Wildfires pose severe threats to terrestrial ecosystems by causing loss of biodiversity, altering landscapes, compromising ecosystem services, and endangering human lives and infrastructure. Chile, with its diverse geography and climate, faces escalating wildfire frequency and intensity due to climate change. This study employs a spatial machine learning approach using a Random Forest algorithm to predict wildfire risk in Central and Southern Chile under current and future climatic scenarios. The model was trained on a time series dataset incorporating climatic, land use, and physiographic variables, with burned-area scars as the response variable. By applying this model to three projected climate scenarios, this study forecasts the spatial distribution of wildfire probabilities for multiple future periods. The model's performance was high, achieving an Area Under the Curve (AUC) of 0.91 for testing and 0.87 for validation. The accuracy, True Positive Rate (TPR), and True Negative Rate (TNR) values were 0.80, 0.87, and 0.73, respectively. Currently, the prediction of wildfire risk in Mediterranean-type climate areas and the central Araucan & iacute;a are most at risk, particularly in agricultural zones and rural-urban interfaces. However, future projections indicate a southward expansion of wildfire risk, with an overall increase in probabilities as climate scenarios become more pessimistic. These findings offer a framework for policymakers, facilitating evidence-based strategies for adaptive land management and effective mitigation of wildfire risk.