Utilizing Machine Learning and Geospatial Techniques to Evaluate Post-Fire Vegetation Recovery in Mediterranean Forest Ecosystem: Tenira, Algeria

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.