Mapping Water Erosion Dynamics in East of Iran using High-Resolution UAV Imaging
Subject Areas : Sustainable Development
Amir Alizadeh
1
,
Zahra Azizi
2
1 - Department of Remote Sensing and GIS, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 - Department of Geoinformation & Geomatics Engineering, Faculty of Civil, Water and Environmental Engineering, Shahid Beheshti University, Tehran, Iran. *(Corresponding Author)
Keywords: Gully erosion, morphometric indices, machine learning, classification tree, spatial analysis.,
Abstract :
Background and Purpose: The Dashtiari region in southeastern Iran is characterized by extensive surface gullies, which remain largely unmonitored and have caused significant damage to villages and infrastructure. This study aims to develop a methodology for automatically extracting gully patterns using high-resolution UAV-derived digital elevation models (DEMs) and a combination of morphometric indices. The focus is on evaluating the effectiveness of these indices in improving gully pattern recognition, a task that requires detailed information and complex modeling processes typically inaccessible to non-experts. Method: We employed simple morphometric indices, including the Valley Depth Index (VD), Topographic Position Index (TPI), Positive Openness Index (PO), Red Relief Image Map (RRIM), elevation, slope degree, and the PO-DEM combination, to extract gully patterns. The automatically extracted gully patterns were compared with ground-truth samples to assess spatial correlation. Additionally, the performance of these indices was compared with that of classification tree (CT) models, a robust machine learning technique, using the same morphometric indices. Results: The performance of pattern extraction techniques was evaluated using four accuracy metrics: Accuracy Index, True Skill Statistic (TSS), Cohen's Kappa, and Matthews Correlation Coefficient (MCC). The results indicated that individual indices such as PO, TPI, and RRIM were insufficient to reliably delineate gully patterns. However, the PO-DEM combined index provided a better classification of gully presence and absence. The CT model, considering all four criteria, demonstrated superior performance in terms of adaptability and predictive power. Discussion:The findings suggest that while individual morphometric indices have limited utility in accurate gully pattern recognition, combining indices, particularly PO-DEM, enhances classification reliability. The CT model's superior performance underscores the potential of machine learning techniques in geospatial analysis. Moreover, the time efficiency of automated techniques compared to manual delineation highlights the practical benefits of integrating UAV imagery and advanced modeling approaches in erosion monitoring and management.
منابع
حيدريان، پ.، رنگزن، ک.، ملکي، س.، تقي¬زاده، ا. 1393. تلفيق تکنيک¬هاي سنجش از دور، GIS و مدل LCM با رويکرد مدل¬سازي توسعه شهري (نمونه موردي: کلان¬شهر تهران)، مطالعات جغرافيايي مناطق خشک، 5 (17): 100-87.
رمضاني، ن.، جعفري، ر. و ايزانلو، ا. 1390، بررسي تغييرات کاربري اراضي اسفراين خراسان شمالي در 4 دهه گذشته، مجله سنجش از دور و GIS ايران، 3 (2): 37-19.
سلمان¬ماهيني، ع.ر. و کامياب، ح.ر. 1389، در ترجمه سنجش از دور و سامانه هاي اطلاعات جغرافيايي کاربردي با نرم افزار ايدريسي، رونالد ايستمن، ج. نشر مهر مهديس، 610 ص.
شريفي، م.ب. و صالحي سده، ر.، 1384. کاربرد شبکه¬هاي عصبي در پيش¬بيني جريان رودخانه در حوزه معرف کارده. کميته تحقيقات شرکت سهامي آب منطقه¬اي خراسان، دفتر فني و پژوهش¬هاي کاربردي شرکت مديريت منابع آب ايران.
عزيزي قلاتي، س.، 1392. مدل¬سازي تغييرات کاربري اراضي با استفاده از تکنيک¬هاي سنجش از دور و سامانه¬هاي اطلاعات جغرافيايي در منطقه کوهمره سرخي استان فارس، پايان¬نامه کارشناسي ارشد، دانشگاه شهيد چمران اهواز.
غلامعلي¬فرد، م.، جورابيان شوشتري، ش.، حسيني کهنوج، س.ح.، و ميرزايي، م. 1391. مدل¬سازي تغييرات کاربري اراضي سواحل استان مازندران با استفاده از LCM در محيط GIS، مجله محيط¬شناسي، 38 (4): 124-109.
فلاحتکار، س.، حسيني، س.م.، سلمان ماهيني، ع.ر.، و ايوبي، ش.ا. 1395. پيش¬بيني تغييرات کاربري اراضي با استفاده از مدل LCM، پژوهش¬هاي محيط زيست، 7 (13): 174-163.
قبائي سوق، م.، مساعدي، ا.، حسام، م.، و هزارجريبي، ا. 1389. ارزيابي تأثیر پيش¬پردازش پارامترهاي ورودي به شبکه عصبي مصنوعي (ANNs) با استفاده از روش¬هاي رگريسون گام به گام و گاما تست بهمنظور تخمين سريع¬تر تبخير و تعرق روزانه، نشريه آب و خاک، 24 (3): 624-610.
کريمي، ک.، و کمکي، چ.ب. 1394. پايش، ارزيابي و پيش¬بيني روند تغييرات مکاني کاربري اراضي/پوشش زمين با استفاده از مدل زنجيره¬اي مارکوف (مطالعه موردي: دشت بسطاق-خراسان جنوبي)، مجله سنجش از دور و سامانه اطلاعات جغرافيايي در منابع طبيعي، 6 (2): 88-75.
ميرعليزاده فرد، س.ر. و علي¬بخشي، س.م. 1395. پايش و پيش¬بيني روند تغييرات کاربري اراضي با استفاده از مدل زنجيره مارکوف و مدلساز تغيير کاربري اراضي (مطالعه¬ي موردي: دشت برتش دهلران، ايلام)، مجله سنجش از دور و سامانه اطلاعات جغرافيايي در منابع طبيعي، 7 (2): 45-33.
Azimi Sardari, M.R.; Bazrafshan, O.; Panagopoulos, T.; Sardooi, E.R. 2019. Modeling the Impact of Climate Change and Land Use Change Scenarios on Soil Erosion at the Minab Dam Watershed. Sustainability, 11, 3353.
Bishop, C. M., & others. (1995). Neural networks for pattern recognition. Oxford university press.
Chin-Wei Chuang, Chao-Yuan Lin, Chang-Hai Chien, Wen-Chieh Chou, 2011, Application of Markov-chain model for vegetation restoration assessment at landslide areas caused by a catastrophic earthquake in Central Taiwan, Ecological Modelling, Volume 222, Issue 3, Pages 835-845.
Dewan, A. M., & Yamaguchi, Y. (2009). Land use and land cover change in Greater Dhaka, Bangladesh: Using remote sensing to promote sustainable urbanization. Applied Geography, 29(3), 390–401. https://doi.org/10.1016/j.apgeog.2008.12.005
Eastman, J. R. (2006). Idrisi Andes Guide to GIS and Image Proccesing, Clark Labs, Clark University, USA. Ellis, E. and L. Porter-Bolland (2008)," Is communitybased forest management more effective than protected areas? A comparison of land use/land cover change in two neighbor. Forest Ecology and Management, (256), 1971–1983.
J.F. Fox, A.N. Papanicolaou, 2008, An un-mixing model to study watershed erosion processes, Advances in Water Resources, Volume 31, Issue 1, Pages 96-108,
Ji, X., Thompson, A., Lin, J., Jiang, F., Li, S., Yu, M., & Huang, Y. (2019). Simulating and assessing the evolution of collapsing gullies based on cellular automata-Markov and landscape pattern metrics: a case study in Southern China. Journal of Soils and Sediments, 19(7), 3044-3055.
Lu, D., Mausel, P., Brondizio, E., & Moran, E. (2004). Change detection techniques. International Journal of Remote Sensing, 25(12), 2365–2401.
Mitsova, D., Shuster, W., and Wang, X. 2011. A cellular automata model of land cover change to integrate urban growth with open space conservation. Landscape and Urban Planning. 99:141-153.
Myint, S. W., & Wang, L. (2006). Multicriteria decision approach for land use land cover change using Markov chain analysis and a cellular automata approach. Canadian Journal of Remote Sensing, 32(6), 390–404. https://doi.org/10.5589/m06-032
Oliveira, K. De, Antonio, C., Soares, A., Eduardo, G., Simões, A., Lemos, N., … Rosa, A. (2018). Markov chains and cellular automata to predict environments subject to deserti fi cation. Journal of Environmental Management, 225(April), 160–167. https://doi.org/10.1016/j.jenvman.2018.07.064
Pérez-Vega, A., Mas, J. F., & Ligmann-Zielinska, A. (2012). Comparing two approaches to land use change modeling and their implications for the assessment of biodiversity loss in a deciduous tropical forest. Environmental Modelling and Software, 29(1), 11–23. https://doi.org/10.1016/j.envsoft.2011.09.011
Petit, C., Scudder, T., & Lambin, E. (2001). Quantifying processes of land-cover change by remote sensing: Resettlement and rapid land-cover changes in south-eastern Zambia. International Journal of Remote Sensing, 22(17), 3435–3456. https://doi.org/10.1080/01431160010006881
Torahi, A. A., & Rai, S. C. (2011). Land Cover Classification and Forest Change Analysis , Using Satellite Imagery - A Case Study in Dehdez Area of Zagros Mountain in Iran. Journal of Geographic Information System, 3(January), 1–11. https://doi.org/10.436/jgis.2011.31001
Weng, Q. 2002. Land use change analysis in the Zhujiang Delta of China using satellite remote sensing, GIS and stochastic modeling. Journal of Environmental Management. 64: 273-284.
Wu, Q., Li, H., Wang, R., Paulussen, J., He, Y., Wang, M., … Wang, Z. (2006). Monitoring and predicting land use change in Beijing using remote sensing and GIS. Landscape and Urban Planning, 78(4), 322–333.
