| تعداد نشریات | 286 |
| تعداد نشریات سازمان | 84 |
| تعداد شماره‌ها | 2,846 |
| تعداد مقالات | 32,300 |
| تعداد مشاهده مقاله | 41,387,042 |
| تعداد دریافت فایل اصل مقاله | 18,562,158 |
تعیین عامل‌های مؤثر و ارزیابی حساسیت به زمین لغزش با روش های جنگل تصادفی و شبکه‌ی عصبی مصنوعی در منطقه‌ی دوآب صمصامی استان چهارمحال و بختیاری | ||
| پژوهش های آبخیزداری | ||
| مقاله 5، دوره 35، شماره 1 - شماره پیاپی 134، فروردین 1401، صفحه 40-60 اصل مقاله (3.22 M) | ||
| نوع مقاله: پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22092/wmrj.2021.354962.1421 | ||
| نویسندگان | ||
| کورش شیرانی* 1؛ رضا نادری سامانی2 | ||
| 1دانشیار پژوهشکده‌ی حفاظت خاک و آبخیزداری، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران | ||
| 2کارشناس مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان اصفهان، سازمان تحقیقات، آموزش و ترویج کشاورزی، اصفهان، ایران | ||
| چکیده | ||
| زمینلغزش از جمله خطرهای زمینشناسی است که امروزه روشهای دادهکاوی مبتنی بر یادگیری ماشین برای مدلسازی و پیشبینی آن توسعه داده شده‌است. هدف‌های این پژوهش اولویت‌بندی عامل‌های مؤثر، پهنهبندی و پیشبینی حساسیت به رخ‌داد زمینلغزش با مدل‌های شبکه‌ی عصبی مصنوعی و جنگل تصادفی، و معرفی مناسبترین آنها در منطقه‌ی دوآب صمصامی استان چهارمحال و بختیاری است. برای پهنهبندی و مدلسازی از 15 عامل زمینشناسی، ریخت‌شناسی، آب‌شناسی، انسانساخت (متغیرهای مستقل) و 174 رخ‌داد زمینلغزش شناسایی و ثبت‌شده (متغیر وابسته) بهره‌گیری شد. رخ‌دادهای زمینلغزش به دو دسته‌ی داده‌ی آموزشی (70%) و آزمایشی (30 %) برای مدلسازی و اعتبارسنجی به‌شکل تصادفی تقسیم شد. ارتباط میان عامل‌های مؤثر و رخ‌دادهای لغزشی با نسبت فراوانی کمّی و وزندار شد. برای کاهش اثر همپوشانی اطلاعاتی عامل‌های مؤثر، با تحلیل وایازی چندمتغیره‌ی خطی، استقلال دادهها آزموده شد. برای مدلسازی و پهنهبندی حساسیت زمین لغزش، مدل‌های جنگل تصادفی و شبکه‌ی عصبی مصنوعی برازش و توسعه داده شد. نقشههای پهنه بندی حساسیت به‌دست‌آمده از برازش دو مدل با شاخصهای نسبت فراوانی-سطح سلول هسته، نرخ توفیق، و سطح زیر منحنی ویژگی عمل‌کرد گیرنده (AUC-ROC) ارزیابی، اعتبارسنجی و مقایسه کرده شد. نتیجه‌های بررسی عامل‌های مؤثر در هر دو مدل نشان داد که عامل‌های سنگ شناسی، کاربری و وجه شیب تأثیر بسزایی در رخ‌داد زمین لغزشها دارند و بخش زیادی (بیش از 82%) از زمینلغزشها در رده‌ها‌ی حساسیت خیلیزیاد و زیاد قرار می‌گیرند. نتیجه ارزیابی طبقهبندی و اعتبارسنجی مدلها نشان داد که دقت و کارآمدی مدل جنگل تصادفی (0/919AUC-ROC=) در پیشبینی رخ‌داد زمین لغزشها بیش‌تر از شبکه‌ی عصبی مصنوعی (0/845AUC-ROC=) است. نتیجه‌های این پژوهش ممکن است برای بهره‌گیری دستگاه‌های اجرایی در مدیریت و برنامه‌ریزی کردن طرح‌های توسعه‌یی و اجرایی عمرانی، توسعه‌ی شهری، و روستایی، برآورد دقیق‌تر در مدل‌های فرسایش و رسوب در آبخیزها، حفاظت خاک و عرصه‌های منابع طبیعی کشور سودمند باشد. | ||
| کلیدواژه‌ها | ||
| پهنهبندی؛ جنگل تصادفی؛ دوآب صمصامی؛ زمینلغزش؛ شبکه‌ی عصبی مصنوعی | ||
| عنوان مقاله [English] | ||
| Determination of Effective factors and Assessment of Landslide Susceptibility Using Random Forest and Artificial Neural Network in Doab Samsami Region, Chaharmahal va Bakhtiari Province | ||
| نویسندگان [English] | ||
| Kourosh Shirani1؛ Reza Naderi Samani2 | ||
| 1Associate Professor, Soil Conservation and Watershed Management Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran | ||
| 2Researcher, Soil Conservation and Watershed Management Research Department, Isfahan Agricultural and Natural Resources, Research and Education Center, AREEO, Isfahan, Iran | ||
| چکیده [English] | ||
| Nowadays, landslides are among the geological hazards that data mining methods based on machine learning have been developed to model and predict. This paper addresses the development of a landslide susceptibility assessment that uses machine learning techniques and GIS. Artificial Neural Network (ANN) and Random Forest (RF) were compared for the landslide spatial modeling. The landslide susceptibility zoning maps consider 15 layers including geologic, morphologic, hydrologic, man-made parameters (independent variables) for landslide susceptibility assessment, and Doab Samsami watershed in Chaharmahal Bakhtiari province was chosen for the application of models due to data availability and the 174 total landslide occurrences (dependent variables). The relationship between effective factors and landslide occurrences was quantified and weighted using frequency ratio. Data independence was tested using linear multivariate regression analysis, tolerance, and VIF indices. In order to implement and validate the model, the landslide locations were randomly divided into two subsets, namely, training (70% of the total) and testing (30%), respectively. Subsequently, RF and ANN models were developed and the landslide susceptibility zonation map was produced. Maps were evaluated and validated using frequency ratio & seed cell area index, success rate, area under of receiver Operating characteristic (AUC-ROC). Results illustrated that the two factors of slope length and topographic wetness index have multicollinearity or information overlap and were removed from the modeling process in later stages. Effective factor analysis in both models showed that lithology, land use, and aspect slope factors had a significant effect on landslides, respectively. Also, the results of classification and validation of models showed that the random forest (RF) model (AUC-ROC = 0.919) was more accurate and efficient than the artificial neural network (AUC-ROC = 0.845) for landslide occurrence prediction. The results of this study can be used by executive administrations for management and planning in development and executive plans, including rural-urban development, accurate estimation in erosion models in watersheds, soil conservation, and natural resources protection. | ||
| کلیدواژه‌ها [English] | ||
| Artificial neural network, Doab Samsami, landslide, random forest, zonation | ||
| مراجع | ||
|
Abdullahzadeh A, Onagh M, Saad Eddin A, Mustafa Zadeh R. 2014. Development of a landslide management plan under normal and critical scenarios for Ziarat Watershed, Golestan Province. Journal of Watershed Management Research, 27(3): 75–84. (In Persian). Afifi MI. 2021. Spatial analysis of landslide risk with emphasis on geomorphological factors using stochastic forest model (Case study: Larestan city in Fars Province). Physical Geography Quarterly, 14(51): 39–53. (In Persian). Arabameri AR, Shirani K, Tazeh M. 2017. Numerical analysis of effective factors in landslide occurrence and its sensitivity zonation using logistic regression and multivariate linear regression (Case study: Marbor Watershed). Journal of Range and Watershed Management (Iranian Journal of Natural Resources), 70(1): 151–168. (In Persian). Ardeshir A, Amiri M, Ghasemi Y, Errington M. 2014. Risk assessment of construction projects for water conveyance tunnels using fuzzy fault tree analysis. International Journal of Civil Engineering, 12(4): 396–412. (In Persian). Avand M, Ramazanzadeh M. 2020. Flood susceptibility mapping using random forest machine learning and generalized bayesian linear model. Journal of Environment and Water Engineering, 6(1): 73–85. (In Persian). Babolimoakher H, Taghian A, Shirani K. 2019. Assessment of landslide susceptibility zoning map using confidence factor logistic regression hybrid method by means of geomorphometric indices. Quantitative Geomorphological Research, 7(3): 91–16. (In Persian). Baharvand S, Soori S. 2016. Landslide hazard zonation using artificial neural network (Case study: Sepiddasht-Lorestan, Iran) Journal of RS and GIS for Natural Resources, pp. 15–31. (In Persian). Breiman L. 2001. Random forests. Machine Learning, 45(1): 5–32. Bui DT, Pradhan B, Lofman O, Revhaug I, Dick OB. 2012. Landslide susceptibility mapping at Hoa binh province (Vietnam) using an adaptive neuro-fuzzy inference system and GIS. Computers and Geosciences, 22(1): 85–95. Constantin M, Bednarik M, Jurchescu MC, Vlaicu M. 2010. Landslide susceptibility assessment using the bivariate statistical analysis and the index of entropy in the Sibiciu basin (Romania). Environmental Earth Science, 63(2): 397–406. Darminto MR, Chu HJ. 2019. Mapping landslide release area using random forest model, Geomatics International Conference, IOP Publishing, 389: 1–16. Emad al-Din S, Moradi A. 2018. Examining the Landslide Risk using Analytic Hierarchy Process (AHP) Artificial Neural Network (ANN) Analysis and Field Studies Aiming for Risk Reduction (Case study: Haraz Road). Quantitative Geomorphological Research, 6(4): 172–190. (In Persian). Fazlzadeh A, Haghigha J, Pourkeivan F, Ahmadian V. 2019. Investigate the operation of random forest and deep neural networks on statistical arbitrage strategy. Journal of Financial Engineering and Securities Management, 10 (40): 349–64. (In Persian). Heydari N, Habib Nejad M, Kavian A, Pourghasemi HR. 2020. Landslide susceptibility modelling using the random forest machine learning algorithm in the Watershed of Rais-Ali Delvari Reservoir. Journal of Watershed Management Research, 33(1) :2–13. (In Persian). Iverson RM, Reid ME, Lahusen RG. 1997. Debris-flow mobilization from landslides. Annual Review of Earth and Planetary Sciences, 25(1): 85–138. Kavian A, Rezaei M, Shahedi K, Hadian Amri MA. 2021. Evaluation of random forest method in landslide susceptibility mapping in Sadat Mahalleh Watershed of Sari. Journal of Watershed Management Research, 34(1): 74–92. (In Persian). Kayastha P, Dhital MR, Smedt FD. 2012. Landslide susceptibility mapping using the weight of evidence method in the Tinau Watershed, Natural Hazards, 63(2): 479–498. Keefer DK. 1984. Landslides caused by earthquakes. Geological Society of America Bulletin, 95(4): 406–421. Komac M. 2006. A landslide susceptibility model using the analytical hierarchy process method and multivariate statistics in perialpine Slovenia, Geomorphology, 74(1–4): 17–28. Mansouri M, Shirani K, Ghazifard A, Emami SN. 2017. Application of probabilistic methods in landslide hazard mapping. Geosciences, 26(102): 267–280. (In Persian). McGuire RK. 1995. Probabilistic seismic hazard analysis and design earthquakes: closing the loop. Bulletin of the Seismological Society of America, 85(5): 1275–1284. Mohammady M, Pourghasemi HR. 2017. Prioritization of landslide-conditioning factors and its landslide susceptibility mapping using random forest new algorithm. Journal of Watershed Management Research, 8(15): 161–170. (In Persian) Mokhtari M, Hosein Zadeh Z, Shirani K. 2020. A comparison study on landslide prediction through FAHP and Dempster–Shafer methods and their evaluation by P–A plots. Environmental Earth Sciences, 79(3):1–13. Moradi HR, Mohammady M, Pourghasemi HR, Mostafa Zadeh R. 2010. Landslide hazard analysis in golestan province using dempster-shafer theory. Researches in Earth Sciences, 1(3): 1–14. Moradi M, Bazyar MH, Mohammadi Z. 2012. GIS-based landslide susceptibility mapping by AHP method, a case study, Dena City, Iran. Journal of Basic and Applied Scientific Research, 2(7): 6715–6723. Mousavi SR, Parsaie F, Rahmani A, Sedri MH, Kohsar Bostani M. 2020. Spatial prediction some of the surface soil properties using interpolation and machine learning models. Electronic Journal of Soil Management and Sustainable Production, 10(3): 27–49. (In Persian). Nam K, Wang F. 2020. An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture (Japan). Geoenvironmental Disasters, 7(1): 1–16. Nefeslioglu HA, Duman TY, Durmaz S. 2008. Landslide susceptibility mapping for a part of tectonic Kelkit Valley (Turkey) Geomorphology, 94(3/4): 401–418. Nhu VH, Shirzadi A, Shahabi H, Singh SK, Al-Ansari N, Clague JJ, Jaafari A. Chen W, Miraki S, Dou G, Luu C, Górski K, Pham BT, Nguyen HD, Ahmad BB. 2020. Shallow landslide susceptibility mapping: A comparison between logistic model tree, logistic regression, naïve bayes tree, artificial neural network, and support vector machine algorithms, International Journal of Environmental Research and Public Health, 17(8): 1–30. Oliveira GG, Chimelo Ruiz F, Guasselli LA, Haetinger C. 2019. Random forest and artificial neural networks in landslide susceptibility modeling: a case study of the fão river basin (Brazil). Natural Hazards, 99(2): 1049–1073. Pailoplee S, Sugiyama Y, Charusiri P. 2010. Probabilistic seismic hazard analysis in Thailand and adjacent areas by using regional seismic source zones. Terrestrial, Atmospheric and Oceanic Sciences, 21(5): 757–766. Parise M. 2002. Landslide hazard zonation of slopes susceptible to rock falls and topples. Natural Hazards and Earth System Sciences, 2(1/2):37–49. Pasha H, Sorbi A. 2018. Landslide risk assessment in Qazvin-Rasht quadrangle zone (Iran). Journal of Geoscience, 27(106): 89–98. (In Persian). Popescu ME. 1994. A suggested method for reporting landslide causes. Bulletin of the International Association of Engineering Geology-Bulletin, 50(1): 71–74. Pradhan B, Lee S. 2010. Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling. Environmental Modelling & Software. 25(6): 747–759. Schwartz DP, Coppersmith KJ. 1984. Fault behavior and characteristic earthquakes: Examples from the Wasatch and San Andreas Fault zones. Journal of Geophysical Research, 89(B7): 5681–5698. Sepah vand AR, Moradi HR, Abdolmaleki P. 2017. Landslide hazard mapping using the artificial neural network a part of haraz watershed, Journal of Watershed Management Research, 29(4): 9–19. (In Persian). Shirani K, Heydari F, Arabameri, A. 2018. Comparison of artificial neural network and multivariate regression methods in landslide hazard zonation (Isfahan). Watershed Engineering and Management, 9(4): 451–464. (In Persian). Shirani K. Pasandi M. Arabameri A. 2018. Landslide susceptibility assessment by dempster–shafer and index of entropy models, sarkhoun basin (Iran). Natural Hazards, 93(3): 1379–1418. Shirani K, Seif A. 2012. Landslide hazard zonation by using statistical methods. Journal of Geoscience, 22(85):149–158. (In Persian). Shirani K, Seif A, Nasr A. 2013. Investigation of effective’s parameters on mass movement by using of landslide hazard zonation maps. Journal of Geoscience, 23(89): 3–10. (In Persian). Soori S. 2012. Landslide hazard zonation using artificial neural networks A case study: Keshvari watershed (Nozhiyan). Journal of Engineering Geology, 5(2): 1269–1286. (In Persian). Suzen ML, Doyuran V. 2004. A comparison of the GIS based landslide susceptibility assessment methods: Multivariate versus bivariate. Environmental Geology, 45(5): 665–679. Swets JA. 1988. Measuring the accuracy of diagnostic systems. Science, 240(4857): 1285–1293. Taalab K, Cheng T, Zhang Y. 2018. Mapping landslide susceptibility and types using random forest, Big Earth Data, 2(2): 159–178. Talebi A, Goodarzi S, Pourghsemi HR. 2018. Investigation of the possibility of landslide hazard mapping using the random forest algorithm. Journal of Natural Environmental Hazards, 7(16): 45–64. (In Persian). Varnes, DJ. 1984. Landslide Hazard Zonation: A Review of Principles and Practice, Natural Hazards. UNESCO, Paris. Yalcin A. 2007. The effects of clay on landslides: A case study. Applied Clay Science, 38(1/2): 77–85. Yilmaz C, Topal T, Süzen ML. 2012. GIS-based landslide susceptibility mapping using bivariate statistical analysis in Devrek (Zonguldak-Turkey). Environmental Earth Sciences, 65(7): 2161–2178. Yilmaz I. 2009. Landslide susceptibility mapping using frequency ratio. logistic regression. artificial neural networks and their comparison: a case study from Kat landslides (Turkey). Computers and Geosciences, 35(6): 1125–1138. Youssef AM, Pourghasemi HR. 2021. Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha basin, asir region. (Saudi Arabia). Geoscience Frontiers, 12(2): 639–655. Zhou C, Yin K, Cao Y, Ahmed B, Li Y, Catani F, Pourghasemi HR. 2017. Landslide susceptibility modeling applying machine learning methods: a case study from Longju in the three gorges reservoir area (China). Computers and Geosciences, 112(1): 23–37. | ||
|
آمار تعداد مشاهده مقاله: 918 تعداد دریافت فایل اصل مقاله: 976 |
||