Landslide Susceptibility Evaluation and Management Using Different Machine Learning Methods in The Gallicash River Watershed, Iran
Open accessThe DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
Abstract
This analysis aims to generate landslide susceptibility maps (LSMs) using various machine learning methods, namely random forest (RF), alternative decision tree (ADTree) and Fisher’s Linear Discriminant Function (FLDA). The results of the FLDA, RF and ADTree models were compared with regard to their applicability for creating an LSM of the Gallicash river watershed in the northern part of Iran close to the Caspian Sea. A landslide inventory map was created using GPS points obtained in a field analysis, high-resolution satellite images, topographic maps and historical records. A total of 249 landslide sites have been identified to date and were used in this study to model and validate the LSMs of the study region. Of the 249 landslide locations, 70% were used as training data and 30% for the validation of the resulting LSMs. Sixteen factors related to topographical, hydrological, soil type, geological and environmental conditions were used and a multi-collinearity test of the landslide conditioning factors (LCFs) was performed. Using the natural break method (NBM) in a geographic information system (GIS), the LSMs generated by the RF, FLDA, and ADTree models were categorized into five classes, namely very low, low, medium, high and very high landslide susceptibility (LS) zones. The very high susceptibility zones cover 15.37% (ADTree), 16.10% (FLDA) and 11.36% (RF) of the total catchment area. The results of the different models (FLDA, RF, and ADTree) were explained and compared using the area under receiver operating characteristics (AUROC) curve, seed cell area index (SCAI), efficiency and true skill statistic (TSS). The accuracy of models was calculated considering both the training and validation data. The results revealed that the AUROC success rates are 0.89 (ADTree), 0.92 (FLDA) and 0.97 (RF) and predication rates are 0.82 (ADTree), 0.79 (FLDA) and 0.98 (RF), which justifies the approach and indicates a reasonably good landslide prediction. The results of the SCAI, efficiency and TSS methods showed that all models have an excellent modeling capability. In a comparison of the models, the RF model outperforms the boosted regression tree (BRT) and ADTree models. The results of the landslide susceptibility modeling could be useful for land-use planning and decision-makers, for managing and controlling the current and future landslides, as well as for the protection of society and the ecosystem.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · cited 1×
“BRT is calculated using the following Equation (10) [95]:”
MethodAn Introduction to Statistical Learning
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013) · Springer Texts in Statistics · doi:10.1007/978-1-4614-7138-7 · Cited by 12,106 · cited 1×
“The response to a parameter depends on the higher node values in the regression tree’s hierarchical structure, and then the relationships between the factors are automatically built [92].”
BackgroundPredicting rainfall erosion losses : a guide to conservation planning
Wischmeier, W. H., & Smith, D. D. (1978) · Cited by 7,379
ALLOUCHE, O., TSOAR, A., & KADMON, R. (2006) · Journal of Applied Ecology · doi:10.1111/j.1365-2664.2006.01214.x · Cited by 5,172 · cited 1×
“also used to analyze the performance of the models [113].”
MethodObject based image analysis for remote sensing
Blaschke, T. (2010) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2009.06.004 · Cited by 4,482
Self-citationHansen, L. K., & Salamon, P. (1990) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.58871 · Cited by 4,260 · cited 1×
“Hansen and Salamon [82] point out that ensemble classification trees are much more precise than any of their individual members.”
BackgroundDigital terrain modelling: A review of hydrological, geomorphological, and biological applications
Moore, I. D., Grayson, R. B., & Ladson, A. R. (1991) · Hydrological Processes · doi:10.1002/hyp.3360050103 · Cited by 3,466 · cited 2×
“edu (Alaska Satellite Facility) SPI = As × tanβ where AS is the upstream contributing area and β is the slope gradient (in degrees) Natural break (Jenks) [68]”
BackgroundDietterich, T. G. (2000) · Machine Learning · doi:10.1023/a:1007607513941 · Cited by 2,941 · cited 1×
“Typically, cross-validation is useful to build the selection [86].”
The Data Model Concept in Statistical Mapping
Jenks, G. F. (1967) · Medical Entomology and Zoology · Cited by 2,116
Ayalew, L., & Yamagishi, H. (2005) · Geomorphology · doi:10.1016/j.geomorph.2004.06.010 · Cited by 1,913 · cited 1×
“Both quantitative and qualitative approaches were used to create the LSMs [15].”
MethodTutorial on maximum likelihood estimation
Myung, I. J. (2003) · Journal of Mathematical Psychology · doi:10.1016/s0022-2496(02)00028-7 · Cited by 1,802 · cited 1×
“S Geological Survey Supervised classification (Maximum likelihood) Maximum likelihood [75]”
MethodQuantitative analysis of land surface topography
Zevenbergen, L. W., & Thorne, C. R. (1987) · Earth Surface Processes and Landforms · doi:10.1002/esp.3290120107 · Cited by 1,610
Landslide hazard and risk zonation—why is it still so difficult?
van Westen, C. J., van Asch, T. W. J., & Soeters, R. (2005) · Bulletin of Engineering Geology and the Environment · doi:10.1007/s10064-005-0023-0 · Cited by 1,427
Arcing classifier (with discussion and a rejoinder by the author)
Breiman, L. (1998) · The Annals of Statistics · doi:10.1214/aos/1024691079 · Cited by 1,105
Yesilnacar, E., & Topal, T. (2005) · Engineering Geology · doi:10.1016/j.enggeo.2005.02.002 · Cited by 870 · cited 1×
“The AUROC is expressed as the percentage of prediction values [107].”
Backgroundrpart: Recursive Partitioning and Regression Trees
Therneau, T., & Atkinson, B. (1999) · CRAN: Contributed Packages · doi:10.32614/cran.package.rpart · Cited by 717
Tien Bui, D., Pradhan, B., Lofman, O., & Revhaug, I. (2012) · Mathematical Problems in Engineering · doi:10.1155/2012/974638 · Cited by 574 · cited 1×
“Using all the learning and testing datasets, this approach was used to construct a curve, and subsequently, it was used to calculate the goodness of fit and model prediction accuracy [109].”
MethodSelf-citationRegmi, A. D., Devkota, K. C., Yoshida, K., Pradhan, B., Pourghasemi, H. R., Kumamoto, T., & Akgun, A. (2014) · Arabian Journal of Geosciences · doi:10.1007/s12517-012-0807-z · Cited by 520
Techniques for evaluating the performance of landslide susceptibility models
Frattini, P., Crosta, G., & Carrara, A. (2010) · Engineering Geology · doi:10.1016/j.enggeo.2009.12.004 · Cited by 504 · cited 1×
“It was necessary to generate non-landslide evidence for modeling as the landslide susceptibility analysis is based on a binary classification [64].”
MethodHong, H., Liu, J., Bui, D. T., Pradhan, B., Acharya, T. D., Pham, B. T., Zhu, A.-X., Chen, W., & Ahmad, B. B. (2018) · CATENA · doi:10.1016/j.catena.2018.01.005 · Cited by 491
Self-citationGIS mapping of regional probabilistic groundwater potential in the area of Pohang City, Korea
Oh, H.-J., Kim, Y.-S., Choi, J.-K., Park, E., & Lee, S. (2011) · Journal of Hydrology · doi:10.1016/j.jhydrol.2010.12.027 · Cited by 454 · cited 6×
“The AUROC reflects the reliability of simulations in correctly predicting landslide occurrence or non-occurrence [108].”
BackgroundMethodInfluentialHong, H., Tsangaratos, P., Ilia, I., Liu, J., Zhu, A.-X., & Chen, W. (2018) · Science of The Total Environment · doi:10.1016/j.scitotenv.2017.12.256 · Cited by 427 · cited 1×
“The closer an AUROC value is to 1, the better the performance of the method [9,10].”
MethodSelf-citationPham, B. T., Bui, D. T., Pourghasemi, H. R., Prakash, I., & Dholakia, M. B. (2015) · Theoretical and Applied Climatology · doi:10.1007/s00704-015-1702-9 · Cited by 369
Letter to the Editor: Stability of Random Forest importance measures
Calle, M. L., & Urrea, V. (2011) · Briefings in Bioinformatics · doi:10.1093/bib/bbq011 · Cited by 367 · cited 1×
“No training set is required to monitor the parameters [84,85].”
BackgroundArabameri, A., Rezaei, K., Cerdà, A., Conoscenti, C., & Kalantari, Z. (2019) · Science of The Total Environment · doi:10.1016/j.scitotenv.2019.01.021 · Cited by 304
Self-citationGayen, A., Pourghasemi, H. R., Saha, S., Keesstra, S., & Bai, S. (2019) · Science of The Total Environment · doi:10.1016/j.scitotenv.2019.02.436 · Cited by 295
Self-citationMachine Learning Feature Selection Methods for Landslide Susceptibility Mapping
Micheletti, N., Foresti, L., Robert, S., Leuenberger, M., Pedrazzini, A., Jaboyedoff, M., & Kanevski, M. (2014) · Mathematical Geosciences · doi:10.1007/s11004-013-9511-0 · Cited by 288
Chen, W., Xie, X., Peng, J., Shahabi, H., Hong, H., Bui, D. T., Duan, Z., Li, S., & Zhu, A.-X. (2018) · CATENA · doi:10.1016/j.catena.2018.01.012 · Cited by 281 · cited 2×
“The conservation and management of land is the main motivation behind the preparation of LSMs [14].”
BackgroundSelf-citationRahmati, O., Haghizadeh, A., Pourghasemi, H. R., & Noormohamadi, F. (2016) · Natural Hazards · doi:10.1007/s11069-016-2239-7 · Cited by 255 · cited 2×
“The topographic factors are of great importance for the preparation of LSM [98].”
BackgroundArabameri, A., Rezaei, K., Cerda, A., Lombardo, L., & Rodrigo-Comino, J. (2019) · Science of The Total Environment · doi:10.1016/j.scitotenv.2018.12.115 · Cited by 233
Self-citationDu, G., Zhang, Y., Iqbal, J., Yang, Z., & Yao, X. (2017) · Journal of Mountain Science · doi:10.1007/s11629-016-4126-9 · Cited by 222
Roy, J., Saha, S., Arabameri, A., Blaschke, T., & Bui, D. T. (2019) · Remote Sensing · doi:10.3390/rs11232866 · Cited by 200
Self-citationTien Bui, D., Le, K.-T., Nguyen, V., Le, H., & Revhaug, I. (2016) · Remote Sensing · doi:10.3390/rs8040347 · Cited by 189
Self-citationLandslide Susceptibility Assessment by Novel Hybrid Machine Learning Algorithms
Thai Pham, B., Shirzadi, A., Shahabi, H., Omidvar, E., Singh, S. K., Sahana, M., Talebpour Asl, D., Bin Ahmad, B., Kim Quoc, N., & Lee, S. (2019) · Sustainability · doi:10.3390/su11164386 · Cited by 189
Arabameri, A., Pradhan, B., & Rezaei, K. (2018) · Journal of Environmental Management · doi:10.1016/j.jenvman.2018.11.110 · Cited by 186 · cited 1×
“In this analysis, we contrast the prediction accuracy of these two models with RF, which is a powerful model in natural hazard modeling [25].”
MethodSelf-citationComparison of machine learning models for gully erosion susceptibility mapping
Arabameri, A., Chen, W., Loche, M., Zhao, X., Li, Y., Lombardo, L., Cerda, A., Pradhan, B., & Bui, D. T. (2020) · Geoscience Frontiers · doi:10.1016/j.gsf.2019.11.009 · Cited by 177
Self-citationArabameri, A., Rezaei, K., Pourghasemi, H. R., Lee, S., & Yamani, M. (2018) · Environmental Earth Sciences · doi:10.1007/s12665-018-7808-5 · Cited by 171
Self-citationYilmaz, C., Topal, T., & Süzen, M. L. (2011) · Environmental Earth Sciences · doi:10.1007/s12665-011-1196-4 · Cited by 163 · cited 1×
“The relationship between the landslide inventory datasets and landslide conditioning factors (LCFs) is the most important for landslide susceptibility mapping [56].”
BackgroundArabameri, A., Pradhan, B., Rezaei, K., & Lee, C.-W. (2019) · Remote Sensing · doi:10.3390/rs11090999 · Cited by 158 · cited 1×
“The benefits and advantages of machine learning ensemble models are not only that these techniques provide transparent computations but they also lead to more accurate models [20].”
BackgroundSelf-citationPaul, G. C., Saha, S., & Hembram, T. K. (2019) · Remote Sensing in Earth Systems Sciences · doi:10.1007/s41976-019-00018-6 · Cited by 148
Self-citationHong, H., Liu, J., Zhu, A., Shahabi, H., Pham, B. T., Chen, W., Pradhan, B., & Bui, D. T. (2017) · Environmental Earth Sciences · doi:10.1007/s12665-017-6981-2 · Cited by 147
Self-citationArabameri, A., Pradhan, B., Pourghasemi, H. R., Rezaei, K., & Kerle, N. (2018) · Applied Sciences · doi:10.3390/app8081369 · Cited by 144
Self-citationThe Effect of Unequal Variance-Covariance Matrices on Fisher's Linear Discriminant Function
Gilbert, E. S. (1969) · Biometrics · doi:10.2307/2528902 · Cited by 143 · cited 1×
“φd) transformation by optimizing the Fisher criterion, as indicated [88]:”
MethodCama, M., Conoscenti, C., Lombardo, L., & Rotigliano, E. (2016) · Environmental Earth Sciences · doi:10.1007/s12665-015-5047-6 · Cited by 119 · cited 1×
“The multi-collinearity was tested by applying the variance inflation factor (VIF) and tolerance [78].”
MethodPham, B. T., & Prakash, I. (2017) · Geocarto International · doi:10.1080/10106049.2017.1404141 · Cited by 101
Aertsen, W., Kint, V., Orshoven, J. V., & Muys, B. (2011) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2011.01.003 · Cited by 95 · cited 2×
“This differentiation ends when nodes become homogeneous [91].”
BackgroundAn ensemble model for landslide susceptibility mapping in a forested area
Arabameri, A., Pradhan, B., Rezaei, K., Lee, S., & sohrabi, M. (2019) · Geocarto International · doi:10.1080/10106049.2019.1585484 · Cited by 83 · cited 1×
“The PALSAR DEM is more accurate for detecting landslides in forested areas [61].”
MethodSelf-citationArabameri, A., Roy, J., Saha, S., Blaschke, T., Ghorbanzadeh, O., & Bui, D. T. (2019) · Remote Sensing · doi:10.3390/rs11243015 · Cited by 82
Self-citationAhlmer, A.-K., Cavalli, M., Hansson, K., Koutsouris, A. J., Crema, S., & Kalantari, Z. (2018) · Environmental Earth Sciences · doi:10.1007/s12665-018-7704-z · Cited by 73
Applying different scenarios for landslide spatial modeling using computational intelligence methods
Arabameri, A., Pourghasemi, H. R., & Yamani, M. (2017) · Environmental Earth Sciences · doi:10.1007/s12665-017-7177-5 · Cited by 73 · cited 1×
“The LIM indicates the spatial distribution of the landslides in the form of points and polygons [17].”
BackgroundSelf-citationArabameri, A., Cerdà, A., & Tiefenbacher, J. P. (2019) · Water · doi:10.3390/w11061129 · Cited by 73
Self-citationA Novel Approach to Canonical Divergences within Information Geometry
Ay, N., & Амари, Ш.-И. (2015) · Entropy · doi:10.3390/e17127866 · Cited by 70 · cited 2×
“>2000 ETM+2002 satellite data (15 m × 15 m) Soil Conservation Section of the Agricultural and Natural Resources Research Center Euclidian Distance Buffering Natural break (Jenks) [72]”
BackgroundArabameri, A., Pradhan, B., & Rezaei, K. (2019) · Geosciences Journal · doi:10.1007/s12303-018-0067-3 · Cited by 60
Self-citationPradhan, B., Seeni, M. I., & Kalantar, B. (2017) · Springer eBooks · doi:10.1007/978-3-319-55342-9_11 · Cited by 59
Roy, J., & Saha, S. (2019) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2019.100247 · Cited by 55
Self-citationArabameri, A., Blaschke, T., Pradhan, B., Pourghasemi, H. R., Tiefenbacher, J. P., & Bui, D. T. (2020) · Sensors · doi:10.3390/s20020335 · Cited by 54
Self-citationRoy, J., & Saha, S. (2018) · Modeling Earth Systems and Environment · doi:10.1007/s40808-018-0467-4 · Cited by 46 · cited 3×
“[1] and Roy and Saha [33] used the multi-collinearity analysis to test the topographical, geomorphological, and environmental factors for LS mapping.”
MethodSelf-citationGully Head-Cut Distribution Modeling Using Machine Learning Methods—A Case Study of N.W. Iran
Arabameri, A., Chen, W., Blaschke, T., Tiefenbacher, J. P., Pradhan, B., & Bui, D. T. (2019) · Water · doi:10.3390/w12010016 · Cited by 44
Self-citationPradhan, B., Seeni, M. I., & Nampak, H. (2017) · Springer eBooks · doi:10.1007/978-3-319-55342-9_4 · Cited by 34 · cited 1×
“The multi-collinearity test may enhance the results of the models by helping in the selection of ideal factors for hazard mapping [77].”
BackgroundAdvances in boosting of temporal and spatial models
Robinzonov, N. (2013) · Electronic Theses of LMU Munich (Ludwig-Maximilians-Universität München) · doi:10.5282/edoc.15338 · Cited by 15
Metadata
- Authors
- Arabameri, A., Saha, S., Roy, J., Chen, W., Blaschke, T., & Tien Bui, D.
- Venue
- Remote Sensing
- Publisher
- MDPI AG
- Published
- 2020-02-03
- Volume
- 12
- Issue
- 3
- Pages
- 475
- ISSN
- 2072-4292 (ISSN-L)
- OpenAlex
- W3005376489
- Cited by
- 237
- References
- 61
- FWCI
- 36.62
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.