Safety in Technosphere Safety in Technosphere Безопасность в техносфере 1998-071X 13652 10.12737/22192 Чрезвычайные ситуации Emergency Чрезвычайные ситуации Methods of Evaluation for Region’s Landslide Susceptibility. Short Overview Методы оценки оползневой чувствительности региона. Краткий обзор https://orcid.org/0000-0002-7368-3303 Кривогуз Денис Олегович Krivoguz Denis Olegovich krivoguzdenis@gmail.com

кандидат географических наук;

candidate of geographical sciences;

 Russian Federal Research Institute Of Fisheries and Oceanography (VNIRO) Rostov-on-Don Россия Russian Federal Research Institute Of Fisheries and Oceanography (VNIRO) Rostov-on-Don Russian Federation 05 05 1905 05 05 1905 6 3 57 60 https://naukaru.ru/en/nauka/article/13652/view

В статье рассматриваются современные подходы к определению оползневой чувствительности региона. Дано описание наиболее широко применяемых методик оценки оползневой чувствительности: логистической регрессии, метода весомости признака, линейного дискриминантного анализа и применения искусственных нейронных сетей. В работе рассматриваются их положительные и отрицательные стороны. Выделены наиболее приемлемые методики для различных условий анализа. Сделан вывод, что к наиболее приемлемым методикам анализа при большом количестве исходных данных о регионе исследования относятся метод логистической регрессии и метод весомости признака. С их помощью достигаются наиболее точные результаты. При недостаточной информации целесообразнее использовать линейный дискриминантный анализ и искусственные нейронные сети, что сведет к минимуму потенциальные неточности анализа.

Modern approaches to the region’s landslide susceptibility assessment are considered in this paper. Have been presented descriptions of the most used techniques for landslide susceptibility assessment: logistic regression, indicator validity, linear discriminant analysis and application of artificial neural networks. These techniques’ advantages and disadvantages are discussed in the paper. The most suitable techniques for various conditions of analysis have been marked. It has been concluded that the most acceptable techniques of analysis for a large number of input data related to the studied region are the method of logistic regression and indicator validity method. With these methods the most accurate results are achieved. When there is a lack of information, it is more expedient to use linear discriminant analysis and artificial neural networks that will minimize potential analysis inaccuracies.

 оползневая чувствительность метод логистической регрессии метод весомости признака линейный дискриминантный анализ искусственные нейронные сети геоинформационные системы. landslide susceptibility method of logistic regression indicator validity method linear discriminant analysis artificial neural networks geo information systems.

Проблема определения оползневой чувствительности широко рассматривается во всем мире. Авторы применяют различные методики для ее определения, основанные на разных методах статистического анализа.

Corominas J. et al. Recommendations for the quantitative analysis of landslide risk // Bull Eng Geol Env. 2014. Vol. 73. P. 209-263. Corominas J. et al. Recommendations for the quantitative analysis of landslide risk // Bull Eng Geol Env. 2014. Vol. 73. P. 209-263. Aydın A., Eker R. Fuzzy rule-based landslide susceptibility mapping in Yığılca Forest District (Northwest of Turkey) // J. J. Fac. For. Istanbul Univ. Anahtar Kelimeler FIS. 2016. Vol. 66, № 662. P. 559-571. Aydın A., Eker R. Fuzzy rule-based landslide susceptibility mapping in Yığılca Forest District (Northwest of Turkey) // J. J. Fac. For. Istanbul Univ. Anahtar Kelimeler FIS. 2016. Vol. 66, № 662. P. 559-571. Bilaşco Ş. et al. Statistical model using GIS for the assessment of landslide susceptibility. Case-study: The Someş Plateau // Journ. Geogr. 2011. Vol. 55, № 2. P. 91-101. Bilaşco Ş. et al. Statistical model using GIS for the assessment of landslide susceptibility. Case-study: The Someş Plateau // Journ. Geogr. 2011. Vol. 55, № 2. P. 91-101. Vahidnia M. H. et al. Landslide Hazard Zonation Using Quantitative Methods in GIS // Int. J. Civ. Eng. 2009. Vol. 7, № 3. P. 176-189. Vahidnia M. H. et al. Landslide Hazard Zonation Using Quantitative Methods in GIS // Int. J. Civ. Eng. 2009. Vol. 7, № 3. P. 176-189. Feizizadeh B., Blaschke T. Uncertainty Analysis of GISbased Ordered Weighted Averaging Method for Landslide Susceptibility Mapping in Urmia Lake Basin, Iran. Feizizadeh B., Blaschke T. Uncertainty Analysis of GISbased Ordered Weighted Averaging Method for Landslide Susceptibility Mapping in Urmia Lake Basin, Iran. Baban S. M.J., Sant K. J. Mapping landslide susceptibility for the Caribbean island of Tobago using GIS, multi-criteria evaluation techniques with a varied weighted approach // Caribb. J. Earth Sci. 2005. Vol. 38. P. 11-20. Baban S. M.J., Sant K. J. Mapping landslide susceptibility for the Caribbean island of Tobago using GIS, multi-criteria evaluation techniques with a varied weighted approach // Caribb. J. Earth Sci. 2005. Vol. 38. P. 11-20. Tazik E. et al. Landslide susceptibility mapping by combining the three methods Fuzzy Logic, Frequency Ratio and Analytical Hierarchy Process in Dozain basin // ISPRS - Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2014. Vol. XL-2/W3. P. 267-272. Tazik E. et al. Landslide susceptibility mapping by combining the three methods Fuzzy Logic, Frequency Ratio and Analytical Hierarchy Process in Dozain basin // ISPRS - Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2014. Vol. XL-2/W3. P. 267-272. Huang J. Investigation on landslide susceptibility using remote sensing and GIS methods. Hong Kong Baptist University, 2014. 118 p. Huang J. Investigation on landslide susceptibility using remote sensing and GIS methods. Hong Kong Baptist University, 2014. 118 p. Coe J. A. et al. Landslide susceptibility from topography in Guatemala. Taylor & Francis Group, 2004. Vol. 1. P. 69-78. Coe J. A. et al. Landslide susceptibility from topography in Guatemala. Taylor & Francis Group, 2004. Vol. 1. P. 69-78. Pradhan B. et al. Application of data mining model for landslide hazard mapping // The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B8. Beijing, 2008. P. 187-196. Pradhan B. et al. Application of data mining model for landslide hazard mapping // The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B8. Beijing, 2008. P. 187-196. Ayalew L., Yamagishi H., Ugawa N. Landslide susceptibility mapping using GIS-based weighted linear combination, the case in Tsugawa area of Agano River, Niigata Prefecture, Japan // Landslides. 2004. Vol. 1, № 1. P. 73-81. Ayalew L., Yamagishi H., Ugawa N. Landslide susceptibility mapping using GIS-based weighted linear combination, the case in Tsugawa area of Agano River, Niigata Prefecture, Japan // Landslides. 2004. Vol. 1, № 1. P. 73-81. Akbari A. et al. Landslide Susceptibility Mapping Using Logistic Regression Analysis and GIS Tools // Electron. J. Geotech. Eng. 2014. Vol. 19. P. 1687-1696. Akbari A. et al. Landslide Susceptibility Mapping Using Logistic Regression Analysis and GIS Tools // Electron. J. Geotech. Eng. 2014. Vol. 19. P. 1687-1696. Mancini F., Ceppi C., Ritrovato G. GIS and statistical analysis for landslide susceptibility mapping in the Daunia area, Italy // Nat. Hazards Earth Syst. Sci. 2010. Vol. 10. P. 1851-1864. Mancini F., Ceppi C., Ritrovato G. GIS and statistical analysis for landslide susceptibility mapping in the Daunia area, Italy // Nat. Hazards Earth Syst. Sci. 2010. Vol. 10. P. 1851-1864. Ercanoglu M. Landslide susceptibility assessment of SE Bartin (West Black Sea region, Turkey) by artificial neural networks // Nat. Hazards Earth Syst. Sci. 2005. Vol. 5. P. 979-992. Ercanoglu M. Landslide susceptibility assessment of SE Bartin (West Black Sea region, Turkey) by artificial neural networks // Nat. Hazards Earth Syst. Sci. 2005. Vol. 5. P. 979-992. Ramos-Cañón A.M. et al. Linear discriminant analysis to describe the relationship between rainfall and landslides in Bogotá, Colombia // Landslides. 2016. Vol. 13, № 4. P. 671-681. Ramos-Cañón A.M. et al. Linear discriminant analysis to describe the relationship between rainfall and landslides in Bogotá, Colombia // Landslides. 2016. Vol. 13, № 4. P. 671-681. Atkinson P. M., Massari R. Generalised linear modelling of susceptibility to landsliding in the Central Apennines, Italy // Comput. Geosci. 1998. Vol. 24, № 4. P. 373-385. Atkinson P. M., Massari R. Generalised linear modelling of susceptibility to landsliding in the Central Apennines, Italy // Comput. Geosci. 1998. Vol. 24, № 4. P. 373-385. Huang Y., Wänstedt S. The introduction of neural network system and its applications in rock engineering // Eng. Geol. Elsevier, 1998. Vol. 49, № 3. P. 253-260. Huang Y., Wänstedt S. The introduction of neural network system and its applications in rock engineering // Eng. Geol. Elsevier, 1998. Vol. 49, № 3. P. 253-260.