Investigating prediction performance of an artificial neural network and a numerical model of the tidal signal at Puerto Belgrano, Bahia Blanca Estuary (Argentina)

• Autorzy: Pierini J. , Lovallo M. , Telesca L. , Gómez E.

Identyfikatory

DOI

10.2478/s11600-012-0093-x

• Języki publikacji: EN

Abstrakty

EN

In the present study we compare performances of the prediction of hourly tidal level variations at Puerto Belgrano, a coastal site in the Bahia Blanca Estuary (Argentina), by means of the MOHID model, which is a numerical model designed for coastal and estuarine shallow water applications, and of an artificial neural network (ANN). It was shown that the ANN model is able to predict the hourly tidal levels over long term duration with at least seven days of observations and with a better performance in respect to the numerical model. Our findings can be useful to implement ANN-based tools for future studies of the hydrodynamics of Bahía Blanca estuary.

Słowa kluczowe

EN

artificial neural network; hydrodynamic model; tides

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2013
• Tom: Vol. 61, no. 6
• Strony: 1522--1537
• Opis fizyczny: Bibliogr. 27 poz.

Twórcy

autor

Pierini J.

• Comisión de Investigaciones Científicas, Universidad Nacional del Sur – Consejo Nacional de Investigaciones Científicas y Técnicas, Bahía Blanca, Argentina

autor

Lovallo M.

• Agenzia Regionale per la Protezione dell’Ambiente (ARPAB), Potenza, Italy

autor

Telesca L.

• National Research Council, Institute of Methodologies for Environmental Analysis, Tito, Italy

autor

Gómez E.

• Centro Cientifico Tecnologico, Universidad Nacional del Sur – Consejo Nacional de Investigaciones Científicas y Técnicas, Bahía Blanca, Argentina

Bibliografia

• 1. Campuzano, F., J.O. Pierini, and P. Leitão (2008), Hydrodynamics and sediments in Bahía Blanca estuary. Data analysis and modelling. In: R. Neves, J. Baretta, and M. Mateus (eds.), Perspectives on Integrated Coastal Zone Management in South America, IST Scientific Publishers, Lisbon, 483-503.
• 2. Chapra, S.C. (1997), Surface Water Quality Modeling, Water Resources and Environmental Engineering Series, McGraw-Hill, New York, 850 pp.
• 3. Deo, M.C., and G. Chaudhari (1998), Tide prediction using neural networks, Comput. Aided Civil Infrastruc. Eng. 13,2, 113-120, DOI: 10.1111/0885-9507.00091.
• 4. Fahlman, S.E. (1988), An empirical study of learning speed in back-propagation networks, Technical report CMU-CS-88-162, Carnegie-Mellon University, Computer Science Dept., Pittsburgh, USA.
• 5. Grubert, J. (1995), Prediction of estuarine instabilities with artificial neural networks, J. Comput. Civil Eng. ASCE 9,4, 266-274, DOI: 10.1061/(ASCE)0887-3801(1995)9:4(266).
• 6. Huang, W., C. Murray, N. Kraus, and J. Rosati (2003), Development of a regional neural network for coastal water level predictions, Ocean Eng. 30,17, 2275-2295, DOI: 10.1016/S0029-8018(03)00083-0.
• 7. IOC, IHO, BODC (2003), Centenary edition of the GEBCO digital atlas, Intergovernmental Oceanographic Commission and the International Hydrographic Organization as part of the General Bathymetric Chart of the Oceans; British Oceanographic Data Centre, Liverpool (CD-ROM).
• 8. Jacobs, R.A. (1988), Increased rates of convergence through learning rate adaptation, Neural Network 1,4, 295-307, DOI: 10.1016/0893-6080(88) 90003-2.
• 9. Lee, T.-L. (2004), Back-propagation neural network for long-term tidal predictions, Ocean Eng. 31,2, 225-238, DOI: 10.1016/S0029-8018(03)00115-X.
• 10. Leitão, P.C. (2003), Integration of scales and processes in the marine environment modelling, Ph.D. Thesis, Technical Superior Institute, Lisbon.
• 11. Lovallo, M., J.O. Pierini, and L. Telesca (2012), Power spectrum and Fisher-Shannon information plane analysis of tidal records, Physica A 391,20, 4711-4719, DOI: 10.1016/j.physa.2012.05.047.
• 12. Makarynskyy, O. (2004), Improving wave predictions with artificial neural networks, Ocean Eng. 31,5-6, 709-724, DOI: 10.1016/j.oceaneng.2003.05.003.
• 13. Martins, F., P.C. Leitão, A. Silva, and R. Neves (2001), 3D modelling in the Sado estuary using a new generic vertical discretization approach, Oceanol. Acta 24, Suppl. 1, 51-62, DOI: 10.1016/S0399-1784(01)00092-5.
• 14. Mase, H. (1995), Evaluation of artificial armour layer stability by neural network method. In: Proc. 26th Congress of IAHR, London, Int. Assoc. Hydraul. Res., The Netherlands, 341-346.
• 15. Mase, H., M. Sakamoto, and T. Sakai (1995), Neural network for stability analysis of rubble-mound breakwaters, J. Waterw. Port Coast. Ocean Eng. ASCE 121,6, 294-299, DOI: 10.1061/(ASCE)0733-950X(1995)121:6(294).
• 16. Mourre, B., L. Crosnier, and C. Le Provost (2006), Real-time sea-level gauge observations and operational oceanography, Philos. Trans. Roy. Soc. A 364,1841, 867-884, DOI: 10.1098/rsta.2006.1743.
• 17. Pierini, J.O. (2007), Circulación y transporte en zonas costeras del estuario de Bahía Blanca, Ph.D. Thesis, Universidad de Buenos Aires, Buenos Aires, 225 pp (in Spanish).
• 18. Pierini, J.O., and E. Gómez (2009), Tidal forecasting using RNN in Bahia Blanca estuary, Argentina, Interciencia 34,12, 851-856.
• 19. Pierini, J.O., J.E. Marcovecchio, F. Campuzano, and G.M.E. Perillo (2008a), Evolution of salinity and temperature in Bahía Blanca estuary, Argentina. In: R. Neves, J.W. Baretta, and M. Mateus (eds.), Perspectives on Integrated Coastal Zone Management in South America, IST Scientific Publishers, Lisbon, 505-513.
• 20. Pierini, J.O., F. Campuzano, J. Marcovecchio, and G.M.E. Perillo (2008b), The application of MOHID to assess the potential effect of sewage discharge system at Bahía Blanca estuary (Argentina). In: R. Neves, J.W. Baretta, and M. Mateus (eds.), Perspectives on Integrated Coastal Zone Management in South America, IST Scientific Publishers, Lisbon, 515-522.
• 21. Pierini, J.O., J. Marcovecchio, F. Campuzano, and G.M.E. Perilo (2008c), MOHID oil spill modelling in coastal zones: A case study in Bahía Blanca estuary (Argentina). In: R. Neves, J.W. Baretta, and M. Mateus (eds.), Perspectives on Integrated Coastal Zone Management in South America, IST Scientific Publishers, Lisbon, IST Scientific Publishers, 523-528.
• 22. Pierini, J.O., M.E. Streitenberger, and M.D. Baldini (2012), Evaluation of faecal contamination in Bahía Blanca estuary (Argentina) using a numerical model, Rev. Biol. Mar. Oceanogr. 47,2, 193-202.
• 23. Rumelhart, D.E., G.E. Hinton, and R.J. Williams (1986), Learning representations by back-propagating errors, Nature 323,6088, 533-536, DOI: 10.1038/323533a0.
• 24. Tsai, C.-P., and T.-L. Lee (1999), Back-propagation neural network in tidal-level forecasting, J. Waterw. Port Coast. Ocean Eng. ASCE 125,4, 195-202, DOI: 10.1061/(ASCE)0733-950X(1999)125:4(195).
• 25. Vaziri, M. (1997), Predicting Caspian Sea surface water level by ANN and ARIMA models, J. Waterw. Port Coast. Ocean Eng. ASCE 123,4, 158-162, DOI: 10.1061/(ASCE)0733-950X(1997)123:4(158).
• 26. Williams, T.P. (1994), Predicting changes in construction cost indexes using neural networks, J. Constr. Eng. Mgmt. ASCE 120,2, 306-320, DOI: 10.1061/(ASCE)0733-9364(1994)120:2(306).
• 27. Willmott, C.J. (1982), Some comments on the evaluation of model performance, Bull. Am. Meteorol. Soc. 63,11, 1309-1369, DOI: 10.1175/1520-0477 (1982)063〈1309:SCOTEOt〉2.0.CO;2.