پیش‌بینی تراکم جریان شکافنده در سواحل میانه با استفاده از شبکه‌های عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار/ دانشگاه آزاد اسلامی جویبار

2 استادیار گروه کامپیوتر، دانشگاه آزاد اسلامی، واحد جویبار

چکیده

جریان‌های شکافنده جریان‌هایی قوی، قارچی شکل هستند که عامل اصلی تلفات ناشی از غرق شدن شناگران در منطقه خیزاب ساحلی محسوب می‌شوند. با توجه به رفتار متغیر این جریان‌ها و محدودیت های بسیار در مشاهدات میدانی، در این پژوهش با استفاده از شبکه‌ عصبی مصنوعی، مدلی در مورد تخمین میزان تراکم جریان‌های شکافنده در سواحل حالت میانه ارائه شده است. به این منظور نخست اطلاعات مرتبط به سیستم جریان شکافنده از طریق مدل عددی Mike21/3 به صورت پارامترهای بی‌بعد عدد فرود، ارتفاع موج، پهنای خیزاب و پهنای کانال جریان استخراج شدند. در گام بعدی تاثیر هر یک از پارامترهای بی‌بعد روی تراکم جریان‌ برای توابع و نرون‌های مختلف شبکه عصبی بررسی شد. سپس نتایج مدل در هجوم امواجی با ارتفاع مختلف با نتایج میدانی سایر محققین مورد مقایسه قرار گرفت و تطابق بسیار خوبی بین آن‌ها مشاهده شد. نتایج این تحقیق نشان می‌دهد با افزایش ارتفاع امواج بر سرعت جریان‌ و فواصل کانال ها افزوده می‌شود و به تدریج از میزان تراکم جریان‎کاسته می‌شود. نتایج دیگر این تحقیق حاکی از آن است در شرایطی که امواج کم‌ارتفاع‌تر بر دریا حاکمند، تابع گرادینت دیسنت ویت آداپتیو لرنینگ ریت (gda) با کمترین خطا (RMSE معادل 013/0) و در شرایطی که امواج مرتفع‌تر بر دریا حاکمند تابع کواسی نیوتن (bfg) با کمترین خطا (RMSE معادل 00282/0) هر کدام با 14 نرون دقیق‌ترین تخمین را از میزان تراکم جریان‌های شکافنده در سواحلی باحالت میانه ارائه می‌دهند.

کلیدواژه‌ها


عنوان مقاله [English]

Prediction of Rip Current Density Using Artificial Neural Networks in Intermediate Beaches

نویسندگان [English]

  • Azadeh Valipour 1
  • Hossein Shirgahi 2
1 Department of Marine Science and Technology, Jouybar Branch, Islamic Azad University, Jouybar, Iran.
2 Department of Computer Engineering, Jouybar Branch, Islamic Azad University, Jouybar, Iran.
چکیده [English]

Rip currents are strong, mushroom-shaped currents that are the main cause of swimmers’ drowning in the surf zones. In this study, a model is presented to estimate the rip current density on the intermediate-state beach using artificial neural network considering the variable behavior of these currents and the many limitations in field observations. For this purpose, the data related to the rip current system were first extracted as non-dimensional parameters including the Froude number, wave height, width of the surf zone, and width of the rip channel using the Mike21/3 numerical model. In the next step, the effect of each of the parameters was investigated on the rip density for different neural network functions and neurons. The results of the model were then compared with field observations of other researchers in different wave heights and very good agreement was observed between them. The results of this study show that with the increase in wave height, the current velocity and spacing of rip channels will increase and the rip density will gradually decrease. Other results of this study indicate that as the lower waves approach the beach, Gradient descent with adaptive learning rate (gda) function with the lowest error (RMSE equals 0.013) and as the higher waves approach the beach, Quasi-Newton (bfg) function each with 14 neurons give the most accurate estimate of the rip density on the intermediate-state beach.

کلیدواژه‌ها [English]

  • rip density
  • surf zone
  • Artificial neural network
  • Froude number
  • intermediate-state beach
[1] MacMahan JH, Thornton EB, Stanton TP, Reniers AJHM. Rip current review. Journal of Coastal Engineering. 2006; 53: 191-208.
[2] Dalrymple RA, MacMahan JH, Reniers AJHM, Nelko V. Rip currents, Annual Review Fluid Mechanics. 2011; 43: 551–81.
[3] Wei Z, Dalrymple RA, Xu M, Garnier R, Derakhti M. Short-crested waves in the surf zone. Journal of Geophysical Research: Oceans. 2017; 122.
[4] Shepard FP, Emery KO, La Fond EC. Rip currents: a process of geological importance. The Journal of Geology. 1941;49:337–69.
[5] Bowen AJ. Rip currents: 1: Theoretical investigations. Journal of Geophysical Research. 1969;74:5467–78.
[6] Bowen AJ, Inman DL. Rip currents. 2: Laboratory and field observations. Journal of Geophysical Research. 1969;74:5479–90.
[7] Dalrymple RA. A mechanism for rip current generation on an open coast. Journal of GeophysicalResearch. 1975; 80(24): 3485–87.
[8] Falques A, Coco G, Huntley DA. A mechanism for the generation of wave-driven rhythmic patterns in the surf zone. Journal of Geophysical Research. 2000; 105 (C10): 24, 071–24, 087.
[9] Mizumura K. Littoral currents around breakwaters. Proceeding of Coastal Structures '79. Washington, DC: ASCE; 1979. Vol.2. p. 778–91.
[10] Wind HG, Vreugdenhil CB. Rip-current generation near structures. Journal of Fluid Mechanics. 1986; 171:459–76.
[11] Castelle B, Scott. T, Brander RW, McCarroll RJ. Rip current types, circulation and hazard. Earth-Science Reviews. 2016; 163: 1– 21.
[12] ShortAD. Rip current type, spacing and persistence, Narrabeen Beach, Australia. Marine geology. 1985; 65: 47-71.
[13] Dean RG. Heuristic models of sand transport in the surf zone. Proceeding of First Australian Conference on Coastal Engineering; 1973; Australia. Sydney, N.S.W; 1973. p. 208-14.
[14] Wright LD, short AD. Morphodynamic variability of surf zones and beaches. Marine Geology. 1984; 56(1-4): 93-118.
[15] Sonu CJ. Field observations of nearshore circulation and meandering currents. Journal of Geophysical Research. 1972;77:3232–47.
[16] Huntley DA, Short AD. On the spacing between observed rip currents. Coastal Engineering. 1992;17:211-25.
[17] Short AD, Brander R. Regional variations in rip density Journal of Coastal Research. 1999; 15(3): 813–22.
[18] Eliot I. The persistence of rip current patterns on sandy beaches. Proceeding of 1st Aus. Conference Coastal Engineering. Australia: Institution of Engineers;1973.p.29–34.
[19] Whyte D, Turner IL, Ranasinghe R. Rip characterization on the Gold Coast, Australia: An analysis using coastal imaging techniques. Proceeding of Coasts and Ports 2005: Coastal Living - Living Coast; Australasian Conference. Australia; Barton, A.C.T.; Institution of Engineers; 2005.p.233–8.
[20] Turner IL, Whyte D, Ruessink BG, Ranasinghe R. Observations of rip spacing, persistence and mobility at a long, straight coastline. Marine Geology. 2007;236(3-4):209-21.
[21] Holman RA, Symonds G, Thornton EB, Ranasinghe R. Rip spacing and persistence on an embayed beach. Journal of Geophysical Research: Oceans. 2006;111:1-17.
[22] Symonds G, Holman RA, Bruno B. Rip currents. In: Thornton EB, editor. Coastal Dynamics'97. American Society of Civil Engineering; 1997. p.584–93.
[23] Babovic V, Kanizares R, Jenson HR, Klinting A. Neural networks as routine for error updating of numerical models. Journal of Hydraulic Engineering. 2001 Mar;127(3):181-93.
[24] Tsai CP, Lee T. Back-propagation neural network in tidal level forecasting. Journal of Waterway, Port, Coastal and Ocean Engineering. 1999; 125: 195–202.
[25] Sztobryn M. Forecast of storm surge by means of artificial neural network. Journal of Sea Research. 2003 Jun 1;49(4):317-22.
[26] Pape L, Ruessink BG, Wiering MA, Turner IL. Recurrent neural network modeling of nearshore sandbar behavior. Neural Networks. 2007; 20: 509–18.
[27] Singh AK, Deo MC, Sanil Kumar V. Prediction of littoraldrift with artificial neural networks. Hydrology and Earth System Sciences. 2008; 12: 267–75.
[28] Wang F, Zhou B, Xu J, Song L, Wang X. Application of neural network and MODIS 250 m imagery for estimating suspended sediments concentration in Hangzhou Bay. China. Environmental Geology. 2009; 56(6): 1093–1101.
[29] Moridnejad A, Abdollahi H, Alavipanah SK, Samani JMV, Moridnejad O, Karimi N. Applying artificial neural networks to estimate suspended sediment concentrations along the southern coast of the Caspian Sea using MODIS images. Arabian Journal of Geosciences. 2015; 8(2): 891–901.
[30] Maanen BV, Coco G, Bryan KR, Ruessink BG. The use of artificial neural networks to analyze and predict alongshore sediment transport. Nonlinear Processes in Geophysics. 2010; 17(5): 395–404.
[31] DHI Software. MIKE 21 User Guide Manual; 2014.
[32] Battjes JA, Janssen JPFM. Energy loss and set-up due to breaking of random waves. Proceeding of 16th International Conference of Coastal Engineering, ASCE; 1978. p. 569-87.
[33] Valipour A, Bidokhti AA. An analytical model for the prediction of rip spacing in intermediate beaches. Journal of Earth system Science. 2018; 127:108.
[34] Dawson CH. Applied Artificial Neural Network. Amazon's Book Store; 2016; 26 p.
[35] Hino M. Theory on the formation of rip-current and cuspidal coast. Proceedings of the 14th International Conference on Coastal Engineering. Copenhagen;American Society of Civil Engineering:1974. p. 901–19.
[36] Dronen N, Karunarathna H, Fredsoe J, Sumer BM, Deigaard R. An experimental study of rip channel flow. Coastal Engineering. 2002; 45(3– 4): 223–8.
[37] Haller MC, Ozkan-Haller T. Wave breaking and rip current circulation. Paper Presented at International Conference on Coastal Engineering.Cardiff;American Society of Civil Engineering: 2002. p.705–17.
[38] Mc Mahan JH, Reniers Ad JHM, Thornton Ed B and Stanton Tim P. Surf zone eddies coupled with rip current morphology. Journal of Geophysical Research: Oceans. 2004; 109: C07004.