Title: | Evaluation of neural networks for modeling nitrate concentrations in rivers |
Authors: | Suen, J.-P. and J.W. Eheart |
Year: | 2003 |
Journal: | Journal of Water Resources Planning and Management |
Volume (Issue): | R9(6) |
Pages: | 505-510 |
Article ID: | |
DOI: | 10.1061/(ASCE)0733-9496(2003)129:6(505) |
URL (non-DOI journals): | |
Model: | SWAT |
Broad Application Category: | pollutant only |
Primary Application Category: | model and/or data comparison |
Secondary Application Category: | hydrologic, pollutant and/or crop indices (or metrics) |
Watershed Description: | 1,424 km^2 Upper Sangamon River, located in east central Illinois, U.S. |
Calibration Summary: | |
Validation Summary: | |
General Comments: | |
Abstract: | Artificial neural networks ~ANNs! are applied to estimating nitrate concentrations in a typical Midwestern river, i.e., the Upper Sangamon River in Illinois. Throughout the Midwestern United States, nitrate in raw water has recently become an increasingly important problem. This is due to recent changes in the U.S. EPA nitrate standard and to the increasingly widespread use of chemical fertilizers in agriculture. Back-propagation neural networks ~BPNNs! and radial basis function neural networks ~RBFNNs! are compared as to their effectiveness in water quality modeling. Training of the RBFNNs is much faster than that of the BPNNs, and yields more robust results. These two types of ANNs are compared to traditional regression and mechanistic water quality modeling, based on overall accuracy and on the frequency of false-negative prediction. The RBFNN achieves the best results of all models in terms of overall accuracy, and both BPNN and RBFNN yield the same false-negative frequency, which is better than that of the traditional models. |
Language: | English |
Keywords: | Neural networks; Nitrates; Potable water; Agricultural watersheds; Illinois; River; Water pollution |