Study of the effectiveness of wavelet genetic programming model for water quality analysis in the Uttar Pradesh region

Abstract

Water constitutes an essential part of the earth as it helps in making the environment greener and support life. But water quality and availability are drastically affected by rising water pollution and its poor sanitation. Water gets contaminated due to the excessive use of chemicals by the industries, fertilizers, and pesticides by the farmers. Not only the surface water, groundwater and river water are also getting contaminated. Several published work in Indian context have used different models for the prediction of water quality. Some of them performed poorly due to the presence of irrelevant and missing data in the training samples. Moreover, these studies have assessed water quality on the basis of biochemical oxygen demand (BOD) and coliform and chemical oxygen demand (COD), whereas dissolved oxygen(DO) is one of the most important parameters in terms of water quality assessment as it is considered a key determinant of pollution. Thus, there is a strong need to categorically identify and visualize the DO as one of the key components responsible for deteriorating the quality of water in Indian context. The main objective of this work is to build a wavelet genetic programming (WGP)-based workflow model for the assessment of water quality in 13 rivers of Uttar Pradesh region. WGP model has a unique feature of discarding the redundant and irrelevant data values from the source data. The proposed WGP model has given promising results which can be attributed to two factors: firstly, the novel use of Morlet wavelet in place of the widely popular Db wavelet, as the mother wavelet, and secondly, the use of MICE technique for missing value imputation in the pre-processing stage. The proposed model not only cleans the data but also demonstrates the feasibility of using DO values as one of the prime factors to assess the water quality.

Appendix

S. No	Abbreviation	Full form
1	W-MGGP	Wavelet pre-processing with multi-gene genetic programming
2	WGEP	Wavelet gene expression programming
3	DWT	Discrete wavelet transform
4	LPM	Linear probability model
5	MGGP	Multi-gene genetic programming
6	PSR	Predictive state representation
7	FNN	False nearest neighbor
8	LASSO	Least absolute shrinkage and selection operator
9	GEP	Genetic evolutionary programming
10	FLGGP	Fixed-length gene genetic programming
11	LGP	Linear genetic programming
12	GP	Genetic programming
13	ARIMA	Autoregressive integrated moving average
14	WGP	Wavelet genetic programming
15	MSGP	Multi-stage genetic programming
16	GBT	Gradient boosting
17	ANN	Artificial neural networks
18	WANN	Wavelet artificial neural networks
19	ANFIS	Adaptive neuro-fuzzy inference system
20	WANFIS	Wavelet adaptive neuro-fuzzy inference system
21	FL	Fuzzy logic
22	SVM	Support vector machine
23	NF	Neuro-fuzzy
24	GA-NN	Genetic algorithm neural networks
25	WNN	Wavelet neural network
26	WSVR	Wavelet support vector regression
27	WLGP	Wavelet linear genetic programming
28	PCA	Principle component analysis
29	LSTM	Long short-term memory
30	RNNs	Recurrent neural networks
31	BP	Back propagation
32	SVR	Support vector regression
33	MSA	Multiple sequence alignments
34	MLP	Multilayer perceptron
35	MLR	Multiple linear regression
36	KNN	K-nearest neighbor
37	MODWT	Maximal overlap discrete wavelet transform
38	FWNN	Wavelet-based fuzzy neural network
39	CWT	Continuous wavelet transform
40	DDM	Data-driven modeling
41	NAR	Non-linear autoregressive neural network
42	RF	Random forest
43	ABM	Agent-based modeling
44	GBU	Gradient boosting unit
45	EMSP	Effective maliciousness score of permission
46	GBT	Gradient boosting technique
47	OAM	Open application model
48	LEM	Learnable evolution model
49	EP	Evolutionary programming
50	AR	Augmented reality
51	WNF	Wavelet neuro-fuzzy
52	WTC	Wavelet task clustering
53	SARIMA	Seasonal autoregressive integrated moving average
54	FNN	Feedforward neural network
55	RMSE	Root mean square error
56	NSE	Nash–Sutcliffe efficiency
57	MAE	Mean absolute error
58	R2	Coefficient of determination
59	MAPE	Mean absolute percentage error
60	MSE	Mean square error
61	AICc	Akaike information criterion
62	AARE	Average absolute relative error
63	MARE	Mean absolute relative error
64	AOI	Index of agreement
65	CE	Coefficient of efficiency
66	NSC	Nearest shrunken centroid
67	SSE	Sum of squared errors
68	MPE	Mean prediction error
69	R	Coefficient of correlation
70	RE	Relative error
71	MRSE	Mean root squared error
72	PARE	Pooled average relative underestimation and over estimation errors
73	NDEI	Non-dimensional error index
74	Ai	Accuracy factor
75	P	Pearson correlation coefficient
76	bias	Absolute value of the average forecast error
77	d	Willmott index of agreement
78	pMAPE	Mean absolute percentage errors of peaks
79	EVS	Explain variance score
80	RPD	Residual prediction deviation
81	Dr	Discrepancy ratio
82	MSRE	Mean square relative error
83	MS4E	Mean higher order error
84	SI	Scatter index
85	MS	Mean squared error
86	SBC	Schwarz Bayesian criterion
87	DO	Dissolved oxygen
88	BOD	Biochemical oxygen demand
89	EC	Electrical conductivity
90	COD	Chemical oxygen demand
91	TDS	Total dissolved solids
92	TP	Total phosphorus
93	TKN	Total Kjeldahl nitrogen
94	NH3-N	Ammoniacal nitrogen
95	RD	River depth
96	RW	River width
97	CA	Cultivated area
98	OA	Orchard area
99	SSL	Suspended sediment load
100	SSC	Suspended sediment concentration
101	NO3+	Nitrate
102	NH4+	Ammonium
103	PO4	Phosphate
104	TSS	Total suspended solids
105	NH4+-N	Ammonium nitrogen
106	WT	Water temperature
107	TU	Turbidity
108	db	Daubechies4
109	dmey	Discrete Meyer
110	bior	Biorthogonal
111	coif	Coiflets
112	sym	Symlets (symmetrical wavelets)
113	MCAR	Missing completely at random
114	MAR	Missing at random
115	MNAR	Missing not at random
116	MICE	Multiple imputation by chained equations