key: cord-0066738-hp15l07p
authors: Beheshti, Ziba; Gharagozlou, Alireza; Monavari, Masoud; Zarkesh, Mirmasoud Kheirkhah
title: Landslides behavior spatial modeling by using evidential belief function model, Promethean II model, and index of entropy in Tabriz, Iran
date: 2021-08-17
journal: Arab J Geosci
DOI: 10.1007/s12517-021-08172-2
sha: 201745ee57f1cf57b911ca18e02ac77805ce2b51
doc_id: 66738
cord_uid: hp15l07p

Due to the increasing construction of clay and marl hills in most areas of Tabriz (Iran), its characteristics in terms of resistance, and its tendency to liquefy during earthquakes, this city is at risk of landslides. This paper studies the landslide vulnerability of Tabriz using visual and statistical evidence. The evaluation of landslide susceptibility was performed using the evidential belief function model (EBF) and the index of entropy. The environmental impact assessment of landslides was carried out using the Promethean II model in three environmental, economic, and social phases. Finally, a landslide strategy plan for decision-makers was developed. The results of the analysis using the EBF model showed that 89.81% of the total area of Tabriz is located in a direct landslide vulnerability zone. The output of the receiver operating characteristics (ROC) curve showed 83.3% accuracy of the EBF model. The impact assessment showed that for the environment, the geological criterion had an output weight of 0.396; for the economy, the road criterion had a weight of 0.477; and for the society, the commercial criterion had a weight of a 0.452; all were the most affected by landslides. The results of monitoring studies of the largest landslides in Tabriz in 1957, 1984, and 2020 showed approximately 41.65 m of land sliding over a period of 63 years. To our knowledge, this study is the first in the world to predict the environmental impact assessment and provide a strategy plan for Tabriz.

Landslides in the form of mass movements pose threats to human safety and security, the environment, and the economy (Pandey et al. 2021; Nsengiyumva et al. 2018 ). According to the Construction Ministry of Jihad in Iran, 15,000 landslides have occurred in Iran since 2006. The earthquakes of 1721 and 1780 were the worst natural disasters in the North Tabriz Fault: the first killed 100,000 people in the northeastern of Tabriz, and the second killed a total of 200,000 people in Tabriz and Turkey. Considering the occurrence of numerous historical earthquakes and the resulting complete destruction of Tabriz 12 times, the North Tabriz Fault has been propounded as one of the well-known seismic faults of Tabriz (Ahadnezhad Reveshty et al. 2014) . Landslide disaster risk reduction is an important common goal in all countries/regions where people living in mountains and slopes are prone to landslides (Akawwi et al. 2018; Vilímek et al. 2020) . Landslide susceptibility can be generally defined as the probability of landslide occurring in Responsible Editor: Biswajeet Pradhan areas under the coupling action of a series of geological environmental factors and human activities (Chen et al. 2019a) . The assessment of landslides in the world suggests that most developing countries are at greater risk of landslides (Pradhan and Siddique 2020; Sah et al. 2018) . Assessing the risk of landslide occurrence can help predict the probability and return period of landslide in an area (He et al. 2019; Mateos et al. 2020) . The consequence of landslides becomes more hazardous if they occur along or near townships (Puente-Sotomayor et al. 2021) . This phenomenon has attracted the attention of the global scientific community, leading to the publication of a large number of studies examining landslide risk assessment (Dikshit et al. 2020; Sassa 2019; Bičer and Ercanoglu 2020) . All of the above studies concluded that for a landslide risk assessment, it is essential to have access to recorded information and results of previous research studies. However, in Tabriz, despite previous landslides incidents and damage to infrastructure and housing "especially in highly developing areas of the city without respecting the laws and regulations of urban planning and geology," there is no reliable scientific research to determine vulnerability to future events. The lack of information regarding the potential damage caused by a severe landslide hazard in Tabriz, being a large metropolis with a particular economic and international situation in Iran, requires an in-depth scientific study and elimination of the research gap in the assessment of landslide in this city. In the event of a landslide, areas that comply with the principles and regulation of urban planning and geology will not significantly be impacted (Skilodimou et al. 2019; Shaaban et al. 2021) . The assessment of the environmental effects of landslides showed an inverse relationship between the severity of landslides and the extent of urban infrastructure (Fahad et al. 2019 ) and the level of noncompliance to urban development regulations (Usman et al. 2020 ). This study focuses on the vulnerability of areas with low living standards (Ayala 2019) in Tabriz. Reducing landslide losses requires an appropriate method to identify the prone area, causal factors, and likelihood of future occurrence (Li et al. 2020; Confuorto et al. 2019) . Landslide susceptibility mapping (LSM) has proven to be an effective module for detecting and predicting landslide-susceptible areas (Nhu et al. 2020; Park et al. 2018; Feizizadeh et al. 2014) . Various machine-learning methods have been used for geotechnical applications such as landslide susceptibility mapping, groundwater spring potential mapping, and other environmental applications (Schäfer and Wenzel 2019; Zhao and Chen 2020Selecting an appropriate mapping unit is an important step for landslide susceptibility evaluation. Statistical models, such as evidential belief function (EBF), have been widely used for generating landslide susceptibility maps (Feby et al. 2020 ). The EBF model is best suited for integration in different environmental and socioeconomic scenarios enhancing the models for urban allocation tasks (Arasteh et al. 2019; Pradhan et al. 2014; Bui et al. 2016) . Successful use of the model by other researchers suggests that the EBF model is suitable for data analysis with GIS (Deng et al. 2017) . Recent advances in remote sensing (RS) and geographic information system (GIS) technology have dramatically improved the efficiency of the LSM module and the reliability of its results (Tavakkoli Piralilou et al. 2019) . In this study, due to the investigation of various urban components such as economic, social, and environmental components, the EBF model was used as a dual model for sociospatial measurement between landslides and conditional factors. The receiver operating characteristic (ROC) is a graphical plot that calculates the area under the ROC curve (AUC) (Thi Ngo et al. 2021 ); the focus is on the positive rate (Murillo et al. 2019 ). The second model is the entropy of index (IOE), which is based on the bivariate analysis principle (Shirani et al. 2018) . The Preference Ranking Organization Method for Enrichment of Evaluations (PROMETHEE) method has been used by many researchers, for the location of wind farms (Amarasinghe and Perera 2020 the evaluation of tourist attraction (Tian et al. 2020) , sustainable composing technology (Makan and Fadili 2020) , the socioeconomic vulnerability of urban (Contreras et al. 2020) . The concept of social vulnerability (SV) to environmental hazards that involves demographic and socioeconomic factors that affect community The consequences of such rapid developments, regardless of regional potential, will be significant environmental destructions and heavy financial losses for residents and urban settlements. Two examples of these consequences include first, the landslides in the Valiasr Town residential complexes in Tabriz during 1993-1994 (the slip site remains so far) and second, the landslides and destructions of the Northern Highway of Tabriz and its reconstruction costs.

This study aims to identify the slippery and vulnerable areas of Tabriz, where the consequences of growing lowcost illegal construction must be taken into consideration.

This study also examines the impact of landslide scale on the city's underground infrastructure. The innovative aspect of this paper is that it evaluates the impact of landslide category in an urban environment applying the environmental impact assessment (EIA) tool and including parameters such as landslide sensitivity mapping, landslide impacts assessment, and mitigation, and monitoring.

This research was conducted in the geographical area of Tabriz (Iran). Tabriz is a city situated at north latitude 30°12′ and east longitude 46°16′. Tabriz lies on the eastern point of the Tabriz plain and the intersection of two rough ranges in the north and south of the city; its area is 70388 km 2 . Geologically, Tabriz is located in an area with various combinations of formations that show intense tectonic activity (Fig. 1) . The most significant landslide in Tabriz occurred in 1956 due to a strong and deadly earthquake with a magnitude of 7.2; in fact, it was the largest and also the most dangerous landslide in Tabriz (Table 1) . This paper presents an application development study conducted through diverse methods, including literature review, field observations, modeling, aerial photography, and satellite photo interpretation. First, the potential and susceptible landslide locations were identified using satellite images by completing extensive field observations and data recorded by GPS to match the existing landslides accurately. ArcGIS 10 software was used to analyze the data and prepare the maps. A total of 29 landslides were identified ( Fig. 2; Tables 2 and 3 ). The landslide data set was randomly divided into two parts so that 70% of cases were used for assessment, and 30% were kept for validating Fig. 6 Areas requiring park and green spaces (a) (areas 3, 4, and 6; dense commercial areas of the city and busy areas) are the areas that encounter a lack of green spaces; meanwhile, Tabriz suffers from a total shortage of 430 ha in terms of green spaces. Accessibility to open and green spaces of the city in Tabriz (b). The lack of green space per capita in Tabriz leads to increased severity of vulnerability to landslides and similar accidents. The more people have access to the city's open and green spaces, the less causality will result in the hours after the landslide the landslide susceptibility map. In the next step, considering the conditions of the study area, eleven factors determining the occurrence of landslides were analyzed in the GIS environment including the slope degree, slope direction, height above mean sea level, distance from the fault, distance from main rivers, distance from minor rivers, distance from oil pipelines, distance from natural gas networks, erosions, soil type, and lithology. It is noteworthy that the study area was local in scale and had homogeneous conditions in terms of climatic variables; therefore, the rainfall criterion was removed (Table 4 ).

The base of the EBF model used in this study is mainly the Dempster-Shafer theory of evidence algorithms (Dempster 2008; Shafer 1976 ). The Dempster-Safer theory is a generalization of the Bayesian subjective probability theory, which relates to the effect of confidence index on the probability of related problems. The main advantage of the EBF model is its flexibility which is the result of accepting uncertainty and incorporating many sources of belief (Bui et al. 2012) . For this reason, it has already been applied in the construction of landslide susceptibility maps. The EBF model consists of the following four main mathematical functions: Bel (degree of belief), Dis (degree of disbelief), Unc (degree of uncertainty), and Pls (degree of plausibility) (Tables 5 and 6 ). The values of these functions range from 0 to 1. Multilayer integration of Bel, Dis, Unc, and Pls is expressed as follows:

Disx

Uncx

where β = 1 − belx 1 disx 2 − disx 1 belx 2 is a normal factor to ensure BEL + UNC + DIS=10.

The second model used for landslide susceptibility analysis in the current study is the index of entropy model. The model indicates the extent of the instability, disorder, imbalance, and uncertainty of a system (Youssef et al. 2015 ) ( Table 7) . The entropy of a landslide refers to the extent to which various factors influence the development of a landslide. Several important factors provide additional entropy in the index system. Thus, the entropy can be used to calculate the objective weights of the index system. The equations used to calculate the information coefficient Wj, which represents the weight value for the parameter as a whole, are as follows:

Pij

The Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) method is a subgroup of the multiple-criteria decision-making (MCDM) method developed in the early 1980s by Brans et al. (Zhou et al. 2018 ). The PROMETHEE technique is an outranking approach for a finite set of alternative actions to be ranked and selected among often contradictory criteria. Due to its flexibility and ease of use, it can be used in various fields. The use of the PROMETHEE method can reinforce the confidence and reliability of decision-makers (Fig. 3) .

To study the geology of Tabriz, a regional geological map at a scale of 1:5000 of lithology was analyzed microscopically using 30 thin sections of existing rock in the region. Regarding the age and structure of the fault and folds of the rocky units of the area, Tabriz geology map at a scale of 1:25000 was used as a reference. In this study, landslide sensitivity in Tabriz city was assessed using EBF and entropy models ( Fig. 4 ; Table 8 ). The EBF model can be used to summarize the spatial correlation between landslide occurrence and landslide conditioning factor. When the Bel value is zero, the expected landslide risk is also zero. 

Analyzing the economic outcome of landslides in roads, residential areas, high-pressure lines, and oil lines using Fig. 8 Accessibility to urban facilities in Tabriz. Nearly 85 ha of the regions of Tabriz suffer from deprivation of accessibility to urban facilities the economic impact criteria showed that the road option with a weight of 0.477 had the most damage due to the landslides (A 1 > A 2 > A 3 > A 4 ). The evaluation of the social outcome of landslides in population, commercial-recreational areas, and health (A 2 > A 1 > A 3 ) showed that the commercial/recreational areas had the most damage due to landslides with a weight of 0.452 (Fig. 5) . Losses from landslides can be significantly reduced through cooperation between geologists, engineers, and planners, which may reduce the scale of mitigation measures to be taken; therefore, a statistical and detailed study of the quantity and quality of infrastructure in vulnerable physical structures is necessary for dealing with the severity of the effects after a landslide in Tabriz.

Mitigation is the final stage of the risk management process (Ferlisi et al. 2019) . One of the mitigation methods is to compensate for the shortcomings. The main infrastructure and parameters of Tabriz which played a significant role in offsetting the effects of a landslide were studied as follows.

Significant parts of the urban spaces in the northwest, southeast, and western parts of Tabriz have been allocated to green spaces and urban open spaces. However, the urban and outdoor spaces in the central part of the city are limited ( Fig. 6 ; Table 9 ). The more accessible open spaces are in a city, the less damage there will be in natural disasters such as landslides.

Improving the quantity and quality of medical centers leads to rapid relief of the injured. In the current global Covid-19 pandemic, if any natural disasters occur in Tabriz, medical centers should be able to provide services to the injured people. Tabriz is currently facing a shortage of 142.6 ha of health facilities ( Fig. 7; Table 10 ).

Infrastructure networks are vital for citizens' and urban life; the absence or vulnerability of these networks affects the lives of citizens. The facilities of Tabriz that have been less studied include water reservoirs, municipal electricity facilities, telecommunication center, gas facilities, emergency facilities, and fire brigade. There are more than 85 ha of shortages of mentioned facilities in Tabriz ( Fig. 8; Table 11 ).

The traffic network per capita in Tabriz is 29.3m 2 , which seems adequate. However, some surveys show a very uneven distribution of the transport network, with 4.9% of the urban population uses 12.5% of the city's urban roads. In comparison, 32.0% of the population living in the suburbs uses 17.08% of the city streets; also in these areas, the building density is very high, which greatly increases the vulnerability (Fig. 9 ). If Tabriz's per capita traffic network does not increase, in the event of a landslide, the increase in population will prevent the rescue team from providing timely assistance.

In terms of quality and condition, the structures of the city's vital infrastructure are classified into three types: usable, restored, and destroyed. This research showed that among all important institutions and service centers, the educational centers had the highest frequency in Tabriz and then the administrative, medical, military, and transit system terminals, respectively. Of the identified institutions and centers, 78.7% are in good condition and usable, 20.7% are restored, and 0.6% are destroyed (Fig. 10) .

Remediation and early warning strategies are generally focused on continuous monitoring of the slope displacements, which can provide crucial information on the dynamics and (Whiteley et al. 2019) . The morphometric monitoring and evaluation of the largest landslides in Tabriz were carried out using RS and GIS at three periods of time, including 1957, 1984, and 2020 . The relevant data of aerial photographs of 1957 and 1984 with a scale of 1:5000 (soil and water studies of Iran) and a satellite image of Google Fig. 9 The degree of impermeability in Tabriz (a); as shown in the map, the highest impermeability was observed in areas where the greatest risk for landslides occurrence was previously predicted; high-risk areas mentioned include 1 and 10 and at low levels 3, 6, and 7. Construction density of Tabriz (b); residential parts less than 100 m are the most vulnerable to natural disasters (earthquakes, landslides, floods, etc.) Fig. 10 Vital and important centers need reconstruction and reinforcement in Tabriz (a); to mitigate landslide impact, it is necessary to reinforce more than 70% of the important and vital centers in Tabriz. Damage ratios of the major centers of the city (b); red spots: some areas such as military, Bazar, and fire station that need to be rehabilitated. The blue dots represent some of the most important and vital new centers, including some training, administrative, military, and fire stations. The yellow dots represent a military site and training site which are in the range of destructive. According to civil engineering and urban planning, new buildings were 10 to 30% more vulnerable to accidents such as landslides. Buildings that required retrofitting had a vulnerability of about 30 to 70% and buildings that were very old and demolished had a vulnerability of about 70 to 100% to a landslide occurrence. Area requiring police and security centers (c), law enforcement, and security forces play a key role in controlling the psychological and social impacts of natural disasters such as landslides, preparing them to deal with their destructive effects Earth in 2020 with a scale of 1:4000 were entered into the GIS software. The average annual slip movement in a 27-year period (1957 to 1984) was 53.29 cm per year, and in the 36year period (1984 to 2020), it was 75.72 cm per year. The increase in human activity in landslide-sensitive areas has led to the ascending increases in landslides between 1984 and 2020; over time, landslide areas have become more unstable. The results showed that the average speed of Tabriz landslides during 63 years is 41.65 m ( Fig. 11 ; Table 12 ).

This study showed that the EBF model is well able to detect landslides in urban areas; this deduction is consistent with the results of a credible study. The results of the landslide sensitivity assessment using the EBF model showed that 82.9% of the Tabriz area is at risk of landslide vulnerability. The output of the ROC curve showed 89.81% accuracy of the EBF model. This study showed that landslides occur at certain altitudes (Chen et al. 2019b) . Areas above 1,700 m from sea level are more at risk of landslides due to human activities. In addition to similar and main criteria used in related articles (Hong et al. 2018) , in this study, others such as distance from oil lines and gas networks were also used. The highest risk of explosion due to landslides in Tabriz in these high-risk lines is at a distance of 5,000 m. Some researchers looking at the environmental impact of landslides also studied the impact of landslide vulnerability economic criteria (Postance et al. 2017) . In this study, we also assessed environmental and social criteria. Regarding the economic impact, the road criterion, with an output weight of 0.477, is the most vulnerable to landslides as a direct effect (road damage and blockage) and an indirect effect (traffic delay and reduced transport efficiency). Moreover, for the environmental impact, the output weight of the geological criterion was 0.396, and for the social impact, the output weight of the recreation areas was 0.452, which all showed the highest vulnerability to landslides in Tabriz. A survey of vital infrastructures in Tabriz revealed shortages in several areas, including medical and rescue facilities, security and enforcement centers, distribution of city facilities users, distribution of essential and vital centers, and green spaces; the quantity and quality of each play a critical role in reducing (or increasing) the severity of landslide vulnerability. The general trend of the results of this study revealed that the areas with a higher population density suffered from a poor economic situation; these areas were located downstream of the mountainous area and were more Different insights of this study provide a valuable and useful basis for more extensive regional and trans-regional research. The mentioned insights deal with the environmental behavior of landslides and the design of strategic policies to mitigate the effects of landslides. The importance of applying the results on an international scale can be summarized into three topics as follows. First, due to the high vulnerability of road criterion in terms of landslide potential, the importance of maintaining the infrastructure of the Tabriz-Turkey road network is revealed; it is the most important international transit road.

Second, due to the extent of the plateaus and interconnection of faults in neighboring countries, the occurrence of geological events in one of two neighboring border cities of neighboring countries leads to the stimulation of faults in the latter. Third, according to the 2009 cooperation agreement between Iran and the United Nations (UN) Office on Transatlantic Affairs, the study results are useful as internationally documented applicable spatial data concerning landslides, strategic policies in crisis management of geological events, and monitoring programs in the physical control of landslides.

Previous studies in Iran have focused on assessing the vulnerability to landslides. However, the influence of landslides in urban areas has not been analyzed by examining environmental, economic, and social vulnerabilities and needs to be investigated. This study is a prototype for assessing vulnerability in urban areas of a developing country. The objective of this study was to identify and predict locations of landslides in Tabriz, as it is one of the most important cities in Iran in terms of geography, economy, and politics. In this study, to improve the performance of government agencies and nongovernmental organizations (NGOs), it was necessary to assess the environmental behavior of landslides concerning the vulnerability of the population living in slippery areas. The results showed that the most landslide vulnerable areas were residential areas with a high population density and weak financial situations (Table 13) . Moreover, these areas include low-density and compact structures with dramatically increasing vulnerability. Therefore, corrective measures must be taken in terms of the quantity and quality of services provided by the government and the health agencies. A natural disaster such as an earthquake or heavy rain will then lead to the destruction of high-risk buildings, significant casualties, and financial losses. Several general strategies can be proposed to manage the situation and reduce the effects of landslides in Tabriz. Short-term strategies include public education and lowcost mitigations such as gully and other drainage facilities.

Monitoring and recording landslide data can also be useful to local authorities for the development and management of the city. Meanwhile, midterm strategies can include establishing an evidence-based decision-making guideline for defining essential projects and governance in areas highly affected by the landslide. Long-term strategies include changing the legal policy and administrative structure of urban development in areas at high landslide risk. In the long run, the high costs of these measures are offset, due to the prevention of post-slip maintenance and its associated costs. Control and maintenance measures may include daily observation, forecast, and assessment of slope slip fences and meteorological devices. Although these measures are described as low-cost operations, they have a significant impact on reducing slip risks. The average size of residential plots is one of the factors affecting the slip vulnerability of urban structures

Landslide susceptibility hazard map in southwest Sweden using artificial neural network

A comparative study on physical vulnerability of urban area against natural hazards: importance of health promoting approach in civil engineering

Landslide, rock fall hazard assessment and risk inventory maps at south

Modeling predictive suitability to determine potential areas for establishing wind power plants in Srilanka

Non-path dependant urban growth potential mapping using a data-driven evidential belief function

time in a bottle: challenges to disaster studies in Latin America and the Caribean

A semi-quantitative landslide risk assessment of central Kahramanmarash city in the eastern Mediterranean region of Turkey

Spatial prediction of landslide hazards in housing province (Vietnam): a comparative assessment of the efficacy of evidential belief function and fuzzy logic models

Spatial prediction model for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression and logistic model tree

Landslide susceptibility modeling using integrated ensemble weights of evidence with logistic regression and random forest models

Applying population-based evolutionary algorithms and a neuro-fuzzy system for modeling landslide susceptibility

Monitoring of remedial works performance on landslide-affected areas through ground-and satellite-based techniques

The spatial dimension in the assessment of urban socio-economic vulnerability related to geohazards

The Dempster-Shafer calculus for statisticians

Validation of spatial prediction models for landslide susceptibility mapping by considering structural similarity

Spatial landslide risk assessment at Phuentsholing

A decision-support framework for emergency evacuation planning during extreme storm events

Landslide susceptibility modelling using integrated evidential belief function based logistic regression method: a study from Southern Western Ghats

A GIS-based extended fuzzy multi-criteria evaluation for landslide susceptibility mapping

A multi-scale methodological approach for slow-moving landslide risk mitigation in urban areas, southern Italy

A landslide susceptibility assessment method based on GIS technology and an AHPweighted information content method: a case study of Southern Anhui

Urban vulnerability in Bantul district, Indonesia-towards safer and sustainable development

Landslide susceptibility mapping using J48 decision tree with Ada boost , bagging and rotation forest ensembles in the Guangchang area

Applicability and performance of statistical index, certain factor and frequency ratio models in mapping landslides susceptibility in Rwanda. Geocarto Int 1-19

Sustainability assessment of large-scale composing technology using PROMETHEE method

Integration of landslide hazard into urban planning across Europe

Landslide susceptibility a statically-based assessment on a depositional pyroclastic ramp

Shallow Landslide susceptibility mapping by random forest base classifier and its ensembles in a semi-arid region of Iran

Landslide susceptibility assessment using spatial multi-criteria evaluation model in Rwanda

Implications of landslide inventory in susceptibility modeling along a Himalayan highway corridor

Landslide susceptibility mapping and comparison using decision tree models: a case study of Jumunjin Area

Extending natural hazard impacts: an assessment of landslide disruptions on a national road transportation network

Stability assessment of landslide-prone road cut rock slopes in Himalayan terrain: A finite element method based approach

Land subsidence susceptibility mapping at Kinta Valley (Malaysia) using the evidential belief function model in GIS

Land policies for landslide risk reduction in Andean cities

Prioritizing disaster-prone areas for large-scale earthquakes' preparedness

Hill slope instability of Nainital City

The Kyoto Landslide Commitment 2020: first signatories

Global megathrust earthquake hazardmaximum magnitude assessment using multi-variate machine learning

Geoenvironmental impact assessment of rock-cutting activities on the mountainous urban areas, western Saudi Arabia

Visualized analysis of developing trends and hot topics in natural disaster research

Landslide susceptibility assessment by Dempster-Shafer and Index of Entropy models, Sarkhoun basin, Southwestern Iran

Multi-hazard assessment modeling via multi-criteria analysis and GIS: a case study

Landslide detection using multi-scale image segmentation and different machine learning models in the higher Himalayas

Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran

Tourism environmental impact assessment based on improved AHP and picture fuzzy PROMETHEE II methods

Geological based on area development: terrain genetic unit method

Contribution of the collaborative effort of the Czech WCoE to landslide risk reduction at the Machupicchu

Geophysical monitoring of moisture-induced landslides: a review

Landslide susceptibility mapping at Al-Hasher Area, Jizan (Saudi Arabia) using GIS-based frequency ratio and index of entropy models

Optimization of computational intelligence models for landslide susceptibility evaluation

Landslide susceptibility modeling applying machine learning methods: a case study from Longju in the Three Gorges Reservoir area, China

Acknowledgements We would like to thank the National Mapping Agency of Iran, the local government of Tabriz, and the professors of the Tehran University of Science and Research.

Conflict of interest The authors declare that they have no competing interests.