Klasifikasi Kebakaran Hutan Riau Menggunakan Random Forest dan Visualisasi Citra Sentinel-2
DOI:
https://doi.org/10.30865/klik.v4i3.1521Keywords:
Random Forest; Forest Fire; Sentinel-2; Normalized Burn Ratio(NBR); RiauAbstract
In September 2019, Riau was severely affected by hazardous haze, impacting the health of the population and disrupting the activities of approximately 6.5 million people. This situation necessitated swift and accurate actions for the mitigation and anticipation of forest and land fires. This research aims to classify forest fires in Riau using Machine Learning algorithms, specifically Random Forests. However, a comprehensive understanding of forest fires requires the visualization of Sentinel-2 satellite imagery using the Normalized Burn Ratio (NBR) index. Sentinel-2 imagery recreates a pivotal role in identifying burnt areas, measuring fire intensity, and assessing environmental impacts. Weather data spanning from January 2015 to September 2019, totaling 1733 data points have been utilized in this study. Experimental results demonstrate that the Random Forest algorithm achieved the highest accuracy of 71% with an 90% training data allocation. Meanwhile, Sentinel-2 imagery can visualize burnt areas with an overall accuracy of 94% and a kappa coefficient of 0.92. This study offers an integrated approach to addressing forest fires in Riau, resulting in improved predictions and a deeper understanding of forest fire disasters. In the context of disaster mitigation, the combination of Machine Learning and Sentinel-2 imagery visualization holds significant potential for providing critical information to stakeholders and authorities
Downloads
References
S. S. Tripathi, Ed., Forest Ecosystem Valuation Study Indonesia. United Nations Office for REDD Coordination in Indonesia(UNORCID), 2015.
K. Satoh, Song Weiguo, dan K. T. Yang, “A study of forest fire danger prediction system in Japan,” dalam Proceedings. 15th International Workshop on Database and Expert Systems Applications, 2004., IEEE, 2004, hlm. 598–602. doi: 10.1109/DEXA.2004.1333540.
“Luas Kawasan Hutan dan Kawasan Konservasi Perairan Indonesia Berdasarkan Surat Keputusan Menteri Lingkungan Hidup dan Kehutanan, 2017-2021,” Badan Pusat Statistik. Diakses: 25 Juli 2023. [Daring]. Tersedia pada: https://www.bps.go.id/statictable/2013/12/31/1716/luas-kawasan-hutan-dan-kawasan-konservasi-perairan-indonesia-berdasarkan-surat-keputusan-menteri-lingkungan-hidup-dan-kehutanan.html
“Global Fire Map,” NASA. Diakses: 25 Juli 2023. [Daring]. Tersedia pada: https://firms.modaps.eosdis.nasa.gov/map/#m:advanced;d:2019-08-31..2019-09-01;@112.3,-4.2,6.0z
Susilawati, Strategi Pengendalian Kebakaran Hutan Untuk Perlindungan Hutan dan Lahan. Banjarbaru: CV Banyubening Cipta Sejahter, 2023.
B. S. Negara, R. Kurniawan, M. Z. A. Nazri, S. N. H. S. Abdullah, R. W. Saputra, dan A. Ismanto, “Riau Forest Fire Prediction using Supervised Machine Learning,” J Phys Conf Ser, vol. 1566, no. 1, hlm. 012002, Jun 2020, doi: 10.1088/1742-6596/1566/1/012002.
R. Kurniawan, M. Z. A. Nazri, dan M. Irsyad, “On machine learning technique selection for classification,” dalam 2015 International Conference on Electrical Engineering and Informatics (ICEEI), IEEE, Agu 2015, hlm. 540–545. doi: 10.1109/ICEEI.2015.7352559.
T. A. Pratiwi, M. Irsyad, R. Kurniawan, S. Agustian, dan B. S. Negara, “Klasifikasi Kebakaran Hutan Dan Lahan Menggunakan Algoritma Naïve Bayes Di Kabupaten Pelalawan,” CESS (Journal of Computer Engineering, System and Science), vol. 6, no. 1, hlm. 139, Feb 2021, doi: 10.24114/cess.v6i1.22555.
I. M. Karo Karo, S. N. Amalia, dan D. Septiana, “Wildfires Classification Using Feature Selection with K-NN, Naïve Bayes, and ID3 Algorithms,” Journal of Software Engineering, Information and Communication Technology (SEICT), vol. 3, no. 1, hlm. 15–24, Jun 2022, doi: 10.17509/seict.v3i1.47537.
H. Haryani, C. I. Agustyaningrum, A. Surniandari, S. Sahara, dan R. K. Sari, “Algoritma Klasifikasi Multilayer Perceptron Dalam Analisa Data Kebakaran Hutan,” Jurnal Infortech, vol. 5, no. 1, hlm. 64–70, Jun 2023, doi: 10.31294/infortech.v5i1.15792.
M. D. Molovtsev dan I. S. Sineva, “Classification Algorithms Analysis in the Forest Fire Detection Problem,” dalam 2019 International Conference “Quality Management, Transport and Information Security, Information Technologies” (IT&QM&IS), IEEE, Sep 2019, hlm. 548–553. doi: 10.1109/ITQMIS.2019.8928398.
N. Febriani, S. Yunidar, R. A. Hidayat, G. Amor, dan P. Indrayani, “Klasifikasi Citra Satelit dengan Metode Random Forest Untuk Observasi Dinamika Landskap Ekosistem Kabupaten Sijunjung,” EL-JUGHRAFIYAH, vol. 2, no. 2, hlm. 75, Agu 2022, doi: 10.24014/jej.v2i2.18730.
F. Filipponi, “Exploitation of Sentinel-2 Time Series to Map Burned Areas at the National Level: A Case Study on the 2017 Italy Wildfires,” Remote Sens (Basel), vol. 11, no. 6, hlm. 622, Mar 2019, doi: 10.3390/rs11060622.
K. I. N. Rahmi dan N. Febrianti, “Pemanfaatan Data Sentinel-2 untuk Analisis Indeks Area Terbakar(Burned Area),” Jurnal Penginderaan Jauh Indonesia, vol. 02, no. 01, hlm. 1–6, 2020.
S. N. Rizqika, Y. Prasetyo, dan M. A. Yusuf, “ANALISIS AKURASI PERBANDINGAN ALGORITMA INDEKS KEBAKARAN HUTAN (NBR, BAIS2, MIRBI, dan NDVI) BERDASARKAN CITRA SENTINEL-2A (Studi Kasus?:Taman Nasional Gunung Merbabu Provinsi Jawa Tengah),” Elipsoida?: Jurnal Geodesi dan Geomatika, vol. 5, no. 1, hlm. 1–8, Jun 2022, doi: 10.14710/elipsoida.2022.16858.
R. Sari, L. Trihardianingsih, R. Firdaus Mulya, M. I. Arief, dan K. Kusrini, “Analisis Index Vegetation Wilayah Terdampak Kebakaran Hutan Riau Menggunakan Citra Landsat-8 dan Sentinel-2,” CogITo Smart Journal, vol. 8, no. 2, hlm. 282–294, Des 2022, doi: 10.31154/cogito.v8i2.439.282-294.
R. D. Pomey, Fajrin, dan Defwaldi, “Klasifikasi Tingkat Kebakaran Berdasarkan Tutupan Lahan Menggunakan Citra Sentinel 2A(Studi Kasus: Kabupaten Rokan Hulu),” Jurnal Geomatika dan Ilmu Alam, vol. 1, no. 2, hlm. 33–43, 2022.
A. R. Kusuma, F. M. Shodiq, M. F. Hazim, dan D. P. Laksono, “Hasil Studi Pola Kebakaran Lahan Gambut melalui Citra Satelit Sentinel-2 dengan Pengimplementasian Machine Learning Metode Random Forest?: Kajian Literatur,” JGISE: Journal of Geospatial Information Science and Engineering, vol. 4, no. 2, hlm. 81, Des 2021, doi: 10.22146/jgise.60828.
S. Liu, S. Wang, T. Chi, C. Wen, T. Wu, dan D. Wang, “An improved combined vegetation difference index and burn scar index approach for mapping cropland burned areas using combined data from Landsat 8 multispectral and thermal infrared bands,” Int J Wildland Fire, vol. 29, no. 6, hlm. 499, 2020, doi: 10.1071/WF18146.
I. K. Hadi, S. H. Mukti, dan W. Widyatmanti, “PEMETAAN POLA SPASIAL KEBAKARAN HUTAN DAN LAHAN DI TAMAN NASIONAL GUNUNG MERBABU BERBASIS PENGINDERAAN JAUH TAHUN 2019,” Jurnal Geografika (Geografi Lingkungan Lahan Basah), vol. 2, no. 1, hlm. 43, Jun 2021, doi: 10.20527/jgp.v2i1.4536.
S. Aldiansyah, K. A. Wahid, dan D. S. W. Ningsih, “PEMETAAN WILAYAH KEBAKARAN HUTAN DAN LAHAN MENGGUNAKAN CITRA MODIS (Studi Kasus: Provinsi Sulawesi Tenggara),” Jurnal Geosaintek, vol. 8, no. 1, hlm. 141, Apr 2022, doi: 10.12962/j25023659.v8i1.12019.
S. S. Adam dan H. Pasongli, “Evaluasi Area Kebakaran Lahan dan Hutan Berbasis Hotspot Citra Modis,” ScientiCO: Computer Science and Informatics Journal, vol. 3, no. 1, hlm. 19–34, 2020.
I. Arizky, M. Rusdi, dan S. Sugianto, “Identifikasi Kebakaran Hutan dengan menggunakan Citra Sentinel-2 pada Kawasan Hutan Seulawah Agam, Aceh Besar,” Jurnal Ilmiah Mahasiswa Pertanian, vol. 7, no. 3, hlm. 525–530, Agu 2022, doi: 10.17969/jimfp.v7i3.20977.
E. Roteta, A. Bastarrika, M. Padilla, T. Storm, dan E. Chuvieco, “Development of a Sentinel-2 burned area algorithm: Generation of a small fire database for sub-Saharan Africa,” Remote Sens Environ, vol. 222, hlm. 1–17, Mar 2019, doi: 10.1016/j.rse.2018.12.011.
D. P. Roy dkk., “Landsat-8 and Sentinel-2 burned area mapping - A combined sensor multi-temporal change detection approach,” Remote Sens Environ, vol. 231, hlm. 111254, Sep 2019, doi: 10.1016/j.rse.2019.111254.
A. Lefebvre dan P. Bogaert, “A Review Of The Potential And Challenges Of Using Satellite Imagery For Wildfire Detection And Management In Close To Real Time,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 151, hlm. 96–116, 2019.
T. M. Liliesand, R. W. Kiefer, dan J. W. Chipman, Remote Sensing and Image Interpretation. Wiley, 2015.
“Pekanbaru, Riau, Indonesia Weather History,” IBM Cloud. Diakses: 15 Oktober 2019. [Daring]. Tersedia pada: https://www.wunderground.com/history/monthly/id/pekanbaru/WIBB
“EO Browser,” Sentinel Hub. Diakses: 25 Juli 2023. [Daring]. Tersedia pada: https://apps.sentinel-hub.com/eo-browser/?zoom=10&lat=41.90074&lng=12.54364&themeId=DEFAULT-THEME&toTime=2023-05-30T14%3A31%3A25.744Z
“Normalized Burn Ratio (NBR),” United Nations General Assembly. Diakses: 25 Juli 2023. [Daring]. Tersedia pada: https://un-spider.org/advisory-support/recommended-practices/recommended-practice-burn-severity/in-detail/normalized-burn-ratio
J. R. Jensen, Introductory Digital Image Processing?: A Remote Sensing Perspective. London: Pearson Education, 2005.
S. Sawangarreerak dan P. Thanathamathee, “Random Forest with Sampling Techniques for Handling Imbalanced Prediction of University Student Depression,” Information, vol. 11, no. 11, hlm. 519, Nov 2020, doi: 10.3390/info11110519.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Klasifikasi Kebakaran Hutan Riau Menggunakan Random Forest dan Visualisasi Citra Sentinel-2
ARTICLE HISTORY
Issue
Section
Copyright (c) 2023 Ahmad Efendi, Iwan Iskandar, Rahmad Kurniawan, Muhammad Affandes
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
