Using an artificial neural network to model seasonal changes in beach profiles

An artificial neural network (ANN) was applied to predict seasonal beach profile evolution at various locations along the Tremadoc Bay, eastern Irish Sea. The beach profile variations in 19 stations for a period of about 7 years were studied using ANN. The model results were compared with field data. The most critical part of constructing ANN was the selection of minimum effective input data and the choice of proper activation function. Accordingly, some numerical techniques such as principal component analysis and correlation analysis were employed to detect the proper dataset. The geometric properties of the beach, wind data, local wave climate, and the corresponding beach level changes were fed to a feedforward backpropagation ANN. The performance of less than 0.0007 (mean square error) was achieved. The trained ANN model results had very good agreement with the beach profile surveys for the test data. Results of this study show that ANN can predict seasonal beach profile changes effectively, and the ANN results are generally more accurate when compared with computationally expensive mathematical model of the same study region. The ANN model results can be improved by the addition of more data, but the applicability of this method is limited to the range of the training data.

[1]  Henrik Kofoed-Hansen,et al.  Modelling of complex coastal environments: Some considerations for best practise , 2007 .

[2]  Kurt Hornik,et al.  Some new results on neural network approximation , 1993, Neural Networks.

[3]  D. Reeve,et al.  An investigation of the multi-scale temporal variability of beach profiles at Duck using wavelet packet transforms , 2007 .

[4]  R. Romanowicz,et al.  Nonlinear Transfer Function Modelling of beach morphology at Duck, North Carolina , 2009 .

[5]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[6]  D. Reeve,et al.  Beach profile evolution as an inverse problem , 2009 .

[7]  Relationship between beach profiles and waves at Duck, North Carolina, determined by canonical correlation analysis , 2000 .

[8]  Riccardo Briganti,et al.  Analysis of wave transmission behind low-crested breakwaters using neural networks , 2007 .

[9]  Oleg Makarynskyy,et al.  A Combined Harmonic Analysis–Artificial Neural Network Methodology for Tidal Predictions , 2007 .

[10]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[11]  Marco Wiering,et al.  Recurrent neural network modeling of nearshore sandbar behavior , 2007, Neural Networks.

[12]  Nicholas C. Kraus,et al.  Development of a regional neural network for coastal water level predictions , 2003 .

[13]  Mohammad Ali Ghorbani,et al.  Sea water level forecasting using genetic programming and comparing the performance with Artificial Neural Networks , 2010, Comput. Geosci..

[14]  N. Booij,et al.  A third-generation wave model for coastal regions-1 , 1999 .

[15]  Michael Blumenstein,et al.  Near-shore swell estimation from a global wind-wave model: Spectral process, linear, and artificial neural network models , 2007 .

[16]  S. Liang,et al.  Prediction models for tidal level including strong meteorologic effects using a neural network , 2008 .

[17]  H. K. Cigizoglu,et al.  Artificial intelligence methods in breakwater damage ratio estimation , 2005 .

[18]  Hanz D. Niemeyer,et al.  Wind-wave variability in a shallow tidal sea—Spectral modelling combined with neural network methods , 2009 .

[19]  Ana C. Teodoro,et al.  Retrieving TSM Concentration From Multispectral Satellite Data by Multiple Regression and Artificial Neural Networks , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Holger R. Maier,et al.  Determining Inputs for Neural Network Models of Multivariate Time Series , 1997 .

[21]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[22]  Edit J. Kaminsky,et al.  Neural network classification of remote-sensing data , 1995 .

[23]  S. Neill,et al.  A model of inter-annual variability in beach levels , 2008 .

[24]  Bing Yan,et al.  Prediction of sand ripple geometry under waves using an artificial neural network , 2008, Comput. Geosci..

[25]  S. Neill,et al.  Changes in wave climate over the northwest European shelf seas during the last 12,000 years , 2009 .

[26]  Dina Makarynska,et al.  Predicting sea-level variations at the Cocos (Keeling) Islands with artificial neural networks , 2008, Comput. Geosci..

[27]  R. Holman,et al.  Application of remote sensing video systems to coastline management problems , 2007 .

[28]  O. Makarynskyy,et al.  Improving wave predictions with artificial neural networks , 2004 .

[29]  Gregorio Iglesias,et al.  Headland-bay beach planform and tidal range: A neural network model , 2009 .

[30]  Oleg Makarynskyy,et al.  Wave Prediction and Data Supplementation with Artificial Neural Networks , 2007 .

[31]  Huixin Chen,et al.  A probability method for predicting time-dependent long-term shoreline erosion , 1999 .

[32]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[33]  Kwokwing Chau,et al.  A review on the integration of artificial intelligence into coastal modeling. , 2006, Journal of environmental management.

[34]  R. Holman,et al.  Morphodynamics of intermediate beaches: a video imaging and numerical modelling study , 2004 .

[35]  H. N. Southgate,et al.  Analysis and modeling of field data on coastal morphological evolution over yearly and decadal time scales. Part 1: Background and linear techniques , 2003 .

[36]  S. Neill,et al.  An enhanced depth-averaged tidal model for morphological studies in the presence of rotary currents , 2007 .

[37]  V. K. Agarwal,et al.  Artificial neural network to translate offshore satellite wave data to coastal locations , 2005 .

[38]  Marco Diani,et al.  Retrieval of sea water optically active parameters from hyperspectral data by means of generalized radial basis function neural networks , 2001, IEEE Trans. Geosci. Remote. Sens..