Evaluation of wavelet-GEP and wavelet-ANN hybrid models for prediction of total nitrogen concentration in coastal marine
- PDF / 2,343,946 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 102 Downloads / 176 Views
ORIGINAL PAPER
Evaluation of wavelet-GEP and wavelet-ANN hybrid models for prediction of total nitrogen concentration in coastal marine waters Taher Rajaee 1 & Akbar Shahabi 1
Received: 10 February 2015 / Accepted: 29 October 2015 # Saudi Society for Geosciences 2016
Abstract Because of increasing worldwide contamination of coastal marine water in the last decades, the exact prediction of water quality parameters in these areas is an important factor in coastal management. In this study, the evaluation of wavelet-gene expression programing (WGEP) and wavelet-artificial neural network (WANN) hybrid model was assessed in prediction of total nitrogen concentration (TN) in Charlotte harbor marine waters. The WANN and WGEP results were compared with traditional predictive models such as ANN, GEP, and multi-linear regression (MLR) methods. The TN monthly time series for 13 years were applied as inputs, and the TN values of the next month for two stations were simulated and predicted with different models. The comparison results of the wavelet hybrid models with others using statistical criteria (E and RMSE) exhibited the best performance of the wavelet conjunction models for prediction of TN in coastal waters. The E values of WGEP and WANN models with respect to the optimal GEP and ANN models increased to 0.858–0.879 and 0.840–0.857 for the first and second station, respectively. The selection process of suitable model indicated that the wavelet hybrid models have good results also in the prediction of maximum and minimum values of TN time series. Using wavelet transforms, different timefrequencies of TN changes of coastal marine water are extracted and sub-time series and sub-signal changes of TN as monthly, seasonally, 6 monthly and yearly can be recognized; thus, ANN and GEP model are improved.
* Taher Rajaee [email protected] 1
Department of Civil Engineering, University of Qom, Qom, Iran
Keywords Total nitrogen concentration . Time series analysis . Discrete wavelet transform . Conjunction model . Charlotte harbor
Introduction The increasing of worldwide contamination in coastal marine water with large number of industrial and chemical composition is one important environmental challenge. The water from the hydrologic cycle that used by human beings return to the same cycle after different using. During the using cycle of water that the substances mixed with it, the water pollution concept as they change the physical, chemical, and biological properties of water is proposed (May and Sivakumar 2009). Nutrients, including nitrogen and phosphorus, are effective components of aquatic life, in addition, have a threat to the quality of water and coastal health. Nutrient overenrichment that is a main cause of water contamination in the world is possibly the oldest and the main water quality problems generated by humankind. The freshwater enrichment with phosphorus and nitrogen on its movement to the ocean and either inputs of water with tidal phenomena is the major reason of nutrient problems in estuaries and coasta
Data Loading...
