.jpg){kind=logo}
Forecasting Fire Hotspots in Indonesia: A Comparative Performance Analysis of SARIMA and Pulse Intervention Models
Abstract
Wildfires in Indonesia have a widespread impact on health, the environment, society, and the economy. The number of hotspots, detected through satellite imagery, is a key indicator in monitoring the severity of fires. Because hotspot data is seasonal and prone to spikes due to extraordinary events such as El Niño, an adaptive forecasting method is needed. The SARIMA model is effective for capturing seasonal patterns, but it is less responsive to extreme spikes. Therefore, intervention analysis with pulse functions is used as an alternative to model sudden and temporary changes in time series data. This study aims to compare the performance of the SARIMA model and an intervention model using a pulse function in forecasting the number of hotspots in Indonesia. The data used in this study were obtained from the Ministry of Environment and Forestry through the SiPongi platform, consisting of monthly data from January 2014 to December 2022. The modeling results show that the SARIMA model produced a MAPE value of 36.93%, an RMSE of 66.27, and an MAE of 47.83. In contrast, the intervention model with a pulse function at order b=0, s=0, and r=1 specifically SARIMAachieved a MAPE of 8.06%, an RMSE of 8.45, and an MAE of 6.67, substantially outperforming the SARIMA model across all metrics. These findings indicate that the intervention model provides much more accurate forecasts of hotspot occurrences in Indonesia. Furthermore, forecasts up to 2025 indicate a declining trend in the number of hotspots over time. However, seasonal patterns remain evident, with expected increases in hotspot activity during the months of February, August, and October. These results are expected to contribute valuable insights for developing more effective forest fire mitigation strategies in Indonesia
Keywords
Full Text:
PDFReferences
R. Kurniawan, “Conservation of Indonesian tropical forests as the lungs of the world,” Inkalindo Environmental Journal, vol. 1, no. 1, pp. 62–66, 2020.
W. Ma, Z. Feng, Z. Cheng, S. Chen, and F. Wang, “Identifying Forest Fire Driving Factors and Related Impacts in China Using Random Forest Algorithm,” Forests, vol. 11, no. 5, p. 507, May 2020, doi: 10.3390/f11050507.
I. Albar, I. Nengah Surati Jaya, B. Hero Saharjo, and B. Kuncahyo, “Spatio-Temporal Typology of Land and Forest Fire in Sumatra,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 4, no. 1, p. 83, Oct. 2016, doi: 10.11591/ijeecs.v4.i1.pp83-90.
Supari, F. Tangang, E. Salimun, E. Aldrian, A. Sopaheluwakan, and L. Juneng, “ENSO modulation of seasonal rainfall and extremes in Indonesia,” Clim. Dyn., vol. 51, no. 7–8, pp. 2559–2580, Oct. 2018, doi: 10.1007/s00382-017-4028-8.
R. D. Field et al., “Indonesian fire activity and smoke pollution in 2015 show persistent nonlinear sensitivity to El Niño-induced drought,” Proceedings of the National Academy of Sciences, vol. 113, no. 33, pp. 9204–9209, Aug. 2016, doi: 10.1073/pnas.1524888113.
S. Nurdiati, A. Sopaheluwakan, and P. Septiawan, “Spatial and Temporal Analysis of El Niño Impact on Land and Forest Fire in Kalimantan and Sumatra,” Agromet, vol. 35, no. 1, pp. 1–10, Jan. 2021, doi: 10.29244/j.agromet.35.1.1-10.
A. D. Nurhayati, B. Hero Saharjo, L. Sundawati, S. Syartinilia, and M. A. Cochrane, “Forest and Peatland Fire Dynamics in South Sumatra Province,” Forest and Society, pp. 591–603, Oct. 2021, doi: 10.24259/fs.v5i2.14435.
M. B. R. Prayoga and R. H. Koestoer, “Improving Forest Fire Mitigation in Indonesia: A Lesson from Canada,” Jurnal Wilayah dan Lingkungan, vol. 9, no. 3, pp. 293–305, Dec. 2021, doi: 10.14710/jwl.9.3.293-305.
J. S. Sze, Jefferson, and J. S. H. Lee, “Evaluating the social and environmental factors behind the 2015 extreme fire event in Sumatra, Indonesia,” Environmental Research Letters, vol. 14, no. 1, p. 015001, Jan. 2019, doi: 10.1088/1748-9326/aaee1d.
Copernicus, “Wildfires wreaked havoc in 2021, CAMS tracked their impact,” 2021.
D. M. Molina-Terrén et al., “Analysis of forest fire fatalities in Southern Europe: Spain, Portugal, Greece and Sardinia (Italy),” Int. J. Wildland Fire, vol. 28, no. 2, p. 85, 2019, doi: 10.1071/WF18004.
J. Paudel, “Natural disasters and economic inequality: Insights from wildfires across the globe,” Helsinki, Feb. 2023. doi: 10.35188/UNU-WIDER/2023/332-1.
Endrawati, Analisis data titik panas (hotspot) dan areal kebakaran hutan dan lahan tahun 2016. Jakarta: Direktorat Inventarisasi dan Pemantauan Sumber Daya Hutan, Ditjen Planolohi Kehutanan dan Tata Lingkungan Kementerian Lingkungan Hidup dan Kehutanan, 2016.
A. Adnan, G. Erda, Wamiliana, and E. Russel, “Modeling Cointegrated Nonstationary Air Pollution Data: A Forecasting Study of NO₂ and SO₂ in Indonesia (1950–2022),” Science and Technology Indonesia, vol. 11, no. 1, pp. 161–173, Jan. 2026, doi: 10.26554/sti.2026.11.1.161-173.
W. W. S. Wei, Time series analysis: Univariate and multivariate methods, 2nd ed. New York: Pearson Education,Inc, 2006.
A. Ramadhani, S. Wahyuningsih, and M. Siringoringo, “Forecasting the Number of Foreign Tourist Visits to Indonesia Used Intervention Analysis with Step Function,” Jurnal Matematika, Statistika dan Komputasi, vol. 19, no. 1, pp. 146–162, Sep. 2022, doi: 10.20956/j.v19i1.21607.
A. L. Schaffer, T. A. Dobbins, and S. A. Pearson, “Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: a guide for evaluating large-scale health interventions,” BMC Med. Res. Methodol., vol. 21, no. 1, pp. 1–12, 2021.
P. Chakorn and L. Jetsada, “The impact of insurgency in the deep south of Thailand on the arrival of Malaysian tourists to Betong district, Yala province using SARIMA with intervention model,” Kasetsart Journal of Social Sciences, vol. 43, no. 1, pp. 81–87, 2022.
A. R. Saputra, S. Wahyuningsih, and M. Siringoringo, “Peramalan Jumlah Titik Panas Provinsi Kalimantan Timur Menggunakan Analisis Intervensi Fungsi Pulse,” EKSPONENSIAL, vol. 12, no. 1, p. 93, Jun. 2021, doi: 10.30872/eksponensial.v12i1.766.
G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, Time series analysis : Forecasting and control, 4th ed. New Jersey: John Wiley & Sons, Inc, 2008.
M. H. Lee, Suhartono, and B. Sanugi, “Multi input intervention model for evaluating the impact of the asian crisis and terrorist attacks on tourist arrivals,” Matematika, vol. 26, no. 1, pp. 83–106, 2010.
S. Nurdiati, A. Sopaheluwakan, and P. Septiawan, “Spatial and Temporal Analysis of El Niño Impact on Land and Forest Fire in Kalimantan and Sumatra,” Agromet, vol. 35, no. 1, pp. 1–10, Jan. 2021, doi: 10.29244/j.agromet.35.1.1-10.
S. Nurdiati, A. Sopaheluwakan, and P. Septiawan, “Joint Distribution Analysis of Forest Fires and Precipitation in Response to ENSO, IOD, and MJO (Study Case: Sumatra, Indonesia),” Atmosphere (Basel)., vol. 13, no. 4, p. 537, Mar. 2022, doi: 10.3390/atmos13040537.
DOI: https://doi.org/10.37905/jjps.v7i1.38133
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Jambura Journal of Probability and Statistics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.