Fuzzy–frequency ratio model for avalanche susceptibility mapping

Abstract

Avalanche activities in the Indian Himalaya cause the majority of fatalities and responsible for heavy damage to the property. Avalanche susceptibility maps assist decision-makers and planners to execute suitable measures to reduce the avalanche risk. In the present study, a probabilistic data-driven geospatial fuzzy-frequency ratio (fuzzy-FR) model is proposed and developed for avalanche susceptibility mapping, especially for the large undocumented region. The fuzzy-FR model for avalanche susceptibility mapping is initially developed and applied for Lahaul-Spiti region. The fuzzy-FR model utilized the six avalanche occurrence factors (i.e. slope, aspect, curvature, elevation, terrain roughness and vegetation cover) and one referent avalanche inventory map to generate the avalanche susceptibility map. Amongst 292 documented avalanche locations from the avalanche inventory map, 233 (80%) were used for training the model and remaining 59 (20%) were used for validation of the map. The avalanche susceptibility map is validated by calculating the area under the receiver operating characteristic curve (ROC-AUC) technique. For validation of the results using ROC-AUC technique, the success rate and prediction rate were calculated. The values of success rate and prediction rate were 94.07% and 91.76%, respectively. The validation of results using ROC-AUC indicated the fuzzy-FR model is appropriate for avalanche susceptibility mapping. ARTICLE HISTORY

Predicting susceptibility to landslides under climate change impacts in metropolitan areas of South Korea using machine learning

“…Study area Method used in study Tien Bui et al (2012) Hoa Binh province, Vietnam Adaptive Neuro-Fuzzy Inference System Zare et al (2013) Vaz Watershed, Iran Multilayer perceptron and radial basic function Pham et al (2016) Uttarakhand state, India. Naïve Bayes Trees, Support Vector Machines Kumar et al (2016) Indian Himalayas Fuzzy-frequency ratio Pham et al (2017) Indian Himalayas Multiple Perceptron Neural Networks Kornejady et al (2017) Golestan Province, Iran Maximum Entropy Chen et al (2017a) Langao County, China. Rotation forest ensembles, Naive Bayes Tree Hong et al (2017) Chongren area, China Frequency ratio, Certainty factor, Index of entropy Nsengiyumva et al (2018) Eastern Province, Rwanda Spatially different criteria evaluation methods Polykretis et al (2019) Mediterranean catchment, Greece Adaptive neuro-fuzzy modeling Pham and Prakash (2019) MuCang Chai, northern Vietnam Bagging-based Naïve Bayes Trees Dou et al (2020aDou et al ( , 2020b Northern parts of Kyushu, Japan Support vector machine hybrid ensembles Wang et al (2020) Sichuan Province, China Deep belief network (DBN)…”

“…As shown in Figure 2, nine factors were used in the study. The selected factors were the same as those used for analyzing the impact or sensitivity of landslides by other studies (Tien Bui et al 2012;Zare et al 2013;Kumar et al 2016;Pham et al 2016;Kornejady et al 2017;Nsengiyumva et al 2018;Polykretis et al 2019). Topographic (elevation, slope, aspect, curvature), geologic (lithology), environmental (road area ratio, forest area ratio), and meteorological (daily maximum precipitation) data pertaining to these variables were collected for analysis from National Geographic Information Institute, Korea Institute of Geoscience and Mineral Resources, Korean Meteorological Administration, and National Disaster Management Research Institute (Table 2).…”

“…Previous research has mostly focused on identifying the factors that cause landslides based on the conditions of the target site, collecting data on those factors, and analyzing vulnerability or sensitivity through statistical models, as shown in Table 1. A review of previous studies indicates that, while the target sites and methodologies differed, the contents of the studies were similar (Tien Bui et al 2012;Zare et al 2013;Kumar et al 2016;Pham et al 2016;Kornejady et al 2017;Chen et al 2017a;Hong et al 2017;Nsengiyumva et al 2018;Pham and Prakash 2019;Polykretis et al 2019;Wang et al 2020;Dou et al 2020a).…”

GIS-based evaluation of diagnostic areas in landslide susceptibility analysis of Bahluieț River Basin (Moldavian Plateau, NE Romania). Are Neolithic sites in danger?

“…During the last decade, at an international level, an increasing trend exists in applying statistical modelling in the field of geosciences to a wide range of natural disasters, such as flooding (Cao et al, 2016), rock falls (Shirzadi et al, 2017), fires (Hong et al, 2017), avalanches (Kumar et al, 2016); others are applied for the assessment of human-induced modifications to the landscape (Al-sharif and Pradhan, 2016), cultural heritage (Nicu 2016a), water resources management (Mousavi et al, 2017), waste management (Taboada-Gonzáles et al, 2014), and renewable energy (Ahmad and Tahar, 2014).…”

Automated snow avalanche release area delineation in data sparse, remote, and forested regions

“…Early versions of GIS based avalanche terrain models (Ghinoi and Chung, 2005;Gruber and Haefner, 1995;Maggioni and Gruber, 2003) struggled to outperform simple slope based avalanche release area estimates (Voellmy, 1955) due to the inability of low resolution DEM (20-30 m) to detect small scale terrain features. Current PRA modelling methods evolved over the course of a decade and benefit from developments in high-resolution DEM production and remote sensing (Andres and Chueca Cía, 2012;Barbolini et al, 2011;Bühler et al, 2013Chueca Cía et al, 2014;Pistocchi and Notarnicola, 2013;Veitinger et al, 2016;Kumar et al, 2016Kumar et al, , 2019. Bühler et al (2013) found that 5 m DEM resolution is the optimal tradeoff between processing efficiency and small-scale feature identification for PRA modelling.…”