Spatio-Temporal Forest and Land Fire Risk Modeling in Sumatra Using Atmospheric-Edaphic Integration via Bivariate Fuzzy C-Means

Ade  Firmansyah; Dedi Darwis

doi:10.59395/ijadis.v7i2.1564

Authors

Ade Firmansyah Faculty of Engineering and Computer Science, Universitas Teknokrat Indonesia, Bandar Lampung, Indonesia
Dedi Darwis Faculty of Engineering and Computer Science, Universitas Teknokrat Indonesia, Bandar Lampung, Indonesia

DOI:

https://doi.org/10.59395/ijadis.v7i2.1564

Keywords:

VLIF-Model, Bivariate Fuzzy C-Means, Vapor Pressure Deficit, Forest and Land Fire, Sumatra

Abstract

The study focused on the persistent forest and land fires in Sumatra and the conventional early warning systems that showed limitations in capturing the dynamics of the soil-atmosphere and tended to overestimate risk zones during the peak periods of fires. Existing multivariate systems also showed limitations when there was a lack of integration between atmospheric water demand and edaphic (soil) vulnerability, resulting in lower spatial efficiency in the risk area. This paper presented a new bivariate physics-based model called the VPD-LVI Integrated Fuzzy (VLIF) Model, which integrated Vapor Pressure Deficit (VPD) and Land Vulnerability Index (LVI). For the VLIF-Model, to ensure a high level of spatial detail, the model processed 2,614,056 spatiotemporal observations, representing a grid resolution of 0.1° over a two-year period (2023–2024). The model showed acceptable structural stability at k=3 (FPC = 0.6137), with distinct risk zoning contrasts. Furthermore, validation against 61,015 VIIRS thermal anomalies indicated the model's predictive reliability with an ROC-AUC of 0.8288 and a Brier Score of 0.0169, suggesting good discrimination and calibration. In the spatial efficiency analysis, 17.80% of the area categorized as 'high' risk captured 62.28% of actual thermal anomaly grids, achieving a lift factor of 3.50 and a recall of 88.91%. The VLIF-Model provided clearer contouring of peak fire zones and enabled a more targeted spatial risk intelligence layer for specific tropical peatland mitigation efforts.

533 188

Downloads

Download data is not yet available.

References

[1] S. Nurdiati et al., “The impact of El Niño southern oscillation and Indian Ocean Dipole on the burned area in Indonesia,” Terr. Atmos. Ocean. Sci., vol. 33, no. 15, 2022, doi: 10.1007/S44195-022-00016-0. DOI: https://doi.org/10.1007/s44195-022-00016-0

[2] L. Kiely et al., “Assessing costs of Indonesian fires and the benefits of restoring peatland,” Nat. Commun., vol. 12, no. 1, pp. 1–11, 2021, doi: 10.5285/fdae44ed-8b22-4935-b889-b4b271138385. DOI: https://doi.org/10.1038/s41467-021-27353-x

[3] S. Mezbahuddin et al., “Accuracy of tropical peat and non-peat fire forecasts enhanced by simulating hydrology,” Sci. Rep., vol. 13, no. 1, pp. 1–10, 2023, doi: 10.1038/s41598-022-27075-0. DOI: https://doi.org/10.1038/s41598-022-27075-0

[4] L. Mareta, A. L. Latifah, and R. Hidayat, “The Influence of Natural and Anthropogenic Factors on the Area of Forest and Land Fires in Kalimantan,” J. Tanah dan Iklim, vol. 43, no. 2, pp. 143–151, 2019. DOI: https://doi.org/10.21082/jti.v43n2.2019.147-155

[5] H. Clarke et al., “Forest fire threatens global carbon sinks and population centres under rising atmospheric water demand,” Nat. Commun., vol. 13, no. 1, pp. 1–10, 2022, doi: 10.1038/s41467-022-34966-3. DOI: https://doi.org/10.1038/s41467-022-34966-3

[6] P. A. Levine et al., “Water Stress Dominates 21st-Century Tropical Land Carbon Uptake,” Global Biogeochem. Cycles, vol. 37, no. 12, pp. 1–17, 2023, doi: 10.1029/2023GB007702. DOI: https://doi.org/10.1029/2023GB007702

[7] A. D. Nurhayati, B. Hero Saharjo, L. Sundawati, Syartinilia, M. A. Cochrane, and C. Hély, “Anthropogenic factors in a forest and peatland fire danger rating system in South Sumatra,” Environ. Res. Lett. , vol. 20, no. 6, 2025, doi: 10.1088/1748-9326/add609. DOI: https://doi.org/10.1088/1748-9326/add609

[8] L. L. B. Graham, V. Arifanti, I. Malik, M. A. Pribadi, and G. B. Applegate, “Steps towards the development of a Peat Fire Danger Rating System in Indonesia,” IOP Conf. Ser. Earth Environ. Sci., vol. 874, no. 1, p. 012010, 2021, doi: 10.1088/1755-1315/874/1/012010. DOI: https://doi.org/10.1088/1755-1315/874/1/012010

[9] N. Itsnaini, B. Sasmito, A. Sukmono, and I. Prasarti, “Analisis Hubungan Curah Hujan Dan Parameter Sistem Peringkat Bahaya Kebakaran (SPBK) Dengan Kejadian Kebakaran Hutan dan Lahan untuk Menentukan Nilai Ambang Batas Kebakaran,” J. Geod. Undip, vol. 6, no. 2, pp. 62–70, 2017, doi: 10.14710/jgundip.2017.16257.

[10] H. Hayasaka, “Peatland Fire Weather Conditions in Sumatra, Indonesia,” Climate, vol. 11, no. 5, 2023, doi: 10.3390/cli11050092. DOI: https://doi.org/10.3390/cli11050092

[11] À. Nebot and F. Mugica, “Forest fire forecasting using fuzzy logic models,” Forests, vol. 12, no. 8, 2021, doi: 10.3390/f12081005. DOI: https://doi.org/10.3390/f12081005

[12] A. A. Jafarzadeh, A. Mahdavi, and H. Jafarzadeh, “Evaluation of forest fire risk using the Apriori algorithm and fuzzy c-means clustering,” J. For. Sci., vol. 63, no. 8, pp. 370–380, 2017, doi: 10.17221/7/2017-JFS. DOI: https://doi.org/10.17221/7/2017-JFS

[13] F. Rohimahastuti, A. Djuraidah, and H. Wijayanto, “Spatio-temporal Bayes model for estimating the number of hotspots as an indicator of forest and land fires in Kalimantan Island, Indonesia,” J. Agrometeorol., vol. 27, no. 1, pp. 27–32, 2025, doi: 10.54386/jam.v27i1.2761. DOI: https://doi.org/10.54386/jam.v27i1.2761

[14] A. Vatresia, R. R. Rais, and R. S. Miliana, “Spatio-Temporal Clustering for Fire Hot Spots Occurrence Over Sulawesi Island,” 2020 FORTEI-International Conf. Electr. Eng., pp. 156–161, 2020, doi: 10.1109/FORTEI-ICEE50915.2020.9249779. DOI: https://doi.org/10.1109/FORTEI-ICEE50915.2020.9249779

[15] Louis Anthony Cox Jr., “Implications of nonlinearity, confounding, and interactions for estimating exposure concentration-response functions in quantitative risk analysis,” Environ. Res., vol. 182, p. 109026, 2020, doi: 10.1016/j.envres.2019.109026. DOI: https://doi.org/10.1016/j.envres.2019.109026

[16] C. P. R. McCarter et al., “Peat fires and legacy toxic metal release: An integrative biogeochemical and ecohydrological conceptual framework,” Earth-Science Rev., vol. 256, no. December 2023, p. 104867, 2024, doi: 10.1016/j.earscirev.2024.104867. DOI: https://doi.org/10.1016/j.earscirev.2024.104867

[17] A. J. Kohlenberg, M. R. Turetsky, D. K. Thompson, B. A. Branfireun, and C. P. J. Mitchell, “Controls on boreal peat combustion and resulting emissions of carbon and mercury,” Environ. Res. Lett., vol. 13, no. 3, 2018, doi: 10.1088/1748-9326/aa9ea8. DOI: https://doi.org/10.1088/1748-9326/aa9ea8

[18] A. J. Rigden, R. S. Powell, A. Trevino, K. A. McColl, and P. Huybers, “Microwave Retrievals of Soil Moisture Improve Grassland Wildfire Predictions,” Geophys. Res. Lett., vol. 47, no. 23, pp. 1–8, 2020, doi: 10.1029/2020GL091410. DOI: https://doi.org/10.1029/2020GL091410

[19] T. Yulianto, A. F. Rahmah, F. Faisol, and R. Amalia, “Clustering Daerah Bencana Alam di Indonesia Menggunakan Metode Fuzzy C-Means,” Unisda J. Math. Comput. Sci., vol. 9, no. 2, pp. 29–39, 2023, doi: 10.52166/ujmc.v9i2.4776. DOI: https://doi.org/10.52166/ujmc.v9i2.4776

[20] N. A. Khairani and E. Sutoyo, “Application of K-Means Clustering Algorithm for Determination of Fire-Prone Areas Utilizing Hotspots in West Kalimantan Province,” Int. J. Adv. Data Inf. Syst., vol. 1, no. 1, pp. 9–16, 2020, doi: 10.25008/ijadis.v1i1.13. DOI: https://doi.org/10.25008/ijadis.v1i1.13

[21] W. Schroeder, P. Oliva, L. Giglio, and I. A. Csiszar, “The New VIIRS 375m active fire detection data product: Algorithm description and initial assessment,” Remote Sens. Environ., vol. 143, pp. 85–96, 2014, doi: 10.1016/j.rse.2013.12.008. DOI: https://doi.org/10.1016/j.rse.2013.12.008

[22] A. S. Nur, Y. J. Kim, J. Lee, and C. W. Lee, “Spatial Prediction of Wildfire Susceptibility Using Hybrid Machine Learning Models Based on Support Vector Regression in Sydney, Australia,” Remote Sens., vol. 15, no. 3, 2023, doi: 10.3390/rs15030760. DOI: https://doi.org/10.3390/rs15030760

[23] P. Sofan, D. Bruce, W. Schroeder, E. Jones, and J. Marsden, “Assessment of VIIRS 375 m active fire using tropical peatland combustion algorithm applied to Landsat-8 over Indonesia’s peatlands,” Int. J. Digit. Earth, vol. 13, pp. 1695–1716, 2020, doi: 10.1080/17538947.2020.1791268. DOI: https://doi.org/10.1080/17538947.2020.1791268

[24] H. Hersbach et al., “The ERA5 global reanalysis,” Q. J. R. Meteorol. Soc., vol. 146, no. 730, pp. 1999–2049, 2020, doi: 10.1002/qj.3803. DOI: https://doi.org/10.1002/qj.3803

[25] N. Sidhu, E. Pebesma, and Y. C. Wang, “Usability study to assess the IGBP land cover classification for Singapore,” Remote Sens., vol. 9, no. 10, pp. 1–15, 2017, doi: 10.3390/rs9101075. DOI: https://doi.org/10.3390/rs9101075

[26] A. Firmansyah, “VLIF-Model Sumatra: Spatio-Temporal Forest and Land Fire Risk Modeling,” 2026, GitHub Repository. [Online]. Available: https://github.com/adefirmansyahuti/VLIF-MODEL-SUMATRA

[27] R. Seager, A. Hooks, A. P. Williams, B. Cook, J. Nakamura, and N. Henderson, “Climatology, variability, and trends in the U.S. Vapor pressure deficit, an important fire-related meteorological quantity,” J. Appl. Meteorol. Climatol., vol. 54, no. 6, pp. 1121–1141, 2015, doi: 10.1175/JAMC-D-14-0321.1. DOI: https://doi.org/10.1175/JAMC-D-14-0321.1

[28] J. J. Brown, M. Pascual, M. C. Wimberly, L. R. Johnson, and C. C. Murdock, “Humidity – The overlooked variable in the thermal biology of mosquito-borne disease,” Ecol. Lett., vol. 26, no. 7, pp. 1029–1049, 2023, doi: 10.1111/ele.14228. DOI: https://doi.org/10.1111/ele.14228

[29] Prayoto, M. I. Ishihara, R. Firdaus, and N. Nakagoshi, “Peatland Fires in Riau, Indonesia, in Relation to Land Cover Type, Land Management, Landholder, and Spatial Management,” J. Environ. Prot. (Irvine,. Calif)., vol. 08, no. 11, pp. 1312–1332, 2017, doi: 10.4236/jep.2017.811081. DOI: https://doi.org/10.4236/jep.2017.811081

[30] F. Mei, T. Boy, R. Hidayat, R. I. Hidayat, and M. H. Fasya, “A Fuzzy C-Means – Based Clustering Model for Analyzing TOEFL Prediction Scores in Higher Education,” vol. 10, no. 1, pp. 115–124, 2026, doi: https://doi.org/10.30871/jaic.v10i1.11468. DOI: https://doi.org/10.30871/jaic.v10i1.11468

[31] G. Roberts, M. J. Wooster, and T. Strydom, “Assessment and validation of Meteosat SEVIRI fire radiative power (FRP) retrievals over Kruger National Park,” Int. J. Appl. Earth Obs. Geoinf., vol. 136, no. October 2024, p. 104375, 2025, doi: 10.1016/j.jag.2025.104375. DOI: https://doi.org/10.1016/j.jag.2025.104375