بهبود هندسه رودخانه و کنترل سیلاب: کاربرد الگوریتم بهینه‌سازی مبتنی بر آموزش و یادگیری

ملکپور, محمد مهدی; احمدی, محمد مهدی; قادری, کورش; رجبی زاده, یوسف

doi:10.61882/jii.2.3.285

بهبود هندسه رودخانه و کنترل سیلاب: کاربرد الگوریتم بهینه‌سازی مبتنی بر آموزش و یادگیری

نوع مقاله : مقاله پژوهشی

نویسندگان

محمد مهدی ملکپور

محمد مهدی احمدی

کورش قادری

یوسف رجبی زاده

گروه مهندسی آب، دانشکده کشاورزی، دانشگاه شهید باهنر کرمان، کرمان، ایران.

10.61882/jii.2.3.285

چکیده

هندسه مقطع رودخانه و تغییر شکل آن یکی از مسائل مهم و تاثیرگذار در زمینه مهندسی آب و رودخانه بوده و تاثیر مستقیم بر مدیریت، سلامت و جریان رودخانه دارد. دستیابی به شکل بهینه مقطع رودخانه از جمله مهمترین اقدامات سازه‌ای برای مدیریت رودخانه بوده که به کنترل سیل و کاهش تلفات جانی و مالی می‌انجامد. در این مطالعه، ابتدا از نرم‌افزار HEC-RAS به‌ منظور استخراج پارامترهای هندسی مقاطع عرضی و بررسی شرایط هیدرولیکی جریان بر روی بازه یک کیلومتری از رودخانه زاینده‌رود در ایران استفاده شد. پس از انجام شبیه‌سازی هیدرولیکی، هندسه بهینه مقاطع عرضی رودخانه توسط الگوریتم بهینه‌سازی مبتنی بر آموزش و یادگیری (TLBO) تعیین شد که هدف آن، حداکثرسازی حجم لایروبی در عین حفظ پایداری هیدرولیکی بود. سپس، ارزیابی میزان تطابق هر مقطع با حالت بهینه آن انجام پذیرفت. بررسی‌ نتایج حاصل از شبیه‌سازی هیدرولیکی نشان داد که روند تغییرات دو پارامتر عرض و عمق به ترتیب افزایش 69/26 درصد و کاهش 28/78 درصدی را از بالادست به پایین‌دست داشته‌اند. پس از فرآیند بهینه‌سازی، مساحت بهینه مقاطع بین %2/16 تا %28/24 افزایش داشته و روند افزایشی آن از بالا‌دست به پایین‌دست مشهود بود که بیانگر نیاز بیشتر به اصلاح مقطع در مقاطع پایین‌دست است. در نهایت، این رویکرد بهینه‌سازی اثربخشی قابل توجهی نشان داد، به‌گونه‌ای که ظرفیت آبگذری رودخانه پس از اجرای بهینه‌سازی تا %10/13 افزایش یافت و این امر در راستای هدف اصلی پژوهش، یعنی کنترل و کاهش ریسک سیلاب و کاهش خسارات جانی و مالی، محقق شد.

کلیدواژه‌ها

رودخانه زاینده‌رود

شبیه‌سازی‌هیدرولیکی

لایروبی

HEC-RAS

عنوان مقاله English

River Geometry Improvement and Flood Control: Application of Teaching Learning-Based Optimization Algorithm

نویسندگان English

Mohammad Mahdi Malekpour

Mohammad Mehdi Ahmadi

Kourosh Qaderi

Yousef Rajabizadeh

Department of Water Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Iran.

چکیده English

The geometry of river cross-sections and their morphological changes are among the most important and influential issues in the field of water and river engineering, directly affecting river management, ecological health, and flow dynamics. Achieving the optimal shape and geometry of river cross-sections is one of the key structural measures in river management, playing a crucial role in flood control, erosion prevention, and the reduction of human and financial losses. In this study, the HEC-RAS software was first employed to extract geometric parameters of cross-sections and to analyze the hydraulic flow conditions over a one-kilometer reach of the Zayandehrud River in Iran. Following the hydraulic simulation, the optimal geometry of the river cross-sections was determined using the Teaching Learning-Based Optimization (TLBO) algorithm, which aimed to maximize the dredging volume while maintaining hydraulic stability. Subsequently, the conformity of each cross-section with its optimal state was evaluated. The results of the hydraulic simulation indicated a significant trend in the changes of two parameters—width and depth—with an increase of 69.26% in width and a decrease of 28.78% in depth from upstream to downstream. After the optimization process, the optimal cross-sectional area increased by 2.16% to 28.24%, showing a clear upward trend from upstream to downstream and highlighting the greater necessity for cross-sectional modification in downstream sections of the river. This outcome emphasizes the spatial variability of river engineering requirements along the studied reach. Ultimately, the applied optimization approach demonstrated effective performance, enhancing the river’s flow capacity by up to 10.13% after optimization, while also contributing to flood risk reduction and significantly lowering potential human and financial losses.

کلیدواژه‌ها English

Dredging

HEC-RAS

Hydraulic simulation

Zayandehrud River

[1] Lord M. L, Germanaski D, Allmandinger N. E. Fluvial geomorphology: monitoring stream systems in response to a changing environment. The Geol Soc of Am, 2009; pp. 69–103.
[2] Singh V. P. On the theories of hydraulic geometry. Int J of Sediment Res, 2003: 18(3): 196–218.
[3] Mondal M, Ghosh S, Satpati L. N, Kolakata W. B. Character of cross-profiles with respect to the optimum channel cross-sections in the middle reach of the Ichamati River of West Bengal, India. Trans. Inst. Indian Geographers, 2016; 38(2): 201.
[4] Mondal M, Ghosh S, Satpati L.N. Optimum cross section index (OCI): a new approach for identification of an optimum channel—a case study of the Ichamati River, India. Arabian Journal of Geosciences, 2018; 11: 333. https://doi.org/10.1007/s12517-018-3667-3.
[5] Rose S, Peters N. E. Effects of urbanization on stream flow in the Atlanta area (Georgia, USA): a comparative hydrological approach. Hydrol. Process. 2001; 15: 1441–1457. doi: 10.1002/hyp.218.
[6] Liao K. H, Chan J. K. H, Huang Y. L. Environmental justice and flood prevention: the moral cost of floodwater redistribution. Landsc. Urban Plan. 2019; 189: 36–45. doi: 10.1016/j.landurbplan.2019.04.012.
[7] Hooke J. M. Channelized rivers: perspectives for environmental management, Andrew Brookes, Wiley, Chichester, 1988. No. of pages: 326. Earth Surf. Process. Landforms, 1990; 15: 291–292. doi: 10.1002/esp.3290150312.
[8] Mahmudi M, Tabatabai M. R. M, Nadoushani S. M. An analytical approach to the estimation of optimum river channel dimensions. Scientia Iranica A, 2019; 26(3): 1169-1181.
[9] Lee J.S, Julien P.Y. Downstream hydraulic geometry of alluvial channels, J. Hydraul. Eng. 2006; 132(12): 1347–1352.
[10] Biswal S, Sahoo B, Jha M.K, Bhuyan M.K. A hybrid machine learning-based multi-DEM ensemble model of river cross-section extraction: Implications on streamflow routing. Journal of Hydrology, 2023; 625(Part A): 129951.
[11] Chang S.Y, Ghahremani Z, Manuel L, Erfani S.M.H, Shen C, Cohen S, Van Meter K.J, Pierce J.L, Meselhe E.A, Goharian E. The Geometry of Flow: Advancing Predictions of River Geometry With Multi-Model Machine Learning. Water Resources Research, 2024; 60(10). https://doi.org/10.1029/2023WR036733.
[12] Shaghaghi S, Bonakdari H, Gholami A, Ebtehaj I, Zeinolabedini M. Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design. Applied Mathematics and Computation, 2017; 313: 271–286. http://dx.doi.org/10.1016/j.amc.2017.06.012.
[13] Malekpour M. M, Mohammad Rezapour Tabari M. Implementation of supervised intelligence committee machine method for monthly water level prediction. Arabian Journal of Geosciences, 2020; 13: 1049 https://doi.org/10.1007/s12517-020-06034-x.
[14] Malekpour M. M, Ahmadi M. M, Gugliotta M. Tabari M. M. R, Qaderi K. Estimation of suspended sediment load utilizing a super-optimized deep learning approach informed by the red fox optimization algorithm. Earth Sci Inform, 2025; 18: 286. https://doi.org/10.1007/s12145-025-01801-4.
[15] Nasiri N, Asghari A, Besalatpour A. A. Quantitative analysis of the human intervention impacts on hydrological drought in the Zayande-Rud River Basin, Iran. Journal of Water and Climate Change, 2022; 13(9): 3473. doi: 10.2166/wcc.2022.188.
[16] Ghenaati B, Ahmadi M. Modeling Hydrologic Consequences of Land Use and Climate Changes: The Case of Zayanderud Basin. AUT Journal of Modeling and Simulation, 2023; 55(2): 327-342. doi:10.22060/miscj.2024.22881.5347.
[17] Abou Zaki N, Torabi Haghighi A, M. Rossi P, Tourian MJ, Bakhshaee A, Kløve B. Evaluating Impacts of Irrigation and Drought on River, Groundwater and a Terminal Wetland in the Zayanderud Basin, Iran. Water, 2020; 12(5): 1302.
[18] Ogdahl M, Steinman A, Uzarski D, Thompson K. A methodology for assessing erosion control best management practice (BMP) effectiveness, 2014; pp. 15–16.
[19] Mehta D, Yadav S. M, Waikhom S, Prajapati K. Stable channel design of tapi river using HEC-RAS for surat region. Environmental Processes and Management, Water Science and Technology Library, 2020; 91: 25-36. https://doi.org/10.1007/978-3-030-38152-3_2.
[20] Sayari S, Mahdavi-Meymand A, Zounemat-Kermani M. Prediction of Critical Velocity in Pipeline Flow of Slurries Using TLBO Algorithm: A Comprehensive Study. Journal of Pipeline Systems Engineering and Practice, 2019; 11(2). https://doi.org/10.1061/(ASCE)PS.1949-1204.0000439.
[21] Kumar V, Yadav S. M. Optimization of Reservoir Operation with a New Approach in Evolutionary Computation Using TLBO Algorithm and Jaya Algorithm. Water Resources Management, 2018; 32: 4375-4391. https://doi.org/10.1007/s11269-018-2067-5.
[22] Malekpour M. M, Malekpoor H. Reservoir water level forecasting using wavelet support vector regression (WSVR) based on teaching learning-based optimization algorithm (TLBO). Soft Computing, 2022; 26: 8897–8909. https://doi.org/10.1007/s00500-022-07296-1.
[23] Rao R. V, Rao V. J, Vakharia D. P. Teaching–learning-based optimization: A novel method for constrained mechanical design optimization problems. Computer-Aided Design, 2011; 43: 303–315. https://doi.org/10.1016/j.cad.2010.12.015.
[24] Burele S, Sharma S, Ahmad Z, Gupta I. Numerical simulation-optimization for channelization of River Kosi. International Journal of Scientific Engineering and Technology, 2014; 3(9):1149-1155.
[25] Chahar B. Optimal design of a special class of curvilinear bottomed channel section. Journal of Hydraulic Engineering, 2007. Doi: 10.1061/(ASCE)0733-9429(2007)133:5(571).
[26] Chang H.H. Geometry of gravel streams, J. Hydraul. Div. 1980; 106(9): 1443–1456.
[27] Fazarinc R, Majes B, Mikoš M. Using results of mathematical modeling of debris flows for optimization of a river channel form to convey debris flows and floods. International Conference on Fluvial Hydraulics - River Flow, 2006; (2). DOI:10.1201/9781439833865.ch234.
[28] Huang, H.Q, Nanson, G.C. A stability criterion inherent in laws governing alluvial channel flow, Earth Surface Processes and Landforms, 2002; 27(9): 929-944.
[29] Lamine B. O. M, Ferreira V. G, Yang Y, Ndehedehe C. E, He X. Estimation of the Niger River cross-section and discharge from remotely-sensed products. Journal of Hydrology: Regional Studies, 2021; 36: 100862. https://doi.org/10.1016/j.ejrh.2021.100862.
[30] Mahesh K. Dredging Analysis and Decision Support System. International Journal of Engineering Innovations and Management Strategies, 2024; 1(5): 1-15.
[31] Nelson A. D, Collins V. D, Payne J. S, Abbe T. B. Proactive river corridor definition: Recommendations for a process-based width optimization approach illustrated in the context of the coastal Pacific Northwest. Wires Water, 2024; 11(3): e1711. https://doi.org/10.1002/wat2.1711.
[32] Prestegaard K. L, Matherne Katyl N. Spatial variations in the magnitude of the 1993 floods, Raccoon River Basin, Iowa. Geomorphol. Nat. Hazards, 1994; 10: 169–182. doi: 10.1016 B978-0-444-82012-9.50016-5.
[33] Ridolfi E, Alfonso L, Di Baldassarre G, Dottori F, Russo F, Napolitano F. An entropy approach for the optimization of cross-section spacing for river modelling. Hydrological Sciences Journal, 2014; 59(1). http://dx.doi.org/10.1080/02626667.2013.822640.
[34] Tabatabaei M. M, Shourian M, Karaimi M. Optimum stable channel geometry design using imperialist competitive algorithm. Environmental Earth Sciences, 2018; 77: 445. https://doi.org/10.1007/s12665-018-7634-9.
[35] Teal M. J, Anderson P.E. Sediment investigation and stable channel design for the lower mud river, in: Proceedings of Impacts of Global Climate Change, ASCE, 2005; pp. 1–12.
[36] Turan M. E, Yurdusev M. A. Optimization of open canal cross sections by differential evolution algorithm. Mathematical and Computational Applications, 2011; 16(1): 77-86.
[37] Yang Y. Construction period and cost optimization for river dredging engineering based on NSGA-II. Journal of Computational Methods in Sciences and Engineering, 2024; 24(4-5): 2879-2894. https://doi.org/10.3233/JCM-247524.