Forest Fire Susceptibility Mapping Research Articles

Forest fire susceptibility assessment under small sample scenario: A semi-supervised learning approach using transductive support vector machine

Forest fires threaten global ecosystems, socio-economic structures, and public safety. Accurately assessing forest fire susceptibility is critical for effective environmental management. Supervised learning methods dominate this assessment, relying on a substantial dataset of forest fire occurrences for model training. However, obtaining precise forest fire location data remains challenging. To address this issue, semi-supervised learning emerges as a viable solution, leveraging both a limited set of collected samples and unlabeled data containing environmental factors for training. Our study employed the transductive support vector machine (TSVM), a key semi-supervised learning method, to assess forest fire susceptibility in scenarios with limited samples. We conducted a comparative analysis, evaluating its performance against widely used supervised learning methods. The assessment area for forest fire susceptibility lies in Dayu County, Jiangxi Province, China, renowned for its vast forest cover and frequent fire incidents. We analyzed and generated maps depicting forest fire susceptibility, evaluating prediction accuracies for both supervised and semi-supervised learning methods across various small sample scenarios (e.g., 4, 8, 12, 16, 20, 24, 28, and 32 samples). Our findings indicate that TSVM exhibits superior prediction accuracy compared to supervised learning with limited samples, yielding more plausible forest fire susceptibility maps. For instance, at sample sizes of 4, 16, and 28, TSVM achieves prediction accuracies of approximately 0.8037, 0.9257, and 0.9583, respectively. In contrast, random forests, the top performers in supervised learning, demonstrate accuracies of approximately 0.7424, 0.8916, and 0.9431, respectively, for the same small sample sizes. Additionally, we discussed three key aspects: TSVM parameter configuration, the impact of unlabeled sample size, and performance within typical sample sizes. Our findings support semi-supervised learning as a promising approach compared to supervised learning for forest fire susceptibility assessment and mapping, particularly in scenarios with small sample sizes.

Comparison of diverse machine learning algorithms for forest fire susceptibility mapping in Antalya, Türkiye

Antalya is one of the provinces with the highest number of forest fires in Türkiye. In 2021, 278 forest fires occurred within the administrative boundaries of Antalya Regional Directorate of Forestry. The main objective of this study is to produce forest fire susceptibility (FFS) maps of Antalya province using machine learning (ML) models. In addition to forest fire inventory data, 16 factors, including topographic, environmental, meteorological, and human-driven, were used in the study. Inventory data included 2166 fire ignition points from the General Directorate of Forestry. 70 % of the inventory dataset was used to train the ML models and 30 % to validate the models. Overall accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC) approaches were considered as validation metrics. FFS maps of Antalya were produced using stand-alone ML algorithms, K-Nearest Neighbors, and Support Vector Machines, as well as tree-based Conditional Inference Trees (CTREE), Random Forest (RF), Gradient Boosting Machines (GBM), and Extreme Gradient Boosting (XGBoost) algorithms. To the best of our knowledge, this is the first study using the CTREE algorithm for forest fire susceptibility mapping. Therefore, this study is important for the related literature. The validation results revealed that the XGBoost model outperformed other models. It is thought that the FFS map produced using the XGBoost model will guide forest engineers, wildland firefighting teams, and firefighters to minimize damage and control forest fires.

Integrated Spatial Analysis of Forest Fire Susceptibility in the Indian Western Himalayas (IWH) Using Remote Sensing and GIS-Based Fuzzy AHP Approach

Forest fires have significant impacts on economies, cultures, and ecologies worldwide. Developing predictive models for forest fire probability is crucial for preventing and managing these fires. Such models contribute to reducing losses and the frequency of forest fires by informing prevention efforts effectively. The objective of this study was to assess and map the forest fire susceptibility (FFS) in the Indian Western Himalayas (IWH) region by employing a GIS-based fuzzy analytic hierarchy process (Fuzzy-AHP) technique, and to evaluate the FFS based on forest type and at district level in the states of Jammu and Kashmir, Himachal Pradesh, and Uttarakhand. Seventeen potential indicators were chosen for the vulnerability assessment of the IWH region to forest fires. These indicators encompassed physiographic factors, meteorological factors, and anthropogenic factors that significantly affect the susceptibility to fire in the region. The significant factors in FFS mapping included FCR, temperature, and distance to settlement. An FFS zone map of the IWH region was generated and classified into five categories of very low, low, medium, high, and very high FFS. The analysis of FFS based on the forest type revealed that tropical moist deciduous forests have a significant vulnerability to forest fire, with 86.85% of its total area having very high FFS. At the district level, FFS was found to be high in sixteen districts and very high in seventeen districts, constituting 25.7% and 22.6% of the area of the IWH region. Particularly, Lahul and Spiti had 63.9% of their total area designated as having very low FSS, making it the district least vulnerable to forest fires, while Udham Singh Nagar had a high vulnerability with approximately 86% of its area classified as having very high FFS. ROC-AUC analysis, which provided an appreciable accuracy of 79.9%, was used to assess the validity of the FFS map produced in the present study. Incorporating the FFS map into sustainable development planning will assist in devising a holistic strategy that harmonizes environmental conservation, community safety, and economic advancement. This approach can empower decision makers and relevant stakeholders to take more proactive and informed actions, promoting resilience and enhancing long-term well-being.

FOREST FIRE SUSCEPTIBILITY MAPPING OF BHUTAN USING LOGISTIC REGRESSION AND FREQUENCY RATIO MODEL

Forest fire is not only observed as one of the most significant sources of forest degradation in Bhutan but also a serious danger to national conservation efforts. As a result, forest fire susceptibility analysis is recognised as an important part of Bhutan's forest fire management strategy. The study's major goal is to create a forest fire susceptibility map for Bhutan using logistic regression (LR) and frequency ratio (FR) models. The study gathered number of fire influencing factors, evaluated them, and created susceptibility maps. Using the relative operating characteristics technique, the efficiency of each of the two models was analysed and compared to select the best model. The Receiver Operating Characteristics (ROC) curves with the area under the curve (AUC) was used to check the correctness of the maps produced by the modelling procedure. The prediction and success rates of the LR model were 88.8% and 87.5%, while for the FR model they were 85.4% and 85.1%, respectively. The results showed that both models are good predictors of forest fire with the LR model performing fairly better than the FR model. So, the LR model was chosen as an optimum model for forest fire susceptibility mapping. The susceptibility map obtained from the optimum LR model was classified into five categories such as; very low, low, moderate, high, and very high.. The findings of this study give useful spatial information for implementing forest management techniques.

Forest fire susceptibility mapping with sensitivity and uncertainty analysis using machine learning and deep learning algorithms

In the hilly region of the Western Himalayas, forest fires play a crucial role in forest destruction and biodiversity loss. Therefore, addressing the problem of forest fires is an immediate priority to mitigate the impact of forest fires. Therefore, the objective of this research is to assess and map the susceptibility zones of forest fire in the hilly state of Uttarakhand using geospatial techniques and machine learning algorithms (MLA) and deep Learning based sensitivity and uncertainty analysis of the forest fire ignition parameters. Thirteen forest fire ignition parameters were used to map forest fire susceptibility. Further, we used five distinct MLAs, including artificial neural networks (ANN), random forest (RF), logistic regression (LR), support vector machine (SVM) and an ensemble machine learning model. The generated models were validated using the receiver operating characteristic (ROC). The result shows that the ''very high'' and ''high'' zones for forest fires cover almost 55% of the total area of Uttarakhand. Validation of the models used indicated that all models produced most significant results. The ensemble machine learning had the highest accuracy (AUC = 0.977), followed by RF (0.973) and ANN (0.972). In addition, a Deep Neural Networks (DNN) based sensitivity approach is proposed to perform sensitivity and uncertainty analysis of the ignition parameters. For this, we have selected the best predictive model (Ensemble Machine Learning) to evaluate the sensitivity and uncertainty analysis. The sensitivity analysis shows that evapotranspiration has the highly influencing parameter to forest fires, followed by annual rainfall, wind speed, distance to agriculture, distance to tourist spots, distance to built-up and distance to road. However, aspect, temperature and distance to religious centers have less influence on susceptibility to forest fires in this study area. This study is unique because it provides new insights into the construction of an ensemble machine learning model and the integration of DNN-based sensitivity and uncertainty for robust and scientific modelling of forest fire susceptibility. The contribution of parameters demonstrates a novel approach in understanding the impact of a single parameter sample on forest fire susceptibility, which will help in developing prevention strategies. A similar approach may be used in other parts of the world with similar natural and anthropogenic conditions for mapping forest fire susceptibility.

USING MACHINE LEARNING COUPLED WITH REMOTE SENSING FOR FOREST FIRE SUSCEPTIBILITY MAPPING. CASE STUDY TETOUAN PROVINCE, NORTHERN MOROCCO

Abstract. Currently there is a public awareness to protect the environment especially forest ecosystems and the forest fire dilemma has become a topic of intense research around the world. In this setting, this study evaluates forest fire susceptibility (FFS) in northern Morocco using three geographic information system (GIS) based on machine learning algorithms: XGBoost (XGB), Random Forest (RF), and Support Vector Machine (SVM). To this effect, a Geographic Information System (GIS) database was developed involving ten independent causal factors (elevation, aspect, slope, distance to roads, distance to residential areas, land cover, normalized difference vegetation index (NDVI), rainfall, temperature and wind speed) and 345 fire pixels. The 345 pixels were split into two sets for training (70%) and validation (30%) and the spatial relationships between factors affecting FFs and fire pixels was analyzed using XGB, RF, and SVM models to generate the FFS maps. The effectiveness of the models was evaluated using the receiver operating characteristic curve, the area under the curve (AUC), and several statistical measures. The results of the three models hinted that XGBoost had the highest performance (AUC = 0.856), followed by RF (AUC) = 0.827), and SVM (AUC = 0.803) in the forecasting of the forest fire. The resulting FFS maps areas can provide crucial support for the management of Mediterranean forest ecosystems and can enhance the effectiveness of planning and management of forest resources and ecological balances in these areas.

A Forest Fire Susceptibility Modeling Approach Based on Light Gradient Boosting Machine Algorithm

A forest fire susceptibility map generated with the fire susceptibility model is the basis of fire prevention resource allocation. A more reliable susceptibility map helps improve the effectiveness of resource allocation. Thus, further improving the prediction accuracy is always the goal of fire susceptibility modeling. This paper developed a forest fire susceptibility model based on an ensemble learning method, namely light gradient boosting machine (LightGBM), to produce an accurate fire susceptibility map. In the modeling, a subtropical national forest park in the Jiangsu province of China was used as the case study area. We collected and selected eight variables from the fire occurrence driving factors for modeling based on correlation analysis. These variables are from topographic factors, climatic factors, human activity factors, and vegetation factors. For comparative analysis, another two popular modeling methods, namely logistic regression (LR) and random forest (RF) were also applied to construct the fire susceptibility models. The results show that temperature was the main driving factor of fire in the area. In the produced fire susceptibility map, the extremely high and high susceptibility areas that were classified by LR, RF, and LightGBM were 5.82%, 18.61%, and 19%, respectively. The F1-score of the LightGBM model is higher than the LR and RF models. The accuracy of the model of LightGBM, RF, and LR is 88.8%, 84.8%, and 82.6%, respectively. The area under the curve (AUC) of them is 0.935, 0.918, and 0.868, respectively. The introduced ensemble learning method shows better ability on performance evaluation metrics.

Forest Fire Susceptibility Assessment and Mapping Using Support Vector Regression and Adaptive Neuro-Fuzzy Inference System-Based Evolutionary Algorithms

Support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS) are two well-known and powerful artificial intelligence techniques which have been frequently used for hazard mapping. So far, a plethora of hybrid models have been developed using a combination of either the SVR or ANFIS and evolutionary algorithms, but there are only a handful of studies that compare the performance of these models when integrated with evolutionary algorithms, especially in forest fire susceptibility mapping (FFSM). The aim of this study was to compare performance of ANFIS-, and SVR-based evolutionary algorithms, namely, the genetic algorithm (GA) and the shuffled frog-leaping algorithm (SFLA) in FFSM in Ajloun Governorate in Jordan. Accordingly, four hybrid models, SVR-GA, SVR-SFLA, ANFIS-GA, and ANFIS-SFLA, were developed and compared. One hundred and one forest fire locations were used in this study to assess and model susceptibility of forests to fires. The forest fire inventory data were divided into a training data subset (70%) and a testing data subset (30%). Fourteen factors affecting incidence of forest fires were employed as conditioning factors. The area under the receiver operating characteristic (AUROC) curve was used to assess performance of the models in the validation phase. The results revealed that the SVR-based hybrid algorithms had better AUROC values than the ANFIS-based algorithms. Of the four integrated models, the SVR-GA model proved to be the model with the highest accuracy and best performance. It had AUROC values of 0.97 and 0.89 in the training and the testing phases, respectively.

GIS-Based Frequency Ratio and Analytic Hierarchy Process for Forest Fire Susceptibility Mapping in the Western Region of Syria

Forest fires are among the most major causes of global ecosystem degradation. The integration of spatial information from various sources using statistical analyses in the GIS environment is an original tool in managing the spread of forest fires, which is one of the most significant natural hazards in the western region of Syria. Moreover, the western region of Syria is characterized by a significant lack of data to assess forest fire susceptibility as one of the most significant consequences of the current war. This study aimed to conduct a performance comparison of frequency ratio (FR) and analytic hierarchy process (AHP) techniques in delineating the spatial distribution of forest fire susceptibility in the Al-Draikich region, located in the western region of Syria. An inventory map of historical forest fire events was produced by spatially digitizing 32 fire incidents during the summers of 2019, 2020, and 2021. The forest fire events were divided into a training dataset with 70% (22 events) and a test dataset with 30% (10 events). Subsequently, FR and AHP techniques were used to associate the training data set with the 13 driving factors: slope, aspect, curvature, elevation, Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), Topographic Wetness Index (TWI), rainfall, temperature, wind speed, TWI, and distance to settlements, rivers and roads. The accuracy of the maps resulting from the modeling process was checked using the validation dataset and receiver operating characteristics (ROC) curves with the area under the curve (AUC). The FR method with AUC = 0.864 achieved the highest value compared to the AHP method with AUC = 0.838. The outcomes of this assessment provide constructive spatial insights for adopting forest management strategies in the study area, especially in light of the consequences of the current war.

Forest fire susceptibility assessment using google earth engine in Gangwon-do, Republic of Korea

Forest fires are one of the most frequently occurring natural hazards, causing substantial economic loss and destruction of forest cover. As the Gangwon-do region in Korea has abundant forest resources and ecological diversity as Korea's largest forest area, spatial data on forest fire susceptibility of the region are urgently required. In this study, a forest fire susceptibility map (FFSM) of Gangwon-do was constructed using Google Earth Engine (GEE) and three machine learning algorithms: Classification and Regression Trees (CART), Random Forest (RF), and Boosted Regression Trees (BRT). The factors related to climate, topography, hydrology, and human activity were constructed. To verify the accuracy, the area under the receiver operating characteristic curve (AUC) was used. The AUC values were 0.846 (BRT), 0.835 (RF), 0.751 (CART). Factor importance analysis was performed to identify the important factors of the occurrence of forest fires in Gangwon-do. The results show that the most important factor in the Gangwon-do region is slope. A slope of approximately 17° (moderately steep) has a considerable impact on the occurrence of forest fires. Human activity and interference are the other important factors that affect forest fires. The established FFSM can support future efforts on forest resource protection and environmental management planning in Gangwon-do.

A new approach of deep neural computing for spatial prediction of wildfire danger at tropical climate areas

Wildfire is an environmental hazard that has both local and global effects, causing economic losses and various severe environmental problems. Due to the adverse effects of climate changes and anthropogenic activities, wildfire is anticipated more frequent and extreme; therefore, new and more efficient tools for forest fire prevention and control are essential. This study proposes a new deep neural computing approach for spatial prediction of wildfire in a tropical climate area. For this purpose, deep neural computing (Deep-NC) with a structure of 3 hidden layers was proposed. The Rectified Linear Unit (ReLU) activation function was adopted to infer wildfire dangers from the input factors. To search and optimize the weights of the model, Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMSProp), Adaptive Moment Estimation (Adam), and Adadelta optimizers were employed. Also, this study has established a Geographic Information System (GIS) database for Gia Lai province (Vietnam) to train and verify the newly developed deep computing approach. The twelve ignition factors, namely, slope, aspect, elevation, curvature, land use, NVDI, NDWI, NDMI, temperature, wind speed, relative humidity, and rainfall, have been used to characterize the study area with respect to forest fire susceptibility. According to experimental results, the Adam optimized Deep-NC model delivered the highest predictive accuracy (AUC = 0.894, Kappa = 0.63). Accordingly, this model has been employed to establish a forest fire susceptibility map for Gia Lai province. The proposed Deep-NC model and the newly constructed forest fire susceptibility map can help local authorities in land use planning and hazard mitigation/prevention.

GIS-based forest fire susceptibility modeling in Pauri Garhwal, India: a comparative assessment of frequency ratio, analytic hierarchy process and fuzzy modeling techniques

This study performs a comparative evaluation of Frequency Ratio (FR), Analytic Hierarchy Process (AHP), and Fuzzy AHP (FAHP) modeling techniques for forest fire susceptibility mapping in Pauri Garhwal, Uttarakhand, India. Locations of past forest fire events reported from November 2002 to July 2019 were collected from the Uttarakhand Forest Department and Forest Survey of India and combined with the ground observations obtained from the manual survey. Then, the locations were categorized into two groups of 70% (10,500 locations) and 30% (4500 locations), randomly, for training and validation purposes, respectively. Forest fire susceptibility mapping was performed on the basis of fourteen different topographic, biological, human-induced and climatic criteria such as Digital Elevation Model, Slope, Aspect, Curvature, Normalized Difference Vegetation Index, Normalized Difference Moisture Index, Topographic Wetness Index, Soil, Distance to Settlement, Distance to Road, Distance to Drainage, Rainfall, Temperature, and Wind Speed. The Receiver Operating Characteristic curve and the Area Under the Curve (AUC) were implemented for validation of the three achieved Forest Fire Susceptibility Maps. The AUC plot evaluation revealed that FAHP has a maximum prediction accuracy of 83.47%, followed by AHP (81.75%) and FR (77.21%). Thus, the map produced by FAHP exhibits the most satisfactory properties. Results and findings of this study will help in developing more efficient fire management strategies in both the open and the protected forest areas (Rajaji and Jim Corbett National Park) of the district.

Forest fire susceptibility mapping via multi-criteria decision analysis techniques for Mugla, Turkey: A comparative analysis of VIKOR and TOPSIS

Turkey has a high forest fire potential along the Aegean and Mediterranean coasts, related to climate and extremely sensitive forests. In Turkey over 10,000-ha forest area has been destroyed every year and inevitable damage has been revealed. Forest fires not only destroy forest areas, but also cause damage to ecosystems, habitats and especially human lives. Because Muğla province has 90% of total pine honey production in the world and a high potential forest fire occurrence rate, sustainability of ecosystems, productivity and economic income require determining forest fire susceptibility zones. Generating forest fire susceptibility zones is a complex study which requires considering environmental, forestry, topographic, economic, and meteorological parameters within a decision support platform. At this point, Geographical Information System (GIS) aided Multi-Criteria Decision Analysis (MCDA) techniques can provide sufficient and effective solutions for fire susceptibility mapping due to the comparable and scalable structure of the criteria that are used to determine the susceptibility map when deciding. In this study, the weight of each criterion is calculated via the Analytical Hierarchy Process (AHP). Then, TOPSIS and VIKOR methods were used to generate forest fire susceptibility maps in Muğla province. The results indicated that 1659.44 ha (13%) and 3952.14 ha (31%) of the study area were assigned as highly prone to forest fire according to the TOPSIS and VIKOR calculations respectively, and an 81% correlation coefficient was calculated between methods. The reliabilities of the maps were verified with 1454 forest fire locations. Considering the respective 89.54%, 86.94% and 88.99% accuracy rate of VIKOR, TOPSIS and AHP susceptibility maps, all the methods could be used in forest fire susceptibility map generation which has comprehensive decision making process.

Forest fire susceptibility modeling using hybrid approaches

AbstractForest fires are considered one of the most highly damaging and devastating of natural disasters, causing considerable casualties and financial losses every year. Hence, it is important to produce susceptibility maps for the management of forest fires so as to reduce their harmful effects. The purpose of this study is to map the susceptibility to forest fires over Nowshahr County in Iran, using an integrated approach of index of entropy (IOE) with fuzzy membership value (FMV), frequency ratio (FR), and information value (IV) with a comparison of their precision. The spatial database incorporated the inventory of forest fire and conditioning factors. As a whole, 41 forest fire locations were identified. Out of these, 29 locations (≈70%) were randomly chosen for the forest fire susceptibility modeling (FFSM), and the remaining 12 locations (≈30%) were utilized for the validation of the models. Subsequently, utilizing FMV‐IOE, FR‐IOE, and IV‐IOE models, forest fire susceptibility maps were acquired. Finally, the modeling ability of the models for FFSM was assessed using an area under the receiver operating characteristic (AUROC) curve. The results manifested that the prediction accuracy of the FMV‐IOE model is slightly higher than that of the FR‐IOE and IV‐IOE models. The incorporation of IOE with FMV, FR, and IV models had AUROC values of 0.890, 0.887, and 0.878, respectively. The resulting FFSM can be effective in fire repression resource planning, sustainable development, and primary warning in regions with similar conditions.

Producing forest fire susceptibility map via multi-criteria decision analysis and frequency ratio methods

Located in the Mediterranean basin, one of the world’s leading places in terms of forest fires, Turkey is one of the countries where forest fires are experienced very often due to both natural and socio-economic conditions. The objective of this study is to conduct a forest fire susceptibility analysis within the boundaries of Karabuk Forestry Directorate. This analysis was conducted considering the factors affecting the forest fire risk (elevation, slope, aspect, distance to road lines, distance to settlement, land surface temperature and stand type). The factors used in the study were analyzed using geographic information systems (GIS) techniques and analytic hierarchy process method and frequency ratio method. The forest fire susceptibility map produced was classified in 5 categories including very low, low, moderate, high and very fire susceptibility. In order to see how much the forest fire susceptibility map produced corresponds to reality, the forest fire susceptibility maps and the forest fire inventory map were highly compared, and a 73.92% correspondence was detected according to the multi-criteria decision analysis method, while a 76.42% correspondence was detected in the frequency ratio method. As a result, it was concluded that high- and very high-sensitive areas were dominant in the study area, and the site had a high forest fire potential. Ultimately, this study indicated that GIS could be used as a tool to help make effective decisions during forest fire planning.

Ubiquitous GIS-Based Forest Fire Susceptibility Mapping Using Artificial Intelligence Methods

This study aimed to prepare forest fire susceptibility mapping (FFSM) using a ubiquitous GIS and an ensemble of adaptive neuro fuzzy interface system (ANFIS) with genetic (GA) and simulated annealing (SA) algorithms (ANFIS-GA-SA) and an ensemble of radial basis function (RBF) with an imperialist competitive algorithm (ICA) (RBF-ICA) model in Chaharmahal and Bakhtiari Province, Iran. The forest fire areas were determined using MODIS satellite imagery and a field survey. The modeling and validation of the models were performed with 70% (183 locations) and 30% (79 locations) of forest fire locations (262 locations), respectively. In order to prepare the FFSM, 10 criteria were then used, namely altitude, rainfall, slope angle, temperature, slope aspect, wind effect, distance to roads, land use, distance to settlements and soil type. After the FFSM was prepared, the maps were designed and implemented for web GIS and mobile application. A receiver operating characteristic (ROC)- area under the curve (AUC) index was used to validate the prepared maps. The ROC-AUC results showed an accuracy of 0.903 for the ANFIS-GA-SA model and an accuracy of 0.878 for the RBF-ICA model. The results of the spatial autocorrelation showed that the occurrence of fire in the study area has a cluster distribution and most of the spatial dependence is related to the distance to settlement, soil and rainfall variables.

Application of learning vector quantization and different machine learning techniques to assessing forest fire influence factors and spatial modelling

This study assesses forest-fire susceptibility (FFS) in Fars Province, Iran using three geographic information system (GIS)-based machine-learning algorithms: boosted regression tree (BRT), general linear model (GLM), and mixture discriminant analysis (MDA). Recently, BRT, GLM, and MDA have become important machine-learning algorithms and their use has been enriched by application to various fields of research. A database of historical FFs identified using Landsat-8 OLI and MODIS satellite images (at 358 locations) and ten influencing factors (elevation, slope, topographical wetness index, aspect, distance from urban areas, annual mean temperature, land use, distance from road, annual mean rainfall, and distance from river) were input into a GIS. The 358 sites were divided into two sets for training (70%) and validation (30%). BRT, GLM, and MDA models were used to analyze the spatial relationships between the factors influencing FFs and the locations of fires to generate an FFS map. The prediction success of each modelled FFS map was determined with the help of the ROC curve, accuracy, overall accuracy, True-skill statistic (TSS), F-measures, corrected classify instances (CCI), and K-fold cross-validation (4-fold). The accuracy results of training and validation dataset in the BRT (AUC = 88.90% and 88.2%) and MDA (AUC = 86.4% and 85.6%) models are more effective than the GLM (AUC = 86.6% and 82.5%) model. Also, the outcome of the 4-fold measure confirmed the results from the other accuracy measures. Therefore, the accuracies of the BRT and MDA models are satisfactory and are suitable for FFS mapping in Fars Province. Finally, the well-accepted neural network application of learning-vector quantization (LVQ) reveals that land use, annual mean rainfall, and slope angle were the most useful determinants of FFS. The resulting FFS maps can enhance the effectiveness of planning and management of forest resources and ecological balances in this province.

Assessing and mapping multi-hazard risk susceptibility using a machine learning technique

The aim of the current study was to suggest a multi-hazard probability assessment in Fars Province, Shiraz City, and its four strategic watersheds. At first, we construct maps depicting the most effective factors on floods (12 factors), forest fires (10 factors), and landslides (10 factors), and used the Boruta algorithm to prioritize the impact of each respective factor on the occurrence of each hazard. Subsequently, flood, landslides, and forest fire susceptibility maps prepared using a Random Forest (RF) model in the R statistical software. Results indicate that 42.83% of the study area are not susceptible to any hazards, while 2.67% of the area is at risk of all three hazards. The results of the multi-hazard map in Shiraz City indicate that 25% of Shiraz city is very susceptible to flooding, while 16% is very susceptible to landslide occurrences. For four strategic watersheds, it is notable that in the Dorodzan Watershed, landslides and floods are the most important hazards; whereas, flood occurrences cover the largest area of the Maharlou Watershed. In contrast, the Tashk-Bakhtegan Watershed is so sensible to floods and landslides, respectively. Finally, in the Ghareaghaj Watershed, forest fire ranks as the strongest hazard, followed by floods. The validation results indicate an AUC of 0.834, 0.939, and 0.943 for the flood, landslide, and forest fire susceptibility maps, respectively. Also, other accuracy measures including, specificity, sensitivity, TSS, CCI, and Gini coefficient confirmed results of the AUC values. These results allow us to forecast the spatial behavior of such multi-hazard events, and researchers and stakeholders alike can apply them to evaluate hazards under various mitigation scenarios.

Fuzzy-metaheuristic ensembles for spatial assessment of forest fire susceptibility

Forests are important dynamic systems which are widely affected by fire worldwide. Due to the complexity and non-linearity of the forest fire problem, employing hybrid evolutionary algorithms is a logical task to achieve a reliable approximation of this environmental threat. Three fuzzy-metaheuristic ensembles, based on adaptive neuro-fuzzy inference systems (ANFIS) incorporated with genetic algorithm (GA), particle swarm optimization (PSO), and differential evolution (DE) evolutionary algorithms are used to produce the forest fire susceptibility map (FFSM) of a fire-prone region in Iran. A sensitivity analysis is also executed to evaluate the effectiveness of the proposed ensembles in terms of time and complexity. The results revealed that all models produce FFSMs with acceptable accuracy. However, the superiority of the GA-ANFIS was shown in both recognizing the pattern (AUROCtrain = 0.912 and Error = 0.1277) and predicting unseen fire events (AUROCtest = 0.850 and Error = 0.1638). The optimized structures of the proposed GA-ANFIS and PSO-ANFIS ensembles could be good alternatives to traditional forest fire predictive models, and their FFSMs can be promisingly used for future planning and decision making in the proposed area.

FOREST FIRE SUSCEPTIBILITY MODELLING USING REMOTE SENSING DATA, GIS AND AHP ANALYSIS (CASE STUDY: SOUHAN, ALGERIA)

The ecosystem loses significant surfaces of forest every year because of wildfires, In Algeria, the majority of wildfires occurrences particularly during summertime, to the point of becoming a matter of national concern due the great losses of vegetal covers they cause every year. in this article we will focus on the municipality of Souhane, largely composed of forest areas and greatly affected by wildfires almost every year. The purpose of our study is to obtain forest fire susceptibility map in this municipality, and this, by combining a geographic information system and the AHP method, several studies have proven the effectiveness of this technique on large areas, in our study, we are willing to verify its usefulness at the scale of a small municipality and its surroundings, and this, to determine the susceptibility of the entire zone to wildfires, in order to do so, we selected six particular factors, calculating than their weights using the AHP method. The obtained results indicated that 49.5 % of the total surface of this municipality is included in both high and very high susceptibility zones, The wildfires that occurred during the year 2019 confirming the relevance of the results obtained, moreover, the calculation of the combustion index has shown that the areas most affected by the fire are those located once again, in the so-called areas of high and very high susceptibility.