Implementasi Metode ST-DBSCAN untuk Pengelompokan Pola Persebaran Titik Api pada Data Kebakaran Hutan di Indonesia

Gita Ramadhani Wardatus Syurifah, Hisyam Fahmi

Abstract


Forest fires are a serious problem that almost always occur in Indonesia every dry season. In 2019 and 2023, many forest fires occurred, especially in Gambus land, due to the prolonged El-Nino phenomenon. This has a negative impact on the economy, social and environment. Therefore, clustering is an important effort to find out the location of areas where forest fires occur. Clustering is a technique used in data mining which works by searching and grouping data that has the same characteristics between one data and other data obtained. This research aims to determine the results of clustering of hotspot distribution patterns in forest fires in Indonesia using the ST-DBSCAN method. The ST-DBSCAN method is a clustering method used to group data using spatial and temporal parameters. The results of this research produced five clusters, noise of 31, and silhouette coefficient of 0.401 with optimal parameters, there are Eps1 = 0.3, Eps2 = 7, and MinPts = 14.

Keywords


Forest Fire; Hotspot; ST-DBSCAN; Data Mining; Clustering

Full Text:

PDF

References


[1]

Han, J., Kamber, M., Pei, J.: Data Mining Concept and Techniques, 3rd ed. Morgan Kaufmann-Elsevier, Amsterdam (2012).

[2]

Birant, D., & Kut, A. (2007). ST-DBSCAN: An algorithm for clustering spatial–temporal data. Data & knowledge engineering, 60(1), 208-221.

[3]

Trisnaningtyas, A. 2014. “Pengelompokan Data Indeks Pembangunan Manusia Di Pulau Jawa Dengan Algoritme ST-DBSCAN dan Bahasa Pemrograman Python”

[4]

Manalu, D. J., Rahmawati, R., & Widiharih, T. (2021). Pengelompokan Titik Gempa di Pulau Sulawesi Menggunakan Algoritma ST-DBSCAN (Spatio Temporal-Density Based Spatial Clustering Application with Noise). Jurnal Gaussian, 10(4), 554-561

[5]

Notohadinegoro,T. 2006. Pembakaran dan Kebakaran Lahan. Prosiding Simposium dampak kebakaran hutan terhadap SDA dan lingkungan, Yogyakarta. 16-17 Desember 1997. Pusat studi energi, Pusat studi bencana alam, pusat studi sumberdaya lahan dan pusat penelitian lingkungan hidup UGM, Ilmu tanah UGM.

[6]

Hatta, M. 2008. Dampak Kebakaran Hutan Terhadap Sifat-sifat Tanah di Kecamatan Besitang Kabupaten Langkat. Sumatera Utara: Universitas Sumatera Utara.

[7]

Fitriana, D., Fahmi, H. (2019). The identification of determinant parameter in forest fire based on future selection algorithms. Sinergi, 23(3), 184-190.

[8]

Purwanto, B.U.B.Y., 2012. Spatial Hotspot Clustering of Forest and Land Fire using DBSCAN and ST-DBSCAN. Scientific Repository (IPB).

[9]

Birant, D., & Kut, A. (2007). ST-DBSCAN: An algorithm for clustering spatial–temporal data. Data & knowledge engineering, 60(1), 208-221.

[10]

Tan, P. N., Steinbach, M., & Kumar, V. (2013). Data mining cluster analysis: basic concepts and algorithms. Introduction to data mining, 487, 533).

[11]

R. Trisminingsih and S. S. Shaztika, "ST-DBSCAN clustering module in SpagoBI for hotspots distribution in Indonesia," 2016 3rd International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), Semarang, Indonesia, 2016, pp. 327-330, doi: 10.1109/ICITACEE.2016.7892465.




DOI: https://doi.org/10.18860/jrmm.v3i5.27314

Refbacks

  • There are currently no refbacks.