A machine learning framework for multi-hazards modeling and mapping in a mountainous area

Abstract

this study sought to produce an accurate multi-hazard risk map for a mountainous region of iran. the study area is in southwestern iran. the region has experienced numerous extreme natural events in recent decades. This study models the probabilities of snow avalanches, landslides, wildfires, land subsidence, and floods using machine learning models that include support vector machine (SVM), boosted regression tree (BRT), and generalized linear model (GLM). Climatic, topographic, geological, social, and morphological factors were the main input variables used. the data were obtained from several sources. The accuracies of GLM, SVM, and functional discriminant analysis (FDA) models indicate that SVM is the most accurate for predicting landslides, land subsidence, and flood hazards in the study area. GLM is the best algorithm for wildfire mapping, and FDA is the most accurate model for predicting snow avalanche risk. The values of AUC (area under curve) for all five hazards using the best models are greater than 0.8, demonstrating that the model's predictive abilities are acceptable. A machine learning approach can prove to be very useful tool for hazard management and disaster mitigation, particularly for multi-hazard modeling. the predictive maps produce valuable baselines for risk management in the study area, providing evidence to manage future human interaction with hazards. Human interactions with natural extreme events, or hazards, are increasing globally 1. Natural disasters have affected people and natural environments generating vast economic losses around the world. However, in some developed counties disasters have been decreasing since 1900 2,3. Hazard is the probability of occurrence in a specified period and within a given area of a potentially damaging of a given magnitude 4,5. The definition incorporates the concepts of location (where?), time (when, or how frequently?) and magnitude (how large?). Total risk (R) means the expected number of lives lost, person injured, damage to property, or disruption of economic activity due to a particular natural phenomenon, and is therefore the product of specific risk (RS) and elements at risk (E) 6. In addition, RS is the expected degree of loss due to a natural phenomenon. Landscapes around the world are reflections of diverse natural processes. The probabilities of extreme natural events are typically greater in more natural areas and are, in fact, extensions of natural systems. Exposure of people to these extreme natural processes could be reduced and limited if predictive models based on new approaches and deeper knowledge of effective factors were employed 7. Mountainous areas are commonly sites of snow avalanches 8,9 , landslides 4,10 , floods 11,12 , mudflows 13 , ice avalanches 14 , soil erosion 15-17 , rock falls 18 , and wildfires 19-24. Most studies focus on a single hazard, even when there are multiple hazardous processes affecting the same landscapes 8,25-30. However, hazards sometimes interact with each other. Sometimes, the mitigation of one

Automated Landslide-Risk Prediction Using Web GIS and Machine Learning Models

“…QGIS have been employed for numerous landslide studies, for example in [ 47 , 48 , 49 ]. Other GIS software are ArcGIS [ 50 ] and SuperMap. However, ArcGIS and SuperMap are license software.…”

Mathematical Modeling of Landslide Slope Dynamics and Sustainable Development of Territories of Asian Russia

“…Spatial modeling of landslide hazards based on statistical analysis of the exposure factors used for solving multidimensional and nonlinear hazard prediction problems by building models based on decision trees is offered by Hosseinalizadeh et al (2019). We consider support vector machine model (SVM) (Yousefi et al 2015(Yousefi et al , 2020 together with the maximum entropy method (Boogar et al 2019) as high-quality machine learning algorithms used for mapping landslide-prone areas with a quite high level of prediction accuracy. Greco et al (2007), Yousefi et al (2020), andPourghasemi et al (2020) analyzed the capabilities of a generalized linear model of multiple regression (GLM) and logistic regression model (LR).…”

“…We consider support vector machine model (SVM) (Yousefi et al 2015(Yousefi et al , 2020 together with the maximum entropy method (Boogar et al 2019) as high-quality machine learning algorithms used for mapping landslide-prone areas with a quite high level of prediction accuracy. Greco et al (2007), Yousefi et al (2020), andPourghasemi et al (2020) analyzed the capabilities of a generalized linear model of multiple regression (GLM) and logistic regression model (LR). A model of boosted regression tree was developed by Yousefi et al (2020), while Pourghasemi and Rossi (2017) used multivariate adaptive regression splines (MARS).…”

“…Greco et al (2007), Yousefi et al (2020), andPourghasemi et al (2020) analyzed the capabilities of a generalized linear model of multiple regression (GLM) and logistic regression model (LR). A model of boosted regression tree was developed by Yousefi et al (2020), while Pourghasemi and Rossi (2017) used multivariate adaptive regression splines (MARS). To predict landslide hazards Yousefi et al (2020) and Huang et al (2018) also used the model of modified analytical hierarchy process (M-AHP), support vector machine model (SVM), frequency ratio model (FR) and the model of artificial neural network (Wang et al 2016); a model based on the algorithm of fuzzy logic theory was offered by Akgun et al (2012).…”

Mountain surface processes and regulation

“…Erosion did not increase with debris-flow magnitude due to a limit of debris-flow bulking set by channel geometry. Yousefi et al 23 developed a machine learning framework for multi-hazards modeling and presented a multi-hazard risk map for five natural hazards (floods, landslides, land subsidence, snow avalanches, and forest fires) in southwestern Iran.…”