Exploring the multidimensional effects of human activity and land cover on fire occurrence for territorial planning

Mapping the probability of forest fire hazard across the European Alps under climate change scenarios

Forest fires are increasing in frequency and intensity worldwide due to the anthropogenic climate change, threatening people's lives and causing huge economic and environmental damages. Recent forest fire events suggest that forest fires are also an urgent issue in the European Alps, but studies assessing the forest fire hazard under future climate scenarios are still rare. Thus, this study aims to analyse the impacts of climate change on the probability of forest fire hazard across the European Alps and surrounding areas. In specific, we (1) explain the current forest fire hazard based on a set of environmental and anthropogenic parameters, and (2) map the forest fire hazard under current and future conditions across the study area using geographically weighted regression. Our results suggest that the fire hazard mainly depends on the frequency of lightning strikes, the annual mean temperature, and the precipitation seasonality. Overall, our results indicate a future increase in forest fire hazard, which is already significant under the SSP126 (+15.5%), while highest increases occur under the SSP370 (30.6%) and the SSP585 (35.4%). However, while the impacts are less pronounced in already fire-prone regions in the southwestern regions in France, the probability of forest fire hazard will greatly increase in the Northern and Eastern regions. Our findings emphasize the urgent need to address these climate-related challenges by decision-making and management through fire-smart forest management. Nevertheless, further efforts are needed to overcome current limitations related to data availability and uncertainties in future scenarios.

Estimation of potential wildfire behavior characteristics to assess wildfire danger in southwest China using deep learning schemes

Accurate estimation of potential wildfire behavior characteristics (PWBC) can improve wildfire danger assessment. However, wildfire behavior has been estimated by most fire spread models with immeasurable uncertainties and difficulties in large-scale applications. In this study, a PWBC estimation model (named PWBC-QR-BiLSTM) was proposed by coupling the Bi-directional Long Short-Term Memory (BiLSTM) and quantile regression (QR) methods. Multi-source data, including fuel, weather, topography, infrastructure, and landscape variables, were input into the PWBC-QR-BiLSTM model to estimate the potential rate of spread (ROS) and fire radiative power (FRP) over western Sichuan of China, and then to estimate the probability density of ROS and FRP. Daily ROS and FRP were extracted from the Global Fire Atlas and the MOD14A1/MYD14A1 product. The optimal PWBC-QR-BiLSTM model was determined using the Non-dominated Sorting Genetic Algorithm Ⅱ (NAGA-Ⅱ). Results showed that the PWBC-QR-BiLSTM performed well in estimating potential ROS and FRP with high accuracy (ROS: R2 > 0.7 and MAPE<30%, FRP: R2 > 0.8 and MAPE<25%). The modal PWBC values extracted from the estimated probability density were closer to the observed values, which can be regarded as a good indicator for wildfire danger assessment. The variable importance analysis also verified that fuel and infrastructure variables played an important role in driving wildfire behavior. This study suggests the potential of utilizing artificial intelligence to estimate PWBC and its probability density to improve the guidance on wildfire management.

A firebreak placement model for optimizing biodiversity protection at landscape scale

A solution approach is proposed to optimize the selection of landscape cells for inclusion in firebreaks. It involves linking spatially explicit information on a landscape's ecological values, historical ignition patterns and fire spread behavior. A firebreak placement optimization model is formulated that captures the tradeoff between the direct loss of biodiversity due to the elimination of vegetation in areas designated for placement of firebreaks and the protection provided by the firebreaks from losses due to future forest fires. The optimal solution generated by the model reduced expected losses from wildfires on a biodiversity combined index due to wildfires by 30% relative to a landscape without any treatment. It also reduced expected losses by 16% compared to a randomly chosen solution. These results suggest that biodiversity loss resulting from the removal of vegetation in areas where firebreaks are placed can be offset by the reduction in biodiversity loss due to the firebreaks' protective function.

Modeling wildfire risk in western Iran based on the integration of AHP and GIS

This study aimed at delineating the wildfire risk zones in a fire-prone region located in a rarely addressed area of western Iran (Paveh city) by assessing the potential of factors such as NDVI, topographic factors (elevation, slope, and aspect), land cover, and evaporation in explaining the fire occurrence probability. Analytic hierarchy process (AHP) and geographical information system (GIS) methods were used synergistically to integrate the mentioned factors into analysis, following an informed categorization of each factor based on the information on previous fire occurrence. In the AHP process, elevation and evaporation data were considered to be the most critical factors. It was found that the predicted wildfire risk areas were in agreement with past fire events by the use of the methodology proposed by this study. Accordingly, the study's final wildfire risk map indicated that approximately 64.7% of the study area is located in the high- and very high-risk zones. Land-use planners and decision-makers may use the developed map to setup and implement fire prevention strategies and enhance or develop the fire-surveillance logistics and infrastructure, including but not limited to the positions of fire watchtowers, fire lines, and fire sensors, with the aim to minimize potential fire impacts.

A Systematic Review of Applications of Machine Learning Techniques for Wildfire Management Decision Support

Wildfires threaten and kill people, destroy urban and rural property, degrade air quality, ravage forest ecosystems, and contribute to global warming. Wildfire management decision support models are thus important for avoiding or mitigating the effects of these events. In this context, this paper aims at providing a review of recent applications of machine learning methods for wildfire management decision support. The emphasis is on providing a summary of these applications with a classification according to the case study type, machine learning method, case study location, and performance metrics. The review considers documents published in the last four years, using a sample of 135 documents (review articles and research articles). It is concluded that the adoption of machine learning methods may contribute to enhancing support in different fire management phases.