Abstract
In the present investigation, a new model based on feedforward neural networks (FFNN) is developed and compared to the standard multiple linear regression (MLR) in modeling Secchi disk depth (SD) in the Saginaw Bay, Lake Huron, Michigan, USA. The model uses four water quality parameters as input, namely total suspended solids (TSS), water temperature (TE), dissolved oxygen (DO) and chlorophyll (Chl). In an attempt to identify the important parameters that influence the SD, four water quality parameters were selected for further investigation. The analysis identified TSS and Chl to have the most important influence on the SD; and the inclusion of DO and TE did not lead to an overall improvement in the performance of the models. The FFNN and MLR were evaluated using well-known statistical indices, i.e., the correlation coefficient (CC), the root mean squared error (RMSE) and the mean absolute error (MAE). The results obtained from the present investigation are very promising, as we demonstrated that the Secchi disk depth can be predicted very well with correlation coefficient equal to 0.918 in the testing phase.
References
Aarup T (2002) Transparency of the North Sea and Baltic Sea a Secchi Depth data mining study. Oceanologia 44(3):323–337
Adamala S, Raghuwanshi NS, Mishra A (2015) Generalized quadratic synaptic neural networks for ET0 modeling. Environ Process 2(2):309–329. doi:10.1007/s40710-015-0066-6
Alexakis D, Tsihrintzis VA, Tsakiris G, Gikas GD (2016) Suitability of water quality indices for application in lakes in the Mediterranean. Water Resour Manag. doi:10.1007/s11269-016-1240-y
Antonopoulos VZ, Georgiou PE, Antonopoulos ZV (2015) Dispersion coefficient prediction using empirical models and ANNs. Environ Process 2(2):379–394. doi:10.1007/s40710-015-0074-6
Azad S, Debnath S, Rajeevan M (2015) Analysing predictability in Indian monsoon rainfall: a data analytic approach. Environ Process 2(4):717–727. doi:10.1007/s40710-015-0108-0
Brezonik PL (1978) Effect of organic color and turbidity of secchi disk transparency. J Fish Res Board Can 35(11):1410–1416. doi:10.1139/f78-222
Carlson RE (1977) A trophic state index for lakes. Limnol Oceanogr 22:361–369. doi:10.4319/lo.1977.22.2.0361
Das DB, Thirakulchaya T, Deka L, Hanspal NS (2015) Artificial neural network to determine dynamic effect in capillary pressure relationship for two-phase flow in porous media with micro-heterogeneities. Environ Process 2(1):1–18. doi:10.1007/s40710-014-0045-3
Davies-Colley RJ (1988) Measuring water clarity with a black disc. Limnol Oceanogr 33:616–623. doi:10.4319/lo.1988.33.4.0616
Davies-Colley RJ, Smith DG (2001) Turbidity suspended sediment, and water clarity: a review. JAWRA J Am Water Resour Assoc 35-5:1085–1101. doi:10.1111/j.1752-1688.2001.tb03624.x
Fahnenstiel GL, Lang GA, Nalepa TF, Johengen TH (1995a) Effects of zebra mussel (Dreissena polymorpha) colonization on water quality parameters in Saginaw Bay, Lake Huron. J Great Lakes Res 21:435–448. doi:10.1016/S0380-1330(95)71057-7
Fahnenstiel GL, Bridgeman TB, Lang GA, McCormick MJ, Nalepa TF (1995b) Phytoplankton productivity in Saginaw Bay, Lake Huron: effects of zebra mussel (Dreissena polymorpha) colonization. J Great Lakes Res 21:465–475. doi:10.1016/S0380-1330(95)71059-0
Gikas GD, Yiannakopoulou T, Tsihrintzis VA (2006) Water quality trends in a coastal lagoon impacted by non-point source pollution after implementation of protective measures. Hydrobiologia 563:385–406. doi:10.1007/s10750-006-0034-2
Gikas GD, Tsihrintzis VA, Akratos CS, Haralambidis G (2009) Water quality trends in Polyphytos reservoir, Aliakmon River, Greece. Environ Monit Assess 149:163–181. doi:10.1007/s10661-008-0191-z
Heddam S, Bermad A, Dechemi N (2011) Applications of radial basis function and generalized regression neural networks for modelling of coagulant dosage in a drinking water treatment: a comparative study. ASCE J Environ Eng 137(12):1209–1214. doi:10.1061/(ASCE)EE.1943-7870.0000435
Heddam S, Bermad A, Dechemi N (2012) ANFIS-based modelling for coagulant dosage in drinking water treatment plant: a case study. Environ Monit Assess 184:1953–1971. doi:10.1007/s10661-011-2091-x
Heddam S, Lamda H, Filali S (2016) Predicting effluent biochemical oxygen demand in a wastewater treatment plant using generalized regression neural network based approach: A comparative study. Environ Process 3(1):153–165. doi:10.1007/s40710-016-0129-3
Hellweger FL, Schlosser P, Lall U, Weissel JK (2004) Use of satellite imagery for water quality studies in New York Harbor. Estuar Coast Shelf Sci 61:437–448. doi:10.1016/j.ecss.2004.06.019
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366. doi:10.1016/0893-6080(89)90020-8
Hornik K, Stinchcombe M, White H (1990) Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Netw 3:551–560. doi:10.1016/0893-6080(90)90005-6
Ibáñez Civera J, Garcia Breijo E, Laguarda Miró N, Gil Sánchez L, Garrigues Baixauli J, Romero Gil I, Masot Peris R, Alcañiz Fillol M (2011) Artificial neural network onto eight bit microcontroller for secchi depth calculation. Sensors Actuators B 156:132–139. doi:10.1016/j.snb.2011.04.001
Johengen TH, Nalepa TF, Fahnentiel GL, Goudy G (1995) Nutrient changes in Saginaw Bay, Lake Huron after the establishment of the zebra mussel (Dreissena polymorpha). J Great Lakes Res 21:449–464. doi:10.1016/S0380-1330(95)71058-9
Johengen TH, Nalepa TF, Lang GA, Fanslow DL, Vanderploeg HA, Agy MA (2000) Physical and Chemical Variables of Saginaw Bay, Lake Huron in 1994-1996. NOAA Technical Memorandum TM-115, Chlorophyll, nutrients, alkalinity, carbon, and total suspended solids data collected in Saginaw Bay, Lake Huron from 1994 to 1996. Builds upon TM-091 http://www.glerl.noaa.gov/ftp/publications/tech_reports/glerl-115/.
Kloiber SM, Brezonik PL, Olmanson LG, Bauer ME (2002) A procedure for regional lake water clarity assessment using Landsat multispectral data. Remote Sens Environ 82:38–47. doi:10.1016/S0034-4257(02)00022-6
Larson GL, Hoffman RL, Hargreaves BR, Collier RW (2007) Predicting Secchi disk depth from average beam attenuation in a deep, Ultra-clear lake. Hydrobiologia 574:141–148. doi:10.1007/s10750-006-0349-z
Legates DR, McCabe GJ (1999) Evaluating the use of “goodness of fit” measures in hydrologic and hydroclimatic model validation. Water Resour Res 35:233–241. doi:10.1029/1998WR900018
Li R, Li J (2004) Satellite remote sensing technology for lake water clarity monitoring: an overview. Environmental Informatics Archives 2:893–901
Li X, Zecchin AC, Maier HR (2015) Improving partial mutual information-based input variable selection by consideration of boundary issues associated with bandwidth estimation. Environ Model Softw 71:78–96. doi:10.1016/j.envsoft.2015.05.013
Luhtala H, Tolvanen H (2013) Optimizing the use of Secchi depth as a proxy for euphotic depth in coastal waters: An empirical study from the Baltic Sea. ISPRS Int J Geo-Inf 2:1153–1168. doi:10.3390/ijgi2041153
Maier HR, Jain A, Dandy GC, Sudheer KP (2010) Methods used for the development of neural networks for the prediction of water resource variables in river systems: current status and future directions. Environ Model Softw 25(8):891–909. doi:10.1016/j.envsoft.2010.02.003
Mandal S, Mahapatra SS, Adhikari S, Patel RK (2015) Modeling of arsenic (III) removal by evolutionary genetic programming and Least Square support vector machine models. Environ Process 2(1):145–172. doi:10.1007/s40710-014-0050-6
MATLAB (2010) the MathWorks Inc., Natick, MA. http://www.mathworks.com.
May R, Dandy G, Maier H (2011) Review of input variable selection methods for artificial neural networks. In: InTech (ed) Artificial neural networks - methodological advances and biomedical applications, Rijeka, pp. 19–44. doi:10.5772/16004
McCulloch WS, Pitts W (1943) A logical calculus of the ideas imminent in nervous activity. Bull Math Biophys 5:115–133. doi:10.1007/BF02478259
Michaud JP (1991) A Citizens’ guide to understanding and monitoring lakes and-streams. Washington State Department of Ecology. www.ecy.wa.gov/programs/wq.
Myre E, Shaw R (2006) The turbidity tube: simple and accurate measurement of turbidity in the field. Michigan Technology University, Houghton
Olmanson LG, Brezonik PL, Bauer ME (2015) Remote sensing for regional lake water quality assessment: capabilities and limitations of current and upcoming satellite systems. In T. Younos, T.E. Parece (eds.) Advances in watershed science and assessment. The Handbook of Environmental Chemistry 33. doi:10.1007/978-3-319-14212-8_5
Santisukkasaem U, Olawuyi F, Oye P, Das DB (2015) Artificial neural network (ANN) for evaluating permeability decline in permeable reactive barrier (PRB). Environ Process 2(2):291–307. doi:10.1007/s40710-015-0076-4
USGS (2014) Estimation of Secchi Depth from turbidity Data in the Willamette River at Portland, OR (14211720). http://or.water.usgs.gov/will_morrison/secchi_depth_model.html.
Wu G, Leeuw JD, Skidmore AK, Prins HT, Liu Y (2008) Comparison of MODIS and Landsat TM5 images for mapping tempo-spatial dynamics of Secchi disk depths in Poyang Lake National Nature Reserve, China. Int J Remote Sens 29(8):2183–2198. doi:10.1080/01431160701422254
Wu G, Leeuw JD, Liu Y (2009) Understanding seasonal water clarity dynamics of Lake Dahuchi from in situ and remote sensing data. Water Resour Manag 23:1849–1861. doi:10.1007/s11269-008-9356-3
Acknowledgments
We would like to thank Professors: Gregory Lang, Thomas H. Johengen, and Henry A. Vanderploeg from the Great Lakes Environmental Research Laboratory, NOAA, Michigan, USA, for giving permission for using the data that made this study possible. Once again, we would like to thank anonymous reviewers and the editor of Environmental Processes for their invaluable comments and suggestions on the contents of the manuscript which significantly improved the quality of the paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Heddam, S. Secchi Disk Depth Estimation from Water Quality Parameters: Artificial Neural Network versus Multiple Linear Regression Models?. Environ. Process. 3, 525–536 (2016). https://doi.org/10.1007/s40710-016-0144-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40710-016-0144-4