Search Results (41)

A substantial proportion of wildfires in Mediterranean regions continue to be recorded without information about the cause or source of ignition, limiting our ability to understand ignition drivers and design effective prevention strategies. In this study, we develop a spatially harmonised wildfire database for mainland Spain by integrating ignition records from the Spanish General Fire Statistics (EGIF) with fire perimeters generated from satellite images. We then apply a Random Forest classifier to infer ignition causes for events lacking cause attribution. To interpret model behaviour, we use Shapley Additive Explanation (SHAP) values at both global and local scales. Results indicate that human-caused ignitions are dominant, with intentional and negligence-related fires accounting for 52.13% of all known events, although they are associated with contrasting climatic and land-use settings. Negligence-related fires tend to occur under hot, dry and windy conditions, often in agricultural interfaces, whereas intentional fires are more frequent under cooler and wetter conditions and in areas with higher population density and land-use change. Lightning-caused fires represent a small fraction of total ignitions (3%) but exhibit a distinct climatic signature, occurring primarily in sparsely populated areas, under intermediate moisture conditions, and often leading to larger burned areas. Despite strong overall model performance (F1-score = 0.82), minority classes (e.g., lightning and fire rekindling, 0.17%) remain challenging to classify, reflecting both data imbalance and uncertainty in causal attribution. Overall, the combined use of machine learning and explainable AI provides a coherent spatial characterisation of wildfire ignition drivers across mainland Spain, highlights systematic differences among ignition causes, and identifies key limitations in existing fire cause records. This framework represents a practical step towards improving fire cause information by integrating remote sensing products with field-based fire reports, thereby supporting more targeted and evidence-based fire risk management. Full article

Lightning is a major natural ignition source of wildfires across forest, grassland, and cropland ecosystems. Accurate prediction of lightning-ignited fire occurrence remains challenging due to uncertainties in spatiotemporal alignment caused by vegetation-dependent smoldering delays and the difficulty of representing heterogeneous fuel conditions in mixed-vegetation regions. This study proposes a semi-automated lightning–fire alignment framework that integrates land cover information and historical fire records to improve spatiotemporal matching across different vegetation types and to reduce misclassification from human-induced fires in agricultural areas. To better characterize fuel conditions, two feature-level vegetation fusion parameters—total vegetation cover and leaf area index weight—are introduced and combined with hourly meteorological variables and lightning characteristics to develop a tuned random forest prediction model. The framework is applied at a regional scale in the Greater Khingan Mountains and southwestern forest regions of China, with predictions conducted at an event-based temporal scale using hourly inputs. The vegetation-fused model achieves an AUC of 0.93, outperforming models without vegetation fusion. Analysis of model outputs indicates that hourly maximum temperature, leaf area index weight, precipitation, and wind speed are key factors influencing lightning-ignited fire occurrence. This study demonstrates the value of semi-automated alignment and vegetation feature fusion for improving lightning-ignited fire prediction in heterogeneous landscapes, supporting regional wildfire risk assessment and potential early-warning applications. Full article

Climate change can impact various facets of a region’s fire regime, such as the frequency and timing of fire ignitions. This study examines the temporal trends of monthly fire counts in the Northwest and Northeast Regions of Ontario, Canada, between 1960 and 2023. Fires ignited by human activities or lightning are analyzed separately. The significance of historical trends is investigated using the Cochrane–Orcutt method, which identifies decreasing trends in the number of human-caused fires for several months, including May through July. A complementary trend analysis of total area burned is also conducted. The forecasting of future months’ fire counts is explored using a Negative Binomial Autoregressive (NB-AR) model suitable for count time series data with overdispersion. In the NB-AR model, the use of climate teleconnections at a range of temporal lags as predictors is investigated, and their predictive skill is quantified through cross-validation estimates of Mean Absolute Error on a testing dataset. Considered teleconnections include the El Niño-Southern Oscillation (ENSO), Pacific Decadal Oscillation (PDO), Arctic Oscillation (AO), North Atlantic Oscillation (NAO), and Atlantic Multidecadal Oscillation (AMO). The study finds the use of teleconnection predictors promising, with a notable benefit for forecasting human-caused fire counts but mixed results for forecasting lightning-caused fire counts. Full article

Lightning is the primary natural cause of wildfires in mid- to high-latitude forests, and it is increasing in frequency under climate change. Traditional fire danger forecasts, reliant on standard meteorological data, often fail to capture extreme events and future risk. To address this issue, we integrate extreme climate indices with meteorological, vegetation, soil, and topographic data, and apply four machine learning methods to build probabilistic models for lightning fire occurrence. The results show that incorporating extreme climate indices significantly improves model performance. Among the models, XGBoost achieved the highest accuracy (87.4%) and AUC (0.903), clearly outperforming traditional fire weather indices (accuracy 60%–71%). Model interpretation with SHapley Additive exPlanations (SHAP) further revealed the driving mechanisms and interaction effects of extreme factors. Extreme temperature and precipitation indices contributed nearly 60% to fire occurrence, with growing season length (GSL), minimum of daily maximum temperature (TXn), diurnal temperature range (DTR), and warm spell duration index (WSDI) identified as key drivers. In contrast, heavy precipitation indices exerted a suppressing effect. Compound hot and dry conditions amplified fuel aridity and markedly increased ignition probability. This interpretable framework improves short-term lightning fire prediction and offers quantitative support for risk warning and resource allocation in a warming climate. Full article

This paper presents findings based on eighty (80) lightning-caused wildfires that occurred on Mount Mainalo, in central Peloponnese, Greece, from May 1998 to November 2022. The frequency of lightning-caused wildfires was found to increase in July and August, consistent with the occurrence of dry summer thunderstorms. Most wildfires ignited in the southern part of the mountain, at elevations between 1200 and 1800 m, and were primarily detected in the afternoon hours. We present spatial data, statistics and frequency distribution histograms of subsets of the database. The likelihood of at least one fire per season is approximately 96%, while the average number of wildfires per fire season is 3.2. These findings on the number of lightning-caused wildfires per year, the holdover time (the time interval between the ignition and fire detection), the wildfire detection time, the elevation of lightning-caused wildfire occurrence, the total annual burned area and the burned area per fire can support improving wildfire management in the region since they provide a thorough description of the regime of lightning-caused wildfire on Mount Mainalo. This research addresses a critical knowledge gap in the study of lightning-caused wildfires in the Mediterranean, which remain underexplored despite their growing relevance under climate change. Full article

This study investigates the latency of lightning-caused fires in the boreal coniferous forests of the Greater Khingan Mountains, employing advanced machine learning techniques to analyze the relationship between meteorological factors, lightning characteristics, and fire ignition and smoldering processes. Using the Random Forest Model (RFM) combined with Recursive Feature Elimination with Cross-Validation (RFECV) and SHapley Additive exPlanations (SHAP), the study identifies key factors influencing fire latency. Two methods, Min distance and Min latency, were used to determine ignition lightning, with the Min distance method proving more reliable. The results show that lightning-caused fires cluster spatially and peak temporally between May and July, aligning with lightning activity. The Fine Fuel Moisture Code (FFMC) and precipitation were identified as the most influential factors. This study underscores the importance of fuel moisture and weather conditions in determining latency of lightning-caused fire, offering valuable insights for enhancing early warning systems. Despite limitations in data resolution and the exclusion of topographic factors, this study advances our understanding of lightning-fire latency mechanisms and provides a foundation for more effective wildfire management strategies under climate change. Full article

Forest fires are among the most devastating natural disasters, causing significant environmental and economic damage. Effective early prediction mechanisms are critical for minimizing these impacts. In our previous work, we developed a smart and secure wireless sensor network (WSN) utilizing physical sensors to emulate forest fire dynamics and predict fire scenarios using machine learning. Building on this foundation, this study explores the integration of virtual sensors to enhance the prediction capabilities of the WSN. Virtual sensors were generated using polynomial regression models and incorporated into a supervector framework, effectively augmenting the data from physical sensors. The enhanced dataset was used to train a multi-layer perceptron neural network (MLP NN) to classify multiple fire scenarios, covering both early warning and advanced fire states. Our experimental results demonstrate that the addition of virtual sensors significantly improves the accuracy of fire scenario predictions, especially in complex situations like “Fire with Thundering” and “Fire with Thundering and Lightning”. The extended model’s ability to predict early warning scenarios such as lightning and smoke is particularly promising for proactive fire management strategies. This paper highlights the potential of combining physical and virtual sensors in WSNs to achieve superior prediction accuracy and scalability of the field without any extra cost. Such findings pave the way for deploying scalable (cost-effective), intelligent monitoring systems capable of addressing the growing challenges of forest fire prevention and management. We obtained significant results in specific scenarios based on the number of virtual sensors added, while in some scenarios, the results were less promising compared to using only physical sensors. However, the integration of virtual sensors enables coverage of much larger areas, making it a highly promising approach despite these variations. Future work includes further optimization of the virtual sensor generation process and expanding the system’s capability to handle large-scale forest environments. Moreover, utilizing virtual sensors will alleviate many challenges associated with the huge number of deployed physical sensors. Full article

Lightning-induced forest fires frequently inflict substantial damage on forest ecosystems, with the Daxing’anling region in northern China recognized as a high-incidence region for such phenomena. To elucidate the occurrence patterns of forest fires caused by lightning and to prevent such fires, this study employs a multifaceted approach, including statistical analysis, kernel density estimation, and spatial autocorrelation analysis, to conduct a comprehensive examination of the spatiotemporal distribution patterns of lightning-induced forest fires in the Greater Khingan Mountains region from 2016–2020. Additionally, the geographical detector method is utilized to assess the explanatory power of three main factors: climate, topography, and fuel characteristics associated with these fires, encompassing both univariate and interaction detections. Furthermore, a mixed-methods approach is adopted, integrating the Zhengfei Wang model with a three-dimensional cellular automaton to simulate the spread of lightning-induced forest fire events, which is further validated through rigorous quantitative verification. The principal findings are as follows: (1) Spatiotemporal Distribution of Lightning-Induced Forest Fires: Interannual variability reveals pronounced fluctuations in the incidence of lightning-induced forest fires. The monthly concentration of incidents is most significant in May, July, and August, demonstrating an upward trajectory. In terms of temporal distribution, fire occurrences are predominantly concentrated between 1:00 PM and 5:00 PM, conforming to a normal distribution pattern. Spatially, higher incidences of fires are observed in the western and northwestern regions, while the eastern and southeastern areas exhibit reduced rates. At the township level, significant spatial autocorrelation indicates that Xing’an Town represents a prominent hotspot (p = 0.001), whereas Oupu Town is identified as a significant cold spot (p = 0.05). (2) Determinants of the Spatiotemporal Distribution of Lightning-Induced Forest Fires: The spatiotemporal distribution of lightning-induced forest fires is influenced by a multitude of factors. Univariate analysis reveals that the explanatory power of these factors varies significantly, with climatic factors exerting the most substantial influence, followed by topographic and fuel characteristics. Interaction factor analysis indicates that the interactive effects of climatic variables are notably more pronounced than those of fuel and topographical factors. (3) Three-Dimensional Cellular Automaton Fire Simulation Based on the Zhengfei Wang Model: This investigation integrates the fire spread principles from the Zhengfei Wang model into a three-dimensional cellular automaton framework to simulate the dynamic behavior of lightning-induced forest fires. Through quantitative validation against empirical fire events, the model demonstrates an accuracy rate of 83.54% in forecasting the affected fire zones. Full article

We are witnessing significant climatic changes and increasingly frequent extreme weather conditions affecting every part of the globe. In order to reduce and stop these unfavourable climate changes, there has been a shift to the use of renewables, and in this sense, a significant contribution of the photovoltaic (PV) power plant is planned. This paper analyses the safety, reliability, and resilience of PV systems to extreme weather conditions such as wind storms, hail, lightning, high temperatures, fire, and floods. In addition to using available information from the literature, temperature measurements were also carried out on the rooftop PV power plant in Slavonski Brod, as well as a numerical stress analysis at extreme wind speeds using Ansys software. The results of the analysis show that existing PV systems are very resilient to extreme weather conditions. Utility-scale PV systems can usually withstand wind speeds of up to 50 m/s without any problems, and only at higher speeds do local stresses occur in certain parts of the structure that are higher than permissible. Resistance to hail is also very high, and manufacturers guarantee resistance to hail up to 25 mm in size. At high air temperatures, the temperature of the panel frame can reach about 70 °C, the panel temperature up to 85 °C, and the temperature of the cable insulation over 60 °C, as measurements have shown. Such high temperatures lead to a drop in electricity production up to 30% but do not pose a fire hazard to the cables and the roof if the roof insulation is conducted correctly. Forest fires do not usually pose a direct threat to PV systems, but the smoke that spreads over a large area reduces the solar radiation reaching the PV panel. It can also cause an unfavourable “wiggle effect”. Lightning strikes to a PV panel are not common, although they are possible. With built-in safeguards, no major damage should occur. Flooding is always a possibility, but with properly designed drainage systems, the damage is minimal in most cases. Full article

Thunderstorms are the main natural source of forest fires. The ignition mechanism of trees begins with the impact of cloud-to-ground lightning discharge. A common drawback of all predicting systems is that they ignore the physical mechanism of forest fire as a result of thunderstorm activity. The purpose of this article is to develop a physically based mathematical model for the ignition of a coniferous tree via cloud-to-ground lightning discharge, taking into account thermophysical, electrophysical, and physicochemical processes. The novelty of the article is explained by the development of an improved mathematical model for the ignition of coniferous trees via cloud-to-ground lightning discharge, taking into account the processes of soot formation caused by the thermal decomposition phase of dry organic matter. Mathematically, the process of tree ignition is described by a system of non-stationary nonlinear differential equations of heat conduction and diffusion. In this research, a locally one-dimensional method is used to solve three-dimensional partial differential equations. The finite difference method is used to solve one-dimensional heat conduction and diffusion equations. Difference analogues of the equations are solved using the marching method. To resolve nonlinearity, a simple iteration method is used. Temperature distributions in a structurally inhomogeneous trunk of a coniferous tree, as well as distributions of volume fractions of phases and concentrations of gas mixture components, are obtained. The conditions for tree trunk ignition under conditions of thunderstorm activity are determined. As a result, a complex three-dimensional mathematical model is developed, which makes it possible to identify the conditions for the ignition of a coniferous tree trunk via cloud-to-ground lightning discharge. Full article

This paper concerns eighty (80) lightning-ignited wildfires on Mount Mainalo, Greece, during the period from 1998 to 2022. Descriptive statistics of the dataset, frequency distribution histograms, and maps were used to describe the number of fires per year, the burned area per fire, the total burned area per year, the elevation of lightning-caused fire occurrences, the wildfire detection time, and the holdover time (the phase between the ignition and fire detection). The analysis shows an increased frequency of lightning-caused wildfires in August and July. Most of the fires took place in the southern part of the mountain and were detected in the afternoon hours. These preliminary findings and conclusions provide a comprehensive understanding of the past regime of natural fire on Mount Mainalo, and they can support improving wildfire prevention and management policies in the region. Full article

There is a complex interaction between lightning-caused fire behavior and the flora and fauna of the forest, which involves the influence of a large number of ecological factors. However, more comprehensive simulation studies under multi-system interactions between lightning ignition, forest fire spread, and animal behavior are not well developed. In this paper, we propose a forest ecosystem model based on the Agent-based modelling approach to explore the detailed linkages between different forms of lightning-caused fires and forest biodiversity. The model simulates the lightning ignition, fire spread, vegetation burning and recovery, and multi-species-survival dynamics. The experimental results show the sensitivity between environmental parameters and the magnitude of lightning-caused fires, and the beneficial ecological consequences of lightning-caused fires on forest ecosystems. By exploring detailed linkages between different forms of lightning-caused fires and forest biodiversity, we provide theoretical insights and reference suggestions for forest system governance and biodiversity conservation. Full article

Warming-driven lightning frequency increases may influence the burning rate within the circumpolar Arctic and influence vegetation productivity (GPP). We considered wildfire occurrence within the different Arctic sectors (Russian, North American, and Scandinavian). We used satellite-derived (MODIS) data to document changes in the occurrence and geographic extent of wildfires and vegetation productivity. Correlation analysis was used to determine environmental variables (lightning occurrence, air temperature, precipitation, soil and terrestrial moisture content) associated with a change in wildfires. Within the Arctic, the majority (>75%) of wildfires occurred in Russia (and ca. 65% in Eastern Siberia). We found that lightning occurrence increase and moisture are primary factors that meditate the fire frequency in the Arctic. Throughout the Arctic, warming-driven lightning influences fire occurrence observed mainly in Eastern Siberia (>40% of explained variance). Similar values (ca. 40%) at the scale of Eurasia and the entire Arctic are attributed to Eastern Siberia input. Driving by increased lightning and warming, the fires’ occurrence boundary is shifting northward and already reached the Arctic Ocean coast in Eastern Siberia. The boundary’s extreme shifts synchronized with air temperature extremes (heat waves). Despite the increased burning rate, vegetation productivity rapidly (5–10 y) recovered to pre-fire levels within burns. Together with increasing GPP trends throughout the Arctic, that may offset fires-caused carbon release and maintain the status of the Arctic as a carbon sink. Full article

Large forest fires can cause significant damage to forest ecosystems and threaten human life and property. Heilongjiang Province is a major forested area in China with the highest number and concentration of lightning-caused forest fires in the country. This study examined the spatial and temporal distribution patterns of forest fires in Heilongjiang Province, as well as the ability of satellite remote sensing to detect these fires using VIIRS 375 m fire point data, ground history forest fire point data, and land cover dataset. The study also investigated the occurrence patterns of lightning-caused forest fires and the factors affecting satellite identification of these fires through case studies. Results show that April has the highest annual number of forest fires, with 77.6% of forest fires being caused by lightning. However, less than 30% of forest fires can be effectively detected by satellites, and lightning-caused forest fires account for less than 15% of all fires. There is a significant negative correlation between the two. Lightning-caused forest fires are concentrated in the Daxing’an Mountains between May and July, and are difficult to monitor by satellites due to cloud cover and lack of satellite transit. Overall, the trend observed in the number of forest fire pixels that are monitored by satellite remote sensing systems is generally indicative of the trends in the actual number of forest fires. However, lightning-caused forest fires are the primary cause of forest fires in Heilongjiang Province, and satellite remote sensing is relatively weak in monitoring these fires due to weather conditions and the timing of satellite transit. Full article

We analyzed the distribution and number of forest fire occurrences, burned areas, and seasonality, and their trends of human- and lightning-caused small (<200 ha) and large (≥200 ha) fires from 1959 to 2021 in the forested 14 subregions of Alberta, based on the Canadian National Fire Database. We applied a non-parametric statistical test, i.e., Mann–Kendall and Sen’s slope estimator, for the patterns and magnitudes of the trends. Our results revealed that all subregions experienced significantly increasing trends of fire occurrences, either monthly or yearly, except the Alpine subregion. In the burned area case, nine ecoregions demonstrated significantly decreasing monthly trends for small fires caused by humans, except for an increasing trend in the Lower Boreal Highlands subregion in May. For seasonality, we found one to two days for both early start and delayed end of fire season, and eventually two to four days longer fire seasons in five ecoregions. This study provides an updated understanding of the fire regimes in Alberta. It would be helpful for fire management agencies to make strategic plans by focusing on high-priority regions to save lives and properties. Full article