Identifying Key Drivers of Wildfires in the Contiguous US Using Machine Learning and Game Theory Interpretation

Climate warming increases extreme daily wildfire growth risk in California

California has experienced enhanced extreme wildfire behaviour in recent years1-3, leading to substantial loss of life and property4,5. Some portion of the change in wildfire behaviour is attributable to anthropogenic climate warming, but formally quantifying this contribution is difficult because of numerous confounding factors6,7 and because wildfires are below the grid scale of global climate models. Here we use machine learning to quantify empirical relationships between temperature (as well as the influence of temperature on aridity) and the risk of extreme daily wildfire growth (>10,000 acres) in California and find that the influence of temperature on the risk is primarily mediated through its influence on fuel moisture. We use the uncovered relationships to estimate the changes in extreme daily wildfire growth risk under anthropogenic warming by subjecting historical fires from 2003 to 2020 to differing background climatological temperatures and aridity conditions. We find that the influence of anthropogenic warming on the risk of extreme daily wildfire growth varies appreciably on a fire-by-fire and day-by-day basis, depending on whether or not climate warming pushes conditions over certain thresholds of aridity, such as 1.5 kPa of vapour-pressure deficit and 10% dead fuel moisture. So far, anthropogenic warming has enhanced the aggregate expected frequency of extreme daily wildfire growth by 25% (5-95 range of 14-36%), on average, relative to preindustrial conditions. But for some fires, there was approximately no change, and for other fires, the enhancement has been as much as 461%. When historical fires are subjected to a range of projected end-of-century conditions, the aggregate expected frequency of extreme daily wildfire growth events increases by 59% (5-95 range of 47-71%) under a low SSP1-2.6 emissions scenario compared with an increase of 172% (5-95 range of 156-188%) under a very high SSP5-8.5 emissions scenario, relative to preindustrial conditions.

A novel framework to improve the consistency of water quality attribution from natural and anthropogenic factors

One critical question for water security and sustainable development is how water quality responses to the changes in natural factors and human activities, especially in light of the expected exacerbation in water scarcity. Although machine learning models have shown noticeable advances in water quality attribution analysis, they have limited interpretability in explaining the feature importance with theoretical guarantees of consistency. To fill this gap, this study built a modelling framework that employed the inverse distance weighting method and the extreme gradient boosting model to simulate the water quality at grid scale, and adapted the Shapley additive explanation to interpret the contributions of the drivers to water quality over the Yangtze River basin. Different from previous studies, we calculated the contribution of features to water quality at each grid within river basin and aggregated the contribution from all the grids as the feature importance. Our analysis revealed dramatic changes in response magnitudes of water quality to drivers within river basin. Air temperature had high importance in the variability of key water quality indicators (i.e. ammonia-nitrogen, total phosphorus, and chemical oxygen demand), and dominated the changes of water quality in Yangtze River basin, especially in the upstream region. In the mid- and downstream regions, water quality was mainly affected by human activities. This study provided a modelling framework applicable to robustly identify the feature importance by explaining the contribution of features to water quality at each grid.

Machine Learning Models Using SHapley Additive exPlanation for Fire Risk Assessment Mode and Effects Analysis of Stadiums

Machine learning methods can establish complex nonlinear relationships between input and response variables for stadium fire risk assessment. However, the output of machine learning models is considered very difficult due to their complex "black box" structure, which hinders their application in stadium fire risk assessment. The SHapley Additive exPlanations (SHAP) method makes a local approximation to the predictions of any regression or classification model so as to be faithful and interpretable, and assigns significant values (SHAP value) to each input variable for a given prediction. In this study, we designed an indicator attribute threshold interval to classify and quantify different fire risk category data, and then used a random forest model combined with SHAP strategy in order to establish a stadium fire risk assessment model. The main objective is to analyze the impact analysis of each risk characteristic on four different risk assessment models, so as to find the complex nonlinear relationship between risk characteristics and stadium fire risk. This helps managers to be able to make appropriate fire safety management and smart decisions before an incident occurs and in a targeted manner to reduce the incidence of fires. The experimental results show that the established interpretable random forest model provides 83% accuracy, 86% precision, and 85% recall for the stadium fire risk test dataset. The study also shows that the low level of data makes it difficult to identify the range of decision boundaries for Critical mode and Hazardous mode.

High-resolution mapping of wildfire drivers in California based on machine learning

Wildfires are important natural disturbances of ecosystems; however, they threaten the sustainability of ecosystems, climate and humans worldwide. It is vital to quantify and map the controlling drivers of wildfires for effective wildfire prediction and risk management. However, high-resolution mapping of wildfire drivers remains challenging. Here we established machine-learning (Random Forests) models using 23 climate and land surface variables as model inputs to reconstruct the spatial variability and seasonality of wildfire occurrence and extent in California. The importance of individual drivers was then quantified based on the Shapley value method. Thus, we provided spatially resolved maps of wildfire drivers at high resolutions up to 0.004° × 0.004°. The results indicated that precipitation and soil moisture are the major drivers dominating 37% of the total burnt area for large and extreme wildfires in summer and 63% in autumn, while elevation plays a major role for 15-58% of burnt areas in small wildfires in all seasons. Winds are also an important contributor to summer wildfires, accounting for 41% of large and extreme burnt areas. This study enhanced our knowledge of spatial variability of wildfire drivers across diverse landscapes in a fine-scale mapping, providing valuable perspectives and case studies for other regions of the world with frequently occurred wildfire.

Study of Driving Factors Using Machine Learning to Determine the Effect of Topography, Climate, and Fuel on Wildfire in Pakistan

As the climate changes with the population expansion in Pakistan, wildfires are becoming more threatening. The goal of this study was to understand fire trends which might help to improve wildland management and reduction in wildfire risk in Pakistan. Using descriptive analyses, we investigated the spatiotemporal trends and causes of wildfire in the 2001–2020 period. Optimized machine learning (ML) models were incorporated using variables representing potential fire drivers, such as weather, topography, and fuel, which includes vegetation, soil, and socioeconomic data. The majority of fires occurred in the last 5 years, with winter being the most prevalent season in coastal regions. ML models such as RF outperformed others and correctly predicted fire occurrence (AUC values of 0.84–0.93). Elevation, population, specific humidity, vapor pressure, and NDVI were all key factors; however, their contributions varied depending on locational clusters and seasons. The percentage shares of climatic conditions, fuel, and topographical variables at the country level were 55.2%, 31.8%, and 12.8%, respectively. This study identified the probable driving factors of Pakistan wildfires, as well as the probability of fire occurrences across the country. The analytical approach, as well as the findings and conclusions reached, can be very useful to policymakers, environmentalists, and climate change researchers, among others, and may help Pakistan improve its wildfire management and mitigation.

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.