Abstract
In this study, we present application of an artificial intelligence (AI) technique model called dynamic evolving neural-fuzzy inference system (DENFIS) based on an evolving clustering method (ECM), for modelling dissolved oxygen concentration in a river. To demonstrate the forecasting capability of DENFIS, a one year period from 1 January 2009 to 30 December 2009, of hourly experimental water quality data collected by the United States Geological Survey (USGS Station No: 420853121505500) station at Klamath River at Miller Island Boat Ramp, OR, USA, were used for model development. Two DENFIS-based models are presented and compared. The two DENFIS systems are: (1) offline-based system named DENFIS-OF, and (2) online-based system, named DENFIS-ON. The input variables used for the two models are water pH, temperature, specific conductance, and sensor depth. The performances of the models are evaluated using root mean square errors (RMSE), mean absolute error (MAE), Willmott index of agreement (d) and correlation coefficient (CC) statistics. The lowest root mean square error and highest correlation coefficient values were obtained with the DENFIS-ON method. The results obtained with DENFIS models are compared with linear (multiple linear regression, MLR) and nonlinear (multi-layer perceptron neural networks, MLPNN) methods. This study demonstrates that DENFIS-ON investigated herein outperforms all the proposed techniques for DO modelling.
Similar content being viewed by others
References
Ahumada R, Vargas J, Pagliero L (2006) Simple model of dissolved oxygen consumption in a bay within high organic loading: an applied remediation tool. Environ Monit Assess 118:179–193. doi:10.1007/s10661-006-1489-3
Altunkaynak A, Ozger M, Cakmakci M (2005) Fuzzy logic modeling of the dissolved oxygen fluctuations in Golden Horn. Ecol Model 189:436–446. doi:10.1016/j.ecolmodel.2005.03.007.
Ansa-Asarea OD, Marra IL, Cresser MS (1999) Evaluation of cycling patterns of dissolved oxygen in a tropical lake as an indicator of biodegradable organic pollution. Sci Total Environ 231:145–158. doi:10.1016/S0048-9697(99)00088-1
Antonopoulos VZ, Gianniou SK (2003) Simulation of water temperature and dissolved oxygen distribution in Lake Vegoritis, Greece. Ecol Model 160:39–53. doi:10.1016/S0304-3800(02)00286-7
Antanasijević DZ, Pocajt VV, Povrenović DS, Perić-Grujić AA, Ristić MĐ (2013) Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study. Environ Sci Pollut Res 20(12):9006–9013. doi:10.1007/s11356-013-1876-6
Ay M, Kisi O (2012) Modeling of dissolved oxygen concentration using different neural network techniques in Foundation Creek, El Paso County, Colorado. ASCE J Environ Eng 138(6):654–662. doi:10.1061/ (ASCE) EE.1943-7870.0000511
Bahadori A, Vuthaluru HB (2010) Simple Arrhenius-type function accurately predicts dissolved oxygen saturation concentrations in aquatic systems. Process Saf Environ Prot 88:335–340. doi:10.1016/j.psep.2010.05.002
Bennett JP, Rathbun RE (1972) Reaeration in open-channel flow, USGS Professional Paper: 737, 75p, U.S. Govt. Print. Off.
Brezonik PL, Stadelmann TH (2002) Analysis and predictive models of stormwater runoff volumes, loads, and pollutant concentrations from watersheds in the Twin Cities metropolitan area, Minnesota, USA. Water Res 36:1743–1757. doi:10.1016/S0043-1354
Bureau of Reclamation (2000) Klamath Project-Historical operation: Klamath Falls, Oregon, Bureau of Reclamation, 53 p. plus appendices, accessed April 2, 2008. http://www.usbr.gov/mp/kbao/docs/Historic%20Operation.pdf -->
Chau KW (2006) A review on integration of artificial intelligence into water quality modelling. Mar Pollut Bull 52:726–733. doi:10.1016/j.marpolbul.2006.04.003
Chandana Prasad PW, Beg A (2009) Investigating data preprocessing methods for circuit complexity models. Expert Syst Appl 36(1):519–526. doi:10.1016/j.eswa.2007.09.052.
Cox BA (2003a) A review of currently available in-stream water-quality models and their applicability for simulating dissolved oxygen in lowland Rivers. Sci Total Environ 314–316:335–377. doi:10.1016/S0048-9697(03)00063-9
Cox BA (2003b) A review of dissolved oxygen modelling techniques for lowland Rivers. Sci Total Environ 314–316:303–334. doi:10.1016/S0048-9697(03)00062-7
Cybenko G (1989) Approximation by superposition of a sigmoidal function. Math Control Signals Syst 2(4):303–314
David AC (2006) Water-quality engineering in natural systems. Wiley, Hoboken, 628p
Diamantopoulou MJ, Antonopoulos VZ, Papamichail DM (2007) Cascade Correlation artificial neural networks for estimating missing monthly values of water quality parameters in rivers. Water Resour Manag 21:649–662. doi:10.1007/s11269-006-9036-0
Dovžan D, Škrjanc I (2011) Recursive fuzzy c-means clustering for recursive fuzzy identification of time-varying processes. ISA Trans 50:159–169. doi:10.1016/j.isatra.2011.01.004.
Deas ML, Orlob GT (1999) Klamath River Modeling Project. Project #96-HP-01. Assessment of alternatives for flow and water quality control in the Klamath River below Iron Gate Dam. University of California Davis Center for Environmental and Water Resources Engineering. Report No. 99–04. 379pp. http://permanent.access.gpo.gov/lps60062/krisweb/Klamath.
Farquad MAH, Ravi V, Raju SB (2010) Support vector regression based hybrid rule extraction methods for forecasting. Expert Syst Appl 37:5577–5589. doi:10.1016/j.eswa.2010.02.055.
Fang X, Stefan HG (1995) Interaction between oxygen transfer mechanisms in lake models. J Environ Eng, ASCE 121(6):447–454. doi:10.1061/(ASCE)0733-9372(1995)121:6(447)
Fausett L (1994) Fundamentals of neural networks: architectures, algorithms, and applications. Prentice Hall, Englewood Cliffs
Funahashi K (1989) On the approximate realization of continuous mapping by neural networks. Neural Netw 2:183–192
Gajate A, Haber R, Del Toro R, Vega P, Bustillo A (2010) Tool wear monitoring using neuro-fuzzy techniques: a comparative study in a turning process. J Intell Manuf 23(3):869–882. doi:10.1007/s10845-010-0443-y
Gannett MW, Lite KE Jr, La Marche JL, Fisher BJ, Polette DJ (2007) Ground-water hydrology of the upper Klamath Basin, Oregon and California: U.S. Geological Survey Scientific Investigations Report 2007–5050, 84 p. http://pubs.usgs.gov/sir/2007/5050/.
Giusti E, Marsili-Libelli S (2009) Spatio-temporal dissolved oxygen dynamics in the Orbetello lagoon by fuzzy pattern recognition. Ecol Model 220:2415–2426. doi:10.1016/j.ecolmodel.2009.06.007
Goldman CR, Horne AJ (1983) Limnology. McGraw-Hill, New York
Haider H, Ali W (2010) Development of dissolved oxygen model for a highly variable flow river: a case study of Ravi River in Pakistan. Environ Monit Assess 15:583–599. doi:10.1007/s10666-010-9240-4
Ham F, Kostanic I (2001) Principles of neurocomputing for science and engineering. McGraw-Hill, New York
Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, Englewood Cliffs
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366
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, Dechemi N (2014) A new approach based on the dynamic evolving neural-fuzzy inference system (DENFIS) for modelling coagulant dosage (Dos): case study of water treatment plant of Algeria. Desalination and Water Treatment. Doi: 10.1080/19443994.2013.878669
He J, Chu A, Cathryn Ryan M, Valeo C, Zaitlin B (2011) Abiotic influences on dissolved oxygen in a riverine environment. Ecol Eng 37:1804–1814. doi:10.1016/j.ecoleng.2011.06.022.
Hwang YC, Song Q (2009) Dynamic Neural Fuzzy Inference System. Proceedings of the international conference on Advances in neuro-information processing ICONIP. Lecture Notes in Computer Science, Volume 5506/2009, 1245–1250. Springer Berlin. Doi: 10.1007/978-3-642-02490-0-151.
Jolai F, Ghanbari A (2010) Integrating data transformation techniques with Hopfield neural networks for solving travelling salesman problem. Expert Syst Appl 37:5331–5335. doi:10.1016/j.eswa.2010.01.002
Kannel PR, Lee S, Lee YS, Kanel SR, Khan SP (2007) Application of water quality indices and dissolved oxygen as indicators for river water classification and urban impact assessment. Environ Monit Assess 132:93–110. doi:10.1007/s10661-006-9505-1
Kasabov N, Song Q, Tian MM (2008) Fuzzy-neuro systems for local and personalized modelling. Forging new frontiers: fuzzy pioneers II. Stud Fuzziness Soft Comput 218(2008):175–197. doi:10.1007/978-3-540-73185-6-8
Kasabov N, Woodford B (1999) Rule Insertion and Rule Extraction from Evolving Fuzzy Neural Networks: Algorithms and Applications for Building Adaptive, Intelligent Expert Systems. In: Proc. of IEEE Intern. Fuzzy Systems Conference: Seoul 1406–1411. Doi:10.1109/FUZZY.1999.790109.
Kasabov N, Song Q (2002) DENFIS: dynamic, evolving neural–fuzzy inference systems and its application for time-series prediction. IEEE Trans Fuzzy Syst 10:144–154. doi:10.1109/91.995117
Kasabov N (2007) Evolving connectionist systems & the knowledge engineering approach, Second editionth edn. Springer, New York, p 465. ISBN 978-1-84628-345-1
Kasabov N (1998) The ECOS framework and the ECO learning method for evolving connectionist systems. J Adv Comput Intell 2(6):195–202
Kasabov N (2003) Evolving connectionist systems: methods and applications in bioinformatics, brain study and intelligent machines. Springer, London
Kasabov N, Chan Z, Song Q, Greer D (2005) Evolving connectionist systems with evolutionary self-optimisation. Stud Fuzz 173:181–202
Lindenberg MK, Hoilman G, Wood TM (2009). Water quality conditions in Upper Klamath and Agency Lakes, Oregon, 2006: U.S. Geological Survey Scientific Investigations Report 2008–5201, 54 p. http://pubs.usgs.gov/of/2008/5201/.
Liu S, Xu LK, Li DL, Li Q, Jiang Y, Tai H, Zeng L (2013) Prediction of dissolved oxygen content in river crab culture based on least squares support vector regression optimized by improved particle swarm optimization. Comput Electron Agric 95:82–91. doi:10.1016/j.engappai.2013.09.019
Loucks DP, Bee EV, Stedinger JR, Dijkman JPM, Villars MT (2005) Water Resources Systems Planning and Management an Introduction to Methods, Models and Applications, Chapter 12. ISBN 92-3-103998-9. Studies and Reports in Hydrology & UNESCO Publishing. http://hdl.handle.net/1813/2804.
Lu S, Yan M, Tai H, Xu L, Li D (2012) Prediction of dissolved oxygen content in aquaculture of hyriopsis cumingii using Elman neural network. D. Li and Y. Chen (Eds.): computer and computing technologies in agriculture V (CCTA) 2011, Part III. IFIP Advances in Information and Communication Technology 370, 508–518. Doi: 10.1007/978-3-642-27275-2-57.
Maier HR, Dandy GC (2000) Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environ Model Softw 15(1):101–124. doi:10.1016/S1364-8152(99)00007-9
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
Maniquiz MC, Lee SY, Kim LH (2010) Multiple linear regression models of urban runoff pollutant load and event mean concentration considering rainfall variables. J Environ Sci 22(6):946–952. doi:10.1016/S1001-0742(09)60203-5
Massoud MA (2012) Assessment of water quality along a recreational section of the Damour River in Lebanon using the water quality index. Environ Monit Assess 184:4151–4160. doi:10.1007/s10661-011-2251-z.
Mrazik S (2007) Oregon Water Quality Index Summary Water Years 1997–2006. Oregon Dept. of Environmental Quality. DEQ07-LAB-007-TR, 13pp. www.deq.state.or.us
Mohanty R, Ravi V, Patra MR (2009) Software Reliability Prediction Using Group Method of Data Handling. In: Sakai H et al (eds) RSFDGrC 2009, LNAI 5908. Springer, Berlin, pp 344–351. doi:10.1007/978-3-642-10646-0
Moriasi DN, Arnold JG, Van Liew MW, Bingner RL, Harmel RD, Veith TL (2007) Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans ASABE Am Soc Agric Biol Eng 50(3):885–900, ISSN 0001–2351
Murty Y, Bahallamudi S, Srinivasan K (2006) Non-uniform flow effect on optimal waste load allocation in rivers. Water Resour Manag 20(4):509–530. doi:10.1007/s11269-006-3084-3
Najah A, El-Shafie A, Karim OA, El-Shafie AH (2014) Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring. Environ Sci Pollut Res 21(3):1658–1670. doi:10.1007/s11356-013-2048-4
Patil A, Deng Z, Malone RF (2012) Temporal scale-induced uncertainty in load duration curves for instream-dissolved oxygen. Environ Monit Assess 185(2):1939–1949. doi:10.1007/s10661-012-2678-x
Poulson SR, Sullivan AB (2010) Assessment of diel chemical and isotopic techniques to investigate biogeochemical cycles in the upper Klamath River, Oregon, USA. Chem Geol 269:3–11. doi:10.1016/j.chemgeo.2009.05.016
Risley JC, Gannett MW, Lea JK, Roehl EA Jr (2001) An analysis of statistical methods for seasonal flow forecasting in the Upper Klamath River Basin of Oregon and California: U.S. Geological Survey Scientific Investigations Report 2005–5177, 44 p. http://pubs.usgs.gov/sir/2005/5177/
Reid GK, Wood RD (1976) Ecology of inland waters and estuaries. Van Nostrand, New York
Rudolf A, Ahumada R, Pérez C (2002) Dissolved oxygen content as an index of water quality in San Vicente Bay, Chile (36°). Environ Monit Assess 78:89–100. doi:10.1023/ A: 1016140819487
Rumelhart DE, McClelland JL (1986) Parallel distribution processing: exploration in the microstructure of cognition. MIT Press, Cambridge
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back propagating errors. Nature 323(9):533–536
Sanchez E, Colmenarejo MF, Vicente J, Rubio A, Garcia MG, Travieso L, Borjac R (2007) Use of the water quality index and dissolved oxygen deficit as simple indicators of watersheds pollution. Ecol Indic 7:315–328. doi:10.1016/j.ecolind.2006.02.005
Singh KP, Basant A, Malik A, Jain G (2009) Artificial neural network modeling of the river water quality—a case study. Ecol Model 220:888–895. doi:10.1016/j.ecolmodel.2009.01.004.
Shahane AN (1976) Interdisciplinary models of water systems. Ecol Model 2:117–145
Soyupak S, Karaer F, Gürbüz H, Kivrak E, Sentürket E, Yazici A (2003) A neural network-based approach for calculating dissolved oxygen profiles in reservoirs. Neural Comput Appl 12, 3–4, 166–172. doi: 10.1007/s00521-003-0378-8.
Streeter HW, Phelps EP (1925) A study of the pollution and natural purification of the Ohio River, vol 146, U.S. Public Health Service. Publication Health Bulletin, Washington
Sugeno M, Kang G (1988) Structure identification of fuzzy model. Fuzzy Sets Syst 26(1):15–33
Sullivan AB, Rounds SA, Deas ML, Sogutlugil IE (2012) Dissolved oxygen analysis, TMDL model comparison, and particulate matter shunting-Preliminary results from three model scenarios for the Klamath River upstream of Keno Dam, Oregon: U.S. Geological Survey Open-File Report 2012–1101, 30 p. http://pubs.usgs.gov/of/2012/1101/.
Sullivan AB, Rounds SA, Deas ML, Asbill JR, Wellman RE, Stewart MA, Johnston MW, Sogutlugil IE (2011) Modeling hydrodynamics, water temperature, and water quality in the Klamath River upstream of Keno Dam, Oregon, 2006–09: U.S. Geological Survey Scientific Investigations Report 2011–5105, 70 p. http://pubs.usgs.gov/sir/2001/5105/.
Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Trans Syst Man Cybern SMC 15(1):116–132
Tan Z, Quek C, Cheng PYK (2011) Stock trading with cycles: a financial application of ANFIS and reinforcement learning. Expert Syst Appl 38:4741–4755. doi:10.1016/j.eswa.2010.09.001
Talei A, Chua LHC, Quek C, Jansson PE (2013) Runoff forecasting using a Takagi-Sugeno neuro-fuzzy model with online learning. J Hydrol 488:17–32. doi:10.1016/j.jhydrol.2013.02.022
USGS Oregon Water Science Center, (2013). http://water.usgs.gov.
USGS (2013) http://ga.water.usgs.gov/edu/dissolvedoxygen.html.
Willmott CJ (1982) Some comments on the evaluation of model performance. Bull Am Meteorol Soc 63:1309–1313
Watts MJ (2004) Evolving Connectionist Systems Characterisation, Simplification, Formalisation, Explanation and Optimisation. PhD Thesis University of Otago, Dunedin, New Zealand. 396pp.
Watts MJA (2009) A decade of Kasabov's evolving connectionist systems: a review. IEEE Trans Syst Man Cybern C Appl Rev 39(3):253–269. doi:10.1109/TSMCC.2008.2012254
Wilding TK, Brown E, Collier KJ (2012) Identifying dissolved oxygen variability and stress in tidal freshwater streams of northern New Zealand. Environ Monit Assess 184:6045–6060. doi:10.1007/s10661-011-2402-2
Wen X, Fang J, Diao M, Zhang C (2013) Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China. Environ Monit Assess 185:4361–4371. doi:10.1007/s10661-012-2874-8.
Zoveidavianpoor M, Samsuri A, Shadizadeh SR (2013) Adaptive neuro fuzzy inference system for compressional wave velocity prediction in a carbonate reservoir. J Appl Geophys 89:96–107. doi:10.1016/j.jappgeo.2012.11.010
Acknowledgments
The authors would like to thank the staff of the United States Geological Survey (USGS) for providing the data that makes this research possible. Once again, we would like to thank anonymous reviewers and the editor of ESPR 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
Additional information
Responsible editor: Michael Matthies
Rights and permissions
About this article
Cite this article
Heddam, S. Modelling hourly dissolved oxygen concentration (DO) using dynamic evolving neural-fuzzy inference system (DENFIS)-based approach: case study of Klamath River at Miller Island Boat Ramp, OR, USA. Environ Sci Pollut Res 21, 9212–9227 (2014). https://doi.org/10.1007/s11356-014-2842-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-014-2842-7