Forest fires pose a significant ecological threat, particularly in the Diamer District, Gilgit-Baltistan, Pakistan, where climatic factors combined with human activities have resulted in severe fire incidents. The present study sought to investigate the correlation between the incidence of forest fires and critical meteorological elements, including temperature, humidity, precipitation, and wind speed, over a period of 25 years, from 1998 to 2023. We analyzed 169 recorded fire events, collectively burning approximately 109,400 hectares of forest land. Employing sophisticated machine learning algorithms, Random Forest (RF), and Gradient Boosting Machine (GBM) revealed that temperature and relative humidity during the critical fire season, which spans May through July, are key factors influencing fire activity. Conversely, wind speed was found to have a negligible impact. The RF model demonstrated superior predictive accuracy compared to the GBM model, achieving an RMSE of 5803.69 and accounting for 49.47% of the variance in the burned area. This study presents a novel methodology for predictive fire risk modeling under climate change scenarios in the region, offering significant insights into fire management strategies. Our results underscore the necessity for real-time early warning systems and adaptive management strategies to mitigate the frequency and intensity of escalating forest fires driven by climate change.

This study investigated post-fire vegetation recovery in Algeria’s Tenira forest using statistical traits (PCA), RFM, and LANDIS-II spatial analysis. The dataset included satellite imagery and environmental variables such as precipitation, temperature, slope, and elevation, spanning over a decade (2010–2020). Tenira forest is composed of Mediterranean species (36.5%); the biological types encountered are dominated by therophytes (39.19%). Ninety fire outbreaks were recorded, resulting in a loss of 1400.56 ha of surface area. Following the PCA results, precipitation, temperature, slope, and elevation were the main drivers of recovery (PC1 explained 43% alone, with the first five principal components accounting for 90% of observed variance, reflecting significant environmental gradients). Based on these components, an RFM predicted the post-fire recovery with an overall accuracy of 70.5% (Cost-Sensitive Accuracy), Quantity Disagreement of 3.1%, and Allocation Disagreement of 76%, highlighting spatial misallocation as the primary source of errors. The evaluation also identified PC4 (species richness) and PC3 (elevation) as significant predictors, collectively accounting for >50% of the variation in post-fire recovery. In the spatial analysis using LANDIS-II, the growth of vegetation, mainly in mid-altitude areas, was shown to be stronger, with the species consisting of those areas being more diverse. As a result, it demonstrated the connection between species richness and recovery capability. These findings can be useful in developing a management and development strategy, as well as proposing actions for species recovery after fire, such as the construction of firebreaks or the introduction of fireproof species, to make the forest more resistant to weather changes in Mediterranean ecosystems.