تحقیقات کاربردی علوم جغرافیایی

تحقیقات کاربردی علوم جغرافیایی

مدل‌سازی حساسیت زمین‌لغزش با وزن‌دهی پویای مکانی-زمانی مبتنی بر PSO-GA در حوضه شمال تهران

نویسندگان
دانشگاه علوم و فنون دریایی خرمشهر
چکیده
زمین‌لغزش‌ها از جمله مخاطرات طبیعی کلیدی در حوضه شمال تهران هستند که به دلیل ویژگی‌های زمین‌شناختی، توپوگرافی ناهموار و فعالیت‌های انسانی مانند جاده‌سازی، تهدیدات قابل‌توجهی ایجاد می‌کنند. این مطالعه یک رویکرد ترکیبی نوآورانه با وزن‌دهی پویا (Dynamic Weighting) مبتنی بر الگوریتم‌های PSO و GA برای پهنه‌بندی حساسیت زمین‌لغزش در حوضه شمال تهران ارائه می‌دهد. برخلاف روش‌های سنتی مانند نسبت فراوانی (FR)، شاخص آماری (SI) و آنتروپی شانون (SE) که از وزن‌های ثابت استفاده می‌کنند، این روش وزن‌های عوامل (مانند فاصله از رودخانه، شیب، و سنگ‌شناسی) را بر اساس داده‌های زمانی مانند بارندگی فصلی و فعالیت‌های انسانی با استفاده از الگوریتم (PSO) تنظیم می‌کند. داده‌های بارندگی و 150 رویداد زمین‌لغزش (2024-2005) از ایستگاه‌های هواشناسی محلی و پایگاه‌های داده زمین‌شناسی جمع‌آوری شدند. داده‌های ورودی شامل هشت عامل کلیدی (فاصله از رودخانه، فاصله از جاده، شیب، سنگ‌شناسی، ارتفاع، جهت شیب، فاصله از گسل، و کاربری اراضی) و داده‌های بارندگی فصلی بودند. نتایج نشان داد که وزن‌دهی پویا دقت پیش‌بینی را تا 15% (بر اساس AUC-ROC) نسبت به مدل‌های ثابت بهبود می‌دهد، به‌ویژه در فصول پرباران که وزن فاصله از رودخانه افزایش می‌یابد (vj=8.2 در مقایسه با vj=7.21 در مدل ثابت). مدل PSO با AUC-ROC=0.923 و GA با AUC-ROC=0.917 دقت بالاتری نسبت به مدل‌های سنتی (FR با AUC-ROC=0.804) نشان دادند. نقشه‌های خطر پویا مناطق پرخطر (مانند نزدیکی رودخانه‌ها با vj=8.23 در فصل بارانی) را با دقت بالاتری شناسایی کردند. این رویکرد برای مدیریت ریسک زمین‌لغزش در مناطق کوهستانی شهری مانند حوضه شمال تهران ارزشمند است و می‌تواند به‌عنوان الگویی برای سایر مناطق مشابه استفاده شود.
کلیدواژه‌ها

عنوان مقاله English

Landslide Susceptibility Modeling Using PSO-GA-Based Dynamic Spatio-Temporal Weighting in Northern Tehran Basin

نویسندگان English

elham salehian dehkordi
heeva elmizadeh
kmsu
چکیده English

Landslides represent a critical natural hazard in the Northern Tehran Basin, posing significant threats due to its complex geological setting, rugged topography, and anthropogenic activities such as road construction. This study introduces an innovative hybrid framework incorporating dynamic weighting based on Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) for landslide susceptibility zonation. Unlike conventional methods (e.g., Frequency Ratio [FR], Statistical Index [SI], and Shannon Entropy [SE]), which employ static weights, our approach dynamically adjusts factor weights (e.g., distance to rivers, slope, lithology) using PSO, accounting for temporal variables such as seasonal rainfall and human activity. We compiled rainfall data and 150 landslide events (2005–2024) from local meteorological stations and geological databases. Input parameters included eight key factors (distance to rivers, distance to roads, slope, lithology, elevation, aspect, distance to faults, and land use) alongside seasonal rainfall. Results demonstrate that dynamic weighting improves prediction accuracy by 15% (AUC-ROC = 0.923 for PSO vs. 0.804 for FR), particularly during high-rainfall seasons where river proximity weight increased (vj = 8.2 vs. 7.21 in static models). The PSO-GA hybrid outperformed traditional models, with PSO (AUC-ROC = 0.923) and GA (AUC-ROC = 0.917) showing superior precision. Dynamic hazard maps accurately identified high-risk zones (e.g., near rivers with vj = 8.23 during rainy seasons). This approach offers a robust tool for landslide risk management in urbanized mountainous regions like Northern Tehran and serves as a replicable model for similar environments globally.

کلیدواژه‌ها English

Dynamic weighting
PSO-GA hybrid algorithm
Northern Tehran Basin
Hazard zonation
Landslide modeling
Agboola, G., Hashemi Beni, L., Elbayoumi, T., & Thompson, G. (2024). Optimizing landslide susceptibility mapping using machine learning and geospatial techniques. Ecological Informatics, 81, 102583. https://doi.org/10.1016/j.ecoinf.2024.102583
Amiri, P., Afifi, M. A., & Moghaleh, M. (2022). Future studies and potential assessment of flood occurrence in Tehran city using support vector machine (SVM) algorithm. Journal of Physical Geography, *14*(55), 77-93. https://doi.org/20.1001.1.20085656.1401.15.55.5.7. (in Persian)
Baharvand, S. (2023). Landslide susceptibility assessment using frequency ratio and fuzzy logic models (Case study: Khorramabad-Arak Freeway). Geography and Environmental Hazards, 12 (1), 103-116. https://doi.org/10.22067/geoeh.2022.75264.1201. (in Persian)
Batar, A. K., & Watanabe, T. (2021). Landslide susceptibility mapping and assessment using geospatial platforms and weights of evidence (WoE) method in the Indian Himalayan region: Recent developments, gaps, and future directions. ISPRS International Journal of Geo-Information, 10(3), 114. https://doi.org/10.3390/ijgi10030114
Bordbar, M., Aghamohammadi, H., Pourghasemi, H. R., Zabihi, M., & Blaschke, T. (2022). Multi-hazard spatial modeling via ensembles of machine learning and meta-heuristic techniques. Scientific Reports, 12, 1451. https://doi.org/10.1038/s41598-022-05364-y
Chen, Z., Tang, J., & Song, D. (2024). Modeling landslide susceptibility using alternating decision tree and support vector. Terrestrial, Atmospheric and Oceanic Sciences, 35(1), 12. https://doi.org/10.1007/s44195-024-00074-6
Cui, H.-Z., Tong, B., Wang, T., Dou, J., & Ji, J. (2024). A hybrid data-driven approach for rainfall-induced landslide susceptibility mapping: Physically-based probabilistic model with convolutional neural network. Journal of Rock Mechanics and Geotechnical Engineering. Advance online publication.
Daniel, M. T., Ng, T. F. A., Kadir, M., & Pereira, J. J. (2021). Landslide susceptibility modeling using a hybrid bivariate statistical and expert consultation approach in Canada Hill, Sarawak, Malaysia. Frontiers in Earth Science, 9, 616225. https://doi.org/10.3389/feart.2021.616225
Dhakal, D., Singh, K., Onyelowe, K. C., Kumar, R., Sharma, A., & Verma, P. (2025). Enhancing landslide disaster prediction by evaluating non-landslide area sampling in machine learning models for Spiti Valley, India. Scientific Reports, 15, 12242. https://doi.org/10.1038/s41598-025-95087-7
Emadodin, S., Taheri, V., Mohammadghasemi, M., & Nazarigozik, Z. (2021). Landslide susceptibility zoning using frequency ratio and statistical index models in Oghan watershed. Quantitative Geomorphological Research, 9(4), 75-95. https://doi.org/10.22034/gmpj.2021.248268.1211. (in Persian)
Feng, L., Zhang, M., Mao, Y., Chen, X., Wang, J., & Liu, H. (2025). Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed. Scientific Reports, 15, 13250. https://doi.org/10.1038/s41598-025-96748-3
Ghanavati, A. A., Ahmadabadi, A., & Gholami, M. (2019). Landslide susceptibility assessment using entropy index and support vector machines algorithm (Case study: Kan watershed). Quantitative Geomorphological Research, 8(1), 16-33. (in Persian)
Ghasemian, B., Abedini, M., Rostaei, S., & Shirzadi, A. (2021). Evaluation of landslide susceptibility using a new hybrid algorithm-based model (Case study: Kamyaran County, Kurdistan Province). Quantitative Geomorphological Research, 9(4), 130-146. https://doi.org/10.22034/gmpj.2021.131015. (in Persian)
Ghasemian, B., Shahabi, H., Shirzadi, A., Al-Ansari, N., Jaafari, A., Geertsema, M., Melesse, A. M., Singh, S. K., & Ahmad, A. (2022). Application of a novel hybrid machine learning algorithm in shallow landslide susceptibility mapping in a mountainous area. Frontiers in Environmental Science, 10, 897254. https://doi.org/10.3389/fenvs.2022.897254
Gu, T., Duan, P., Wang, M., Zhang, X., Liu, Y., & Chen, H. (2024). Effects of non-landslide sampling strategies on machine learning models in landslide susceptibility mapping. Scientific Reports, 14, 7201. https://doi.org/10.1038/s41598-024-57964-5
Halder, K., Srivastava, A. K., Ghosh, A., Chatterjee, R., Mukhopadhyay, A., & Das, S. (2025). Improving landslide susceptibility prediction through ensemble recursive feature elimination and meta-learning framework. Scientific Reports, 15, 5170. https://doi.org/10.1038/s41598-025-87587-3
Hemmati, F., & Hejazi, A. (2017). Landslide hazard zoning using logistic regression statistical method in Lavasanat watershed. Applied Research in Geographical Sciences, 17(45), 7-25. https://doi.org/20.1001.1.22287736.1396.17.45.1.9. (in Persian)
Hong, H. (2023). Assessing landslide susceptibility based on hybrid Best-first decision tree with ensemble learning model. Ecological Indicators, 146, 109968. https://doi.org/10.1016/j.ecolind.2023.109968
Kainthura, P., & Sharma, N. (2022). Hybrid machine learning approach for landslide prediction, Uttarakhand, India. Scientific Reports, 12, 20101. https://doi.org/10.1038/s41598-022-22814-9
Kaushal, A., Gupta, A. K., & Sehgal, V. K. (2024). A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data. Scientific Reports, 14, 30071. https://doi.org/10.1038/s41598-024-79266-6
Khosravi, S., Entezari, M., Ahmadabadi, A., & Pourmousavi, S. M. (2020). Analysis of the effect of Tehran's urban development on the hydrologic and geomorphologic cycle of Ovin-Darakeh River. Quantitative Geomorphological Research, 9(1), 184-202. https://doi.org/10.22034/gmpj.2020.109542. (in Persian)
Li, M., Wang, H., Chen, J., & Zheng, K. (2024). Assessing landslide susceptibility based on the random forest model and multi-source heterogeneous data. Ecological Indicators, 158, 111600. https://doi.org/10.1016/j.ecolind.2024.111600
Liang, Z., Wang, C., Duan, Z., Liu, H., Liu, X., & Ullah Jan Khan, K. (2021). A Hybrid Model Consisting of Supervised and Unsupervised Learning for Landslide Susceptibility Mapping. Remote Sensing, 13(8), 1464. https://doi.org/10.3390/rs13081464
Onyelowe, K. C., Moghal, A. A. B., Ahmad, F., Ebid, A. M., Alrowais, R., & Sutanto, M. H. (2024). Numerical model of debris flow susceptibility using slope stability failure machine learning prediction with metaheuristic techniques trained with different algorithms. Scientific Reports, 14, 19562. https://doi.org/10.1038/s41598-024-70634-w
Ozturk, D., & Uzel-Gunini, N. (2022). Investigation of the effects of hybrid modeling approaches, factor standardization, and categorical mapping on the performance of landslide susceptibility mapping in Van, Turkey. Natural Hazards, 114(3), 2571-2604. https://doi.org/10.1007/s11069-022-05480-y
Rafiei Sardooi, E. (2022). Landslide susceptibility simulation with data mining models in Rabor region, Kerman Province. Watershed Management Research Journal, 35(2), 101-118. https://doi.org/10.22092/wmrj.2021.356462.1439. (in Persian)
Rodrigues Neto, J. M., & Bhandary, N. P. (2024). Landslide susceptibility assessment by machine learning and frequency ratio methods using XRAIN radar-acquired rainfall data. Geosciences, 14(6), 171. https://doi.org/10.3390/geosciences14060171
Rohan, E., Shelef, B., Mirus, T., & Coleman, T. (2023). Prolonged influence of urbanization on landslide susceptibility. Landslides, 20(5), 1023-1035. https://doi.org/10.1007/s10346-023-02034-6
Roshanzamir, S. (2025). Investigating the factors affecting landslide occurrence and susceptibility zoning using Dempster-Shafer model in Mazlaghanchai watershed, Markazi Province. Watershed Management Research Journal, 38(1), 113-127. https://doi.org/10.22092/wmrj.2023.360607.1502. (in Persian)
Tan, J., Yang, C., Wang, Y., Xiong, H., & Ma, C. (2024). A hybrid model to overcome landslide inventory incompleteness issue for landslide susceptibility prediction. Geocarto International, 39(1). https://doi.org/10.1080/10106049.2024.2322066
Tang, L., Yu, X., Jiang, W., Zhang, J., & Li, Y. (2023). Comparative study on landslide susceptibility mapping based on unbalanced sample ratio. Scientific Reports, 13, 5823. https://doi.org/10.1038/s41598-023-33186-z
Viet, D. T., Doan, A. T., & Tran, A. I. (2023). Deep learning to assess the effects of land use/land cover and climate change on landslide susceptibility in the Tra Khuc river basin of Vietnam. Geocarto International, 38(1), 1-25. https://doi.org/10.1080/10106049.2023.2198856
Xu, S. (2024). Fast hybrid methods for modeling landslide susceptibility in Ardal County. Scientific Reports, 14, 3003. https://doi.org/10.1038/s41598-024-53120-1
Ye, C., Wu, H., Oguchi, T., Tang, Y., Pei, X., & Wu, Y. (2025). Physically Based and Data-Driven Models for Landslide Susceptibility Assessment: Principles, Applications, and Challenges. Remote Sensing, 17(13), 2280. https://doi.org/10.3390/rs17132280
Youssef, K., Shao, K., Moon, S., Zhang, X., Liu, Q., & Li, X. (2023). Landslide susceptibility modeling by interpretable neural network. Communications Earth & Environment, 4, 162. https://doi.org/10.1038/s43247-023-00806-5
Zhou, W., Zhou, Y., Liang, S., Chen, X., Li, J., & Wang, R. (2025). A new framework for landslide susceptibility mapping in contiguous impoverished areas using machine learning and catastrophe theory. Scientific Reports, 15, 10620. https://doi.org/10.1038/s41598-025-88070-9