Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Artificial neural network and regression techniques in modelling surface water quality

Wybrane pełne teksty z tego czasopisma
Warianty tytułu
Języki publikacji
Surface water quality variables with the common nature of complex, nonlinear, multivariable and high variability need the application of alternative techniques to define optimum input variables and to develop effective models. The present paper describes the systematic or hierarchical development and validation of artificial neural network (ANN) and multiple linear regression (MLR) models for the purpose of predicting chlorophyll a (Chl-a) concentration from nine surface water quality variables in order to investigate the significant input variables and their contribution order. A multilayer feed-forward network (FFN) trained by back-propagation algorithm was used as ANN approach. Both FFN and MLR techniques were first calibrated with the same three-fourth of the water quality data (304 samples) and then tested with the remaining one-fourth of the data. The performances of hierarchical models of both techniques were evaluated by using two statistical parameters such as coefficient of determination (R2) and root mean square error (RMSE). The systematic or hierarchical analysis results showed that only four input variables such as biological oxygen demand (BOD), water temperature (T ), dissolved oxygen (DO), and phosphorus (P) among nine variables explained 75 and 88% of the variability in Chl-a compared to the full models of FFN and MLR techniques, respectively. Using these four substantial input variables and adding their powers and possible interaction terms as inputs increased the prediction ability of MLR technique by 13%. The best model of MLR was better than the full model of FFN for predicting Chl-a based on R2 of 0.69 and 0.61%, and RMSE of 14.99 and 16.35, respectively. The study results show that both FFN and MLR techniques are capable of simulating Chl-a with acceptable accuracy and suggest that the abilities of them should be further investigated in different environments and under different conditions with hierarchical model development.
Opis fizyczny
bibliogr. 15 poz.
  • [1] HARDING L.W., PERRY E.S., Long-term increase of phytoplankton biomass in Chesapeake Bay, 1950– 1994, Marine Ecology Progress Series, 1997, 157, 39–52.
  • [2] HARDING L.W., Long-term trends in the distribution of phytoplankton in Chesapeake Bay: Roles of light, nutrients and streamflow, Marine Ecology Progress Series, 1994, 104, 267–291.
  • [3] CHAVES P., TSUKATANI T., KOJIRI T., Operation of storage reservoir for water quality by using optimization and artificial intelligence techniques, Mathematics and Computers in Simulation, 2004, 67, 419–432. Predicted chlorophyll-a (μg/dm3) Predicted chlorophyll-a (μg/dm3) Measured chlorophyll-a (μg/dm3) Measured chlorophyll-a (μg/dm3)
  • [4] LEK S., GUIRESSE M., GIRAUDEL J.L., Predicting stream nitrogen concentration from watershed features using neural networks, Water Research, 1999, 33, 3469–3478.
  • [5] LEK S., DELACOSTE M., BARAN P., DIMOPOULOS I., LAUGA J., AULANIER S., Application of neural networks to modeling nonlinear relationships in ecology, Ecological Modeling, 1996, 90, 39–52.
  • [6] CHAU K.W., A review on integration of artificial intelligence into water quality modeling, Marine Pollution Bulletin, 2006, 52, 726–733.
  • [7] SAHOO G.B., RAY C., MEHNERT E., KEEFER D.A., Application of artificial neural networks to assess pesticide contamination in shallow groundwater, Science of the Total Environment, 2006, 367, 234–251.
  • [8] HOLMBERG M., FORSIUS M., STARR M., HUTTUNEN M., An application of artificial neural networks to carbon, nitrogen and phosphorus concentrations in three boreal streams and impacts of climate change, Ecological Modeling, 2006, 195, 51–60.
  • [9] YABUNAKA K., HOSOMI M., MURAKAMI A., Novel application of a back-propagation artificial neural network model formulated to predict algal bloom, Water Science and Technology, 1997, 36, 89–97.
  • [10] KARUL C., SOYUPAK S., ÇILESIZ A.F., AKBAY N., GERMEN E., Case studies on the use of neural networks in eutraphication modeling, Ecological Modeling, 2000, 134, 145–152.
  • [11] LEE J.H.W., HUANG Y., DICKMAN M., JAYAWARDENA A.W., Neural network modeling of coastal algal blooms, Ecological Modeling, 2003, 159, 179–201.
  • [12] KUO J.T., HSIEH M.H., LUNG W.S., SHE N., Using artificial neural network for reservoir eutrophication prediction, Ecological Modeling, 2007, 200, 171–177.
  • [13] OUYANG D., BARTHOLIC J., Predicting sediment delivery ratio in Saginaw Bay Watershed, the 22nd National Association of Environmental Professionals Conference Proceedings, May 19–23, Orlando, FL, 659–671.
  • [14] COSCARELLI M., Targeting environmental restoration in the Saginaw River/Bay area of concern (AOC), 2002, prepared for the Great Lakes Commission on behalf of the Partnership for the Saginaw Bay Watershed.
  • [15] HAYKIN S., Neural Networks: A Comprehensive Foundation, second edition, Upper Saddle River, New Jersey, 1999.
Typ dokumentu
Identyfikator YADDA
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.