بررسی کارایی مدل های هوش مصنوعی و آماری دو متغیره در تعیین مناطق حساس به وقوع زمین لغزش در استان آذربایجان غربی
محورهای موضوعی : مباحث نوین در فیزیک خاکآزاد آرام 1 , محمدرضا دلالیان 2 , سیامک ساعدی 3 , امید رفیعیان 4 , صمد دربندی 5
1 - دانشجوی دکتری، گروه علوم و مهندسی خاک، واحد تبریز، دانشگاه آزاد اسلامی، تبریز، ایران.
2 - استادیار گروه علوم و مهندسی خاک دانشکده کشاورزی، واحد تبریز، دانشگاه آزاد اسلامی، تبریز، ایران.
3 - استادیار، گروه علوم و مهندسی خاک، واحد تبریز، دانشگاه آزاد اسلامی، تبریز، ایران.
4 - استادیار، گروه محیطزیست، واحد تبریز، دانشگاه آزاد اسلامی، تبریز، ایران.
5 - استادیار، گروه علوم و مهندسی آب، واحد تبریز، دانشگاه آزاد اسلامی، تبریز، ایران.
کلید واژه: نسبت فراوانی, آنتروپی شانون, بگینگ, جنگل تصادفی, هوش مصنوعی,
چکیده مقاله :
زمینه و هدف: زمین لغزش، یکی از مخاطرات طبیعی است که منجر به خسارات جانی و مالی فراوان می شود. پژوهشگران در موضوع حساسیت به وقوع زمین لغزش، به بررسی احتمال وقوع زمین لغزش با توجه به شرایط توپوگرافی و ژئومحیطی می پردازند و اطلاعات به دست آمده، در مدیریت خطر زمین لغزش حیاتی است. تهیه نقاط حساس به وقوع زمین لغزش یک ابزار ضروری برای ارزیابی خطر زمین لغزش بوده و در برنامه ریزی و مدیریت بهتر این مناطق بسیار کاربردی است. در این پژوهش مدل های مبتنی بر هوش مصنوعی و دو متغیره آماری در تعیین نقاط حساس به زمین لغزش در استان آذربایجان غربی مورد بررسی و مقایسه قرار گرفته است.روش پژوهش: برای تهیه نقاط حساس به وقوع زمین لغزش در استان آذربایجان غربی که در شمال غربی ایران واقع شده است، از روش-های مبتنی بر هوش مصنوعی و دو متغیره آماری بهره گرفته شد. این مطالعه در چهار مرحله صورت گرفت. مرحله اول شامل مطالعه زمین-لغزش های منطقه بر اساس بانک اطلاعات سازمان جنگل ها، مراتع و آبخیزداری ایران (FRWO) و شناسایی 110 زمین لغزش با بررسی های میدانی، تفسیر عکس های هوایی و تصاویر ماهواره ای گوگل ارث، مرحله دوم جمع آوری داده ها و ایجاد پایگاه داده های مکانی فاکتورهای مؤثر، مرحله سوم به کارگیری روش نسبت فراوانی (FR)، آنتروپی شانون (SE)، بگینگ (BA)، جنگل تصادفی (RF) و مدل ترکیبی جنگلهای تصادفی و بگینگ (RF-BA) و مرحله چهارم: اعتبارسنجی روش ها با استفاده از روش منحنی مشخصه عملکرد سیستم (ROC) بود. بر اساس بررسی های میدانی و مطالعات مشابه، 12 عامل مؤثر بر وقوع زمین لغزش شامل ارتفاع، زاویه شیب، جهت شیب، فاصله از گسل، فاصله از رودخانه، فاصله از جاده، تراکم زهکشی، تراکم جاده، بارندگی، خاک، کاربری زمین و سنگ شناسی شناسایی شد. در بررسی های میدانی، 110 زمین لغزش در استان آذربایجان غربی مشخص شد. 70 درصد از داده ها بهطور تصادفی انتخاب و برای مدل سازی مورد استفاده قرار گرفتند و 30 درصد داده ها برای اعتبار سنجی استفاده گردید.یافته ها: در میان جهت های جغرافیایی، جهت جنوبی با وزن 49/1 دارای بیش ترین تأثیر بر وقوع زمین لغزش های استان بود. کمترین وزن نیز مربوط به مناطق مسطح بود که در آن هیچگونه لغزشی رخ نداده است. نتایج فاکتور شیب نشان داد که شیب های میانی دارای بیشترین تأثیر بر وقوع زمین لغزش است، به طوری که در شیب های کم به دلیل وجود جاذبه کم، زمین لغزش کم تر رخ می دهد و شیب های بسیار تند نیز مربوط به مناطق کوهستانی بوده که با سنگ پوشیده شده و خاک بسیار نازکی وجود دارد که برای لغزش مناسب نمی باشد. بررسی عامل کاربری اراضی نشان داد که 48 درصد از لغزش ها در مناطق کشاورزی رخ می دهد. بر طبق بررسی های این پژوهش، بیشتر زمین لغزش ها در نزدیکی رودخانه ها و گسل ها رخ داده است. همچنین در بعضی مناطق، نزدیک ترین فواصل به جاده، بیشترین خطر را برای زمین لغزش دارد.نتایج: نتایج این تحقیق نشان داد که مدل های هوش مصنوعی (جنگل تصادفی RF و مدل ترکیبی جنگلهای تصادفی و بگینگ RF-BA) دارای کارایی بالاتری نسبت به مدل های آماری (نسبت فراوانی FR و آنتروپی شانون SE) است. دقت مدل های ترکیبی بیشتر از مدل های منفرد بود. نتایج منحنی ROC دقت 92/0، 91/0، 89/0 و 88/0 را با مدلهای RF-BA، RF، FR و SE نشان داد.
Background and Aims: Landslide is one of the natural hazards that lead to a lot of human and financial losses. Researchers on the subject of landslide susceptibility are investigating the possibility of landslides with respect to topographic and geo-environmental conditions, and the obtained information is critical in landslide risk management Preparation of landslide sensitive points is an essential tool for assessing landslide risk and is very useful in better planning and management of these areas. In this research, models based on artificial intelligence and two statistical variables in determining landslide sensitive points in West Azerbaijan province have been studied and compared.Methods: Methods based on artificial intelligence and two statistical variables were used to prepare landslide-sensitive points in the province of West Azerbaijan, which is located in northwestern Iran. This study was conducted in four stages. The first stage: the study of landslides in the studied region based on the database of the Forests, Rangelands and Watershed Organization of Iran (FRWO) and the identification of 110 landslides through field surveys, interpretation of aerial photographs and Google Earth satellite images, the second stage: data collecting and creating a spatial databases of effective factors, the third stage: applying the Frequency Ratio (FR), Shannon Entropy (SE), Bagging (BA), Random Forest (RF) and hybrid model (RF-BA) and stage four: methods validating using the system performance curve (ROC). Based on field surveys and similar studies, 12 factors affecting landslide occurrence including altitude, slope angle, slope direction, distance from fault, distance from river, distance from road, drainage density, road density, rainfall, soil, land use and lithology were identified. In the field survey, 110 landslides were identified in West Azerbaijan. 70 percent of the data were randomly selected and used for modeling and 30 percent of the data were used for validation.Results: In terms of geographical directions, the southern direction with a weight of 1.49 had the greatest impact on the occurrence of landslides in the province. The least weight was related to flat areas where no landslide occurred. The results of slope factor showed that the middle slopes had the greatest effect on the occurrence of landslides, so that in low slopes due to low gravity, less landslides occur and too much slopes were related to mountainous areas that were covered with rocks and there was very thin soil that is not suitable for landslide. The study of land use factor showed that 48 percent of landslides occured in agricultural areas. The results showed that most of the landslides occurred near rivers and faults. Also, in some areas, the closest distances to the road had the greatest risk of landslideConclusion: The results of this study showed that the artificial intelligence models (RF and the combined model RF-BA) had the higher efficiency than the statistical models (FR and SE). The accuracy of the combined models was higher than the single models. The ROC curve results showed the accuracy of 0.92, 0.91, 0.89 and 0.88 with RF-BA, RF, FR and SE models, respectively.
Al-Hinai, H.Y. & Abdalla, R.I.F.A.A.T. (2020). Spatial Prediction of Coastal Flood Susceptible Areas in Muscat Governorate Using an Entropy Weighted Method. WIT Transactions on Engineering Sciences; WIT Press: Southampton, UK, 129: 121-133.
Arca, D., Hacısalihoğlu, M. & Kutoğlu, Ş. H. (2020). Producing forest fire susceptibility map via multi-criteria decision analysis and frequency ratio methods. Natural Hazards, 104(1): 73-89.
Arora, A., Arabameri, A., Pandey, M., Siddiqui, M. A., Shukla, U.K., Bui, D.T., & Bhardwaj, A. (2021). Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India. Science of The Total Environment, 750: 141565.
Bui, D. T., Pradhan, B., Revhaug, I., Nguyen, D. B., Pham, H. V., & Bui, Q. N. (2015). A novel hybrid evidential belief function-based fuzzy logic model in spatial prediction of rainfall-induced shallow landslides in the Lang Son city area (Vietnam). Geomatics, Natural Hazards and Risk, 6(3), 243-271.
Chen, W., Shirzadi, A., Shahabi, H., Ahmad, B. B., Zhang, S., Hong, H., & Zhang, N. (2017a). A novel hybrid artificial intelligence approach based on the rotation forest ensemble and naïve Bayes tree classifiers for a landslide susceptibility assessment in Langao County, China. Geomatics, Natural Hazards and Risk, 8(2), 1955-1977.
Chen, W., Chen, X., Peng, J., Panahi, M. & Lee, S. (2021). Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer. Geoscience Frontiers, 12(1): 93-107.
Fang, Z., Wang, Y., Peng, L. & Hong, H. (2020). Integration of convolutional neural network and conventional machine learning classifiers for landslide susceptibility mapping. Computers & Geosciences, 139: 104470.
Gaidzik, K. & Ramírez-Herrera, M. T. (2021). The importance of input data on landslide susceptibility mapping. Scientific reports, 11(1): 1-14.
Khosravi, K., Pham, B.T., Chapi, K., Shirzadi, A., Shahabi, H., Revhaug, I., & Bui, D.T. (2018). A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran. Science of the Total Environment, 627: 744-755.
Khosravi, K., Pourghasemi, H. R., Chapi, K. & Bahri, M. (2016). Flash flood susceptibility analysis and its mapping using different bivariate models in Iran: a comparison between Shannon’s entropy, statistical index, and weighting factor models. Environmental monitoring and assessment, 188(12): 1-21.
Khosravi, K., Shahabi. H., Pham, B.T., Adamowski, J., Shirzadi, A., Pradhan, B., Dou, J., Ly, H. B., Grof, G., Ho, H. L., Hong, H., Chapi, K. & Prakash, I., (2019). A comparative assessment of flood susceptibility modeling using Multi-Criteria Decision-Making Analysis and Machine Learning Methods, Journal of Hydrology, 573: 311-323.
Liang, G., Zhu, X. & Zhang, C. (2011). An empirical study of bagging predictors for different learning algorithms. In Twenty-Fifth AAAI Conference on Artificial Intelligence.
Liu, L., Chin, S.P. & Tran, T.D. (2019). Reducing sampling ratios and increasing number of estimates improve bagging in sparse regression. In 2019 53rd Annual Conference on Information Sciences and Systems (CISS) (pp. 1-5). IEEE.
Malekinezhad, H., Sepehri, M., Pham, Q.B., Hosseini, S.Z., Meshram, S.G., Vojtek, M. & Vojteková, J. (2021). Application of entropy weighting method for urban flood hazard mapping. Acta Geophysica: 1-14.
Nampak, H., Pradhan, B., Manap, M.A. (2014). Application of GIS based data driven evidential belief function model to predict groundwater potential zonation, Journal of Hydrology, 513: 283-300.
Ngo, P.T.T., Panahi, M., Khosravi, K., Ghorbanzadeh, O., Kariminejad, N., Cerda, A. & Lee, S. (2021). Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran. Geoscience Frontiers, 12(2): 505-519.
Pham, B.T., Bui, D.T., Pourghasemi, H.R., Indra, P. and Dholakia, M.B. (2017b). Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods. Theoretical and Applied Climatology, 128(1-2), pp.255-273.
Pham, B.T., Bui, D.T., Prakash, I. & Dholakia, M.B. (2016b). Rotation forest fuzzy rule-based classifier ensemble for spatial prediction of landslides using GIS. Natural Hazards, 83(1), pp.97-127.
Pham, B.T., Tien Bui, D., Indra, P., & Dholakia, M.B. (2015b). Landslide susceptibility assessment at a part of Uttarakhand Himalaya, India using GIS–based statistical approach of frequency ratio method. Int J Eng Res Technol, 4, 338-344.
Piao, Y., Piao, M., Jin, C.H., Shon, H.S., Chung, J.-M., Hwang, B., Ryu, K.H. (2015). A new ensemble method with feature space partitioning for high-dimensional data classification. Mathematical Problems in Engineering
Piryonesi, S.M. & El-Diraby, T. E. (2020). Data analytics in asset management: Cost-effective prediction of the pavement condition index. Journal of Infrastructure Systems, 26(1): 04019036.
Pourghasemi, H.R., Pradhan, B., Gokceoglu, C., Mohammadi, M. & Moradi, H.R. (2013). Application of weights-of-evidence and certainty factor models and their comparison in landslide susceptibility mapping at Haraz watershed, Iran. Arabian Journal of Geosciences, 6(7): 2351-2365.
Pourghasemi, H.R. & Rahmati, O. (2018). Prediction of the landslide susceptibility: Which algorithm, which precision? CATENA, 162: 177-192.
Raghuvanshi, T.K., Ibrahim, J., Ayalew, D. (2014). Slope stability susceptibility evaluation parameter (SSEP) rating scheme—an approach for landslide hazard zonation. J. Afr Earth. Sci., 99:595-612
Rodriguez, J.J., Kuncheva, L.I., & Alonso, C.J. (2006). Rotation Forest: A new classifier ensemble method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(10), 1619-1630.
Sarkar, D., Saha, S. and Mondal, P. 2021. GIS-based frequency ratio and Shannon's entropy techniques for flood vulnerability assessment in Patna district, Central Bihar, India. International Journal of Environmental Science and Technology: 1-22.
Sassa, K. & Canuti, P. eds., (2008). Landslides-disaster risk reduction. Springer Science & Business Media.
Shirzadi, A., Bui, D.T., Pham, B.T., Solaimani, K., Chapi, K., Kavian, A., Shahabi, H. and Revhaug, I. (2017a). Shallow landslide susceptibility assessment using a novel hybrid intelligence approach. Environmental Earth Sciences, 76(2), 60.
Sun, D., Shi, S., Wen, H., Xu, J., Zhou, X. & Wu, J. (2021). A hybrid optimization method of factor screening predicated on GeoDetector and Random Forest for Landslide Susceptibility Mapping. Geomorphology, 379: 107623.
Terlien, M.T., van Westen, C.J., & van Asch, T.W. (1995). Deterministic modelling in GIS-based landslide hazard assessment. In A. Carrara & F. Guzzetti (Eds.), Geographical Information Systems in Assessing Natural Hazards, PP: 57-77. Netherlands: Springer.
Youssef, A.M. & Pourghasemi, H.R. (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.
_||_Al-Hinai, H.Y. & Abdalla, R.I.F.A.A.T. (2020). Spatial Prediction of Coastal Flood Susceptible Areas in Muscat Governorate Using an Entropy Weighted Method. WIT Transactions on Engineering Sciences; WIT Press: Southampton, UK, 129: 121-133.
Arca, D., Hacısalihoğlu, M. & Kutoğlu, Ş. H. (2020). Producing forest fire susceptibility map via multi-criteria decision analysis and frequency ratio methods. Natural Hazards, 104(1): 73-89.
Arora, A., Arabameri, A., Pandey, M., Siddiqui, M. A., Shukla, U.K., Bui, D.T., & Bhardwaj, A. (2021). Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India. Science of The Total Environment, 750: 141565.
Bui, D. T., Pradhan, B., Revhaug, I., Nguyen, D. B., Pham, H. V., & Bui, Q. N. (2015). A novel hybrid evidential belief function-based fuzzy logic model in spatial prediction of rainfall-induced shallow landslides in the Lang Son city area (Vietnam). Geomatics, Natural Hazards and Risk, 6(3), 243-271.
Chen, W., Shirzadi, A., Shahabi, H., Ahmad, B. B., Zhang, S., Hong, H., & Zhang, N. (2017a). A novel hybrid artificial intelligence approach based on the rotation forest ensemble and naïve Bayes tree classifiers for a landslide susceptibility assessment in Langao County, China. Geomatics, Natural Hazards and Risk, 8(2), 1955-1977.
Chen, W., Chen, X., Peng, J., Panahi, M. & Lee, S. (2021). Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer. Geoscience Frontiers, 12(1): 93-107.
Fang, Z., Wang, Y., Peng, L. & Hong, H. (2020). Integration of convolutional neural network and conventional machine learning classifiers for landslide susceptibility mapping. Computers & Geosciences, 139: 104470.
Gaidzik, K. & Ramírez-Herrera, M. T. (2021). The importance of input data on landslide susceptibility mapping. Scientific reports, 11(1): 1-14.
Khosravi, K., Pham, B.T., Chapi, K., Shirzadi, A., Shahabi, H., Revhaug, I., & Bui, D.T. (2018). A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran. Science of the Total Environment, 627: 744-755.
Khosravi, K., Pourghasemi, H. R., Chapi, K. & Bahri, M. (2016). Flash flood susceptibility analysis and its mapping using different bivariate models in Iran: a comparison between Shannon’s entropy, statistical index, and weighting factor models. Environmental monitoring and assessment, 188(12): 1-21.
Khosravi, K., Shahabi. H., Pham, B.T., Adamowski, J., Shirzadi, A., Pradhan, B., Dou, J., Ly, H. B., Grof, G., Ho, H. L., Hong, H., Chapi, K. & Prakash, I., (2019). A comparative assessment of flood susceptibility modeling using Multi-Criteria Decision-Making Analysis and Machine Learning Methods, Journal of Hydrology, 573: 311-323.
Liang, G., Zhu, X. & Zhang, C. (2011). An empirical study of bagging predictors for different learning algorithms. In Twenty-Fifth AAAI Conference on Artificial Intelligence.
Liu, L., Chin, S.P. & Tran, T.D. (2019). Reducing sampling ratios and increasing number of estimates improve bagging in sparse regression. In 2019 53rd Annual Conference on Information Sciences and Systems (CISS) (pp. 1-5). IEEE.
Malekinezhad, H., Sepehri, M., Pham, Q.B., Hosseini, S.Z., Meshram, S.G., Vojtek, M. & Vojteková, J. (2021). Application of entropy weighting method for urban flood hazard mapping. Acta Geophysica: 1-14.
Nampak, H., Pradhan, B., Manap, M.A. (2014). Application of GIS based data driven evidential belief function model to predict groundwater potential zonation, Journal of Hydrology, 513: 283-300.
Ngo, P.T.T., Panahi, M., Khosravi, K., Ghorbanzadeh, O., Kariminejad, N., Cerda, A. & Lee, S. (2021). Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran. Geoscience Frontiers, 12(2): 505-519.
Pham, B.T., Bui, D.T., Pourghasemi, H.R., Indra, P. and Dholakia, M.B. (2017b). Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods. Theoretical and Applied Climatology, 128(1-2), pp.255-273.
Pham, B.T., Bui, D.T., Prakash, I. & Dholakia, M.B. (2016b). Rotation forest fuzzy rule-based classifier ensemble for spatial prediction of landslides using GIS. Natural Hazards, 83(1), pp.97-127.
Pham, B.T., Tien Bui, D., Indra, P., & Dholakia, M.B. (2015b). Landslide susceptibility assessment at a part of Uttarakhand Himalaya, India using GIS–based statistical approach of frequency ratio method. Int J Eng Res Technol, 4, 338-344.
Piao, Y., Piao, M., Jin, C.H., Shon, H.S., Chung, J.-M., Hwang, B., Ryu, K.H. (2015). A new ensemble method with feature space partitioning for high-dimensional data classification. Mathematical Problems in Engineering
Piryonesi, S.M. & El-Diraby, T. E. (2020). Data analytics in asset management: Cost-effective prediction of the pavement condition index. Journal of Infrastructure Systems, 26(1): 04019036.
Pourghasemi, H.R., Pradhan, B., Gokceoglu, C., Mohammadi, M. & Moradi, H.R. (2013). Application of weights-of-evidence and certainty factor models and their comparison in landslide susceptibility mapping at Haraz watershed, Iran. Arabian Journal of Geosciences, 6(7): 2351-2365.
Pourghasemi, H.R. & Rahmati, O. (2018). Prediction of the landslide susceptibility: Which algorithm, which precision? CATENA, 162: 177-192.
Raghuvanshi, T.K., Ibrahim, J., Ayalew, D. (2014). Slope stability susceptibility evaluation parameter (SSEP) rating scheme—an approach for landslide hazard zonation. J. Afr Earth. Sci., 99:595-612
Rodriguez, J.J., Kuncheva, L.I., & Alonso, C.J. (2006). Rotation Forest: A new classifier ensemble method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(10), 1619-1630.
Sarkar, D., Saha, S. and Mondal, P. 2021. GIS-based frequency ratio and Shannon's entropy techniques for flood vulnerability assessment in Patna district, Central Bihar, India. International Journal of Environmental Science and Technology: 1-22.
Sassa, K. & Canuti, P. eds., (2008). Landslides-disaster risk reduction. Springer Science & Business Media.
Shirzadi, A., Bui, D.T., Pham, B.T., Solaimani, K., Chapi, K., Kavian, A., Shahabi, H. and Revhaug, I. (2017a). Shallow landslide susceptibility assessment using a novel hybrid intelligence approach. Environmental Earth Sciences, 76(2), 60.
Sun, D., Shi, S., Wen, H., Xu, J., Zhou, X. & Wu, J. (2021). A hybrid optimization method of factor screening predicated on GeoDetector and Random Forest for Landslide Susceptibility Mapping. Geomorphology, 379: 107623.
Terlien, M.T., van Westen, C.J., & van Asch, T.W. (1995). Deterministic modelling in GIS-based landslide hazard assessment. In A. Carrara & F. Guzzetti (Eds.), Geographical Information Systems in Assessing Natural Hazards, PP: 57-77. Netherlands: Springer.
Youssef, A.M. & Pourghasemi, H.R. (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.