<![CDATA[Peatland fires occur almost annually in Bengkalis District, Riau Province, Indonesia, where peatlands cover about 65% of the area and contribute significantly to carbon emissions and regional haze, highlighting the need for improved fire risk prediction. This research aims to apply a probabilistic logistic regression approach to predict peatland fire hotspot occurrence and identify its key drivers. Hotspot data from 2015–2023 were derived from VIIRS satellite observations and classified into low (l), nominal (n), and high (h) confidence levels. Then hotspot confidence levels are classified into two scenarios: (1) the nh scenario (l = 0; n–h = 1) and (2) the h scenario (l–n = 0; h = 1), representing different fire thresholds. The predictor variable was modeled using anthropogenic and environmental, with multicollinearity testing to ensure model stability. The results show that the nh scenario performs better, with Nagelkerke R² = 0.0681, Hosmer–Lemeshow χ² = 5.7663, AUC = 0.69, and accuracy = 95.19%, indicating acceptable fit and moderate discrimination. Significant predictors include plantation land use, peat characteristics, and precipitation. These findings suggest that the approach can support peatland fire risk assessment, although further refinement is required.]]>
Copyrights © 2026
