Visualisasi Interaktif Simulasi Penyebaran Kebakaran Hutan dan Lahan Berbasis WebGIS Menggunakan Leaflet.js

Joko Supriyanto; Muhammad Immawan Aulia; Khairina Eka Setya Putri; Arif Ramadan; Gilar Adi Prayatna

doi:10.33506/insect.v12i2.6127

Authors

Joko Supriyanto Program Studi Informatika, Universitas Siber Muhammadiyah, Yogyakarta
Muhammad Immawan Aulia Program Studi Informatika, Universitas Islam Mulia, Yogyakarta
Khairina Eka Setya Putri Program Studi Sistem Informasi, Universitas Siber Muhammadiyah, Yogyakarta
Arif Ramadan Program Studi Sistem Informasi, Universitas Siber Muhammadiyah, Yogyakarta
Gilar Adi Prayatna Program Studi Sistem Informasi, Universitas Siber Muhammadiyah, Yogyakarta

DOI:

https://doi.org/10.33506/insect.v12i2.6127

Keywords:

Leaflet.js, WebGIS, Visualisasi Interaktif, Simulasi Kebakaran, Peta Digital

Abstract

Kebakaran hutan dan lahan di Indonesia terjadi hampir setiap tahun dan memerlukan alat bantu visualisasi yang mudah diakses oleh petugas lapangan untuk mendukung pengambilan keputusan mitigasi bencana secara cepat, tanpa bergantung pada perangkat lunak Sistem Informasi Geografis (SIG) yang kompleks dan berlisensi mahal. Penelitian ini membangun dan mengevaluasi lapisan visualisasi interaktif berbasis pustaka Leaflet.js untuk menampilkan hasil simulasi penyebaran api pada peta digital, terintegrasi dengan mesin simulasi rambatan api berbasis Probabilistic Cellular Automata dan model Rothermel yang berjalan sepenuhnya di sisi klien (client-side) tanpa server backend. Metode penelitian menggunakan pendekatan Experimental Software Engineering deskriptif dan implementatif: merancang arsitektur tiga lapisan (layer) Leaflet.js berupa peta dasar (basemap), overlay tingkat risiko bahan bakar (fuel risk), dan poligon perimeter api dinamis, kemudian mengujinya secara fungsional (black-box testing) pada tiga aspek pengujian. Hasil pengujian pada delapan skenario dengan durasi berbeda (20, 24, 32, dan 48 jam) menunjukkan bahwa Leaflet.js mampu merender data grid geospasial dan poligon vektor pada peramban standar; pada skenario tiga titik api rendering berlangsung tanpa kegagalan yang teramati hingga luas area terbakar 109 ha, sedangkan skenario berdurasi 24 hingga 48 jam menghasilkan luas 604 hingga 2.338 ha dengan poligon perimeter tetap tertampil. Dapat disimpulkan bahwa Leaflet.js berpotensi menjadi pilihan pustaka visualisasi WebGIS sumber terbuka yang fleksibel, bebas lisensi berbayar, dan sesuai untuk aplikasi mitigasi bencana kebakaran berbasis web dengan sumber daya komputasi terbatas, meskipun validasi kuantitatif lebih lanjut terhadap kinerja rendering (penggunaan memori dan frame rate) pada variasi perangkat keras masih diperlukan.

References

[1] Puspitadewi, C. H., Dhini, A., Laoh, E., dan Sudiana, D., “GIS-based wildfire prediction model in Indonesia using stacking ensemble learning,” Artificial Intelligence in Geosciences, vol. 7, no. 2, hal. 100228, 2026, https://doi.org/10.1016/j.aiig.2026.100228.

[2] Ghosh, R., Adhikary, J., dan Chemlal, R., “Fire Spread Modeling using Probabilistic Cellular Automata,” arXiv:2403.08817 (pracetak), 2024, https://arxiv.org/abs/2403.08817.

[3] Freire, J. G., dan DaCamara, C. C., “Using cellular automata to simulate wildfire propagation and to assist in fire management,” Natural Hazards and Earth System Sciences, vol. 19, no. 1, hal. 169–179, 2019, https://doi.org/10.5194/nhess-19-169-2019.

[4] Agafonkin, V., “Leaflet — an open-source JavaScript library for interactive maps,” 2024, https://leafletjs.com/.

[5] Balla, D., dan Gede, M., “Comparative performance analysis of open source web mapping libraries for rendering large amounts of vector data,” Abstracts of the ICA, vol. 10, hal. 14, 2025, https://doi.org/10.5194/ica-abs-10-14-2025.

[6] Ott, N., dan Mäs, S., “Analysis of free web mapping libraries: As decision support tool for the World Heat Flow Database Project,” Zenodo, 2023, https://doi.org/10.5281/zenodo.8139086.

[7] Puttinaovarat, S., Saeliw, A., Pruitikanee, S., Kongcharoen, J., Seksan, J., Wangpoonsarp, A., Anucharn, T., dan Iamchuen, N., “WildfireGO: A Multi-Source Wildfire Detection and Validation System Integrating Crowdsourcing, Satellite Hotspots, and Deep Learning,” Applied System Innovation, vol. 9, no. 7, hal. 136, 2026, https://doi.org/10.3390/asi9070136.

[8] Mutthulakshmi, K., Wee, M. R. E., Wong, Y. C. K., Lai, J. W., Koh, J. M., Acharya, U. R., dan Cheong, K. H., “Simulating forest fire spread and fire-fighting using cellular automata,” Chinese Journal of Physics, 2020, https://doi.org/10.1016/j.cjph.2020.04.001.

[9] Zhuang, H., Liu, N., Xie, X., Xu, X., Li, M., Zhang, Y., dan Wang, R., “Simulating wildfire spread based on continuous time series remote sensing images and cellular automata,” International Journal of Wildland Fire, vol. 34, no. 1, hal. WF24130, 2025, https://doi.org/10.1071/WF24130.

[10] Anderson, H. E., “Aids to determining fuel models for estimating fire behavior,” USDA Forest Service, Intermountain Forest and Range Experiment Station, Ogden, UT, USA, Gen. Tech. Rep. INT-122, 1982.

[11] Pais, C., Carrasco, J., Martell, D. L., Weintraub, A., dan Woodruff, D. L., “Cell2Fire: A Cell-Based Forest Fire Growth Model to Support Strategic Landscape Management Planning,” Frontiers in Forests and Global Change, vol. 4, hal. 692706, 2021, https://doi.org/10.3389/ffgc.2021.692706.

[12] Radke, D., Hessler, A., dan Ellsworth, D., “FireCast: Leveraging Deep Learning to Predict Wildfire Spread,” dalam Proc. 28th International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, Tiongkok, 2019, hal. 4575–4581, https://doi.org/10.24963/ijcai.2019/636.

[13] Gonçalves, J., Barroso, G. M., dan Barata, C. S., “PROTEGE: A Near Real-Time Geospatial Information System for Wildfire Detection and Response in the Brazilian Amazon,” dalam Anais do Seminário Integrado de Software e Hardware (SEMISH), Porto Alegre: SBC, 2026, hal. 542–553, https://doi.org/10.5753/semish.2026.22629.

[14] Martins, L., Almeida, R. V. de, Maia, A., dan Vieira, P., “Analysing Fire Propagation Models: A Case Study on FARSITE for Prolonged Wildfires,” Fire, vol. 8, no. 5, hal. 166, 2025, https://doi.org/10.3390/fire8050166.

[15] Beyki, S. M., Lopes, A. M. G., Santiago, A., dan Laím, L., “Improving wildfire simulation accuracy using satellite active fire data for interval reinitialization and rate of spread adjustment,” Remote Sensing Applications: Society and Environment, hal. 101648, 2025, https://doi.org/10.1016/j.rsase.2025.101648.

[16] Xu, H., Zlatanova, S., Liang, R., dan Canbulat, I., “Generative AI as a Pillar for Predicting 2D and 3D Wildfire Spread: Beyond Physics-Based Models and Traditional Deep Learning,” Fire, vol. 8, no. 8, hal. 293, 2025, https://doi.org/10.3390/fire8080293.

[17] Brasiel, H. C., dan Lima, D. A., “Clustered-map probabilistic cellular automata for fire propagation in the Brazilian Cerrado with heterogeneous vegetation and wind interference,” Urban Resilience and Sustainability, vol. 2, no. 1, hal. 45–75, 2024, https://doi.org/10.3934/urs.2024004.

[18] Singh, H., Ang, L.-M., Paudyal, D., Acuna, M., Srivastava, P. K., dan Srivastava, S. K., “A Comprehensive Review of Empirical and Dynamic Wildfire Simulators and Machine Learning Techniques used for the Prediction of Wildfire in Australia,” Technology, Knowledge and Learning, 2025, https://doi.org/10.1007/s10758-025-09839-5