Structural optimisation and input selection of an artificial neural network for river level prediction

Summary Accurate river level prediction, necessary for reliable flood forecasting, is a difficult task due to the complexity and inherent nonlinearity of the catchment hydrological system. Although artificial neural networks (ANNs) offer advantages over mechanistic or conceptual hydrological models for river level prediction, their applicability is limited by the fact that each ANN has to be specifically optimised and trained for a particular prediction problem and suitable input vectors selected. A recently developed novel optimisation algorithm combining properties of simulated annealing and tabu search is used to arrive at an optimal ANN for the prediction of river levels 5 h in advance. The algorithm seeks to minimise the value of a cost function based on the complexity and performance of the ANN. This is done by removing inter-neuron connections and adjusting the weights of the remaining connections. The candidate inputs presented to the algorithm were: current values of river levels at the flood location and two upstream locations; the change in level over the previous 4 h at the flood point, mean sea level pressure (SLP) and the change in SLP over the previous 24 h. The optimisation removed 79% of the network connections and three of the candidate inputs, leaving the current levels at the two upstream locations and at the flood point as the only inputs. The optimised ANN was then trained using the standard backpropagation algorithm. This methodology produces an ANN of greatly reduced complexity albeit with a reduced performance compared to an unoptimised ANN trained with backpropagation only. However, it has the advantage of being generally applicable and represents an improvement over trial and error as a method of ANN structural optimisation and input selection. For this prediction problem, current levels at two upstream locations and at the flood point are the best predictors of the level at the flood point.

[1]  Teresa Bernarda Ludermir,et al.  An Optimization Methodology for Neural Network Weights and Architectures , 2006, IEEE Transactions on Neural Networks.

[2]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[3]  Jenq-Neng Hwang,et al.  The cascade-correlation learning: a projection pursuit learning perspective , 1996, IEEE Trans. Neural Networks.

[4]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[5]  Robert J. Abrahart,et al.  Symbiotic adaptive neuro-evolution applied to rainfall-runoff modelling in northern England , 2006, Neural Networks.

[6]  Randall S. Sexton,et al.  Simultaneous optimization of neural network function and architecture algorithm , 2004, Decis. Support Syst..

[7]  Richard Labib,et al.  Performance of Neural Networks in Daily Streamflow Forecasting , 2002 .

[8]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[9]  K. P. Sudheer,et al.  Short‐term flood forecasting with a neurofuzzy model , 2005 .

[10]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[11]  H. Riedwyl.  Goodness of Fit , 1967 .

[12]  Ozgur Kisi,et al.  River Flow Modeling Using Artificial Neural Networks , 2004 .

[13]  K. P. Sudheer,et al.  Rainfall‐runoff modelling using artificial neural networks: comparison of network types , 2005 .

[14]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[15]  N. Null.  Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[16]  Sharad K. Jain,et al.  Setting Up Stage-Discharge Relations Using ANN , 2000 .

[17]  Ashu Jain,et al.  Comparative Analysis of Event-Based Rainfall-Runoff Modeling Techniques—Deterministic, Statistical, and Artificial Neural Networks , 2003 .

[18]  David E. Rumelhart,et al.  Generalization by Weight-Elimination with Application to Forecasting , 1990, NIPS.

[19]  Vijay P. Singh,et al.  Analysis of Soil Water Retention Data Using Artificial Neural Networks , 2004 .

[20]  Teresa Bernarda Ludermir,et al.  Comparison of the Effectiveness of Different Cost Functions in Global Optimization Techniques , 2007, 2007 International Joint Conference on Neural Networks.

[21]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[22]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[23]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[24]  A. Elshorbagy,et al.  Performance Evaluation of Artificial Neural Networks for Runoff Prediction , 2000 .

[25]  R. S. Govindaraju,et al.  Artificial Neural Networks in Hydrology , 2010 .

[26]  M. Parlange,et al.  Conditioning stochastic properties of daily precipitation on indices of atmospheric circulation , 1998 .

[27]  K. Thirumalaiah,et al.  Hydrological Forecasting Using Neural Networks , 2000 .

[28]  A. Soldati,et al.  River flood forecasting with a neural network model , 1999 .

[29]  R. Falconer,et al.  Neural Networks tor Predicting Seawater Bacterial Levels , 2005 .

[30]  R Govindaraju,et al.  ARTIFICIAL NEURAL NETWORKS IN HYDROLOGY: II, HYDROLOGIC APPLICATIONS , 2000 .

[31]  Kuolin Hsu,et al.  Application of a recurrent neural network to rainfall-runoff modeling , 1997 .

[32]  Dara Entekhabi,et al.  Preserving high-resolution surface and rainfall data in operational-scale basin hydrology: a fully-distributed physically-based approach , 2004 .

[33]  W. White.  Water in rivers: flooding , 2001 .

[34]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[35]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.