Wildfire susceptibility mapping via machine learning: the case study of Liguria Region, Italy

2020 ◽  
Author(s):  
Paolo Fiorucci ◽  
Mirko D'Andrea ◽  
Andrea Trucchia ◽  
Marj Tonini
Keyword(s):  
Machine Learning ◽  
Natural Hazards ◽  
Predisposing Factors ◽  
Susceptibility Mapping ◽  
Burned Area ◽  
Susceptibility Map ◽  
Susceptibility Maps ◽  
Vegetation Heterogeneity ◽  
Wildfire Susceptibility

<p>Risk and susceptibility analyses for  natural hazards are of great importance for the sake of  civil protection, land use planning  and risk reduction programs. Susceptibility maps are based on the assumption that future events are expected to occur under similar conditions as the observed ones. Each unit area is assessed in term of relative spatial likelihood, evaluating the potential to experience a particular hazard in the future based solely on the intrinsic local characteristics. These concept is well-consolidated in the research area related with the risk assessment, especially for landslides. Nevertheless, the need exist for developing new quantitative and robust methods allowing to elaborate susceptibility  maps and to apply this tool to the study of other natural hazards.  In  the presented work, such  task is pursued for the specific  case of wildfires in Italy. The  two main approaches for such studies are the adoption  of physically based models and the data driven methods. In  the presented work, the latter  approach is  pursued, using  Machine Learning techniques in order to learn  from and make prediction  on the available information (i.e. the observed burned area and the predisposing factors) . Italy is severely affected by wildfires due to the high topographic and vegetation heterogeneity of its territory  and  to  its   meteorological conditions. The present study has as its main objective the  elaboration of a wildfire susceptibility map for Liguria region (Italy) by making use of Random Forest, an ensemble ML algorithm based on decision trees. The quantitative evaluation of susceptibility is carried out considering two different aspects: the location of past  wildfire occurrences, in terms of burned area, and the related anthropogenic and geo-environmental  predisposing factors that may favor fire spread. Different implementation of the model  were performed and compared. In  particular,  the effect of  a pixel's  neighboring land cover (including the type of vegetation and no-burnable area) on the output susceptibility map is investigated. In order to assess the  performance  of the model, the spatial-cross validation has been carried  out, trying  out different  number of folders. Susceptibility maps for the two fire seasons (the  summer  and  the winter  one) were finally computed  and validated. The  resulting  maps show  higher susceptibility zones , developing closer to the coast in summer and along the interior part of  the region in winter. Such zones matched well with the testing burned area, thus  proving the  overall  good performance of the proposed method.</p><p><strong>REFERENCE</strong></p><p> Tonini M., D’Andrea M., Biondi G., Degli Esposti S.; Fiorucci P., A machine learning based approach for wildfire susceptibility mapping. The case study of Liguria region in Italy. <em>Geosciences</em> (2020, submitted)</p><p><br><br></p>

scholarly journals A Machine Learning-Based Approach for Wildfire Susceptibility Mapping. The Case Study of the Liguria Region in Italy

Geosciences ◽  
2020 ◽  
Vol 10 (3) ◽  
pp. 105 ◽  
Author(s):  
Marj Tonini ◽  
Mirko D’Andrea ◽  
Guido Biondi ◽  
Silvia Degli Esposti ◽  
Andrea Trucchia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Expert Knowledge ◽  
Vegetation Type ◽  
Climatic Conditions ◽  
Predisposing Factors ◽  
Machine Learning Algorithms ◽  
Susceptibility Map ◽  
Susceptibility Maps ◽  
A Site ◽  
Wildfire Susceptibility

Wildfire susceptibility maps display the spatial probability of an area to burn in the future, based solely on the intrinsic local proprieties of a site. Current studies in this field often rely on statistical models, often improved by expert knowledge for data retrieving and processing. In the last few years, machine learning algorithms have proven to be successful in this domain, thanks to their capability of learning from data through the modeling of hidden relationships. In the present study, authors introduce an approach based on random forests, allowing elaborating a wildfire susceptibility map for the Liguria region in Italy. This region is highly affected by wildfires due to the dense and heterogeneous vegetation, with more than 70% of its surface covered by forests, and due to the favorable climatic conditions. Susceptibility was assessed by considering the dataset of the mapped fire perimeters, spanning a 21-year period (1997–2017) and different geo-environmental predisposing factors (i.e., land cover, vegetation type, road network, altitude, and derivatives). One main objective was to compare different models in order to evaluate the effect of: (i) including or excluding the neighboring vegetation type as additional predisposing factors and (ii) using an increasing number of folds in the spatial-cross validation procedure. Susceptibility maps for the two fire seasons were finally elaborated and validated. Results highlighted the capacity of the proposed approach to identify areas that could be affected by wildfires in the near future, as well as its goodness in assessing the efficiency of fire-fighting activities.

scholarly journals A Machine Learning based Approach for Wildfire Susceptibility Mapping. The Case Study of Liguria Region in Italy

2020 ◽  
Author(s):  
Marj Tonini ◽  
Mirko D'Andrea ◽  
Guido Biondi ◽  
Silvia Degli Esposti ◽  
Andrea Trucchia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cross Validation ◽  
Expert Knowledge ◽  
Meteorological Conditions ◽  
Susceptibility Map ◽  
Occurrence Probability ◽  
The Past ◽  
Susceptibility Maps ◽  
Wildfire Susceptibility

Wildfire susceptibility maps display the wildfires occurrence probability, ranked from low to high, under a given environmental context. Current studies in this field often rely on expert knowledge, including or not statistical models allowing to assess the cause-effect correlation. Machine learning (ML) algorithms can perform very well and be more generalizable thanks to their capability of learning from and make predictions on data. Italy is highly affected by wildfires due to the high heterogeneity of the territory and to the predisposing meteorological conditions. The main objective of the present study is to elaborate a wildfire susceptibility map for Liguria region (Italy) by applying Random Forest, an ensemble ML algorithm based on decision trees. Susceptibility was assessed by evaluating the probability for an area to burn in the future considering where wildfires occurred in the past and which are the geo-environmental factors that favor their spread. Different models were compared, including or not the neighboring vegetation and using an increasing number of folds for the spatial-cross validation. Susceptibility maps for the two fire seasons were finally elaborated and validated and results critically discussed highlighting the capacity of the proposed approach to identify the efficiency of fire fighting activities.

Wildfire susceptibility assessment: evaluation of the performance of different machine learning algorithms

2021 ◽  
Author(s):  
Andrea Trucchia ◽  
Sara Isnardi ◽  
Mirko D'Andrea ◽  
Guido Biondi ◽  
Paolo Fiorucci ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Assessment ◽  
Expert Knowledge ◽  
Susceptibility Mapping ◽  
Machine Learning Algorithms ◽  
Validation Dataset ◽  
Burned Area ◽  
Support Vector ◽  
Testing Dataset ◽  
Wildfire Susceptibility

<p><span>Wildfires constitute a complex environmental disaster triggered by several interacting natural and human factors that can affect the biodiversity, species composition and ecosystems, but also human lives, regional economies and environmental health. Therefore, wildfires have become the focus on forestry and ecological research and are receiving considerable attention in forest management. Current advances in automated learning and simulation methods, like machine learning (ML) algorithms, recently aroused great interest in wildfires risk assessment and mapping. This quantitative evaluation is carried out by taking into account two factors: the location and spatial extension of past wildfires events and the geo-environmental and anthropogenic predisposing factors that favored their ignition and spreading. When dealing with risk assessment and predictive mapping for natural phenomena, it is crucial to ascertain the reliability and validity of collected data, as well as the prediction capability of the obtained results. In a previous study (Tonini et al. 2020) authors applied Random Forest (RF) to elaborate wildfire susceptibility mapping for Liguria region (Italy). In the present study, we address to the following outstanding issues, which are still unsolved: (1) the vegetation map included a class labeled “burned area” that masked to true burned vegetation; (2) the implemented model based on RF gave good results, but it needs to be compared with other ML based approaches; (3) to test the predictive capabilities of the model, the last three years of observations were taken, but these are not fully representative of different wildfires regimes, characterizing non-consecutives years. Thus, by improving the analyses, the following results were finally achieved. 1) the class “burned areas” has been reclassified based on expert knowledge, and the type of vegetation correctly assigned. This allowed correctly estimating the relative importance of each vegetation class belonging to this variable. (2) Two additional ML based approach, namely Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM), were tested besides RF and the performance of each model was assessed, as well as the resulting variable ranking and the predicting outputs. This allowed comparing the three ML based approaches and evaluating the pros and cons of each one. (3) The training and testing dataset were selected by extracting the yearly-observations based on a clustering procedure, allowing accounting for the temporal variability of the burning seasons. As result, our models can perform on average better prediction in different situations, by taking into considering years experiencing more or less wildfires than usual. The three ML-based models (RF, SVM and MLP) were finally validated by means of two metrics: i) the Area Under the ROC Curve, selecting the validation dataset by using a 5-folds cross validation procedure; ii) the RMS errors, computed by evaluating the difference between the predicted probability outputs and the presence/absence of an observed event in the testing dataset. </span></p><p><strong><span>Bibliography: </span></strong></p><p><span>Tonini, M.; D’Andrea, M.; Biondi, G.; Degli Esposti, S.; Trucchia, A.; Fiorucci, P. A Machine Learning-Based Approach for Wildfire Susceptibility Mapping. The Case Study of the Liguria Region in Italy. </span><span><em>Geosciences</em></span><span> </span><span>2020</span><span>, </span><span><em>10</em></span><span>, 105.</span> <span>https://doi.org/10.3390/geosciences10030105</span></p>

scholarly journals A Novel Hybrid Method for Landslide Susceptibility Mapping-Based GeoDetector and Machine Learning Cluster: A Case of Xiaojin County, China

2021 ◽  
Vol 10 (2) ◽  
pp. 93
Author(s):  
Wei Xie ◽  
Xiaoshuang Li ◽  
Wenbin Jian ◽  
Yang Yang ◽  
Hongwei Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hybrid Method ◽  
Roc Curve ◽  
Landslide Susceptibility ◽  
Susceptibility Mapping ◽  
Assessment Model ◽  
Landslide Susceptibility Mapping ◽  
Support Vector ◽  
Susceptibility Map ◽  
Area Index

Landslide susceptibility mapping (LSM) could be an effective way to prevent landslide hazards and mitigate losses. The choice of conditional factors is crucial to the results of LSM, and the selection of models also plays an important role. In this study, a hybrid method including GeoDetector and machine learning cluster was developed to provide a new perspective on how to address these two issues. We defined redundant factors by quantitatively analyzing the single impact and interactive impact of the factors, which was analyzed by GeoDetector, the effect of this step was examined using mean absolute error (MAE). The machine learning cluster contains four models (artificial neural network (ANN), Bayesian network (BN), logistic regression (LR), and support vector machines (SVM)) and automatically selects the best one for generating LSM. The receiver operating characteristic (ROC) curve, prediction accuracy, and the seed cell area index (SCAI) methods were used to evaluate these methods. The results show that the SVM model had the best performance in the machine learning cluster with the area under the ROC curve of 0.928 and with an accuracy of 83.86%. Therefore, SVM was chosen as the assessment model to map the landslide susceptibility of the study area. The landslide susceptibility map demonstrated fit with landslide inventory, indicated the hybrid method is effective in screening landslide influences and assessing landslide susceptibility.

scholarly journals Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China

2020 ◽  
Vol 12 (2) ◽  
pp. 295 ◽  
Author(s):  
Ke Xiong ◽  
Basanta Raj Adhikari ◽  
Constantine A. Stamatopoulos ◽  
Yu Zhan ◽  
Shaolin Wu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Debris Flow ◽  
Sichuan Province ◽  
Susceptibility Mapping ◽  
Boosted Regression Trees ◽  
Support Vector ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Susceptibility Maps ◽  
Debris Flow Susceptibility

Debris flow susceptibility mapping is considered to be useful for hazard prevention and mitigation. As a frequent debris flow area, many hazardous events have occurred annually and caused a lot of damage in the Sichuan Province, China. Therefore, this study attempted to evaluate and compare the performance of four state-of-the-art machine-learning methods, namely Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), and Boosted Regression Trees (BRT), for debris flow susceptibility mapping in this region. Four models were constructed based on the debris flow inventory and a range of causal factors. A variety of datasets was obtained through the combined application of remote sensing (RS) and geographic information system (GIS). The mean altitude, altitude difference, aridity index, and groove gradient played the most important role in the assessment. The performance of these modes was evaluated using predictive accuracy (ACC) and the area under the receiver operating characteristic curve (AUC). The results of this study showed that all four models were capable of producing accurate and robust debris flow susceptibility maps (ACC and AUC values were well above 0.75 and 0.80 separately). With an excellent spatial prediction capability and strong robustness, the BRT model (ACC = 0.781, AUC = 0.852) outperformed other models and was the ideal choice. Our results also exhibited the importance of selecting suitable mapping units and optimal predictors. Furthermore, the debris flow susceptibility maps of the Sichuan Province were produced, which can provide helpful data for assessing and mitigating debris flow hazards.

scholarly journals EVALUATING THE VARIATIONS IN THE FLOOD SUSCEPTIBILITY MAPS ACCURACIES DUE TO THE ALTERATIONS IN THE TYPE AND EXTENT OF THE FLOOD INVENTORY

2017 ◽  
Vol XLII-4/W5 ◽  
pp. 209-214 ◽  
Author(s):  
M. Sh. Tehrany ◽  
S. Jones
Keyword(s):  
Area Under Curve ◽  
Natural Hazard ◽  
Susceptibility Map ◽  
Inventory Data ◽  
Flood Susceptibility ◽  
Susceptibility Maps ◽  
Rapid Processing ◽  
The Impact ◽  
Measurement Approach

This paper explores the influence of the extent and density of the inventory data on the final outcomes. This study aimed to examine the impact of different formats and extents of the flood inventory data on the final susceptibility map. An extreme 2011 Brisbane flood event was used as the case study. LR model was applied using polygon and point formats of the inventory data. Random points of 1000, 700, 500, 300, 100 and 50 were selected and susceptibility mapping was undertaken using each group of random points. To perform the modelling Logistic Regression (LR) method was selected as it is a very well-known algorithm in natural hazard modelling due to its easily understandable, rapid processing time and accurate measurement approach. The resultant maps were assessed visually and statistically using Area under Curve (AUC) method. The prediction rates measured for susceptibility maps produced by polygon, 1000, 700, 500, 300, 100 and 50 random points were 63 %, 76 %, 88 %, 80 %, 74 %, 71 % and 65 % respectively. Evidently, using the polygon format of the inventory data didn’t lead to the reasonable outcomes. In the case of random points, raising the number of points consequently increased the prediction rates, except for 1000 points. Hence, the minimum and maximum thresholds for the extent of the inventory must be set prior to the analysis. It is concluded that the extent and format of the inventory data are also two of the influential components in the precision of the modelling.

A comparative study on machine learning modeling for mass movement susceptibility mapping (a case study of Iran)

2020 ◽  
Vol 79 (10) ◽  
pp. 5291-5308
Author(s):  
Sayed Naeim Emami ◽  
Saleh Yousefi ◽  
Hamid Reza Pourghasemi ◽  
Shahla Tavangar ◽  
M. Santosh
Keyword(s):  
Machine Learning ◽  
Comparative Study ◽  
Mass Movement ◽  
Susceptibility Mapping
Sign in / Sign up

Export Citation Format

Share Document