Neural networks for predicting nitrate-nitrogen in drainage water

Two artificial neural network (ANN) models, a trainable fast back-propagation (FBP) network and a self-organizing radial basis function (RBF) network, were developed for simulation of subsurface drain outflow and nitrate-nitrogen concentration in tile effluent. Experimental data collected at the Greenbelt Research Farm of Agriculture Canada over a 40-month period were used to train and validate the two models. The available field data were divided into training and testing scenarios, with the training file consisting of eight inputs and two outputs. A sensitivity analysis was performed by varying the network parameters to minimize the prediction error and determine the optimum network configuration. The best architecture for the FBP model comprised of 20 neurons in the hidden layer and a learning rate of 0.02, while the RBF network with a tolerance of 20 and a receptive field of 15 yielded 547 neurons in the hidden layer. Overall, the performance of the RBF neural network was superior to the FBP model in predicting the concentration of nitrate-nitrogen in drain outflow due to the application of manure and/or fertilizer. This information, in turn, can be used for proper fertilizer management; thereby, reducing not only the loss of valuable nitrogen fertilizer but also the potential for pollution of subsurface water by nitrate.

[1]  A. E. Greenberg,et al.  Standard methods for the examination of water and wastewater : supplement to the sixteenth edition , 1988 .

[2]  Anastasios N. Venetsanopoulos,et al.  Artificial neural networks - learning algorithms, performance evaluation, and applications , 1992, The Kluwer international series in engineering and computer science.

[3]  Qing Zhang,et al.  Forecasting raw-water quality parameters for the North Saskatchewan River by neural network modeling , 1997 .

[4]  Chun-Chieh Yang,et al.  Applications of Artificial Neural Networks to Land Drainage Engineering , 1996 .

[5]  R. L. Kushwaha,et al.  Applications of neural networks to simulate soil-tool interaction and soil behavior , 1999 .

[6]  N. K. Patni,et al.  Groundwater Quality under Conventional and No Tillage: I. Nitrate, Electrical Conductivity, and pH , 1998 .

[7]  H. Maier,et al.  The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters , 1996 .

[8]  Chandra A. Madramootoo,et al.  Nutrient Losses Through Tile Drains from Two Potato Fields , 1992 .

[9]  S. Lek,et al.  Predicting stream nitrogen concentration from watershed features using neural networks , 1999 .

[10]  T. J. Logan,et al.  Tillage, crop and climatic effects of runoff and tile drainage losses of nitrate and four herbicides , 1994 .

[11]  S. O. Prasher,et al.  Use of Artificial Neural Networks in Transient Drainage Design , 1996 .

[12]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[13]  P. Milburn.  Nitrate concentration of subsurface drainage water from a corn field in southern New Brunswick , 1994 .