با همکاری انجمن آبخیزداری ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش‌آموخته دکتری علوم و مهندسی آبخیزداری، دانشکده منابع طبیعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری

2 استاد دانشکده منابع طبیعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری، ایران

3 دانش‌آموخته کارشناسی ارشد آبخیزداری، دانشکده منابع طبیعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری

4 استاد، دانشکده کشاورزی، دانشگاه شیراز، ایران

5 استاد، دانشکده ژئومورفولوژی و علوم دریایی، دانشگاه پالرمو، ایتالیا

6 دانشیار، دانشکده منابع طبیعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری، ایران

چکیده

ناپایداری­‌های دامنه و زمین­‌لغزش­‌ها از مخاطرات مهمی برای فعالیت­‌های  انسانی هستند که اغلب سبب از دست رفتن منابع اقتصادی، خسارات به اموال و تأسیسات می­شوند. این مخاطرات در شیب­‌های طبیعی و یا شیب­‌هایی که به دست انسان تغییر یافته­‌اند، اتفاق می­‌افتد. در پژوهش حاضر، به­‌منظور مدل‌سازی و تهیه نقشه حساسیت‌­پذیری خطر زمین‌لغزش حوزه آبخیز گرگان‌رود از مدل بیشینه آنتروپی که یکی از مدل­‌های پیشرفته داده‌­کاوی است، استفاده شده است. در مرحله اول نقشه پراکنش زمین‌لغزش‌­های منطقه شامل 351 نقطه لغزشی بود تهیه شد. برای مدل­‌سازی بیشینه آنتروپی 18 متغیر مستقل به‌­عنوان عوامل پیش‌­بینی کننده شامل مدل رقومی ارتفاعی، درصد شیب، جهت شیب، بارندگی، فاصله از گسل، فاصله از شبکه زهکشی، فاصله از جاده، کاربری اراضی، تراکم زهکشی، سازند سنگ‌شناسی، بافت خاک، انحنای طرح، انحنای پروفیل، شاخص رطوبت توپوگرافی، عامل طول شیب، شاخص توان جریان، موقعیت شیب نسبی و شاخص زبری سطح شناسایی و به مدل معرفی شد. سه سری متفاوت از نقاط وقوع زمین­لغزش (S1, S2, S3) شامل 70 درصد برای آموزش مدل و 30 درصد برای اعتبارسنجی به‌صورت تصادفی آماده شد تا قوت یا استحکام مدل مورد ارزیابی قرار بگیرد. دقت مدل بر اساس شاخص ROC مورد ارزیابی قرار گرفت و مدل بیشینه آنتروپی دقت پیش‌بینی عالی (بالای 80 درصد) از خود نشان داد. همچنین، در این پژوهش درجه اهمیت متغیر­ها به‌­وسیله مدل مورد بررسی قرار گرفت و عوامل مدل رقومی ارتفاعی (32.4 درصد اهمیت)، سنگ‌­شناسی (22.9 درصد اهمیت) و فاصله از گسل (14.8 درصد اهمیت) به‌­ترتیب به­‌عنوان مهمترین عوامل پیش‌­بینی­ کننده در این منطقه شناسایی شدند.

کلیدواژه‌ها

عنوان مقاله [English]

Identification the most important predictors in landslide susceptibility mapping using Maximum Entropy Model

نویسندگان [English]

  • Narges Javidan 1
  • Ataollah Kavian 2
  • Sajad Rajabi 3
  • Hamidreza Pourghasemi 4
  • Christian Conoscenti 5
  • Zeinab Jafarian 6

1 1PhD of Watershed Management, Faculty of Natural Resources, Sari Agricultural Sciences and Natural Resources University, Iran

2 Professor of Watershed Management, Faculty of Natural Resources, Sari Agricultural Sciences and Natural Resources University, Iran

3 MSc of Watershed Management, Faculty of Natural Resources, Sari Agricultural Sciences and Natural Resources University, Iran

4 Professor, Faculty of Agriculture, Shiraz University, Shiraz, Iran

5 Professor of Earth and Marine Sciences (DISTEM), University of Palermo, Italy

6 Assistant Professor of Range Management, Sari Agricultural Sciences and Natural Resources University, Iran

چکیده [English]

Slope instability and landslides are important hazards to human activities that often result in the loss of economic resources, property damage and facilities. These hazards occur in the natural or man-made slopes. In the current study, the maximum entropy model was used which is one of the progressive data mining models, in order to modelling landslide susceptibility map for Gorganrood watershed. In the first step, the landslide inventory map was prepared consiste of 351 landslides. 18 geo-environmental factors were selected as predictors, such as: Digital elevation model, slope percent, aspect, distance from fault, distance from river, distance from road, rainfall, landuse, drainage density, lithology, soil texture, plan curvature, profil curvature, lithological formation, Topographic wetness index, LS factor, stream power index, Relative Slope Position and Surface roughness index. Three different sample data sets (S1, S2, and S3) including 70% for training and 30% for validation were randomly prepared to evaluate the robustness of the model. The accuracy of the predictive model was evaluated by drawing receiver operating characteristic (ROC) curves and by calculating the area under the ROC curve (AUC). The ME model performed excellently both in the degree of fitting and in predictive performance (AUC values well above 0.8), which resulted in accurate predictions. Furthermore, In this study the importance of variables was evaluated by the model. Dem (digital elevation model) (32.4% importance), lithology (22.9% importance) and distance from fault (14.8% importance) were identified respectively the main controlling factor among all other variables.

کلیدواژه‌ها [English]

  • Data mining model
  • Gorganrood Watershed
  • Instability
  • Robustness
  • ROC curve
  1. Angileri, S.E., C. Conoscenti, V. Hochschild, M. Märker, E. Rotigliano and V. Agnesi. 2016. Water erosion susceptibility mapping by applying Stochastic Gradient Treeboost to the Imera Meridionale River Basin (Sicily, Italy). Geomorphology, 262: 61-76.
  2. Azareh, A., O. Rahmati, E. Rafiei-Sardooi, J.B. Sankey, S. Lee, H. Shahabi and B.B. Ahmad. 2019. Modelling gully-erosion susceptibility in a semi-arid region, Iran: investigation of applicability of certainty factor and maximum entropy models. Science of the Total Environment, 655: 684-696.
  3. Benda, L. and T. Dunne. 1997. Stochastic forcing of sediment supply to channel networks from landsliding and debris flow. Water Resources Research, 33: 2849-2863.
  4. Böhner, J. and T. Selige. 2006. Spatial prediction of soil attributes using terrain analysis and climate regionalisation. Gottinger Geographische Abhandlungen, 115: 13-28.
  5. Conoscenti, C., S. Angileri, C. Cappadonia, E. Rotigliano, V. Agnesi and M. Märker. 2014. Gully erosion susceptibility assessment by means of GIS-based logistic regression: a case of Sicily (Italy). Geomorphology, 204(1): 399–411.
  6. Conoscenti, C., M. Ciaccio, N.A. Caraballo-Arias, A. Gómez-Gutiérrez, E. Rotigliano and V. Agnesi. 2015. Assessment of susceptibility to earth-flow landslide using logistic regression and multivariate adaptive regression splines: a case of the Belice River Basin (Western Sicily, Italy). Geomorphology, 242: 49-64.
  7. Dickson, M.E. and G.L. Perry. 2016. Identifying the controls on coastal cliff landslides using machine-learning approaches. Environmental Modelling and Software, 76: 117-127.
  8. Felicĺsimo, Á., A. Cuartero, J. Remondo and E. Quirόs. 2013. Mapping landslide susceptibility with logistiv regression, multiple adaptive regression splines, classification and regression tress, amd maximum entropy methods: a comparative study. Landslides, 10: 175-189.
  9. Feizizadeh, B., M.S. Roodposhti, T. Blaschke and J. Aryal. 2017. Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping. Arabian Journal of Geosciences, 10(5): 112-122.
  10. Goetz, J.N., A. Brenning, H. Petschko and P. Leopold. 2015. Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling. Computers and Geosciences, 81: 1-11.
  11. Hoseinzadeh, M.M., M. Amini and B. Mirbagheri. 2012. Landslide zonation in the Googerd Watershed. Earth Science Research, 3(10): 98-110 (in Persian).
  12. Hong, H., B. Pradhan, C. Xu and D.T. Bui. 2015. Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and support vector machines. Catena, 133: 266-281.
  13. Hong, H., B. Pradhan, M.N. Jebur, D.T. Bui, C. Xu and A. Akgun. 2016. Spatial prediction of landslide hazard at the luxi area (China) using support vector machines. Environmental Earth Sciences, 75(1): 1-14.
  14. Javidan, N., A. Kavian, H.R. Pourghasemi, C. Conoscenti and Z. Jafarian. 2020. Gully erosion susceptibility mapping using multivariate adaptive regression splines replications and sample size scenarios. Water, 11(11): 19-23.
  15. Kanungo, D.P., M.K. Arora, S. Sarkar and R.P. Gupta. 2006. A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas. Engineering Geology, 2: 347-366.
  16. Kakembo, V., W.W. Xanga and K. Rowntree. 2009. Topographic thresholds in gully development on the hillslopes of communal areas in Ngqushwa local municipality, Eastern Cape, South Africa. Geomorphology, 110(3-4): 188-194.
  17. Kornejady, A., M. Ownegh and Bahremand. 2017. Landslide susceptibility assessment using maximum entropy model with two different data sampling methods. Catena, 152: 144-162.
  18. Kornejady, A. and H.R. Pourghasemi. 2019. Landslide susceptibility assessment using data mining models, a case study: Chehel-Chai Basin. Scientific Information Database, 11(1): 28-42.
  19. Lee, S. and J. Choi. 2004. Landslide susceptibility mapping in the Damrei Romel area, Cambodia using frequency ratio and logistic regression models. Environmental Geology, 50(6): 847-855.
  20. Marmion, M., J. Hjort., W. Thuiller and M. Luoto. 2008. A comparison of predictive methods in modelling the distribution of periglacial landforms in Finnish Lapland. Earth Surface Processes and Landforms, 33(14): 2241-2254.
  21. Mousavi, S.Z., A. Kavian, K. Soleimani, S.R. Mousavi and A. Shirzadi. 2011. GIS-based spatial prediction of landslide susceptibility using logistic regression model. Geomatics, Natural Hazards and Risk, 2(1): 33-50.
  22. Marjanović, M., M. Kovačević, B. Bajat and V.Voženílek. 2011. Landslide susceptibility assessment using SVM machine learning algorithm. Engineering Geology, 123(3): 225-234.
  23. Meinhardt, M., M. Fink and H. Tunschel. 2015. Landslide susceptibility analysis in central Vietnam based on an incomplete landslide inventory: comparison of a new method to calculate weighting factors by means of bivariate statistics. Geomorphology, 234: 80–97.
  24. Mohamadi, M. and H.R. Pourghasemi. 2017. Prioritization of effective factors on landslide occurrence and preparing sensitivity map using a new random forest algorithm, case study: part of Golestan. Journal of Watershed Management, 8(15): 161-170 (in Persian).
  25. Moghaddam, D.D., H.R. Pourghasemi and O. Rahmati. 2019. Assessment of the contribution of geo-environmental factors to flood inundation in a semi-arid region of SW Iran: comparison of different advanced modeling approaches. In Natural Hazards GIS-Based Spatial Modeling Using Data Mining Techniques. Springer, Cham, 59-78 pages.
  26. Ost, L., E.M. Van-Den, J .Poesen and M.C. Vanmaercke-Gottigny. 2003. Characteristics and spatial distribution of large land-slides in the Flemish Ardennes (Belgium). Zeitschrift für Geomorphologie, 47(3): 329-350.
  27. Phillips, S.J., R.P. Anderson and R.E. Schapire. 2006. Maximum entropy modeling of species geographic distributions. Ecological Modelling, 190(3-4): 231-259.
  28. Pradhan, B. and M.F. Buchroithner. 2010. Comparison and validation of landslide susceptibility maps using an artificial neural network model for three test areas in Malaysia. Environmental and Engineering Geoscience, 16(2): 107–126.
  29. Pourtaghi, Z.S., H.R. Pourghasemi. 2014. GIS-based groundwater spring potential assessment and mapping in the Birjand Township, southern Khorasan Province, Iran. Hydrogeology Journal, 22(3): 643-662.
  30. Park, N.W. 2015. Using maximum entropy modeling for landslide susceptibility mapping with multiple geoenvironmental data sets. Environmental Earth Sciences, 73(3): 937-949.
  31. Pourghasemi, H.R., M. Mohammady and B. Pradhan. 2012a. Landslide susceptibility mapping using index of entropy and conditional probability models in GS: Safarood Basin, Iran. Catena, 97: 71-84.
  32. Pourghasemi, H.R., H. Moradi and M. Fatemioghdas. 2012b. Landslide susceptibility mapping using adaptive neuro-fuzzy inference system in north of Tehran. Earth Science Research, 3(10): 63-78 (in Persian).
  33. Pourghasemi, H.R., A.G. Jirandeh, B. Pradhan, C. Xu and C. Gokceoglu. 2013. Landslide susceptibility mapping using support vector machine and GIS at the Golestan Province, Iran. Journal of Earth System Science, 122(2): 349-369.
  34. Pourghasemi, H.R., S. Yousefi, A. Kornejady and A. Cerdà. 2017. Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling. Science of the Total Environment, 609: 764–775.
  35. Pourghasemi, H.R. and O. Rahmati. 2018. Prediction of the landslide susceptibility: which algoritm, which precision? Catena, 162: 177-192.
  36. Rahmati, O., H.R. Pourghasemi and A.M. Melesse. 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.
  37. Rahmati, O., S.A. Naghibi, H. Shahabi, D.T. Bui, B. Pradhan, A. Azareh, E. Rafiei-Sardooi, A.N. Samani and A.M. Melesse. 2018. Groundwater spring potential modelling: comprising the capability and robustness of three different modeling approaches. Journal of Hydrology, 565: 248–261.
  38. Solaimani, K., S.Z. Mousavi and A. Kavian. 2013. Landslide susceptibility mapping based on frequency ratio and logistic regression models. Arabian Journal of Geosciences, 6(7): 2557-2569.
  39. Song, Y., J. Gong, S. Gao, D. Wang, T. Cui, Y. Li and B. Wei. 2012. Susceptibility assessment of earthquake-induced landslides using Bayesian network: a case study in Beichuan, China. Computers and Geosciences, 42: 189-199.
  40. Shirzadi, A. 2017. Prediction of surface landslides around Bijar City using innovative data mining algorithms. PhD Thesis, 225 pages (in Persian).
  41. Trigila, A., C. Iadanza, C. Esposito and G. Scarascia-Mugnozza. 2015. Comparison of logistic regression and random forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy). Geomorphology, 249: 119-136.
  42. Vorpahl, P., H. Elsenbeer, M. Mӓrker and B. Schröder. 2012. How can statistical models help to determine driving factors of landslides? Ecological Modelling, 239: 27-39.
  43. Walter, S.D. 2002. Properties of the Summary Receiver Operating Characteristic (SROC) curve for diagnostic test data. Stat Med, 21: 1237–1256.
  44. Yessilnacar, E.K. 2005. The application of computational intelligence of landslide susceptibility mapping in Turkey. PhD Thesis, Department of Geomatics the University of Melbourne, 423
  45. Yost, A.C., S.L. Petersen, M. Gregg and R. Miller. 2008. Predictive modeling and mapping sage grouse (Centrocercus urophasianus) nesting habitat using Maximum Entropy and a long-term dataset from Southern Oregon. Ecological Informatics, 3(6): 375-386.
  46. Yalcin, A. 2008. GIS-based landslide susceptibility mapping using analytical hierarchy process and bivariate statistics in Ardesen (Turkey): comparisons of results and confirmations. Catena, 72: 1–12.
  47. Yamani, M., A. Ahmadabadi and G.h Zare. 2012. Implementation of SVM algoritm in mapping landslide in Darake Watershed. Journal of Geography and Natural Hazards, 3: 125-142 (in Persian).