Modeling Forest Fire Susceptibility Based on Bioclimatic Environmental Variables in Ambon Island, Indonesia
Abstract
Forest fires in small-island regions such as Ambon Island threaten ecosystem sustainability and community safety; however, precise geospatial risk mapping in these areas remains very limited. Therefore, this study aims to model forest fire vulnerability levels using the Maximum Entropy (MaxEnt) algorithm based on bioclimatic variables. The modeling integrated 58 MODIS hotspots as presence points with 11 bioclimatic predictor variables free from multicollinearity (BIO 2, BIO 3, BIO 4, BIO 7, BIO 8, BIO 9, BIO 10, BIO 12, BIO 14, BIO 15, and BIO 17), and its accuracy was evaluated using Receiver Operating Characteristic (ROC) curve analysis based on the testing Area Under the Curve (AUC) value. The results showed that the MaxEnt model had good spatial discrimination performance, with a mean testing AUC of 0.821. Fire vulnerability dynamics were predominantly controlled by the Mean Temperature of the Driest Quarter (BIO 9; contribution of 37.3%), Annual Precipitation (BIO 12; 21.4%), and Temperature Seasonality (BIO 4; 11.3%), which cumulatively contributed 70.0% to the modeling, with supporting contributions from BIO 14, BIO 2, BIO 3, BIO 17, BIO 10, BIO 7, BIO 15, and BIO 8. Spatially, high-vulnerability zones were clustered in wildland–urban interface (WUI) areas in the Nusaniwe (20.58 ha), Leihitu (16.82 ha), and Salahutu (16.77 ha) Districts. The synergy between extreme temperature stress and precipitation deficits was shown to accelerate vegetation fuel moisture depletion, which has strategic policy implications for transforming disaster management from reactive response to proactive prevention through the integration of vulnerability maps into Regional Spatial Planning and the Regional Disaster Management Agency, strengthening real-time early warning systems, preparing field monitoring posts, and actively involving local communities in community-based prevention management.
Downloads
References
Abdul Muin, & H. R. (2023). Pemetaan Kerentanan Kebakaran Hutan di Pulau Buru, Provinsi Maluku Berdasarkan Fire Hotspot. INSOLOGI: Jurnal Sains Dan Teknologi, 2(4), 675–683. https://doi.org/https://doi.org/10.55123/insologi.v2i4.2256
Agustiyara, A., Koren, G., & Székely, B. (2026). Comparative assessment of forest fire susceptibility and risk mapping in Riau Peatlands, Sumatra using remote sensing. Remote Sensing Applications: Society and Environment, 42, 102066. https://doi.org/https://doi.org/10.1016/j.rsase.2026.102066
Apostol, B., Capalb, F., Chivulescu, S., & Petrila, M. (2025). Assessing and Mapping Forest Fire Vulnerability in Romania Using Maximum Entropy and eXtreme Gradient Boosting. 1–33.
Astuti, R., & Fatimah, Y. A. (2024). Science in the court: Expert knowledge and forest fires on Indonesia’s plantations. Environmental Science & Policy, 151, 103631. https://doi.org/https://doi.org/10.1016/j.envsci.2023.103631
BPS. (2025). Kota Ambon Dalam Angka 2025 (BPS Kota Ambon, Ed.). BPS Kota Ambon. https://ambonkota.bps.go.id/publication/2020/04/27/0072157fa7d7bf288ceb130a/kota-ambon-dalam-angka-2020.html#:~:text=Kota Ambon Dalam Angka 2020 merupakan seri publikasi tahunan BPS,demografi dan perekonomian di Indonesia.
Butar Butar, M. B., Nasution, S., Parinduri, A. H., & Zaen, M. (2026). Traceability-based environmental burden indicators for Indonesia’s pulp sector: Corporate-group evidence from forest-risk supply chains. Environmental and Sustainability Indicators, 32, 101526. https://doi.org/https://doi.org/10.1016/j.indic.2026.101526
Chepashev, D., Nurakynov, S., Sharma, D., Sydyk, N., & Kabdulova, G. (2025). Mapping fire hazard potential in Kazakhstan: a machine learning and remote sensing perspective. International Journal of Wildland Fire, 34(9), WF24232. https://doi.org/10.1071/WF24232
Choi, J., & Chae, H. (2025). Assessing Wildfire Risk in South Korea Under Climate Change Using the Maximum Entropy Model and Shared Socioeconomic Pathway Scenarios.
Fick, S. E., & Hijmans, R. J. (2017). WorldClim 2: new 1-km spatial resolution climate surfaces for global land areas. International Journal of Climatology, 37(12), 4302–4315. https://doi.org/10.1002/joc.5086
Goltas, M. (2026). Predicting forest fire probability under current conditions and future climate change scenarios in Türkiye. Forest Ecosystems, 17(July), 100525. https://doi.org/10.1016/j.fecs.2026.100525
Goltas, M., Sinclair, A. L., Lb, L., Cochrane, M. A., Saharjo, B. H., Thomas, A., Applegate, G., Mendham, D. S., Pp, S., Mahdiyasa, A. W., Chaim, J. F., Pasaribu, U. S., Sumarga, E., Muljadi, B. P., Chrysanti, A., Muin, A., Rakuasa, H., Geografi, M. P., Jakarta, U. N., … A, S. N. (2025). Ecological Risk Assessment and Management of Forest Fires in Tamil Nadu, India: A MaxEnt Model‐Based Approach for Strategic Resource Allocation and Fire Mitigation. Risk Analysis, 45(11), 3604–3625. https://doi.org/10.1111/risa.70098
Herdian, A., Boreel, A., & Loppies, R. (2021). Tingkat kerawanan kebakaran hutan dan lahan menggunakan sistem informasi geografis (SIG) di Kota Ambon (studi kasus di jazirah leitimur selatan). JURNAL HUTAN PULAU-PULAU KECIL, 5(1), 1-13.
Jaouani, M., Boubekraoui, H., & Ghallab, A. (2027). Spatio-temporal analysis and MaxEnt modeling of wildfires in the Tangier-Tetouan-Al Hoceima region (northern Morocco). Kuwait Journal of Science, 54(1), 100691. https://doi.org/https://doi.org/10.1016/j.kjs.2026.100691
Kamyo, T., Kamyo, P., Panthong, K., Howpinjai, I., Kamton, R., & Asanok, L. (2025). Assessing Fire Risk Zones in Phrae Province, Northern Thailand, Using a MaxEnt Model. Geographies, 5(3). https://doi.org/10.3390/geographies5030051
Karurung, W. S., Lee, K., & Lee, W. (2025). Assessment of forest fire vulnerability prediction in Indonesia: Seasonal variability analysis using machine learning techniques. International Journal of Applied Earth Observation and Geoinformation, 138, 104435. https://doi.org/https://doi.org/10.1016/j.jag.2025.104435
Lorenț, A., Petrila, M., Apostol, B., Capalb, F., Chivulescu, Șerban, Șamșodan, C., Marcu, C., & Badea, O. (2025). Assessing and Mapping Forest Fire Vulnerability in Romania Using Maximum Entropy and eXtreme Gradient Boosting. In Forests (Vol. 16, Number 7, p. 1156). https://doi.org/10.3390/f16071156
Meraj, G., Hashimoto, S., Dasgupta, R., & Mitra, B. K. (2025). Ecological Risk Assessment and Management of Forest Fires in Tamil Nadu, India: A MaxEnt Model-Based Approach for Strategic Resource Allocation and Fire Mitigation. Risk Analysis, 45(11), 3604–3625. https://doi.org/https://doi.org/10.1111/risa.70098
Mupfiga, U., Mutanga, O., & Dube, T. (2025). Assessing drivers of vegetation fire occurrence in Zimbabwe - Insights from Maxent modelling and historical data analysis. Remote Sensing Applications: Society and Environment, 37, 101404. https://doi.org/https://doi.org/10.1016/j.rsase.2024.101404
Paudel, G., Pandey, K., Lamsal, P., Bhattarai, A., Bhattarai, A., & Tripathi, S. (2024). Geospatial forest fire risk assessment and zoning by integrating MaxEnt in Gorkha District , Nepal. Heliyon, 10(11), e31305. https://doi.org/10.1016/j.heliyon.2024.e31305
Phillips, S. J., Anderson, R. P., & Schapire, R. E. (2006). Maximum entropy modeling of species geographic distributions. Ecological Modelling, 190(3–4), 231–259. https://doi.org/10.1016/j.ecolmodel.2005.03.026
Purnomo, H., Puspitaloka, D., Okarda, B., Andrianto, A., Jalil, A., Prasetyo, P., Kusumadewi, S. D., Komarudin, H., Dermawan, A., & Brady, M. A. (2024). Community-based fire prevention and peatland restoration in Indonesia : A participatory action research approach. Environmental Development, 50(October 2022), 100971. https://doi.org/10.1016/j.envdev.2024.100971
Rakuasa, H. (2022). Analisis Spasial Temporal Suhu Permukaan Daratan/ Land Surface Temperature (LST) Kota Ambon Berbasis Cloud Computing: Google Earth Engine. Jurnal Ilmiah Informatika Komputer, 27(3), 194–205. https://doi.org/10.35760/ik.2022.v27i3.7101
Salakory, M., Rakuasa, H. (2022). Modeling of Cellular Automata Markov Chain for predicting the carrying capacity of Ambon City. Jurnal Pengelolaan Sumberdaya Alam Dan Lingkungan (JPSL), 12(2), 372–387. https://doi.org/https://doi.org/10.29244/jpsl.12.2.372-387
Tian, P., Wu, S., Yan, Y., Xiao, D., Li, J., Liu, Y., Zhang, H., & Ying, C. (2026). Spatiotemporal dynamic of global fires and their effects on land cover and vegetation recovery. Global and Planetary Change, 258, 105309. https://doi.org/https://doi.org/10.1016/j.gloplacha.2026.105309
Usmadi, D. (2023). Maximum entropy application in predicting the vulnerability of land and forest fires in South Sumatra Province, Indonesia. IOP Conference Series: Earth and Environmental Science, 1183(1), 12105. https://doi.org/10.1088/1755-1315/1183/1/012105
Copyright (c) 2026 BIOPENDIX: Jurnal Biologi, Pendidikan dan Terapan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement 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 websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works
2
