Please wait a minute...
Frontiers of Environmental Science & Engineering

ISSN 2095-2201

ISSN 2095-221X(Online)

CN 10-1013/X

Postal Subscription Code 80-973

2018 Impact Factor: 3.883

Front Envir Sci Eng    2012, Vol. 6 Issue (2) : 238-245    https://doi.org/10.1007/s11783-011-0382-7
RESEARCH ARTICLE
Determination of the principal factors of river water quality through cluster analysis method and its prediction
Liang GUO, Ying ZHAO, Peng WANG()
State Key Laboratory of Urban Water Resource and Environment, Harbin Institute of Technology, Harbin 150090, China
 Download: PDF(212 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

In this paper, an artificial neural network model was built to predict the Chemical Oxygen Demand (CODMn) measured by permanganate index in Songhua River. To enhance the prediction accuracy, principal factors were determined through the analysis of the weight relation between influencing factors and forecasting object using cluster analysis method, which optimized the topological structure of the prediction model input items of the artificial neural network. It was shown that application of the principal factors in water quality prediction model can improve its forecasting skill significantly through the comparison between results of prediction by artificial neural network and the measurements of the CODMn. This methodology is also applicable to various water quality prediction targets of other water bodies and it is valuable for theoretical study and practical application.

Keywords water quality forecast      principal factor      cluster analysis method      artificial neural network     
Corresponding Author(s): WANG Peng,Email:pwang73@hit.edu.cn   
Issue Date: 01 April 2012
 Cite this article:   
Liang GUO,Ying ZHAO,Peng WANG. Determination of the principal factors of river water quality through cluster analysis method and its prediction[J]. Front Envir Sci Eng, 2012, 6(2): 238-245.
 URL:  
https://academic.hep.com.cn/fese/EN/10.1007/s11783-011-0382-7
https://academic.hep.com.cn/fese/EN/Y2012/V6/I2/238
timevaluetemperature/°Cturbidity/(NTU)chromaticity/(NTU)quantity of water/(m3·h-1)pHalkalinity/(μS·cm-1)NH3/(mg·L-1)NO3-/(mg·L-1)conductivity/(μS·cm-1)the next day’s CODMn/(mg·L-1)
Januaryrange0–1.55.42–27.220–747670–105006.9–7.252–1311.1–4.40.0028–0.036109–2094.32–6.91
mean0.1416.1934.169158.337.0384.862.200.011159.605.54
S. D.0.36567.788111.6067590.08230.089719.97060.90410.008427.95140.6239
Februaryrange0–14.37–17.720–367700–101706.88–772–1041.7–4.40.004–0.034148–2034.74–6.52
mean0.0548.5227.528895.546.9287.643.100.01173.255.59
S. D.0.22723.14034.6043562.06410.03075.23070.96320.009713.34200.3537
Marchrange0–32.89–17.318–407600–109606.88–7.3560–921.2–3.60.005–0.136125–1834.12–6.74
mean0.897.3927.039543.807.0274.782.270.019147.725.26
S. D.0.96602.60505.5696721.78630.10046.61470.59220.023814.83630.6176
Aprilrange0–155.59–22120–2504200–112106.9–7.7356–1220.6–20.005–0.06114–2294.16–11.55
mean6.5155.5865.389366.167.2971.701.370.017152.216.73
S. D.5.141153.854441.67701029.27400.198611.11660.33060.0125927.77221.5990
Mayrange10–3217.7–27745–2007670–102906.95–8.4146–1220.16–30.007–0.06140–3054.91–12.48
mean14.7660.4085.659266.267.55750.600.02189.888.16
S. D.8.833751.028236.8634594.03080.342417.93580.39920.011346.72781.2248
Junerange15–2815.8–32250–2507830–108006.93–8.2852–1200.2–2.40.007–0.08135–3855.38–14.02
mean20.9575.71114.2899580.237.6382.020.570.03225.118.24
S. D.2.844355.323252.2344677.99570.298314.58860.41430.017048.99311.6845
Julyrange21–2840.3–34960–5007860–108706.81–7.8844–1000.12–3.20.005–0.194–4625.12–15.83
mean25.54108.80157.479486.997.3973.851.150.03212.419.56
S. D.1.410879.650495.7568832.46330.293316.72471.24320.026675.58952.5221
Augustrange20–2764.8–80380–11006450–117306.91–7.7150–1020.14–30.003–0.05106–2496.19–24.64
mean23.09221.86285.279622.427.3069.160.630.02166.8211.35
S. D.1.5029174.1045242.66271234.20800.220812.32730.61620.010443.00924.0928
Septemberrange13–2453.4–19740–3507160–116207–7.7749–1380.04–3.60.002–0.04497–2424.43–17.06
mean17.7795.21121.0310019.317.3676.890.510.01166.058.95
S. D.3.079229.653255.9440892.78350.208824.53640.70290.008643.56473.2455
Octoberrange3–1836.1–25850–3595300–118407–8.2546–1540.15–0.70.001–0.01754–2824.1–14.8
mean8.9179.27127.0410067.937.3984.890.400.01156.877.48
S. D.3.427929.311877.05481124.06100.226828.45840.07070.005152.60081.9778
Novemberrange0–911.3–13415–4675500–110506.95–7.5560–1340.24–20.001–0.017108–2783.29–9.44
mean1.7449.30117.309388.647.2791.990.87140.0096155.935.51
S. D.1.588135.214482.12471167.3590.148523.23410.45760.003631.73041.5251
Decemberrange0–1.56.18–44.215–1146300–105706.88–7.3862–1440.52–4.440.005–0.027128–2343.52–7.13
mean0.2514.4249.849113.667.1496.331.800.01170.785.24
S. D.0.44617.547927.4536755.43080.127023.14570.89030.004726.56940.7472
number12345678910
Tab.1  Water quality characteristics of Songhua River and the number of variables
Fig.1  Structure drawing of neural network forecasting model
stagecluster combinedcoefficientsstage cluster first appearsnext stage
cluster 1cluster 2cluster 1cluster 2
1780.000003
25100.000003
3570.004214
4150.008037
5230.211006
6260.383507
7120.560468
8192.031709
9147477.148800
Tab.2  Procedure of cluster analysis
Fig.2  Sequence of cluster analysis
dateobserved valuesforecasting values
Jan 2nd6.386.01
Jan 3rd4.755.02
Jan 4th5.415.67
Feb 1st5.915.84
Feb 2nd5.455.31
Feb 3rd5.365.62
Mar 1st4.864.52
Mar 2nd5.665.91
Mar 3rd4.554.89
Apr 1st4.934.58
Apr 3rd5.855.4
Apr 4th5.085.67
May 2nd7.387.11
May 3rd8.318.65
May 4th9.979.65
June 1st7.137.34
June 2nd6.697.11
June 3rd8.688.51
July 1st 8.68.35
July 2nd7.237.64
July 3rd8.639.15
Aug 2nd9.649.25
Aug 3rd9.519.84
Aug 4th9.259.65
Sep 1st8.678.85
Sep 2nd10.1810.41
Sep 3rd10.5811.18
Oct 2nd7.157.35
Oct 3rd6.566.16
Oct 4th6.926.48
Nov 1st4.524.62
Nov 2nd4.624.32
Nov 3rd 4.394.32
Oec 1st7.567.14
Oec 3rd5.25.53
Oec 4th5.935.62
Tab.3  Forecasting values and practical measured values of COD by traditional method/(mg·L)
Fig.3  COD comparison curves of forecasting values and observed values by traditional method
Fig.4  Forecasting error curves of COD values by traditional method
dateobserved valuesforecasting values
Jan 2nd6.386.12
Jan 3rd4.754.62
Jan 4th 5.415.62
Feb 1st5.915.85
Feb 2nd5.455.31
Feb 3rd5.365.06
Mar 1st4.864.58
Mar 2nd5.665.92
Mar 3rd4.554.32
Apr 1st4.934.68
Apr 3rd5.855.49
Apr 4th5.085.52
May 2nd7.387.51
May 3rd8.318.66
May 5th9.979.69
June 1st7.137.04
June 2nd6.697.13
June 3rd8.688.81
July 1st8.68.69
July 3rd7.237.65
July 5th8.639.05
Aug 2nd9.649.35
Aug 5th9.519.27
Aug 6th9.259.55
Sep 3rd8.678.89
Sep 4th10.1810.01
Sep 6th10.5811.18
Oct 2nd7.157.06
Oct 3rd6.566.19
Oct 5th6.926.78
Nov 1st4.524.62
Nov 2nd4.624.37
Nov 3rd4.394.32
Oec 1st7.567.76
Oec 3rd5.25.56
Oec 4th5.936.28
Tab.4  Forecasting values and observed values of COD by cluster analysis method/(mg·L)
Fig.5  COD comparison curves of forecasting values and observed values by cluster analysis method
Fig.6  Forecasting error curves of COD values by cluster amalysis method
1 Gallant S I. Neural Network Learning and Expert Systems. Massachusetts: MIT Press, 1993
2 Smith M. Neural Networks for Statistical Modelling. New York: van Nostrand Reinhold, 1994
3 Singh K P, Basant A, Malik A, Jain G. Artificial neural network modeling of the river water quality—a case study. Ecological Modelling , 2009, 220(6): 888–895
doi: 10.1016/j.ecolmodel.2009.01.004
4 Maier H R, Jain A, Dandy G C, Sudheer K PKPS. Methods used for the development of neural networks for the prediction of water resource variables in river systems: current status and future directions. Environmental Modelling & Software , 2010, 25(8): 891–909
doi: 10.1016/j.envsoft.2010.02.003
5 Gardner M W, Dorling S R. Artificial neural network (the multilayer perceptron) —a review of applications in the atmospheric sciences. Atmospheric Environment , 1998, 32(14–15): 2627–2636
doi: 10.1016/S1352-2310(97)00447-0
6 Rogers L L, Dowla F U. Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling. Water Resources Research , 1994, 30(2): 457–481
doi: 10.1029/93WR01494
7 Raman H, Chandramouli V. Deriving a general operating policy for reservoirs using neural networks. Journal of Water Resources Planning and Management , 1996, 122(5): 342–347
doi: 10.1061/(ASCE)0733-9496(1996)122:5(342)
8 Wen C W, Lee C S. A neural network approach to multiobjective optimization for water quality management in a river basin. Water Resources Research , 1998, 34(3): 427–436
doi: 10.1029/97WR02943
9 Lek S, Guegan J F. Artificial neural networks as a tool in ecological modelling, an introduction. Ecological Modelling , 1999, 120(2–3): 65–73
doi: 10.1016/S0304-3800(99)00092-7
10 Kuo Y M, Liu C W, Lin K H. Evaluation of the ability of an artificial neural network model to assess the variation of groundwater quality in an area of blackfoot disease in Taiwan. Water Research , 2004, 38(1): 148–158
doi: 10.1016/j.watres.2003.09.026 pmid:14630112
11 Dogan E, Sengorur B, Koklu R. Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique. Journal of Environmental Management , 2009, 90(2): 1229–1235
doi: 10.1016/j.jenvman.2008.06.004 pmid:18691805
12 Dixon M, Gallop J, Lambert S, Lardon L, Healy J, Steyer J. Data mining to support anaerobic WWTP monitoring. Control Engineering Practice , 2007, 15(8): 987–999
doi: 10.1016/j.conengprac.2006.11.010
13 Yin Y F. A proximate dynamics model for data mining. Expert Systems with Applications , 2009, 36(6): 9819–9833
doi: 10.1016/j.eswa.2009.02.033
14 Liao X Y. The application research on spatial data mining in surface water quality evaluation and prediction. Dissertation for the Master Degree . Changchun: Northeast Normal University, 2006 (in Chinese)
15 Holger R M, Nicolas M, Maier H, Christopher W K C. Use of artificial neural networks for predicting optimal alum doses and treated water quality parameters. Environmental Modelling & Software , 2004, 19(5): 485–494
doi: 10.1016/S1364-8152(03)00163-4
16 Grishma R S, Heidar M, Shankararaman C. Predicting contaminant removal during municipal drinking water nanofiltration using artificial neural networks. Journal of Membrane Science , 2003, 212(1–2): 99–112
17 Nikolaos M, Mastrogiannis N, Boutsinas B, Giannikos I, Basilis B, Ioannis G. A method for improving the accuracy of data mining classification algorithms. Computers & Operations Research , 2009, 36(10): 2829–2839
doi: 10.1016/j.cor.2008.12.011
18 Chen Q W, Chen Q, Mynett A E,Arthur E M. Integration of data mining techniques and heuristic knowledge in fuzzy logic modeling of eutrophication in Taihu Lake. Ecological Modelling , 2003, 162(1–2): 55–67
doi: 10.1016/S0304-3800(02)00389-7
19 Yang Y B, Lin H, Guo Z Y, Jiang J X. A data mining approach for heavy rainfall forecasting based on satellite image sequence analysis. Computers & Geosciences , 2007, 33(1): 20–30
doi: 10.1016/j.cageo.2006.05.010
20 Chu B H, Tsai M S, Ho C S. Toward a hybrid data mining model for customer retention. Knowledge-Based Systems , 2007, 20(8): 703–718
doi: 10.1016/j.knosys.2006.10.003
21 Massart D L, Kaufman L. The Interpretation of Analytical Chemical Data by the Use of Cluster Analysis. New York: Wiley, 1983
22 Willet. Similarity and Clustering in Chemical Information Systems, Research Studies Press. New York: Wiley, 1987
23 Razmkhah H, Abrishamchi A, Torkian A. Evaluation of spatial and temporal variation in water quality by pattern recognition techniques: a case study on Jajrood River (Tehran, Iran). Journal of Environmental Management , 2010, 91(4): 852–860
doi: 10.1016/j.jenvman.2009.11.001 pmid:20056527
24 Chang Q L, Zhou H Q, Hou C J. Using particle swarm optimization algorithm in an artificial neural network to forecast the strength of paste filling material. Journal of China University of Mining and Technology , 2008, 18(4): 551–555
doi: 10.1016/S1006-1266(08)60292-8
25 Feng L H, Lu J. The practical research on flood forecasting based on artificial neural networks. Expert Systems with Applications , 2010, 37(4): 2974–2977
doi: 10.1016/j.eswa.2009.09.037
26 Palani S, Liong S Y, Tkalich P. An ANN application for water quality forecasting. Marine Pollution Bulletin , 2008, 56(9): 1586–1597
doi: 10.1016/j.marpolbul.2008.05.021 pmid:18635240
27 Grivas G, Chaloulakou A. Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece. Atmospheric Environment , 2006, 40(7): 1216–1229
doi: 10.1016/j.atmosenv.2005.10.036
28 Lee T L, Jeng D S. Application of artificial neural networks in tide-forecasting. Ocean Engineering , 2002, 29(9): 1003–1022
doi: 10.1016/S0029-8018(01)00068-3
29 Imrie C E, Durucan S, Korre A. River flow prediction using artificial neural networks: generalisation beyond the calibration range. Journal of Hydrology (Amsterdam) , 2000, 233(1–4): 138–153
doi: 10.1016/S0022-1694(00)00228-6
30 Kim M, Choi C Y, Gerba C P. Source tracking of microbial intrusion in water systems using artificial neural networks. Water Research , 2008, 42(4–5): 1308–1314
doi: 10.1016/j.watres.2007.09.032 pmid:17988708
31 Jeng D S, Daeho C, Michael B. Neural network model for the prediction of wave-induced liquefaction potential. Ocean Engineering , 2004, 31(17–18): 2073–2086
doi: 10.1016/j.oceaneng.2004.05.006
32 Chong E K P, Zak S H. An Introduction to Optimization. New York: Wiley, 1996
33 Moller M F. A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks , 1993, 6(4): 525–533
doi: 10.1016/S0893-6080(05)80056-5
34 Adamowski J, Sun K. Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. Journal of Hydrology (Amsterdam) , 2010, 390(1–2): 85–91
35 Tsai M J, Li C H, Chen C C. Optimal laser-cutting parameters for QFN packages by utilizing artificial neural networks and genetic algorithm. Journal of Materials Processing Technology , 2008, 208(1–3): 270–283
[1] Ziming Zhao, Wenjun Sun, Madhumita B. Ray, Ajay K Ray, Tianyin Huang, Jiabin Chen. Optimization and modeling of coagulation-flocculation to remove algae and organic matter from surface water by response surface methodology[J]. Front. Environ. Sci. Eng., 2019, 13(5): 75-.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed