Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, replicable, and operationally viable seasonal fire probability mapping methodology using a Random Forest (RF) machine learning model in the Google Earth Engine (GEE) platform. We trained the model on historical fire occurrence and fire predictor layers from 2016–2023 and applied it to 2024 conditions to generate a probabilistic fire prediction. Our novel approach improves upon existing operational methods and scientific literature in several ways. It uses a more representative sample design which is agnostic to the burn history of fire presences and absences, pairs fire and fire predictor data from each year to account for interannual variation in conditions, empirically refines the most influential fire predictors from a comprehensive set of predictors, and provides a reproducible and accessible framework using GEE. Predictor variables include both socioeconomic and environmental drivers of fire, such as topography, fuels, potential fire behavior, forest type, vegetation characteristics, climate, water availability, crop type, recent burn history, and human influence and accessibility. The model achieves an Area Under the Curve (AUC) of 0.841 when applied to 2016–2023 data and 0.848 when applied to 2024 data, indicating strong discriminatory power despite the additional spatial and temporal variability introduced by our sample design. The highest fire probabilities emerge in forested and agricultural areas at mid elevations and near human settlements and roads, which aligns well with the known anthropogenic drivers of fire in Thailand. Distinct areas of model uncertainty are also apparent in cropland and forests which are only burned intermittently, highlighting the importance of accounting for localized burning cycles. Variable importance analysis using the Gini Impurity Index identifies both natural and anthropogenic predictors as key and nearly equally important predictors of fire, including certain forest and crop types, vegetation characteristics, topography, climate, human influence and accessibility, water availability, and recent burn history. Our findings demonstrate the heavy influence of data preprocessing and model design choices on model results. The model outputs are provided as interpretable probability maps and the methods can be adapted to future years or augmented with local datasets. Our methodology presents a scalable advancement in wildfire probability mapping with machine learning and open-source tools, particularly for data-constrained landscapes. It will support Thailand’s fire managers in proactive fire response and planning and also inform broader regional fire risk assessment efforts.

Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, replicable, and operationally viable seasonal fire probability mapping methodology using a Random Forest (RF) machine learning model in the Google Earth Engine (GEE) platform. We trained the model on historical fire occurrence and fire predictor layers from 2016-2023, and applied it to 2024 conditions to generate a probabilistic fire prediction. Our novel approach uses a more representative sample design which is agnostic to the burn history of fire presences and absences, pairs fire and fire predictor data from each year to account for interannual variation in conditions, empirically refines the most influential fire predictors from a comprehensive set of predictors, and provides a reproducible and accessible framework using GEE. Predictor variables include both socioeconomic and environmental predictors of fire, such as topography, fuels, potential fire behavior, forest type, vegetation characteristics, climate, water availability, crop type, recent burn history, and human influence and accessibility. The model achieved an Area Under the Curve (AUC) of 0.841 when applied to 2016-2023 data and 0.848 when applied to 2024 data, indicating strong discriminatory power. The highest fire probabilities emerged in forested and agricultural areas at mid elevations and near human settlements and roads, which aligns with the known anthropogenic drivers of fire Thailand. Variable importance analysis using the Gini Impurity Index identified both natural and anthropogenic predictors as key drivers of fire, including certain forest and crop types, vegetation characteristics, topography, climate, human influence and accessibility, water availability, and recent burn history. Our findings demonstrate the influence of model design choices on model results. The model outputs are provided as interpretable probability maps and the methods can be adapted to future years or augmented with local datasets. Our methodology presents a scalable advancement in wildfire probability mapping with machine learning and open-source tools, particularly for data-constrained landscapes. It can support Thailand’s fire managers in proactive fire response and planning, and also inform broader regional fire risk assessment efforts.

Background: Effective forest fuel reduction treatments reduce hazardous fuel conditions, wildfire behavior and severity. It has been suggested and partially quantitatively analyzed that these treatments may also reduce future wildfire emissions, but this potential is debated. We apply a previously published, encompassing modeling approach to assess the potential of forest fuel reduction treatments to reduce future wildfire emissions. Aims: Evaluate the effectiveness of four fuel treatment types at reducing future wildfire greenhouse gas (GHG) emissions across a range of forest types and initial fire hazard levels. Methods: Forest growth, fire behavior, fire spread and emissions models were used to simulate fuel treatments and their potential impacts. Key results: The ‘underburn only’ and ‘thin from below + pile burn’ treatments had a minimum annual fire probability (AFP) 5–35% lower than other treatment types to achieve reduced GHG emissions. When AFP was high, the ‘stand density index (SDI) thin + underburn’ treatment reduced GHG emissions 13–54% more than the next best treatment. Conclusions: AFP, forest type and initial hazard level should be primary considerations when selecting a fuel treatment type for reducing future GHG emissions. Implications: These results provide decision support when selecting a fuel treatment type for reducing future GHG emissions.