Spatio-temporal feature attribution of European summer wildfires with Explainable Artificial Intelligence (XAI)

Li, Hanyu; Vulova, Stenka; Rocha, Alby Duarte; Kleinschmit, Birgit

doi:10.1016/j.scitotenv.2024.170330

Cited by 13 publications

(5 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, this type of analysis has no scientific precedent. Previous studies on forest fires have either focused on general patterns at a global scale [85,86] or on a continental or subcontinental level [87,88] but not on the evolution of relative positions of fire and built-up areas. As this is a pioneering study, it is challenging to make comparisons with previous studies.…”

Section: Discussionmentioning

confidence: 99%

Analysis of Trends in the Distance of Wildfires from Built-Up Areas in Spain and California (USA): 2007–2015

Marey-Perez,

López-Álvarez,

Franco-Vázquez

2024

Forests

View full text Add to dashboard Cite

Wildfires present a significant risk to societies globally due to population growth, concentrated activities, climate change, and extreme environmental conditions. To establish effective fire suppression and management policies, it is crucial to determine whether the distance between ignition points and urban areas is increasing or decreasing. This study analyzes 101,597 fires in Spain and California between 2007 and 2015, where ignition points and all built-up areas were precisely geolocated in 2014. The study employs the Mann–Kendall test to determine trends and analyze the relative distance of wildfires to human buildings over time. The results indicate that wildfires are becoming statistically significantly closer in several areas. It is also observed that the majority of wildfires are moving away from buildings, although this is not a significant finding. These results suggest the possibility of further research into the reasons behind these observations and possible future developments and their consequences.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of Trends in the Distance of Wildfires from Built-Up Areas in Spain and California (USA): 2007–2015

Marey-Perez,

López-Álvarez,

Franco-Vázquez

2024

Forests

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, this type of analysis has no scientific precedent. Previous studies on forest fires have either focused on general patterns at global scale [82,83] or on a continental or subcontinental level [84,85] but not in the evolution of relative positions of fire and built up areas.…”

Section: Discussionmentioning

confidence: 99%

Are Wildfires Coming Closer to Our Doors? Analysis in Spain and California 2007-2015

Marey-Perez,

López-Álvarez,

Franco-Vázquez

2024

Preprint

View full text Add to dashboard Cite

Wildfires present a significant risk to societies globally due to population growth, con- centrated activities, climate change, and extreme environmental conditions. To establish effective fire suppression and management policies, it is crucial to determine whether the distance between ignition points and urban areas is increasing or decreasing. This study analyses 101,597 fires in Spain and California between 2007 and 2015, using the Mann-Kendall test to determine trends. The study analyses the location and cause of fires to determine their distance from human constructions over time at two spatial scales. The findings suggest that wildfires are not moving away from buildings and, in some areas, are moving significantly closer.

show abstract

“…The reason for this finding may be the extent of the study area, as meteorological conditions do not show high spatial variation within Brandenburg. Meteorological conditions may be more important when analysing FFS on a national or international scale (Busico et al, 2019;He et al, 2022;Li et al, 2024). According to the Lower Forestry Authority of the State of Brandenburg (2023), a high number of fires were caused by intentional arson and other anthropogenic actions such as open fires or smoking (see Table S 2 in the supplement).…”

Section: Forest Fire Susceptibility Under Current and Future Scenariosmentioning

confidence: 99%

“…For example, Saidi et al (2021) developed a GIS-remote sensing approach to investigate forest fire risk in Tunisia, whereas He et al (2022) studied the drivers of bushfires in New South Wales, Australia over a time period of 40 years. The current state of research on forest fires suggests that topography, climate, land use, and anthropogenic influences are the most influential parameters (Abdollahi and Pradhan, 2023;Cilli et al, 2022;Ghorbanzadeh et al, 2019;He et al, 2022;Ruffault and Mouillot, 2017;Saidi et al, 2021;Li et al, 2024). For example, Ruffault and Mouillot (2017) consider human influence, land cover, and weather conditions for the assessment of influencing factors for wildfires in the French Mediterranean region.…”

Section: Introductionmentioning

confidence: 99%

Modelling Current and Future Forest Fire Susceptibility in north-east Germany

Horn,

Vulova,

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. Preventing and fighting forest fires has been a challenge worldwide in recent decades. Forest fires alter forest structure and composition, threaten people’s livelihoods, and lead to economic losses, as well as soil erosion and desertification. Climate change and related drought events, paired with anthropogenic activities, have magnified the intensity and frequency of forest fires. It is crucial to identify the conditions that cause the emergence and spread of forest fires to improve prevention and management. We applied Random Forest (RF) machine learning (ML) algorithm to model current and future forest fire susceptibility (FFS) in the federal state of Brandenburg (Germany) using topographic, climatic, anthropogenic, soil, and vegetation predictors. FFS was modelled at a spatial resolution of 50 metres for current (2014–2022) and future scenarios (2081–2100) considering different shared socioeconomic pathways (SSP3.70 and SSP5.85). Model accuracy ranged between 69 % (RFtest) and 71 % (LOYO), showing a moderately high model reliability for predicting FFS. The model results underscore the importance of anthropogenic parameters and vegetation parameters in modelling FFS on a regional level. This study will allow forest managers and environmental planners to better identify areas, which are most susceptible to forest fires, enhancing warning systems and prevention measures.

show abstract

Spatio-temporal feature attribution of European summer wildfires with Explainable Artificial Intelligence (XAI)

Cited by 13 publications

References 61 publications

Analysis of Trends in the Distance of Wildfires from Built-Up Areas in Spain and California (USA): 2007–2015

Analysis of Trends in the Distance of Wildfires from Built-Up Areas in Spain and California (USA): 2007–2015

Are Wildfires Coming Closer to Our Doors? Analysis in Spain and California 2007-2015

Modelling Current and Future Forest Fire Susceptibility in north-east Germany

Contact Info

Product

Resources

About