DOI QR코드

DOI QR Code

Current and Future Status of GIS-based Landslide Susceptibility Mapping: A Literature Review

  • Lee, Saro (Geoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM))
  • Received : 2019.02.12
  • Accepted : 2019.02.16
  • Published : 2019.02.28

Abstract

Landslides are one of the most damaging geological hazards worldwide, threating both humans and property. Hence, there have been many efforts to prevent landslides and mitigate the damage that they cause. Among such efforts, there have been many studies on mapping landslide susceptibility. Geographic information system (GIS)-based techniques have been developed and applied widely, and are now the main tools used to map landslide susceptibility. We reviewed the status of landslide susceptibility mapping using GIS by number of papers, year, study area, number of landslides, cause, and models applied, based on 776 articles over the last 20 years (1999-2018). The number of studies published annually increased rapidly over time. The total study area spanned 65 countries, and 47.7% of study areas were in China, India, South Korea, and Iran, where more than 500 landslides, 27.3% of all landslides, have occurred. Slope (97.6% of total articles) and geology (82.7% of total articles) were most often implicated as causes, and logistic regression (26.9% of total articles) and frequency ratio (24.7% of total article) models were the most widely used models. We analyzed trends in the causes of and models used to simulate landslides. The main causes were similar each year, but machine learning models have increased in popularity over time. In the future, more study areas should be investigated to improve the generalizability and accuracy of the results. Furthermore, more causes, especially those related to topography and soil, should be considered and more machine learning models should be applied. Finally, landslide hazard and risk maps should be studied in addition to landslide susceptibility maps.

Keywords

1. Introduction

Landslides are one of the most frequent natural and geological hazards worldwide. Hence, there is widespread concern over landslides, not only among scientists, engineers, and policy-makers, but also the general public. Many studies have investigated landslides. For instance, application of probabilistic, statistical, and machine learning-based technologies to the study of landslides has increased substantially over time, and geographic information system (GIS) technology is now used widely.In particular, GIS-based landslide susceptibility mapping has increased rapidly in recent years.

There are three assessment steps in landslide analysis: susceptibility, hazard (or possibility), and risk, as defined in Equations(1), (2), and (3) (Einstein, 1988):

\(Susceptibility =f(landslide, landslide-related factors)\)        (1)

\(Hazard = f(susceptibility,\ impact\ factors)\)       (2)

\(Risk = f(hazard,\ damageable\ objects)\)       (3)

The susceptibility term is a function of the probability of potential landslide occurrence and landslide-related factors. It does not depend on influencing factors, such as rainfall, earthquakes, and human activity. The hazard term depends on both influencing factors and susceptibility. The risk term depends on the presence of vulnerable target, such as people and property, and the hazard term. Influencing factors, such as precipitation and seismic activity, are very important.

Among these steps, susceptibility has been studied most frequently. To evaluate the status and trends of GIS-based landslide susceptibility mapping, we analyzed 776 relevant articles published over the last 20 years (1999–2018) in terms of study area, number of articles, number of landslides, causes, and models used. Furthermore, we analyzed the causes and models used in three periods to identify temporal trends. The purpose of this study was to analyze the status and trends in GIS-based landslide susceptibility mapping studies and propose avenues for future study.

There have been several reviews of GIS-based landslide susceptibility mapping (Sudhakar et al., 2013; Wu et al., 2015; Pourghasemi et al., 2018). The differences between these studies and our study is that we analyzed more articles, including newly published articles, so that we could better identify trends. Moreover, we suggest avenues for future study based on our analysis.

2. Methodology

To clarify the status of GIS-based landslide susceptibility mapping, we analyzed 776 articles published over the last 20 years (1999–2018). The articles were retrieved fromScopus(www.scopus.com) using the keywords “landslide” and “GIS.”We selected all articlesfrom the retrieved data, omitting conference and review papers. After excluding several references that appeared in the search but could not be downloaded, we retrieved 768 articles.We also retrieved allrelevant articles from the website of the Korean Society of Remote Sensing (http://ksrs.or.kr/), of which there were eight in total.

The articles were classified by year to determine the number of articles published per year.Thisinformation was used to identify yearly trends in GIS-based landslide susceptibility mapping studies. The study areas and number oflandslides were extracted from the articles to evaluate the status of global landslide occurrence. Moreover, the study area and number of landslides can be used by researchers in the future to identify new causes, apply new models, and generalize and standardize results.We also extracted the causes of and models used to simulate landslides from the articles. To more clearly identify temporal trends, the articles were divided into three periods of 5 or 10 years based on the publication year and considering the number of articles: 1999–2008 (10 years), which included 146 articles; 2009–2013 (5 years), which included 250 articles; and 2014–2018 (5 years), which included 380 articles. We used information from each period to determine which landslide cause and model were most common and identify trends.

3. Results

1) Temporal trends in published articles

During 1999–2018, 776 articles on GIS-based landslide susceptibility mapping were published. Hence, an average of 39 articles were published each year. Generally, the number of articles published per year increased over time (Fig. 1). Whereas only 40 articles were published in the first 5 years(1999–2013), 9.5 times as many papers(380 articles) were published in the final 5 years (2013–2018). Of these, 87 articles were published in each of 2016 and 2017. During the whole study period, the gradient of the trendline of number of publications per year was 4.60 and the coefficient of determination (R2 ) was 0.92, indicative of a rapid increase with a reliable fit.

OGCSBN_2019_v35n1_179_f0001.png 이미지

Fig. 1. Number of published articles in the research field of landslide from 1999 to 2018.

2) Study area and number of landslides

The study areas of the investigated articles spanned many regions from 65 countries (Fig. 2); however, 83.1% of articles originated from 15 countries. The most common study areas were China (143 articles, 18.5%), India (89 articles, 11.5%), South Korea (70 articles, 9.1%), Iran (67 articles, 8.7%), Malaysia (53 articles, 6.9%), Turkey (46 articles, 6.0%), Italy (39 articles, 5.0%), Nepal(23 articles, 3.0%), United States (22 articles, 2.8%), Greece (19 articles, 2.5%),Vietnam (19 articles, 2.5%), Romania (15 articles, 1.9%),Japan (14 articles, 1.8%), Hong Kong (13 articles, 1.7%), and Taiwan (13 articles, 1.7%), respectively (Fig. 2). Although Hong Kong is a Chinese territory, it was separated forthe purpose ofthis analysis because ofthe large number of landslide studies in Hong Kong. Examples of these studies included GIS-based landslide susceptibility mapping in China (Chen et al., 2018) and India (Singh and Kumar, 2017), as well as landslide susceptibility modeling in South Korea (Park et al., 2018a), Iran (Kalantar et al., 2018), Malaysia (Tien Bui et al., 2018), Turkey (Arca et al., 2016), and Italy (Borrelli et al., 2018), respectively.

OGCSBN_2019_v35n1_179_f0002.png 이미지

Fig. 2. Number of landslide study areas used for the published articles with respect to countries.

More than 700,000 landslides were used for GISbased landslide susceptibilitymapping, with an average of 1072 landslidesstudied per paper. Of note, it was not possible to count the number of landslides considered in some articles, because they used pixel numbers or contained no data. According to the number of landslides (Fig. 3), 182 articles (27.1%) studied less than 100 landslides (Oh et al., 2018), 143 articles (21.3%)studied 101–200 landslides(Lee et al., 2018a), 73 articles(10.9%)studied 201–300 landsides(Truong et al., 2018), 45 articles (6.7%) studied 301–400 landsides (Shirani et al., 2018), 45 articles (6.7%) studied 401–500 landslides (Hadji, 2017), 91 articles (13.6%) studied 501–1000 landslides (Kadavi et al., 2018), 47 articles(7.0%)studied 1001–2000 landslides (Aghdam et al., 2016), and 45 articles (6.7%) studied more than 2000 landslides (Lee et al., 2017; Pellicani et al., 2017).

OGCSBN_2019_v35n1_179_f0003.png 이미지

Fig. 3. Number of published articles with respect to number of landslides occurred in the study area of each published article.

3) Causes of landslides and trends

Many researchers have considered a variety of causes of landslides when performing GIS-based landslide susceptibility mapping and have found many causes of landslides. Each of the 776 investigated articles considered multiple causes for GIS-based landslide susceptibility mapping, for a total of 7030 causes. In terms of the trends in the number of causes studied, 1079, 2190, and 3761 causes were considered during the first(1999–2008),second (2009–2013), and third (2014–2018) periods, respectively. On average, 7.4, 8.8 and 9.9, causes were considered in the first, second and third periods, respectively.

The causes could be divided into six major groups: topographic, hydrologic, transportation, geologic,soil, forest, and land use. Topographic factors included elevation, slope, aspect, curvature, relief, and geomorphology. Many types of curvature (e.g., planar, plan, and profile curvature) have been implicated as causes. Generally, many factors can be extracted using digital elevation models(DEMs).Among topographic factors,slope was considered very frequently (Nguyen et al., 2017), and other topographic factors such as aspect (Cui et al., 2017), curvature (Ge et al., 2018), elevation (Pourghasemi and Rahmati, 2018), and geomorphology (Ahmed and Dewan, 2017) were considered frequently. Common hydrological factors included distance from and density ofriver,stream, and drainage (Lyu et al., 2018); topographic wetnessindex (TWI) (Abdulwahid and Pradhan, 2017); and stream power index (SPI) (Lee et al., 2018b). Transportationrelated factors included distance from roads and railways, and density ofroads and railways(Kornejady et al., 2017). Common geological factors included lithology, distance from fault and lineament, density of faults and lineaments, bedding, and foliation (Achour et al., 2017), among which distance from faults (Park et al., 2018b) and lineaments(Singh and Kumar, 2018) have been implicated frequently as causative factors. Soil-related causes included soil type, material, thickness, drainage, and strength (Pham et al., 2017). Commonly investigated forest-related factorsincluded forest type, age, diameter, density, vegetation, and normalized difference vegetation index (NDVI) (Kim et al., 2018). Finally, within land use, researchers have considered both land use (Tien Bui et al., 2017) and land cover. Other notable influencing factors included precipitation and earthquakes (Jeong et al., 2018).

As shown in Fig. 4, slopes were considered in 757 times of total factors (10.8%). The other most commonly considered factors were geology (642 times; 9.1%), aspect (592 times; 8.5%), river or stream (580 times; 8.3%), curvature (567 times; 8.1%), land use (461 times; 6.6%), elevation (450 times; 6.4%), soil (433 times; 6.2%) and fault (5.2%).

OGCSBN_2019_v35n1_179_f0004.png 이미지

Fig. 4. Number of published articles with respect to the factor used as landslide causes in all of the published articles used for this study

The most commonly included influencing factors during the first period (1999–2008) were slope (141 times; 13.1%), geology (112 times; 10.4%), soil (109 times; 10.1%), aspect (101 times; 9.4%), land use (83 times; 7.7%),forest(78 times; 7.2%), and curvature (73 times; 6.8) were used most widely (Fig. 5). The most commonly included influencing factors during the second period (2009–2013) were slope (241 times; 11.0%), geology (217 times; 86.8%), river or stream (201 times; 9.2%), aspect (191 times; 8.7%), land use (168 times; 7.7%), curvature (154 times; 7.0%) and fault (129 times; 5.9%) (Fig. 6). The most commonly included influencing factors during the third period (2014–2018) were slope (375 times; 10.0%), curvature (340 times; 9.0%), geology (313 times; 8.3%), river or stream (307 times; 8.2%), aspect (303 times; 8.1%), elevation (264 times; 7.0%) and land use (210 times; 5.6%) (Fig. 7).

OGCSBN_2019_v35n1_179_f0005.png 이미지

Fig. 5. Number of published articles with respect to the factor used as landslide causes in the articles published in the first period (1999–2008).

OGCSBN_2019_v35n1_179_f0006.png 이미지

Fig. 6. Number of published articles with respect to the factor used as landslide causes in the articles published in the second period (2009–2013).

OGCSBN_2019_v35n1_179_f0007.png 이미지

Fig. 7. Number of published articles with respect to the factor used as landslide causes in the articles published in the third period (2014–2018).​​​​​​​

4) Models used to analyze landslide susceptibility and their trends

A wide range of models, algorithms, and techniques are used for GIS-based landslide susceptibility mapping. Models can be divided into data- and knowledge-driven categories. Data-driven models can be further divided into three categories: probabilistic, statistical, and machine learning models. Among knowledge-driven models, the analytic hierarchy process (AHP) and weight overlay are used widely. Among probabilistic models, frequency ratio, weight of evidence, evidential belief function, information value, and certainty factor models are used frequently. Among statistical models, logistic regression and statistical index models are used widely. Finally, popular machine learning models include artificial neural networks support vector machines, decision trees, adaptive neuro-fuzzy inference systems, and random forests.

Based on the literature review, there were 1498 instances of model use for GIS-based landslide susceptibility mapping in the 776 articles published during 1999–2018, with an average of 1.9 models used per article. Logistic regression models, used in 209 times (14.0%), were used most frequently (e.g., Lee and Lee, 2017; Zhu et al., 2018) (Table 1). Other most frequently used models were frequency ratio model (192 times; 12.8%) (e.g., Son et al., 2016; Aditian et al., 2018), artificial neural networks(121 times; 8.1%) (e.g., Chen et al., 2017; Gorsevski et al., 2016), fuzzy logic (114 times; 7.6%) (e.g., Mallick et al., 2018; Rostami et al., 2016), support vector machine (98 times; 6.5%) (e.g., Tien Bui et al., 2016; Hong et al., 2018),AHP(90 times; 6.0%)(e.g., Demir, 2018; Nicu, 2018), and weight of evidence (86 times; 11.1%) (Rahman et al., 2017; Jaafari, 2018). In addition to these frequently used models, index of entropy, naïve Bayes, boosted trees, functional trees, bagging, adaptive boosting, relevance vector machines, and logistic model trees have also been used.

Table 1. Models used in the published articles​​​​​​​

OGCSBN_2019_v35n1_179_t0001.png 이미지

Next, we analyzed the trends in model usage in the three periods.In the first period (1999–2008), the most frequently used models were logistic regression (48 times; 25.0%), frequency ratio (33 times; 17.2%), weight of evidence (15 times; 7.8%), artificial neural network (14 articles; 7.3%), and fuzzy logic (13 times; 6.89%) (Table 2). In the second period (2009–2013), the most widely used models were logistic regression (69 times; 14.4%), frequency ratio (65 times; 13.5%), artificial neural network (65 times; 13.5%),fuzzy logic (62 times; 12.9%), and weight of evidence (31 times; 6.5%) (Table 3). During the third period (2014–2018), the most frequently used models were logistic regression (96 times; 10.9%),support vector machine (72 times; 8.7%),AHP (54 times; 6.5%), and artificial neural network (42 times; 5.1%) (Table 4).

Table 2. Models used in the articles published in the first period (1999–2008)​​​​​​​

OGCSBN_2019_v35n1_179_t0002.png 이미지

Table 3. Models used in the articles published in the second period (2009–2013)​​​​​​​​​​​​​​

OGCSBN_2019_v35n1_179_t0003.png 이미지

Table 4. Models used in the articles published in the third period (2014–2018)​​​​​​​

OGCSBN_2019_v35n1_179_t0004.png 이미지

5. Conclusion and Discussion

In thisstudy, we reviewed 776 articles on GIS-based landslide susceptibility mapping from the last 20 years (1999–2018) and analyzed them by year, country, number of landslides, causes, and model. In addition, we divided the articles into three periods to identify temporal trends.

The number of articles published annually increased rapidly over the 20-year study period, with more than 9.5 times the number of articles in the first 5 years (1999–2003) published in the last 5 years(2014–2018). Thisincrease may have been driven by the availability of digital data, including remote sensing data, and development of new modelssuch as machine learning models. This increase indicates that many researchers are interested in landslides, likely due to their global ubiquity and ability to inflict serious damage to both people and property, and have carried out GIS-based landslide susceptibility mapping studies. Furthermore, GIS technology has become a popular tool for analyzing landslide susceptibility, further driving the increase in the number of articles published on this subject.

The investigated articles covered many study areas in 65 countries; however, China (18.5% of studies), India (11.5%), and South Korea (9.1%) were particular targets of study. The results mirrored the global occurrence oflandslides.The incidence oflandslidesis related to country-specific characteristics. Forinstance, countries with more mountainous areas and impact events (e.g., rainfall and earthquakes) are more likely to experience landslides, resulting in greater data availability and supporting more studies. In addition to collecting more landslide data, there should be concerted academic effort towards understanding landslides. Therefore, further case studies are required to improve the generalizability and accuracy of landslide information and modeling.

Among the 776 investigated papers, more than 700,000 landslides were considered; however,some of these may have been duplicates.Regardless, numerous landslides have been studied in individual studies, indicating that landslides occur very frequently. In particular, 94 articles considered more than 1000 landslides. These landslide data can be used for further analysis based on new and more accurate models, and the data can be merged for more reliable analysis. Hence, we recommend that researchers partake in international collaborations in which new models are applied to merged data on landslide locations and causes.

Causes, including DEM-based information, drainage, road, geology, fault, soil, forest, land use and others, were considered more than 7000 times in the GISbased landslide susceptibility mapping studies.Among these causes, slopes were included in 97.6% of the articles and geology (82.7%), aspect(76.7%), hydrology (74.7%), and curvature (73.1%) were considered very frequently in the total articles. Furthermore, land use, elevation, soil, fault, transportation, rainfall, forest, TWI, lineament, NDVI, SPI, and geomorphology were considered frequently. These causes were considered frequently, suggestive of their close association with landslide occurrence. Over the three investigated periods, the average number of causes considered per article increased (first period: 7.4; second period: 8.8; third period: 9.9). However, the causes implicated in landslides did not vary significantly over the study period. To more clearly understand the relationships between causes and landslide occurrence and to improve the accuracy of mapping results, more causes should be identified and analyzed using existing data, such as DEM with SAGA GIS (Conrad et al., 2015). Furthermore, the importance or weights of causes can be analyzed using sensitivity analysis, artificial neural networks, or other models. Finally, the most predictive causes should be selected and standardized.

In terms of the models used, more than 100 types of models were used for GIS-based landslide susceptibilitymapping, with a total of 1498 applications of models among all studies, corresponding to 1.9 model applications per article. Logistic regression models were applied most frequently (26.9% of all articles)to GIS-based landslide susceptibility mapping. Frequency ratio, artificial neural network, fuzzy logic, support vector machine, AHP, and weight of evidence models were applied in more than 10% of the articles. Logistic regression, frequency ratio, artificial neural network, fuzzy logic, and AHP models were used frequently during all three periods. Machine learning models,such assupport vectormachine,randomforest, decision tree, and naïve Bayes models, have been applied more recently

Landslide analysisinvolvesthree steps:susceptibility, hazard, and risk mapping. Many studies have analyzed susceptibility, including the present literature review. However, there are fewer articles on the hazard and risk steps. Hence, more studiesshould be carried out on the hazard and risk stepsto decrease the damage caused by landslides, save lives, and protect property

Acknowledgments

I specially thanks for Mr. Prima Riza Kadavi and Mr. Sung-Jae Park to arrange data in the articles. This research was conducted by the Basic Research Project of the Korea Institute of Geoscience and Mineral Resources(KIGAM)funded by theMinistry of Science and ICT.​​​​​​​

References

  1. Abdulwahid, W.M. and B. Pradhan, 2017. Landslide vulnerability and risk assessment for multi-hazard scenarios using airborne laser scanning data (LiDAR), Landslides, 14(3): 1057-1076. https://doi.org/10.1007/s10346-016-0744-0
  2. Achour, Y., A. Boumezbeur, R. Hadji, A. Chouabbi, V. Cavaleiro, and E.A. Bendaoud, 2017. Landslide susceptibility mapping using analytic hierarchy process and information value methods along a highway road section in Constantine, Algeria, Arabian Journal of Geosciences, 10(8): 194. https://doi.org/10.1007/s12517-017-2980-6
  3. Aditian, A., T. Kubota, and Y. Shinohara, 2018. Comparison of GIS-based landslide susceptibility models using frequency ratio, logistic regression, and artificial neural network in a tertiary region of Ambon, Indonesia, Geomorphology, 318: 101-111. https://doi.org/10.1016/j.geomorph.2018.06.006
  4. Aghdam, I.N., M.H.M. Varzandeh, and B. Pradhan, 2016. Landslide susceptibility mapping using an ensemble statistical index (Wi) and adaptive neuro-fuzzy inference system (ANFIS) model at Alborz Mountains (Iran), Environmental Earth Sciences, 75(7): 553. https://doi.org/10.1007/s12665-015-5233-6
  5. Ahmed, B. and A. Dewan, 2017. Application of bivariate and multivariate statistical techniques in landslide susceptibility modeling in Chittagong City Corporation, Bangladesh, Remote Sensing, 9(4): 304. https://doi.org/10.3390/rs9040304
  6. Arca, D., H.S. Kutogu, and K. Becek, 2016. Landslide susceptibility mapping in an area of underground mining using the multicriteria decision analysis method, Environmental Monitoring and Assessment, 190(12): 725. https://doi.org/10.1007/s10661-018-7085-5
  7. Borrelli, L., M. Ciurleo, and G. Gulla, 2018. Shallow landslide susceptibility assessment in granitic rocks using GIS-based statistical methods: the contribution of the weathering grade map, Landslides, 15(6): 1127-1142. https://doi.org/10.1007/s10346-018-0947-7
  8. Chen, W., H.R. Pourghasemi, and Z. Zhao, 2017. A GIS-based comparative study of Dempster-Shafer, logistic regression and artificial neural network models for landslide susceptibility mapping, Geocarto International, 32(4): 367-385. https://doi.org/10.1080/10106049.2016.1140824
  9. Chen, W., H. Shahabi, S. Zhang, K. Khosravi, A. Shirzadi, K. Chapi, B.T. Pham, T. Zhang, L. Zhang, H. Chai, J. Ma, Y. Chen, X. Wang, R. Li, and B.B. Ahmad, 2018. Landslide susceptibility modeling based on GIS and Novel Baggingbased Kernel logistic regression, Applied Sciences (Switzerland), 8(12): 2540. https://doi.org/10.3390/app8122540
  10. Conrad, O., B. Bechtel, M. Bock, H. Dietrich, E. Fischer, L. Gerlitz, J. Wehberg, V. Wichmann, and J. Bohner, 2015. System for Automated Geoscientific Analyses (SAGA) v. 2.1.4, Geoscientific Model Development, 8: 1991-2007. https://doi.org/10.5194/gmd-8-1991-2015
  11. Cui, K., D. Lu, and W. Li, 2017. Comparison of landslide susceptibility mapping based on statistical index, certainty factors, weights of evidence and evidential belief function models, Geocarto International, 32(9): 935-955. https://doi.org/10.1080/10106049.2016.1195886
  12. Demir, G., 2018. Landslide susceptibility mapping by using statistical analysis in the North Anatolian Fault Zone (NAFZ) on the northern part of Susehri Town, Turkey, Natural Hazards, 92(1): 133-154. https://doi.org/10.1007/s11069-018-3195-1
  13. Einsten, H. H., 1988. Landslide risk assessment procedure, In: Bonnard, C. (ed), Proc. of the Fifth International Symposium on Landslides, vol. 2, pp. 1085-1090.
  14. Ge, Y., H. Chen, B. Zhao, H. Tang, Z. Lin, Z. Xie, L. Lv, and P. Zhong, 2018. A comparison of five methods in landslide susceptibility assessment: a case study from the 330-kV transmission line in Gansu Region, China, Environmental Earth Sciences, 77(19): 662. https://doi.org/10.1007/s12665-018-7814-7
  15. Gorsevski, P.V., M.K. Brown, K. Panter, C.M. Onasch, A. Simic, and J. Snyder, 2016. Landslide detection and susceptibility mapping using LiDAR and an artificial neural network approach: a case study in the Cuyahoga Valley National Park, Ohio, Landslides, 13(3): 467-484. https://doi.org/10.1007/s10346-015-0587-0
  16. Hadji, R., K. Rais, L. Gadri, A. Chouabi, and Y. Hamed, 2017. Slope Failure Characteristics and Slope Movement Susceptibility Assessment Using GIS in a Medium Scale: A Case Study from Ouled Driss and Machroha Municipalities, Northeast Algeria, Arabian Journal for Science and Engineering, 42(1): 281-300. https://doi.org/10.1007/s13369-016-2046-1
  17. Hong, H., B. Pradhan, M.I. Sameen, B. Kalantar, A. Zhu, and W. Chen, 2018. Improving the accuracy of landslide susceptibility model using a novel region-partitioning approach, Landslides, 15(4): 753-772. https://doi.org/10.1007/s10346-017-0906-8
  18. Jaafari, A., 2018. LiDAR-supported prediction of slope failures using an integrated ensemble weights-of-evidence and analytical hierarchy process, Environmental Earth Sciences, 77(2): 42. https://doi.org/10.1007/s12665-017-7207-3
  19. Jeong, S., A. Kassim, M. Hong, and N. Saadatkhah, 2018. Susceptibility assessments of landslides in Hulu Kelang area using a geographic information system-based prediction model, Sustainability (Switzerland), 10(8): 2941. https://doi.org/10.3390/su10082941
  20. Kadavi, P., C.-W. Lee, and S. Lee, 2018. Application of Ensemble-Based Machine Learning Models to Landslide Susceptibility Mapping, Remote Sensing, 10(8): 1252. https://doi.org/10.3390/rs10081252
  21. Kalantar, B., B. Pradhan, S. Amir Naghibi, A. Motevalli, and S. Mansor, 2018. Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN), Geomatics, Natural Hazards and Risk, 9(1): 49-69. https://doi.org/10.1080/19475705.2017.1407368
  22. Kim, J.-C., S. Lee, H.-S. Jung, and S. Lee, 2018. Landslide susceptibility mapping using random forest and boosted tree models in Pyeong-Chang, Korea, Geocarto International, 33(9): 1000-1015. https://doi.org/10.1080/10106049.2017.1323964
  23. Kornejady, A., M. Ownegh, and A. Bahremand, 2017. Landslide susceptibility assessment using maximum entropy model with two different data sampling methods, Catena, 152: 144-162. https://doi.org/10.1016/j.catena.2017.01.010
  24. Lee, J.-H., M.I. Sameen, B. Pradhan, and H.-J. Park, 2018b. Modeling landslide susceptibility in data-scarce environments using optimized data mining and statistical methods, Geomorphology, 303: 284-298. https://doi.org/10.1016/j.geomorph.2017.12.007
  25. Lee, S. and M.-J. Lee, 2017. Susceptibility Mapping of Umyeonsan Using Logistic Regression (LR) Model and Post-validation through Field Investigation, Korean Journal of Remote Sensing, 33(6-2): 1047-1060 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2017.33.6.2.2
  26. Lee, S., S.-M. Hong, and H.-S. Jung, 2017. A support vector machine for landslide susceptibility mapping in Gangwon Province, Korea, Sustainability (Switzerland), 9(1): 48. https://doi.org/10.3390/su9010048
  27. Lee, S., M.-J. Lee, and S. Lee, 2018a. Spatial prediction of urban landslide susceptibility based on topographic factors using boosted trees, Environmental Earth Sciences, 77(18): 656. https://doi.org/10.1007/s12665-018-7778-7
  28. Lyu, H.-M., J.S. Shen, and A. Arulrajah, 2018. Assessment of geohazards and preventative countermeasures using AHP incorporated with GIS in Lanzhou, China, Sustainability (Switzerland), 10(2): 304. https://doi.org/10.3390/su10020304
  29. Mallick, J., R.K. Singh, M.A. AlAwadh, S. Islam, R.A. Khan, and M.N. Qureshi, 2018. GIS-based landslide susceptibility evaluation using fuzzy-AHP multi-criteria decision-making techniques in the Abha Watershed, Saudi Arabia, Environmental Earth Sciences, 77(7): 276. https://doi.org/10.1007/s12665-018-7451-1
  30. Nguyen, Q.-K., D.T. Bui, N.-D. Hoang, P.T. Trinh, V.-H. Nguyen, and I. Yilmaz, 2017. A novel hybrid approach based on instance based learning classifier and rotation Forest ensemble for spatial prediction of rainfall-induced shallow landslides using GIS, Sustainability, 9(5): 813. https://doi.org/10.3390/su9050813
  31. Nicu, I.C., 2018. Application of analytic hierarchy process, frequency ratio, and statistical index to landslide susceptibility: an approach to endangered cultural heritage, Environmental Earth Sciences, 77(3): 79. https://doi.org/10.1007/s12665-018-7261-5
  32. Oh, H.-J., P. Kadavi, C.-J. Lee, and S. Lee, 2018. Evaluation of landslide susceptibility mapping by evidential belief function, logistic regression and support vector machine models, Geomatics, Natural Hazards and Risk, 9(1): 1053-1070. https://doi.org/10.1080/19475705.2018.1481147
  33. Park, S.-J., C.-W. Lee, S. Lee, and M.-J. Lee, 2018a. Landslide Susceptibility Mapping and Comparison Using Decision Tree Models: A Case Study of Jumunjin Area, Korea, Remote Sensing, 10(10): 1545. https://doi.org/10.3390/rs10101545
  34. Park, S.-J., P. Kadavi, and C.-W. Lee, 2018b. Landslide Susceptibility Mapping and Comparison Using Probabilistic Models: A Case Study of Sacheon, Jumunzin Area, Korea, Korean Journal of Remote Sensing, 34(5): 721-738 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2018.34.5.2
  35. Pellicani, R., I. Argentiero, and G. Spilotro, 2017. GIS-based predictive models for regional-scale landslide susceptibility assessment and risk mapping along road corridors, Geomatics, Natural Hazards and Risk, 8(2): 1012-1033. https://doi.org/10.1080/19475705.2017.1292411
  36. Pham, B.T., D. Tien Bui, I. Prakash, L.H. Nguyen, and M.B. Dholakia, 2017. A comparative study of sequential minimal optimization-based support vector machines, vote feature intervals, and logistic regression in landslide susceptibility assessment using GIS, Environmental Earth Sciences, 76(10): 371. https://doi.org/10.1007/s12665-017-6689-3
  37. Pourghasemi, H.R. and O. Rahmati, 2018. Prediction of the landslide susceptibility: Which algorithm, which precision?, Catena, 162: 177-192. https://doi.org/10.1016/j.catena.2017.11.022
  38. Pourghasemi, H.R., Z. T. Yansari, P. Panagos, and B. Pradhan, 2018. Analysis and evaluation of landslide susceptibility: a review on articles published during 2005-2016 (periods of 2005-2012 and 2013-2016), Arabian Journal of Geosciences, 11: 193. https://doi.org/10.1007/s12517-018-3531-5
  39. Rahman, M.S., B. Ahmed, and L. Di, 2017. Landslide initiation and runout susceptibility modeling in the context of hill cutting and rapid urbanization: a combined approach of weights of evidence and spatial multi-criteria, Journal of Mountain Science, 14(10): 1919-1937. https://doi.org/10.1007/s11629-016-4220-z
  40. Rostami, Z.A., S.A. Al-modaresi, H. Fathizad, and M. Faramarzi, 2016. Landslide susceptibility mapping by using fuzzy logic: a case study of Cham-gardalan catchment, Ilam, Iran, Arabian Journal of Geosciences, 9(17): 685. https://doi.org/10.1007/s12517-016-2720-3
  41. Shirani, K., M. Pasandi, and A. Arabameri, 2018. Landslide susceptibility assessment by Dempster-Shafer and Index of Entropy models, Sarkhoun basin, Southwestern Iran, Natural Hazards, 93(3): 1379-1418. https://doi.org/10.1007/s11069-018-3356-2
  42. Singh, K. and V. Kumar, 2017. Landslide hazard mapping along national highway-154A in Himachal Pradesh, India using information value and frequency ratio, Arabian Journal of Geosciences, 10(24): 539. https://doi.org/10.1007/s12517-017-3315-3
  43. Singh, K. and V. Kumar, 2018. Hazard assessment of landslide disaster using information value method and analytical hierarchy process in highly tectonic Chamba region in bosom of Himalaya, Journal of Mountain Science, 15(4): 808-824. https://doi.org/10.1007/s11629-017-4634-2
  44. Son, J., J. Suh, and H.-D. Park, 2016. GIS-based landslide susceptibility assessment in Seoul, South Korea, applying the radius of influence to frequency ratio analysis, Environmental Earth Sciences, 75(4): 310. https://doi.org/10.1007/s12665-015-5149-1
  45. Pardeshi, S. D., S. E. Autade, and S. S. Pardeshi, 2013. Landslide hazard assessment: recent trends and techniques, SpringerPlus, 2(1): 523. https://doi.org/10.1186/2193-1801-2-523
  46. Tien Bui, D., H. Shahabi, A. Shirzadi, K. Chapi, M. Alizadeh, W. Chen, A. Mohammadi, B.B. Ahmad, M. Panahi, H. Hong, and Y. Tian, 2018. Landslide detection and susceptibility mapping by AIRSAR data using support vector machine and index of entropy models in Cameron Highlands, Malaysia, Remote Sensing, 10(10): 1527. https://doi.org/10.3390/rs10101527
  47. Tien Bui, D., T.A. Tuan, N.-D. Hoang, N.Q. Thanh, D.B. Nguyen, N. Van Liem, and B. Pradhan, 2017. Spatial prediction of rainfall-induced landslides for the Lao Cai area (Vietnam) using a hybrid intelligent approach of least squares support vector machines inference model and artificial bee colony optimization, Landslides, 14(2): 447-458. https://doi.org/10.1007/s10346-016-0711-9
  48. Tien Bui, D., T.A. Tuan, H. Klempe, B. Pradhan, and I. Revhaug, 2016. Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree, Landslides, 13(2): 361-378. https://doi.org/10.1007/s10346-015-0557-6
  49. Truong, X.L., M. Mitamura, Y. Kono, V. Raghavan, G. Yonezawa, X.Q. Truong, T.H. Do, D.T. Bui, and S. Lee, 2018. Enhancing prediction performance of landslide susceptibility model using hybrid machine learning approach of bagging ensemble and logistic model tree, Applied Sciences (Switzerland), 8(7): 1046. https://doi.org/10.3390/app8071046
  50. Wu, X., I.X. Wu, I.F. Chen, B. Zhan, and S. Hong, 2015. Global research trends in landslides during 1991-2014: a bibliometric analysis, Landslides, 12: 1215-1226. https://doi.org/10.1007/s10346-015-0624-z
  51. Zhu, A.-X., Y. Miao, R. Wang, T. Zhu, Y. Deng, J. Liu, L. Yang, C.-Z. Qin, and H. Hong, 2018. A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping, Catena, 166: 317-327. https://doi.org/10.1016/j.catena.2018.04.003

Cited by

  1. Evidential Belief Function, Weight of Evidence 및 Artificial Neural Network 모델을 이용한 산사태 공간 취약성 예측 연구 vol.35, pp.2, 2019, https://doi.org/10.7780/kjrs.2019.35.2.9
  2. 해외 사례 분석과 국내 공간정보 분석을 통한 화산재 피해 분야 선정 vol.35, pp.5, 2019, https://doi.org/10.7780/kjrs.2019.35.5.1.11
  3. Estimating rainfall threshold and temporal probability for landslide occurrences in Darjeeling Himalayas vol.24, pp.2, 2019, https://doi.org/10.1007/s12303-020-0001-3
  4. Landslide Risk Mapping in an Urban Area of the City of Natal, Brazil vol.12, pp.22, 2019, https://doi.org/10.3390/su12229601
  5. A Review on Remote Sensing and GIS Applications to Monitor Natural Disasters in Indonesia vol.36, pp.6, 2019, https://doi.org/10.7780/kjrs.2020.36.6.1.3