This research presents a computational algorithm to predict fire behavior, designed to classify potentially dangerous fires in rural areas, integrating empirical criteria from fire management experts and open source data obtained in real-time to substantially improve predictions, providing valuable information on strategic decision-making processes for fire mitigation in rural areas.The study of fire behavior in forested areas is of great interest to researchers, but few academic papers study the conditions of ignition probability in rural and non-forest settings or investigate the complexity of fire spread rates in these contexts.This research addresses the growing concern of how anthropogenic activity affects the incidence of fires, which show increased intensity and impact. Consequently, there is a pressing need for immediate information that will enable the relevant authorities to model, classify, and assess the likelihood of hazardous events, thereby directing resources more efficiently.Particularly during periods of dry weather and high temperatures, the frequency of rural fires tends to increase. To ensure effective fire control, responsible agencies must have real-time information that can help rank risks, size hazards and allocate resources to high-priority areas.The algorithm predicts fire behavior in rural fires, incorporating factors such as topography, weather conditions, and land use. Publicly available datasets, such as NASA’s Fire Information for Resource Management System (FIRMS), OpenStreetMap, and OpenTopoData, were used for its modeling to build decision-making scenarios for each point of interest analyzed.Existing wildfire hazard assessment systems are not always effective in rural areas because they were designed for homogeneous vegetation zones, and do not consider the diversity of land uses and fuel types. This research proposes a new rural fire danger index system based on algorithms using fuzzy logic and machine learning to classify and weigh the ignition potential of vegetation ground cover in rural areas.