemala, Ade Putera ORCID: https://orcid.org/0000-0003-1926-7904 and Syahputra, Muhammad Edo (2023) Indonesian forest fire data clustering using spatiotemporal data using grid density-based clustering algorithm. Presented at Pacific Rim Knowledge Acquisition Workshop 2023.

Text 18921.pdf Download (839kB)

Abstract

Forest fires are major environmental issues, especially in Indonesia which has the large area of forests. It becomes national problems that must be integrally and systematically resolved. Forest fires prediction and mapping are one of the approaches providing information about potential forest fire areas. The meteorological conditions (e.g., temperature, wind speed, humidity) are known features influencing forest fires to spread. In this research, we combine the information from meteorological data and the forest fires incident in Indonesia for a specific location and time to map and predict forest fire areas. Forest fires data obtained from BNPB website from 2011 until 2023 and then combined with meteorological data at the corresponding time. Grouping closest points into one cluster is the first step to map the data using IMSTAGRID algorithm. This algorithm is the adaptation of the grid density clustering method implemented for spatiotemporal data which provides a good clustering result with Silhouette values up to 0.8175.

Item Type:	Conference (Paper)
Keywords:	Forest Fires; Spatio-temporal; Data Mining; Grid Density Based Clustering; HDBSCAN
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
Divisions:	Faculty of Mathematics and Sciences > Department of Mathematics
Depositing User:	Hisyam Fahmi
Date Deposited:	17 May 2024 13:58

Downloads

Origin of downloads

Actions (login required)

View Item