Recent times have witnessed wildfires causing harm to both ecological communities and urban–rural regions, underscoring the necessity to comprehend wildfire triggers and assess measures for mitigation. This research hones in on Cartagena del Chairá, diving into the interplay between meteorological conditions and land cover/use that cultivates a conducive environment for wildfires. Meteorologically, the prevalence of wildfires is concentrated during boreal winter, characterized by warm and dry air, strong winds, and negligible precipitation. Additionally, wildfires gravitate toward river-adjacent locales housing agriculture-linked shrubs, notably in the northern part of the zone, where a confluence of land attributes and meteorological factors synergize to promote fire incidents. Employing climate scenarios, we deduced that elevated temperature and reduced humidity augment wildfire susceptibility, while wind speed and precipitation discourage their propagation across most scenarios. The trajectory toward a warmer climate could instigate fire-friendly conditions in boreal summer, indicating the potential for year-round fire susceptibility. Subsequently, via machine-learning-driven sensitivity analysis, we discerned that among the scrutinized socio-economic variables, GINI, low educational attainment, and displacement by armed groups wield the most substantial influence on wildfire occurrence. Ultimately, these findings converge to shape proposed wildfire mitigation strategies that amalgamate existing practices with enhancements or supplementary approaches.

Throughout the years, wildfires have negatively impacted ecological systems and urban areas. Hence, reinforcing territorial risk management strategies against wildfires is essential. In this study, we built an early alert system (EAS) with two different Machine Learning (ML) techniques to calculate the meteorological conditions of two Colombian areas: (i) A 3D convolutional neural net capable of learning from satellite data and (ii) a convolutional network to bias-correct the Weather Research and Forecasting (WRF) model output. The results were used to quantify the daily Fire Weather Index and were coupled with the outcomes from a land cover analysis conducted through a Naïve-Bayes classifier to estimate the probability of wildfire occurrence. These results, combined with an assessment of global vulnerability in both locations, allow the construction of daily risk maps in both areas. On the other hand, a set of short-term preventive and corrective measures were suggested to public authorities to implement, after an early alert prediction of a possible future wildfire. Finally, Soil Management Practices are proposed to tackle the medium- and long-term causes of wildfire development, with the aim of reducing vulnerability and promoting soil protection. In conclusion, this paper creates an EAS for wildfires, based on novel ML techniques and risk maps.