A Comprehensive Assessment of XGBoost Algorithm for Landslide Susceptibility Mapping in the Upper Basin of Ataturk Dam, Turkey
Source abstract
Abstract
The success rate in landslide susceptibility mapping efforts increased with the advancements in machine learning algorithms and the availability of geospatial data with high spatial and temporal resolutions. Existing data-driven susceptibility mapping models are not globally applicable due to the high variability of landslide conditioning parameters and the limitations in the availability of up-to-date and accurate data. Among numerous applications, landslide susceptibility maps are essential for site selection and health monitoring of engineering structures, such as dams, for increasing their lifetime and to prevent from disastrous events caused by the damages. In this study, landslide susceptibility mapping performance of XGBoost algorithm was evaluated in a landslide-prone area in the upper basin of Ataturk Dam, which is a prime investment located in the southeast of Turkey. The study area has a size of 2718.7 km2 with an elevation difference of ca. 2000 m and contains 27 lithological units. EU-DEM v1.1 from the Copernicus Programme was used to derive the geomorphological features. High classification accuracy with area under curve value of 0.96 could be obtained from the XGBoost algorithm. According to the results, the main factors controlling the landslides in the study area are the lithology, altitude and topographic wetness index.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Landslides and related hazards · Fire effects on ecosystems · Soil erosion and sediment transport
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Geomatics Engineering, Hacettepe University, 06800 Beytepe Ankara, Turkey
Department of Geological Engineering, Hacettepe University, 06800 Beytepe Ankara, Turkey
References (56)
Show source-provided references
1. United Nations Sustainable Development Goals SDG Indicators (2021, March 04). E/CN.3/2020/2. Available online: https://unstats.un.org/sdgs/indicators/indicators-list/.
2. AFAD (2021, March 04). Afet ve Acil Durum Yönetimi Baskanligi Afet Yönetimi Kapsaminda 2019 Yilina Bakis ve Doga Kaynakli Olay Istatistikleri; Technical Report, AFAD, Ankara, Turkey: 7 July 2020, Available online: https://www.afad.gov.tr/kurumlar/afad.gov.tr/e_Kutuphane/Kurumsal-Raporlar/Afet_Istatistikleri_2020_web.pdf.
3. Settlement and slaking problems in the world’s fourth largest rock-fill dam, the Ataturk Dam in Turkey10.1016/S0013-7952(99)00049-6 ↗
4. Akbaş, B., Akdeniz, N., Aksay, A., Altun, İ., Balcı, V., Bilginer, E., Bilgiç, T., Duru, M., Ercan, T., and Gedik, İ. (2016). Turkey Geological Map, Mineral Research & Exploration General Directorate.
5. (2021, March 04). MTA Yerbilimleri Harita Goruntuleyici ve Cizim Editorü, Available online: http://yerbilimleri.mta.gov.tr/.
6. Yanar, T., Kocaman, S., and Gokceoglu, C. (2020). Use of Mamdani Fuzzy Algorithm for Multi-Hazard Susceptibility Assessment in a Developing Urban Settlement (Mamak, Ankara, Turkey). ISPRS Int. J. Geo-Inf., 9.10.3390/ijgi9020114 ↗
7. Possible contributions of citizen science for landslide hazard assessment10.5194/isprs-archives-XLII-3-W4-295-2018 ↗
8. A CitSci app for landslide data collection10.1007/s10346-018-1101-2 ↗
9. Chen, T., and Guestrin, C. (2016, January 13–17). XG Boost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining-KDD, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
10. European Environment Agency (2021, February 23). Copernicus Land Monitoring Service-Reference Data: EU-DEM, Factsheet, May. Available online: https://land.copernicus.eu/user-corner/publications/eu-dem-flyer/at_download/file.
11. (2021, March 04). Copernicus Land Monitoring Service. Available online: https://land.copernicus.eu/ See also: https://land.copernicus.eu/imagery-in-situ/eu-dem/eu-dem-v1.1/view.
12. An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps10.1016/j.enggeo.2008.01.004 ↗
13. Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed, Iran10.1007/s11069-012-0217-2 ↗
14. A comparison of logistic regression-based models of susceptibility to landslides in western Colorado, USA10.1007/s10346-012-0380-2 ↗
15. Sevgen, E., Kocaman, S., Nefeslioglu, H.A., and Gokceoglu, C. (2019). A Novel Performance Assessment Approach Using Photogrammetric Techniques for Landslide Susceptibility Mapping with Logistic Regression, ANN and Random Forest. Sensors, 19.10.3390/s19183940 ↗
16. Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling10.1016/j.scitotenv.2018.06.389 ↗
17. Mutlu, B., Nefeslioglu, H.A., Sezer, E.A., Akcayol, M.A., and Gokceoglu, C. (2019). An experimental research on the use of recurrent neural networks in landslide susceptibility mapping. ISPRS Int. J. Geo-inf., 8.10.3390/ijgi8120578 ↗
18. On the use of hierarchical fuzzy inference systems (HFIS) in expert-based landslide susceptibility mapping: The central part of the Rif Mountains (Morocco)10.1007/s10064-019-01548-5 ↗
19. Landslide susceptibility mapping with random forest model for Ordu, Turkey10.5194/isprs-archives-XLIII-B3-2020-1229-2020 ↗
20. Karakas, G., Kocaman, S., and Gokceoglu, C. (2021). Aerial photogrammetry and machine learning based regional landslide susceptibility assessment for an earthquake prone area in Turkey. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., accepted.10.5194/isprs-archives-XLIII-B3-2021-713-2021 ↗
21. Kocaman, S., Tavus, B., Nefeslioglu, H.A., Karakas, G., and Gokceoglu, C. (2020). Evaluation of Floods and Landslides Triggered by a Meteorological Catastrophe (Ordu, Turkey, August 2018) Using Optical and Radar Data. Geofluids, 2020.10.1155/2020/8830661 ↗
22. Integration of convolutional neural network and conventional machine learning classifiers for landslide susceptibility mapping10.1016/j.cageo.2020.104470 ↗
23. How do machine learning techniques help in increasing accuracy of landslide susceptibility maps?10.1016/j.gsf.2019.10.001 ↗
24. Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer10.1016/j.gsf.2020.07.012 ↗
25. Rainfall-based criteria for assessing slump rate of mountainous highway slopes: A case study of slopes along Highway 18 in Alishan, Taiwan10.1016/j.enggeo.2011.01.001 ↗
26. Neural network-based model for assessing failure potential of highway slopes in the Alishan, Taiwan Area: Pre-and post-earthquake investigation10.1016/j.enggeo.2008.11.007 ↗
27. Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance10.1016/j.earscirev.2020.103225 ↗
28. Pradhan, A.M.S., and Kim, Y.-T. (2020). Rainfall-Induced Shallow Landslide Susceptibility Mapping at Two Adjacent Catchments Using Advanced Machine Learning Algorithms. ISPRS Int. J. Geo-Inf., 9.10.20944/preprints202008.0089.v1 ↗
29. Sahin, E.K. (2020). Comparative analysis of gradient boosting algorithms for landslide susceptibility mapping. Geocarto Int., 1–25.10.1080/10106049.2020.1831623 ↗
30. Multi-geohazards susceptibility mapping based on machine learning—A case study in Jiuzhaigou, China10.1007/s11069-020-03927-8 ↗
31. Perdition of gully erosion susceptibility mapping using novel ensemble machine learning algorithms10.1080/19475705.2021.1880977 ↗
32. Zhang, Y., Ge, T., Tian, W., and Liou, Y.A. (2019). Debris flow susceptibility mapping using machine-learning techniques in Shigatse area, China. Remote Sens., 11.10.3390/rs11232801 ↗
33. Uncertainties in the shuttle radar topography mission (SRTM) Heights: Insights from the indian Himalaya and Peninsula10.1038/srep41672 ↗
34. Tethyan evolution of Turkey: A plate tectonic approach10.1016/0040-1951(81)90275-4 ↗
35. Late Cretaceous arc and back-arc formation within the southern neotethys: Whole-rock, trace element and Sr-Nd-Pb isotopic data from basaltic rocks of the Yüksekova complex (Malatya-Elazığ, SE Turkey)
36. Karakas, G., Nefeslioglu, H.A., Kocaman, S., Buyukdemircioglu, M., Yurur, T., and Gokceoglu, C. (2021). Derivation of earthquake-induced landslide distribution using aerial photogrammetry: The January 24, 2020, Elazig (Turkey) earthquake. Landslides, 1–17.10.1007/s10346-021-01660-2 ↗
37. GDAL/OGR Contributors (2021, March 03). GDAL/OGR Geospatial Data Abstraction Software Library, Open Source Geospatial Foundation. Available online: https://gdal.org.
38. Jordahl, K., Van den Bossche, J., Fleischmann, M., Wasserman, J., McBride, J., Gerard, J., Tratner, J., Perry, M., Badaracco, A.G., and Farmer, C. (2021, March 03). Geopandas/Geopandas: V0.8.1 (Version V0.8.1). Zenodo 2020. Available online: http://doi.org/10.5281/zenodo.3946761.
39. System for Automated Geoscientific Analyses (SAGA) v. 2.1.410.5194/gmd-8-1991-2015 ↗
40. The 17 March 2005 Kuzulu landslide (Sivas, Turkey) and landslide-susceptibility map of its near vicinity10.1016/j.enggeo.2005.07.011 ↗
41. (2021, March 06). ESRI ArcGIS Software. Available online: https://www.esri.com/en-us/arcgis/about-arcgis/overview.
42. Digital terrain modeling: A review of hydrological, geomorphological, and biological applications10.1002/hyp.3360050103 ↗
43. Wilson, J.P., and Gallant, J.C. (2000). Terrain Analysis Principles and Applications, John Wiley and Sons Inc.
44. Greedy function approximation: A gradient boosting machine10.1214/aos/1013203451 ↗
45. Stochastic gradient boosting10.1016/S0167-9473(01)00065-2 ↗
46. Nielsen, D. (2016). Tree Boosting with XGBoost-Why Does XGBoost Win “Every” Machine Learning Competition?. [Master’s Thesis, Department of Mathematical Sciences, Norwegian University of Science and Technology]. Available online: https://ntnuopen.ntnu.no/ntnu-xmlui/bitstream/handle/11250/2433761/16128_FULLTEXT.pdf.
47. Imbalance-XGBoost: Leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost10.1016/j.patrec.2020.05.035 ↗
48. Hastie, T., Tibshirani, R., and Friedman, J.H. (2009). 10. Boosting and Additive Trees. The Elements of Statistical Learning, Springer. [2nd ed.].10.1007/978-0-387-84858-7 ↗
49. Random search for hyper-parameter optimization
50. Scikit-learn: Machine learning in Python
51. A Unified Approach to Interpreting Model Predictions
52. From local explanations to global understanding with explainable AI for trees10.1038/s42256-019-0138-9 ↗
53. An Introduction to ROC Analysis10.1016/j.patrec.2005.10.010 ↗
54. Davis, J., and Goadrich, M. (2006, January 25–29). The Relationship between Precision-Recall and ROC Curves. Proceedings of the 23rd international conference on Machine learning, Pittsburgh, PA, USA.10.1145/1143844.1143874 ↗
55. Decision trees: A recent overview10.1007/s10462-011-9272-4 ↗
56. Input data for decision trees10.1016/j.eswa.2006.12.030 ↗