Fire Susceptibility Mapping Research Articles

Wildland Fire Susceptibility Mapping Using Support Vector Regression and Adaptive Neuro-Fuzzy Inference System-Based Whale Optimization Algorithm and Simulated Annealing

Fires are one of the most destructive forces in natural ecosystems. This study aims to develop and compare four hybrid models using two well-known machine learning models, support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS), as well as two meta-heuristic models, the whale optimization algorithm (WOA) and simulated annealing (SA) to map wildland fires in Jerash Province, Jordan. For modeling, 109 fire locations were used along with 14 relevant factors, including elevation, slope, aspect, land use, normalized difference vegetation index (NDVI), rainfall, temperature, wind speed, solar radiation, soil texture, topographic wetness index (TWI), distance to drainage, and population density, as the variables affecting the fire occurrence. The area under the receiver operating characteristic (AUROC) was used to evaluate the accuracy of the models. The findings indicated that SVR-based hybrid models yielded a higher AUROC value (0.965 and 0.949) than the ANFIS-based hybrid models (0.904 and 0.894, respectively). Wildland fire susceptibility maps can play a major role in shaping firefighting tactics.

Fire-susceptibility mapping in the natural areas of Iran using new and ensemble data-mining models.

Fires have increased in northeastern Iran as its semi-arid climate landscape is desiccated by human activities. To combat fire outbreaks in any region, fire susceptibility must be mapped using accurate and efficient models. This research mapped fire susceptibility in the forests and rangelands of Golestan Province in northeastern Iran using new data-mining models. Fire effective factors, including elevation, slope angle, annual mean rainfall, annual mean temperature, wind effect, topographic wetness index (TWI), plan curvature, distance to river, distance to road, and distance to village were obtained from several sources. The relative importance of each variable was determined using a random-forest algorithm. Fire-susceptibility maps were produced in R 3.0.2software using GAM, MARS, SVM algorithms, and a new ensemble of the three models: GAM-MARS-SVM. The four fire-susceptibility maps were validated using the area under the curve. The results show that the distance tothe village, annual mean rainfall, and elevation were of greatest importance in predicting fire susceptibility. The new GAM-MARS-SVM ensemble model achieved the highest precision offire-susceptibility mapping. The fire-susceptibility map produced using the GAM-MARS-SVM ensemble model best detected the high fire risk areas in Golestan Province. The fire-susceptibility map produced by the ensemble model can be very useful for creating and enhancing management strategies for preventing fires, particularly in the higher-risk portions of Golestan Province.

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.

The temporal and spatial relationships between climatic parameters and fire occurrence in northeastern Iran

Fire is a natural disturbance in a wide range of ecosystem types around the world. Although the majority of fires are caused by anthropogenic ignitions, climate and weather are known to influence the risk of fire spread, regardless of ignition source. However, the specific relationships among these factors remain under-studied for many regions of the world. The objective of this study was to investigate the effect of climatic variables on forest and rangeland fire regimes in the Golestan Province of Iran in three recent decades. Specifically, we sought to determine: (a) the quantitative temporal relationships between climatic variables and fire occurrence; and (b) the spatial relationships between climatic variables and fire occurrence. To assess quantitative temporal relationships, we used correlation and regression analyses to identify and describe statistically significant relationships between climatic data (mean annual temperature, mean annual precipitation, mean annual relative humidity, and mean annual wind velocity) and fire data (number of fire and area burned), using climatic data from the Golestan Meteorological Administration and fire statistics from the Golestan Natural Resources Administration (GNRA). To determine the spatial relationships between climatic variables and fire occurrence, we combined geospatial data on climatic variables (mean annual temperature, mean annual rainfall, wind effect, and topographic wetness index (TWI)) obtained from ASTER-GDEM and active fires derived from MODIS fire products in a random forest (RF) model approach to construct a map of fire susceptibility at 30 m spatial resolution. Our results showed that there was a significant temporal relationship between the number of fires and mean annual temperature, mean annual relative humidity, and mean annual wind velocity. There were also significant temporal relationships between area burned and mean annual relative humidity and mean annual wind velocity. Based on the RF model, the mean annual rainfall had the highest relative importance in fire spatial occurrence. Validation of the fire susceptibility map using area under the curve (AUC) indicated that the RF model created an accurate fire susceptibility map (AUC: 0.823), suggesting that the map can be used as a spatio-temporal climatic alarm system for fire occurrence in the different climatic conditions of the Golestan Province. The results from this study will be important for helping perform climate-change analyses for investigating future temporal and spatial patterns of wildfire in the Golestan Province.

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.

A novel optimized repeatedly random undersampling for selecting negative samples: A case study in an SVM-based forest fire susceptibility assessment

The negative sample selection method is a key issue in studies of using machine learning approaches to spatially assess natural hazards. Recently, a Repeatedly Random Undersampling (RRU) was proposed to address the randomness problem faced in Single Random Sampling. However, the RRU cannot guarantee that the generated classifier has the best classification performance during the repeatedly random sampling process. To address this weakness, in this study we proposed an optimized RRU, which follows the idea of RRU, and then changing its rule to find a best classifier. Then, the selected classifier, the actual most accurate classifier (MAC), was employed to compute the probability of hazard occurrence. Support Vector Machine (SVM) was selected as the analysis method, and Genetic Algorithm was employed to compute the parameters of SVM. Forest fire susceptibility was assessed in Huichang County in China due to its forest values and frequent fire events. The results indicated that compared with the RRU, the optimized RRU can find out an actual MAC which has the best classification performance among possible MACs; also, the fire susceptibility map generated by the actual MAC comforts to objective facts. The generated fire susceptibility map can provide useful decision supports for local government to reduce forest fire risks. Moreover, the proposed sampling method, the optimized RRU, presented an enhanced approach for selecting negative samples, which makes the results of forest fire susceptibility assessment more reliable and accurate.

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.

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.

Evaluating the effects of forest fire on water balance using fire susceptibility maps

Abstract Sudden and long term changes in the landscape can be attributed to periodic wildfires which, is a cyclic occurrence at Kudremukh national forest in Western Ghats of India. These land-use changes influence the hydrology of landscape, causing disintegration of soil, loss of biodiversity, changes in stream and flooding. To understand and account for these land-use changes, a new approach was implemented by developing fire susceptibility map from topographic, climatic and human-induced factors and validating it with MODIS (Moderate-resolution Imaging Spectro-radiometer) fire points for discretising accuracy. The fire susceptibility map can be used for studying the long-term (year or more) effects of fire on water balance systems. The fire susceptibility map generated for the years 2005 and 2017 was overlaid with MODIS LULC (Land Use Land Cover) for establishing the post-fire scenario whereas MODIS LULC MCD12Q1 (2005 and 2017) was considered as the no-fire scenario to analyse the intensity of the fire and its effect on streamflow and infiltration. These maps along with historical satellite hydro-climatic datasets, were used to assess the effect of forest fire on hydrological parameters using the SWAT (Soil and Water Assessment Tool) model. No-fire and post-fire conditions were established by modifying SCS-CN (Soil Conservation Service-Curve Number) based on previous works of literature to represent the catchment as unburnt and burnt area. The SWAT model was calibrated (2002–2008) and validated (2009–2012) for establishing a baseline scenario. The sensitive parameters obtained from SUFI-2 (Sequential Uncertainty Fitting) algorithm in SWAT-CUP (Calibration and Uncertainty Programs) were used to simulate stream flows till 2017 due to lack of observed streamflow data for the year 2017. It was inferred that the effect of wildfire on flows in recent years (2017) had increased radically when compared to the flows before a decade (2005), diminishing the rate of infiltration and causing the deficit in groundwater to energise. The methodology can further be executed in any forest area for distinguishing fire hazard zones and implementing prior actions in those areas for mitigation of forest fires and maintaining sustainable water balance.

Forest Fire Susceptibility and Risk Mapping Using Social/Infrastructural Vulnerability and Environmental Variables

Forests fires in northern Iran have always been common, but the number of forest fires has been growing over the last decade. It is believed, but not proven, that this growth can be attributed to the increasing temperatures and droughts. In general, the vulnerability to forest fire depends on infrastructural and social factors whereby the latter determine where and to what extent people and their properties are affected. In this paper, a forest fire susceptibility index and a social/infrastructural vulnerability index were developed using a machine learning (ML) method and a geographic information system multi-criteria decision making (GIS-MCDM), respectively. First, a forest fire inventory database was created from an extensive field survey and the moderate resolution imaging spectroradiometer (MODIS) thermal anomalies product for 2012 to 2017. A forest fire susceptibility map was generated using 16 environmental variables and a k-fold cross-validation (CV) approach. The infrastructural vulnerability index was derived with emphasis on different types of construction and land use, such as residential, industrial, and recreation areas. This dataset also incorporated social vulnerability indicators, e.g., population, age, gender, and family information. Then, GIS-MCDM was used to assess risk areas considering the forest fire susceptibility and the social/infrastructural vulnerability maps. As a result, most high fire susceptibility areas exhibit minor social/infrastructural vulnerability. The resulting forest fire risk map reveals that 729.61 ha, which is almost 1.14% of the study areas, is categorized in the high forest fire risk class. The methodology is transferable to other regions by localisation of the input data and the social indicators and contributes to forest fire mitigation and prevention planning.

Testing a New Ensemble Model Based on SVM and Random Forest in Forest Fire Susceptibility Assessment and Its Mapping in Serbia’s Tara National Park

The main objectives of this paper are to demonstrate the results of an ensemble learning method based on prediction results of support vector machine and random forest methods using Bayesian average. In this study, we generated susceptibility maps of forest fire using supervised machine learning method (support vector machine—SVM) and its comparison with a versatile machine learning algorithm (random forest—RF) and their ensembles. In order to achieve this, first of all, a forest fire inventory map was constructed using Serbian historical forest fire database, Moderate Resolution Imaging Spectro radiometer (MODIS), Landsat 8 OLI and Worldview-2 satellite images, field surveys, and interpretation of aerial photo images. A total of 126 forest fire locations were identified and randomly divided by a random selection algorithm into two groups, including training (70%) and validation data sets (30%). Forest fire susceptibility maps were prepared using SVM, RF, and their ensemble models using the training dataset and 14 selected different conditioning factors. Finally, to explore the performance of the mentioned models we used the values for area under the curve (AUC) of receiver operating characteristics (ROC). The results depicted that the ensemble model had an AUC = 0.848, followed by the SVM model (AUC = 0.844), and RF model (AUC = 0.834). According to achieved AUC results, it can be deduced that SVM, RF, and their ensemble method had satisfactory performance. The study was applied in the Tara National Park (West Serbia), a region of about 191.7 sq. km distinguished by a very high forest density and a large number of forest fires.

Metaheuristic algorithms in optimizing neural network: a comparative study for forest fire susceptibility mapping in Dak Nong, Vietnam

Meta-heuristic algorithms become common approaches in finding sufficiently good solutions for optimization problems. This study proposed and compared three novel hybrid methods, namely Biogeography-based Optimization (BBO), Gravitational Search Algorithm (GSA) and Grey Wolf Optimization (GWO) in combination with the popular Neural Network classifier for forest fire modeling. Dak Nong province was selected as a case study as it had undergone a critical drought season. One thousand three hundred and thirty-eight historic fired locations during the first several months of 2017 were chosen as dependent variables. On the other hand, topological, climatic and socio-economic data were used as independent predictor variables. For accuracy assessment, root mean square error derivable from the neural network was used as an objective function to be optimized by three proposed algorithms. The results showed that the area under Receiver Operating Characteristic curves (AUC) were in BBO (0.9515), GWO (0.9509), (0.9398) outperformed the Regular neural with backpropagation algorithm (AUC = 0.9271). Even though the differences between prediction results were small, but they were significant by using a paired t-test. It could be concluded that three hybrid models are suitable to map forest fire susceptibility in the selected study area and could be considered as alternative methods for studying forest fire in other locations.

A novel ensemble modeling approach for the spatial prediction of tropical forest fire susceptibility using LogitBoost machine learning classifier and multi-source geospatial data

A reliable forest fire susceptibility map is a necessity for disaster management and a primary reference source in land use planning. We set out to evaluate the use of the LogitBoost ensemble-based decision tree (LEDT) machine learning method for forest fire susceptibility mapping through a comparative case study at the Lao Cai region of Vietnam. A thorough literature search would indicate the method has not previously been applied to forest fires. Support vector machine (SVM), random forest (RF), and Kernel logistic regression (KLR) were used as benchmarks in the comparative evaluation. A fire inventory database for the study area was constructed based on data of previous forest fire occurrences, and related conditioning factors were generated from a number of sources. Thereafter, forest fire probability indices were computed through each of the four modeling techniques, and performances were compared using the area under the curve (AUC), Kappa index, overall accuracy, specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV). The LEDT model produced the best performance, both on the training and on validation datasets, demonstrating a 92% prediction capability. Its overall superiority over the benchmarking models suggests that it has the potential to be used as an efficient new tool for forest fire susceptibility mapping. Fire prevention is a critical concern for local forestry authorities in tropical Lao Cai region, and based on the evidence of our study, the method has a potential application in forestry conservation management.

GIS-based evolutionary optimized Gradient Boosted Decision Trees for forest fire susceptibility mapping

Rampant pasture burning has lead to various forest fires taking their toll over the health of many forests. Nanda Devi Biosphere Reserve, located in the northern part of India, witnessed a majority of these incidents in the recent past, though, it remains comprehensively untouched from research studies. The scale of these wildfires has led to an immense requirement of preventive measures to be taken for recuperating from such events. This requires for an in-depth analysis of the study area, its history of wildfires and their causes. These efforts would assist in laying a blueprint for a contingency plan in the event of a wildfire. This work proposes an evolutionary optimized gradient boosted decision trees for preparing wildfire susceptibility maps for the study area that would aid in the government’s forest preservation and disaster management activities. The study took 18 ignition factors of elevation, slope, aspect, plan curvature, topographic position index, topographic water index, normalized difference vegetation index, soil texture, temperature, rainfall, aridity index, potential evapotranspiration, relative humidity, wind speed, land cover and distance from roads, rivers and habitations into consideration. The study revealed that approximately 1432.025 km2 of area was very highly susceptible to forest fires while 1202.356 km2 was highly susceptible to forest fires. The proposed model was compared against various machine learning models such as random forest, neural networks and support vector machines, and it outperformed them by achieving an overall accuracy of 95.5%. The proposed model demonstrated good prospects for application in the field of hazard susceptibility mappings.

Applying genetic algorithms to set the optimal combination of forest fire related variables and model forest fire susceptibility based on data mining models. The case of Dayu County, China

The main objective of the present study was to utilize Genetic Algorithms (GA) in order to obtain the optimal combination of forest fire related variables and apply data mining methods for constructing a forest fire susceptibility map. In the proposed approach, a Random Forest (RF) and a Support Vector Machine (SVM) was used to produce a forest fire susceptibility map for the Dayu County which is located in southwest of Jiangxi Province, China.For this purpose, historic forest fires and thirteen forest fire related variables were analyzed, namely: elevation, slope angle, aspect, curvature, land use, soil cover, heat load index, normalized difference vegetation index, mean annual temperature, mean annual wind speed, mean annual rainfall, distance to river network and distance to road network. The Natural Break and the Certainty Factor method were used to classify and weight the thirteen variables, while a multicollinearity analysis was performed to determine the correlation among the variables and decide about their usability. The optimal set of variables, determined by the GA limited the number of variables into eight excluding from the analysis, aspect, land use, heat load index, distance to river network and mean annual rainfall.The performance of the forest fire models was evaluated by using the area under the Receiver Operating Characteristic curve (ROC-AUC) based on the validation dataset. Overall, the RF models gave higher AUC values. Also the results showed that the proposed optimized models outperform the original models. Specifically, the optimized RF model gave the best results (0.8495), followed by the original RF (0.8169), while the optimized SVM gave lower values (0.7456) than the RF, however higher than the original SVM (0.7148) model. The study highlights the significance of feature selection techniques in forest fire susceptibility, whereas data mining methods could be considered as a valid approach for forest fire susceptibility modeling.