ارزیابی روش جنگل تصادفی در تهیه نقشه حساسیت به زمین‌لغزش در آبخیز سادات‌محله، ساری

نوع مقاله : پژوهشی

نویسندگان

1 استاد گروه علوم و مهندسی آبخیزداری، دانشگاه علوم کشاورزی و منابع طبیعی ساری

2 دانش‌آموخته‌ی کارشناسی‌ارشد علوم و مهندسی آبخیزداری، دانشگاه علوم کشاورزی و منابع طبیعی ساری

3 دانشیار گروه علوم و مهندسی آبخیزداری، دانشگاه علوم کشاورزی و منابع طبیعی ساری

4 استادیار بخش تحقیقات حفاظت خاک و آبخیزداری مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی مازندران، سازمان تحقیقات آموزش و ترویج کشاورزی، ساری، ایران

چکیده

زمین‌لغزش یکی از ناپایداری‌های دامنه‌یی است که هرساله زیان‌های مالی و تلفات جانی فراوانی را بر زندگی انسان‌ها وارد می­کند. هدف از این پژوهش ارزیابی‌کردن حساسیت به زمین‌لغزش با روش جنگل تصادفی در آبخیز سادات محله‌ی ساری است. عامل‌هایی مانند ارتفاع از تراز دریا، زمین‌شناسی، کاربری زمین، شیب (شامل درجه، جهت، طول و شکل)، فاصله از عنصرهای خطی چون گسل، آب‌راه، و جاده، و شاخص پوشش گیاهی تفاضلی بهنجار­شده ویژگی‌های مؤثر در وقوع زمین‌لغزش گرفته شد. پهنه‌بندی حساسیت زمین‌لغزش در نرم‌افزار R و آرک جی‌آی‌اس 10.3 انجام شد. برای تعیین‌کردن وزن هریک از عامل‌ها و طبقات تأثیرگزار در پهنه‌بندی حساسیت زمین‌لغزش و اعتبارسنجی نقشه‌های پیش‌بینی توان زمین‌لغزش به­ترتیب روش نسبت فراوانی و شاخص ویژگی‌های عامل نسبی  ROC به‌کار گرفته شد. نتیجه‌ها نشان داد که پوشش گیاهی و کاربری زمین به­ترتیب بیش‌ترین تأثیر را بر وقوع زمین‌لغزش در منطقه  داشت. نقشه‌ی حساسیت زمین‌لغزش به پنج طبقه‌ی حساسیت خیلی‌کم (3/85 %)، کم (5/38 %)، متوسط (23/08 %)، زیاد (50 %) و خیلی‌زیاد (7/69 %) تقسیم شد. نتیجه‌های اعتبارسنجی نقشه‌های پهنه‌بندی حساسیت زمین‌لغزش نشان داد که سطح زیر منحنی برای روش جنگل تصادفی 0/709 و خطای معیاری آن 0/10 است. می‌توان نتیجه گرفت که دقت روش جنگل تصادفی در تهیه‌کردن نقشه‌ی حساسیت زمین‌لغزش پذیرفتنی است. نقشه‌ی تعیین حساسیت زمین‌لغزش اطلاعات کامل و جامعی را برای مدیران منابع طبیعی در مدیریت‌کردن منطقه‌های حساس به زمین‌لغزش فراهم می­کند.

کلیدواژه‌ها

عنوان مقاله [English]

Evaluation of Random Forest Method in Landslide Susceptibility Mapping in Sadat Mahalleh Watershed of Sari

نویسندگان [English]

  • Ataollah Kavian 1
  • Mohammad Rezaei 2
  • Kaka Shahedi 3
  • Mohammad Ali Hadian Amri 4
1 Professor, Department of Watershed Management Engineering, Sari University of Agricultural Sciences and Natural Resources, Sari, Iran
2 M.Sc. Student, Department of Management Engineering, Sari University of Agricultural Sciences and Natural Resources
3 Associate Professor, Department of Watershed Management Engineering, Sari University of Agricultural Sciences and Natural Resources, Sari, Iran
4 Assistant Professor, Soil Conservation and Watershed Management Department, Mazandaran Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Sari, Iran
چکیده [English]

Landslides are one of the major types of slope instability which cause enormous financial losses and casualties; therefore, it is imperative to consider them in the study of geomorphology, erosion and sedimentation in important watershed. The aim of the present study was to investigate and rank the landslide susceptibility using a random forest method in the Sadat Mahalleh Watershed, Sari. Elevation from the sea level, geology, land use, slope (degree, direction, shape and length), distance from linear elements such as faults, streams and roads, normalized difference vegetation index and slope form were considered as effective parameter in the landslide occurrence. Zoning landslide sensitivity was achieved by coding in the R and GIS10.3 soft wares. In order to determine the weight of each of the factors and classes effective in zoning the landslide sensitivity and validation of landslide potential prediction maps, the abundance ratio method and the receiver operating characteristics (ROC) were used. The results indicated that among the effective factors, vegetative cover and land use, had the most paramount impact on the landslide occurrence in the study area. A landslide sensitivity map was prepared using the random forest method by dividing into five class, namely: very low (3.85%), low (5.38%), moderate (23.08%), high (50%) and very high (7.69%) sensitivities. Validation of the results of the landslide sensitivity zoning maps, using the relative factor characteristics index diagram, indicated that the area under the curve (AUC) for random forest method was 0.709 and its standard error was 0.10. It is reasonable to claim that the forest method provided an acceptable accuracy for mapping the landslide sensitivity. A landslide sensitivity map provides prone complete and accurate information for natural resource managers to detect the landslide areas.

کلیدواژه‌ها [English]

  • Frequency ratio method
  • susceptibility zoning
  • validation
  • vegetation index

مراجع

Abadinejad SA, Yamani M, Maghsoudi M, Shadfar S. 2007. Evaluation of Fuzzy Logic Operators in landslide analysis case study: Shirood Watershed. Iranian Journal of Watershed Management Science, 1(2):39–44. (In Persian).
Abadini M, Fathi MH, Bahashti javid A. 2015. Landslide hazard zonation using fuzzy logic model (Case study: Gory hay River Basin). Conference on Geographical Sciences of Iran, 31(1): 43–64. (In Persian).
Ahmadi A. 2007. Applied Geomorphology of Iran, Water Erosion (1). University of Tehran Publications, 715 p. (In Persian).
Akgun A, Kincaland C, Pradhan B. 2011. Application of remote sensing data and GIS for landslide risk assessment as an environmental threat to Izmir city (West Turkey). Environmental Monitoring and Assessment, 184(9): 5453–5470.
Akgun A, Sezer EA, Nefeslioglu HA, Gokceoglu C, Pradhan B. 2012. An easy-to-use MATLAB program (Maylands) for the assessment of landslide susceptibility using a Mamdani fuzzy algorithm. Computers & Geosciences, 38(1): 23–34.
Althuwaynee OF, Pradhan B, Park HJ, Lee JH. 2014. A novel ensemble decision tree-based Chi squared Automatic Interaction Detection (CHAID) and multivariate logistic regression models in landslide susceptibility mapping. Landslides, 11(6): 1063–1078.
Amir Ahmadi A, Kamrani Dalir H, Sadeghi M. 2011. Landslide Hazard Zonation, through hierarchical analysis method (HAM), the case of chelav.  Geography, 8(27): 182–203.
Asghari S, Khodabandehlou B, Naseri A, Moradi A. 2019.  Extracting Land Use Map based on a comparison between Pixel-Based and Object-Oriented Classification Methods. Case study: Zanjan City Scientific - Research Quarterly of Geographical Data (SEPEHR), 28(110):195–208. (In Persian).
Bai SB, Wang J, Lü GN, Zhou PG, Hou SS, Xu SN. 2010. GIS-based logistic regression for landslide susceptibility mapping of the Zhongxian segment in the Three Gorges area, China. Geomorphology, 115(1–2): 23–31.
‏Breiman L, HFriedman J, Olshen RA, Stone CJ. 1984. Classification and regression trees. Chapman & Hall, New York.
Caniani D, Pascale S, Sado F, Sole A. 2008. Neural networks and landslide susceptibility: a case study of the urban area of Potenza. Natural Hazards, 45 (1): 55–72.
Catani F, Lagomarsino D, Segoni S, Tofani V. 2013. Landslide susceptibility estimation by random forests technique: sensitivity and scaling issues. Natural Hazards Earth System Science, 13: 2815–2831.
Chauhan S, Sharma M, Arora MA. 2010. Landslide susceptibility zonation of the Chamoli region, Garhwal Himalayas, using logistic regression model. Landslides, 7(4): 411–423.
Chen W, Li X, Wang Y, Chen G, Liu S. 2014. Forested landslide detection using LiDAR data and the random forest algorithm: A case study of the Three Gorges. China. Remote Sensing of Environment, 152: 291–301.
Demir G, Aytekin M, Akgun A, Ikizler SB, Tatar O. 2013. A comparison of landslide susceptibility mapping of the eastern part of the North Anatolian Fault Zone (Turkey) by likelihood-frequency ratio and analytic hierarchy process methods. Natural Hazards, 65(3): 1481–1506.
Devkota KC, Regmi AD, Pourghasemi HR, Yoshida K, Pradhan B, Ryu IC, Dhital MR, Althuwaynee OF. 2013. Landslide susceptibility mapping using certainty factor, index of entropy and logistic regression models in GIS and their comparison at Mugling-Narayanghat road section in Nepal Himalaya. Natural Hazards, 65(1): 135–165.
Eemini L, Catani F, Casagli N. 2005. Artificial neural networks applied to landslide susceptibility assessment. Geomorphology, 66(1–4): 327–343.
Garaei P, Mousavi SR, Kavian A. 2009. Regional Modeling of Landslide Hazard, Using Multivariate Statistic Method in Lajemrood –Sari Basin. Geosciences, 19(73): 29–36.
Glade T. 1997. Establishing the frequency and magnitude of landslide-triggering rainstorm events in New Zealand. Environmental Geology, 35(2–3): 160–174.
Geographical Organization of the Army. 2006. Topographic maps of Iran. Sheet No. 37. Armed Forces Publications. Tehran.
Guns M, Vanacker V. 2014. Shifts in landslide frequency–area distribution after forest conversion in the tropical Andes. Anthropocene, 6: 75–5.
Hastie T. 2001. The elements of statistical learning: data mining, inference, and prediction, In Springer series in statistics New York, xvi: 533 p.
Ilanlo M, Moghimi E, Servati MR, Ghahroodi tali M. 2010. Hazard zonation of mass movements using fuzzy logic method (case study: Sierra catchment). Journal of Studies of Human Settlements Planning, 5(11): 12–26. (In Persian).
 Jaafari A, Mafi Gholami D. 2017. Wildfire hazard mapping using an ensemble method of frequency ratio with Shannon’s entropy. Iranian Journal of Forest and Poplar Research, 25(2): 232–243. (In Persian).
 Jaafari A, Najafi A, Pourghasemi H.R, Rezaeian J, Sattarian A. 2014. GIS-based frequency ratio and index of entropy models for landslide susceptibility assessment in the Caspian forest, northern Iran. International Journal of Environmental Science and Technology, 11(4): 909–926.
Jebur MN, Pradhan B, Shafri HZ.M, Yusoff ZM, Tehrany MS. 2015. An integrated user-friendly ArcMap tool for bivariate statistical modeling in geoscience applications. Geoscientific Model Development, 8(3): 881–891.
Kavian A, Safari A, Parsakhoo A. 2016. Comparison of soil loss from experimental plots established in different parts of a forest road. Journal of Water and Soil Conservation, 23(3): 25–45.
Kelarestaghi A, Habibnejad M, Ahmadi H, 2007. A study of landslide occurrence in relation to land use changes and road construction: Case study Tadjan Watershed, Sari. Geographical Research Quarterly, 39(62): 81–91. (In Persian).
Koehorst BAN, Kjekstad O, Patel D, Lubkowski Z, Knoeff JG, Akkerman GJ. 2005. Work Package 6, Determination of Socio-Economic Impact of Natural Disasters. Assessing Socio-Economic Impact in Europe. 173 p.
Komac M. 2006. A landslide susceptibility model using the analytical hierarchy process method and multivariate statistics in per alpine Slovenia. Geomorphology, 74(1): 17–28.
Le EM, Jones, DK. 2004. Landslid risk assessment. London: Thomas Telford. 454 p.
Lieb M, Glaser B, Huwe B. 2012. Uncertainty in the spatial prediction of soil texture: comparison of regression tree and Random Forest models. Geoderma, 170: 70–79.
Lin WT, Chou W, Lin CY. 2008. Earthquake-induced landslide hazard and vegetation recovery assessment using remotely sensed data and a neural network-based classifier: A case study in central Taiwan. Natural Hazards, 47(3): 331–347.
Mathew J, Jha VK, Rawat GS. 2007. Application of binary logistic regression analysis and its validation for landslide susceptibility mapping in part of Garhwal Himalaya, India. International Journal of Remote Sensing, 28(10): 2257–2275.
Mohamadnia M, Amirahmadi A, Akbari E, Bahrami SH. 2016. Landslide hazard zonation in Binalud Mountains by Bayesian method (Torghabeh- Darrod new Transit road). Journal of Geographic Space, 16(55):217–238. (In Persian).
Mohammady M, Pourghasemi HR, Pradhan B. 2012. Landslide susceptibility mapping at Golestan Province, Iran: A comparison between frequency ratio, Dempster-Shafer and weights of evidence models. Journal of Asian Earth Sciences, 61: 221–236.
Mohammady M, Pourghasemi HR, Moradi HR, Fiznia S. 2007. Landslide hazard analysis in GIS environment and its application in soil and water conservation, 4th National Conference on Watershed Management Science and Engineering of Iran Watershed Management, 6 p. (In Persian).
Mohammady M, Pourghasemi HR. 2017. Prioritization of landslide-conditioning factors and its landslide susceptibility mapping using random forest new algorithm (Case study: A part of Golestan Province). Journal of Watershed Management Research. 8 (15):161–170. (In Persian).
Mokhtari D, Ebrahimy H, Salmani, S. Land subsidence susceptibility modeling using random forest approach (Case study: Tasuj plane catchment). RS & GIS for Natural Resources, 10(3): 93–105. (In Persian).
Mosaffaie J, Ownegh M, Mesdaghi M, Shariat Jafari M. 2009. Comparing the efficiency of statistical and empirical landslide hazard zonation models in Alamout watershed. Journal of Water and Soil Conservation, 16: 43–61.
Mosaffaie J, Ownegh M. 2011. Landslide hazard zonation by AHP and regression model, Case study: Alamout Watershed. Watershed Engineering and Management, 3 (1): 149–158. (In Persian).
Mosavi Khatir SZ, Kavian A, Soleimani K. 2009. Landslide susceptibility mapping in Sajaroud Basin using logistic regression Model. Journal of Water and Soil Science (Journal of Science and Technology of Agriculture and Natural Resources), 14 (53): 99–112. (In Persian).
National Cartographic Center. 1949. Geological Survey & Mineral Exploration of IRAN. Tehran Iran.
Nandi A, Shakoor A. 2010. A GIS-based landslide susceptibility evaluation using bivariate and multivariate statistical analyses. Engineering Geology, 110(1): 11–20.
Nefeslioglu HA, Gokceoglu C, Sonmez H. 2008. An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps. Engineering Geology, 97 (3–4): 171–191.
Oh H-J, Pradhan B. 2011. Application of a neuro-fuzzy model to landslide susceptibility mapping for shallow landslides in a tropical hilly area. Computers & Geosciences, 37 (9): 1264–1276.
Ownegh M. 2004. Assessing the Applicability of Australian Landslide databases for hazard management. In 13 th International Soil Conservation Organization Conference-Brisbane, July. Conserving Soil and Water for Society: Sharing Solutions.
Pachauri AK, Pant M. 1992. Landslide hazard mapping based on geological attributes. Engineering Geology, 32(1–2): 81–100.
Pachauri AK, Gupta PV, Chander R. 1998. Landslide zoning in a part of the Garhwal Himalayas. Environmental Geology, 36: 325–334.
Pahlavan Rad MR, Khormali F, Toomanian N, Kiani F, Komaki ChB. 2015. Digital soil mapping using Random Forest model in Golestan Province. Journal of Water and Soil Conservation, 21(6): 73–93. (In Persian).
Peters J, Verhoest N, Samson R, Boeckx P, De Baets B. 2008. Wetland vegetation distribution modelling for the identification of constraining environmental variables. Landscape Ecology, 23 (9): 1049–1065.
Pourghasemi HR, Kerle N. 2016. Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran. Environmental Earth Sciences, 75(185): 1–17.
Pourghasemi HR, Moradi HR, Fatemi Aghda SM. 2013. Landslide susceptibility mapping by binary logistic regression, analytical hierarchy process, and statistical index models and assessment of their performances. Nat Hazards, 69:749–779.
Pourghasemi HR, Moradi HR, Mohammadi M,   Mostafazadeh R,  Goli Jirandeh A. 2013.  Landslide hazard zoning using bayesian theory.  Journal of Water and Soil Science, 16(62): 109–121. (In Persian).
Pourghasemi HR, Moradi HR, Mohammadi M. 2014. Landslide susceptibility zoning, using weight of evidence probabilistic model. Engineering Journal of Geospatial Information Technology, 1(2): 69–80. (In Persian).
Pradhan B, 2013. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Computer & Geoscience, 51: 350–365.
Pradhan B, Lee S. 2010. Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models. Environmental Earth Sciences, 60(5): 1037–1054.
Pradhan B, Lee S. 2010. Landslide susceptibility assessment and factor effect analysis: Back propagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modeling. Environmental Modeling and Software, 25 (6): 747–759.
Rahmati O, Pourghasemi HR. Melesse AM. 2016. Application of GIS-based data-driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran. Catena, 137: 360–372.
Rajabi M, Feyzolahpour M. 2014. Zoning the Landslides of Givichay River Basin by Using Multi-Layer Perceptron Model. Geography and Development Iranian Journal, 2(36): 161–180. (In Persian).
Rastegarnia M, Sanati A. 2016. Determination of hydrological units using random forest method for one of Iran's oil reservoirs. Promotional Science Monthly Oil and Gas Exploration and Production, 135: 55–59. (In Persian).
Safari A, Moghimi A. 2011. Geomorpholigic assessment of urban development and vulnerability caused by landslide in mountainous hillsides of Tehran Metropolis. Physical Geography Research Quarterly, 41(67): 53–71.
Sah MP, Mazari RK. (1998). Anthropogenic ally accelerated mass movement, Kulu Valley, Himachal Pradesh, India. Geomorphology, 26(1), 123–138.
Samareh H, Rezazadeh R. 2012. Landslide hazard spatial analysis using Kanagava model. 5th National Conference on Watershed Management and Water Resources Management, Gorgan University of Agricultural Sciences & Natural Resources, IRAN. (In Persian).
ShariatJafari M. 1996. Landslide (principles and basics of stability of natural slopes). Sazeh Publications, 218 p. (In Persian).
Shirani K, Chavoshi S, Ghayoumian J. 2006. Investigation and evaluation of landslide hazard zonation methods in Marbor River Basin. Research Journal of University of Isfahan "SCIENCE", 23(1): 22–38. (In Persian).
Stumpf A, Kerle N. 2011. Object-oriented mapping of landslides using Random Forests. Remote Sensing of Environment, 115 (10): 2564–2577.
Talebi A, Goudarzi S, Pourghsemi HR. 2018. Investigation of the possibility of landslide hazard mapping using the Random Forest algorithm (Case study: Sardarabad Watershed, Lorestan Province). Journal of Natural Environmental Hazards, 7(16): 45–64. (In Persian).
Trigila A, Catani F, Casagli N, Crosta G, Esposito C, Frattini P, Iadanza C, Lagomarsino D, Lari S, Scarascia Mugnozza G, Segoni S, Spizzichino D, Tofani V. 2012. The landslide susceptibility map of Italy at 1: 1 million scale. In EGU General Assembly Conference Abstracts, 22–27 April, Vienna, Austria.
Trigila A, Iadanza C, Esposito C, Scarascia-Mugnozza G. 2015. Comparison of logistic regression and random forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy). Geomorphology, 249: 119–136.
United States Geological Survey. 2020. https://earthexplorer.usgs.gov/. Accessed: 20/10/2019.
Urmiae A, Safaei M. 1996. Comparison of two methods of Kanagawa and Anbalagan in landslide hazard zonation in Nkarood watershed. Proceedings of the Second Iranian Geological Society Conference, pp. 23–40. (In Persian).
Varnes DJ. 1984. Landslide hazard zonation: A review of principles and practice (No. 3).
Vorpahl P, Elsenbeer H, Marker M, Schroder B. 2012. How can statistical models help to determine driving factors of landslides? Ecological Modelling, 239: 27–39.
Yalcin A, Reis S, Aydinoglu AC, Yomralioglu T. 2011. A GIS-based comparative study of frequency ratio, analytical hierarchy process, bivariate statistics and logistics regression methods for landslide susceptibility mapping in Trabzon, NE Turkey. Catena, 85(3): 274–287.
Yesilnacar EK. 2005.The application of computational intelligence to landslide susceptibility mapping in Turkey, Ph.D. Thesis Department of Geomatics the University of Melbourne, 423 p.
Youssef AM, Pourghasemi HR, Pourtaghi ZS, Al-Katheeri MM. 2015. Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia. Landslides, 13(5): 839–856.
Zabihi M, Pourghasemi HR,  Behzadfar M. 2015. Groundwater potential mapping using Shannon's Entropy and random forest models in the Bojnourd Township. Iranian Journal of Eco Hydrology, 2(2): 221–231. (In Persian).
Zongji Y, Jianping Q, Xiaogang Z. 2010. Regional landslide zonation based on entropy method in Three Gorges area, China. In Fuzzy Systems and Knowledge Discovery (FSKD). Seventh International Conference 10–12 Aug, Yantai, China.

فایل ها

سابقه مقاله

  • تاریخ دریافت: 30 دی 1398
  • تاریخ بازنگری: 24 اردیبهشت 1399
  • تاریخ پذیرش: 30 شهریور 1399

هم رسانی

ارجاع به این مقاله

آمار