
تعداد نشریات | 163 |
تعداد شمارهها | 6,760 |
تعداد مقالات | 72,808 |
تعداد مشاهده مقاله | 131,594,753 |
تعداد دریافت فایل اصل مقاله | 103,394,792 |
ارزیابی نقش ویژگی های ژئومورفیک مؤثر بر آسیبپذیری و حساسیت اراضی به زمین لغزش با استفاده از روش های یادگیری ماشین (مطالعة حوزة آبخیز کاکاشرف استان لرستان) | ||
نشریه محیط زیست طبیعی | ||
دوره 77، شماره 4، اسفند 1403، صفحه 731-747 اصل مقاله (284.15 K) | ||
نوع مقاله: مقاله پژوهشی | ||
شناسه دیجیتال (DOI): 10.22059/jne.2024.376982.2675 | ||
نویسندگان | ||
رضا فتحی گنجی1؛ علی اکبر نظری سامانی* 2؛ سادات فیض نیا2؛ عبدارضا نوریزدان3 | ||
1گروه آبخیزداری، دانشکدة منابع طبیعی، دانشگاه تهران. تهران، کرج، ایران. | ||
2گروه احیا مناطق خشک و کوهستانی، دانشکدة منابع طبیعی، دانشگاه تهران، کرج. ایران. | ||
3ادارة مهندسی و مطالعات ادارة کل منابع طبیعی و آبخیزداری لرستان، لرستان، ایران. | ||
چکیده | ||
زمینلغزشها بهعنوان یک مخاطره و اختلال زمینی، اثرات مستقیم و غیر مستقیمی زیادی بر شرایط جوامع انسانی، محیط طبیعی و تغییر سیمای سرزمین دارند و میتوانند موجب خسارتهای جانی و مالی گستردهای شود. بنابراین تعیین عوامل مؤثر بر آسیبپذیری به آن برای مدیریت این مخاطره ضروری است. هدف این پژوهش، شناخت عوامل مؤثر بر حساسیت اراضی به زمینلغزش و تهیة نقشة حساسیت به زمینلغزش با پایۀ تلفیق روش های یادگیری ماشین و مدلسازی آماری است. در این بررسی با استفاده از الگوریتم جنگل تصادفی، از بین عوامل مؤثر (شیب، جهت شیب، موقعیت توپوگرافی، رطوبت توپوگرافی، انحنای سطحی، سنگ شناسی، فاصله از گسل، فاصله ازآبراهه، فاصله از جاده و کاربری اراضی) وزن و درجۀ اهمیت مشخص شد. سپس با تکنیک های شبکة عصبی مصنوعی و MaxEnt برای مدلسازی و پیشبینی مناطق مستعد زمینلغزش استفاده شد. برای ارزیابی دقت مدل ها، با انجام اعتبارسنجی در محدودۀ مجاور حوزة آبخیز کاکاشرف، شاخصهای ارزیابی محاسبه شد. نتایج نشان داد که عوامل فاصله از گسل و شیب، بهترتیب بیشترین اهمیت را در حساسیت اراضی به زمینلغزش دارند. بر پایة شاخص سطح زیر منحنی (AUC) مدل شبکة عصبی 0/92 نسبت به مدل MaxEnt با مقدار 0/801 دقت بیشتری در پیشبینی مناطق مستعد به زمینلغزش را نشان داد. بیشترین آسیبپذیری متعلق به اراضی مجاور آبراهه فاصلة کمتر از 200 متر با خطوط گسلش و شیب 40-20% است؛ بنابراین مدیریت و پوشش کاربری اراضی در این اراضی از اولویت بیشتری برخوردار است. این نتایج میتواند در بهبود مدیریت و برنامهریزی اراضی در مناطق مستعد زمینلغزش، حفاظت از منابعطبیعی و مدیریت ریسک مؤثر باشد. | ||
کلیدواژهها | ||
جنگل تصادفی؛ حساسیت اراضی؛ شبکة عصبی؛ MaxEnt | ||
عنوان مقاله [English] | ||
Evaluating the role of geomorphic characteristics in landslide vulnerability and sensitivity | ||
نویسندگان [English] | ||
Reza Fathiganji1؛ Aliakbar Nazari Samani2؛ Sadat Feiznia2؛ Abdolreza Nourizdan3 | ||
1Department of Arid and Mountainous Regions Reclamation, Faculty of Natural Resources, University of Tehran, Karaj, Iran. | ||
2Department of Arid and Mountainous Regions Reclamation, Faculty of Natural Resources, University of Tehran, Karaj, Iran. | ||
3Department of Engineering and Studies of the General Department of Natural Resources and Watershed of Lorestan, Iran. | ||
چکیده [English] | ||
Landslides, as a natural hazard and geomorphic disturbance, have numerous direct and indirect impacts on human communities, the natural environment, and landscape transformation, and can lead to significant human and financial losses.Therefore, identifying the factors influencing vulnerability to this hazard is essential for effective management. The aim of this study is to identify the factors affecting land susceptibility to landslides and to prepare a susceptibility map by integrating machine learning methods and statistical modeling. In this research, the Random Forest algorithm was used to determine the weight and importance of influencing factors including slope, aspect, topographic position index, topographic wetness index, Plan curvature, lithology, distance from faults, distance from stream, distance from roads, and land use. Subsequently, Artificial Neural Networks (ANN) and Maximum Entropy (MaxEnt) models were applied to model and predict landslide-prone areas. To evaluate model performance, validation was conducted in an adjacent area to the Kakashraf watershed, and relevant evaluation indices were calculated. The results indicated that distance from faults and slope were the most significant factors influencing landslide susceptibility. According to the Area Under the Curve (AUC), the ANN model (0.92) had higher predictive accuracy than the MaxEnt model (0.801). The most vulnerable areas were found within 200 meters of stream, near fault lines, and with slopes between 20% and 40%. Therefore, land use management in such areas should be prioritized. These findings can contribute to improved land planning, natural resource protection, and effective landslide risk management. | ||
کلیدواژهها [English] | ||
MaxEnt, Neural network, Random forest, Sensitivity | ||
مراجع | ||
Agboola,G.,Hashemi Beni, L.,Elbayoumi,T.,Thompson G., 2024.Optimizin landslide susceptibility mapping using machine learning and geospatial techniques. Ecological Informatics 81, 102583. Ahmadi, H., Faiz Nia, S., 2012. Formations of the Quaternary Period (Theoretical and Practical Basis in Natural Resources) Tehran University Publications, Third Edition. (In Persian) Azimpour Moghadam, V., Vahabzadeh, Gh., 2014. Landslide risk zoning using the Dempster-Schiffer method (case study: a part of Babolrud watershed), the third national conference of environmental and agricultural researches of Iran, Hamedan. (In Persian) Barlow, J., Martin, Y., Franklin, S.E., 2003. Detecting translational landslide scars using segmentation of Landsat ETM+ and DEM data in the northern Cascade Mountains, British Columbia. Canadian Journal of Remote Sensing 29(4), 510-517. Boussouf, S., Fernández, T., Hart, A.B., 2023. Landslide susceptibility mapping using maximum entropy (MaxEnt) and geographically weighted logistic regression (GWLR) models in the Río Aguas catchment (Almería, SE Spain). Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer; International Society for the Prevention and Mitigation of Natural Hazards 117(1), 207-235 Demir, G., Aytekin Akgun, A., 2015. Landslide susceptibility mapping by frequency ratio and logistic regression methods: an example from Niksar-Resadiye (Tokat, Turkey). Arabian Journal of Geosciences 8, 1801-1812. Ercanoglu, M., Gokceoglu, C., 2002. Assessment of landslide susceptibility for a landslide-prone area (north ofYenice, NW Turkey) by fuzzy approach. Environmental Geology 41, 720-730 Evans, J.S., Cushman, S.A., 2009. Gradient modeling of conifer species using random forests. Landscape Ecology 24, 673-683. Froude, M., Petley, D., 2018. Global fatal landslide occurrence from 2004 to 2016. Natural Hazards and Earth System Sciences ,18, 2161–2181.ISSN 1561-8623 Ganesh, B., Vincent, S., Pathan, S., Benitez,S.R.G., 2023. Integration of GIS and Machine Learning Techniques for Mapping the Landslide-Prone Areas in the State of Goa, India. Journal of the Indian Society of Remote Sensing 51(7), 1479-1491 Guzzetti, F., Mondini, A.C., Cardinali, M., Fiorucci, F., Santangelo, M., Chang, K.T., 2012. Landslide inventory maps: new tools for an old problem. Earth-Science Reviews, Earth-Science Reviews 112, 42-66. Hastie, T., Tibshirani, R., Friedman, J., 2009. the Element of Statistical learning:Data Mining, inference, and Prediction.2and Edition. Springer. Karimi Sangchini, E., Dastranj, A., Arami, S.H., Shadfar, S., Vayskarami, I., 2024. Application of maximum entropy machine learning algorithm in landslide hazard zoning in Karganeh Watershed, Lorestan Province. Iranian Journal of Watershed Management Science and Engineering 18(64), 5. (In Persian) KohPeima, A., 2016. Susceptibility Zoning, Landslide Risk Assessment and Management (Case Study: Letyan Watershed) Doctoral Dissertation in Watershed Engineering, Tehran University, 149 p. (In Persian) Makram, M., Negahban, S., 2013. Classification of landforms using topographic position index (TPI) case study: southern region of Darab city. Scientific-Research Quarterly of Geographical Information "Sepehr 23(92), 57-65. (In Persian) Meng, Xingmin., 2022. landslide". Encyclopedia Britannica, 3 Feb. Mokhtari, D., Rahmati, F., Rouhanizadeh, S., 2023. Landslide Risk Zoning Using Fuzzy Hierarchy Process (AHP) (Case Study: Mehr Kian Housing District, Saqqah), 12th International Conference on Agriculture, Environment, urban and rural development. Nojavan, M.R., Sadat Shahzaidi, S., Davoudi, M., Amin Al-Raaiai, A., 2018. Landslide risk zoning using the combination of two hierarchical and fuzzy process models (Case study: Kameh watershed of Isfahan province). Quantitative Geomorphology 7(28), 159-142. (In Persian) Pandey, V.K., Pourghasemi, H.R., Sharma, M.C., 2018. Landslide susceptibility mapping using maximum entropy and support vector machine models along the highway corridor, Garhwal Himalaya. Geocarto International 35(2), 168-187. Pearson, R.G., 2007. Species’ distribution modeling for conservation educators and practitioners. Synthesis. American Museum of Natural History 50, 54-89. Sadidi, J., Maleki, R., 2022. Comparison of support vector machine, random forest and logistic regression algorithms in landslide risk zoning in Mahabad Sardasht road. Remote Sensing and GIS Applications in Environmental Sciences 10(15), 5047. (In Persian) Saha, S., Majumdar, P., Bera, B., 2023. Deep learning and benchmark machine learning based landslide susceptibility investigation, Garhwal Himalaya (India). Quaternary Science Advances 10, 100075. Shafique, M., van der Meijde, M., Asif Khan, M., 2005. A review of the Kashmir earthquake-induced landslides; from a remote sensing prospective. Journal of Asian Earth Sciences 118, 68-80. Shannon, C.E., 1948. A mathematical theory of communication. Bell System Technical Journal 27(3), 379-423. Shano, L., Raghuvanshi, T.K., Meten, M., 2022. Landslide Hazard Zonation using Logistic Regression Model: The Case of Shafe and Baso Catchments, Gamo Highland, Southern Ethiopia. Geotechnical and Geological Engineering 40, 83-101 Siadati Far, M.H., Tajbakhsh Fakhrabadi, M., Jazgi, J., Ahmadi, K., 2022. Evaluation of Landslide Sensitivity and Zoning Using Support Vector Machine Algorithm - Case Study: Khosef City-Ailki Watershed, 17th National Science Conference and watershed engineering of Iran, focusing on watershed management and sustainable food security, Jiroft. (In Persian) Taimouri, M., Asadi Nalivan, O., 2019. Zoning susceptibility and prioritizing factors affecting landslide occurrence using the maximum entropy model (Case study: Lorestan Province). Hydrogeomorphology 6(21), 155-179. (In Persian) Varens, D.J., 1978. slope movement types and processes Special Report 176, 33-11. Yu, X., Gao, H., 2020 A landslide susceptibility map based on spatial scale segmentation: A case study at Zigui-Badong in the Three Gorges Reservoir Area, China. PLoS ONE 15(3), e0229818. Zakeri Nejad, R., Amooshahi, N., 2022. Landslide hazard assessment using remote sensing data and the maximum entropy model (Case study: Kameh Watershed, southern Isfahan Province). Quantitative Geomorphological Research 11(2), 128-149. (In Persian) | ||
آمار تعداد مشاهده مقاله: 154 تعداد دریافت فایل اصل مقاله: 5 |