A Review of the Artificial Neural Network Models for Water Quality Prediction

Abstract

Water quality prediction plays an important role in environmental monitoring, ecosystem sustainability, and aquaculture. Traditional prediction methods cannot capture the nonlinear and non-stationarity of water quality well. In recent years, the rapid development of artificial neural networks (ANNs) has made them a hotspot in water quality prediction. We have conducted extensive investigation and analysis on ANN-based water quality prediction from three aspects, namely feedforward, recurrent, and hybrid architectures. Based on 151 papers published from 2008 to 2019, 23 types of water quality variables were highlighted. The variables were primarily collected by the sensor, followed by specialist experimental equipment, such as a UV-visible photometer, as there is no mature sensor for measurement at present. Five different output strategies, namely Univariate-Input-Itself-Output, Univariate-Input-Other-Output, Multivariate-Input-Other(multi), Multivariate-Input-Itself-Other-Output, and Multivariate-Input-Itself-Other (multi)-Output, are summarized. From results of the review, it can be concluded that the ANN models are capable of dealing with different modeling problems in rivers, lakes, reservoirs, wastewater treatment plants (WWTPs), groundwater, ponds, and streams. The results of many of the review articles are useful to researchers in prediction and similar fields. Several new architectures presented in the study, such as recurrent and hybrid structures, are able to improve the modeling quality of future development.

Wildfire Damage Assessment over Australia Using Sentinel-2 Imagery and MODIS Land Cover Product within the Google Earth Engine Cloud Platform

“…Finally, all samples were randomly divided into three groups: training (50%), validation (17%), and test (33%). The validation dataset was used as an intermediate dataset for the fine tuning of the utilized classifiers [28].…”

The Use of Artificial Neural Networks to Predict the Physicochemical Characteristics of Water Quality in Three District Municipalities, Eastern Cape Province, South Africa

“…An artificial neural network (ANN) is a computing system animated by studies of the brain and nervous system [ 37 ] as in the human brain [ 18 ]. ANN carries out perfect mathematical complex systems and is based on a system of interconnected “neurons” [ 36 , 48 , 58 ] forming the basis of neural network operation. The network has computational models that are defined by four parameters: (i) processing elements known as neurons, (ii) a topology comprising weighted connections between neurons, (iii) a learning algorithm for training the network, (iv) a recall algorithm for testing or classifying purposes [ 59 ].…”

“…Moreover, the models are less sensitive to data insufficiency; the structures are flexible, non-linear, and robust, and can handle vast amounts of data and data at different scales [ 60 , 61 , 62 , 63 , 64 , 65 ]. As a result, many researchers have explored artificial neural networks (ANN), multilayer perceptron (MLP) and feed-forward neural networks (FFNN) [ 40 , 66 , 67 , 68 ], to predict; forecast, and model future water quality in groundwater [ 2 , 48 ], surface water [ 1 , 6 , 7 , 9 , 31 , 33 , 40 , 42 , 58 , 67 , 69 , 70 , 71 , 72 , 73 , 74 , 75 ], and wastewater treatment plants [ 68 , 76 ]. A review on water quality prediction by [ 58 ] for a period 2008–2019 concluded that the MLP architecture in ANN was the widely used architecture to complete prediction tasks during this period.…”

“…As a result, many researchers have explored artificial neural networks (ANN), multilayer perceptron (MLP) and feed-forward neural networks (FFNN) [ 40 , 66 , 67 , 68 ], to predict; forecast, and model future water quality in groundwater [ 2 , 48 ], surface water [ 1 , 6 , 7 , 9 , 31 , 33 , 40 , 42 , 58 , 67 , 69 , 70 , 71 , 72 , 73 , 74 , 75 ], and wastewater treatment plants [ 68 , 76 ]. A review on water quality prediction by [ 58 ] for a period 2008–2019 concluded that the MLP architecture in ANN was the widely used architecture to complete prediction tasks during this period. The common reason behind the MLP outperforming other architectures, across all literature, lies in the MLP’s ability to approximate any relationship between input(s) and output(s) through the typical three layers and its advantage of being easy to use [ 1 , 2 , 6 , 7 , 9 , 31 , 33 , 40 , 42 , 48 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 ,…”

“…A review on water quality prediction by [ 58 ] for a period 2008–2019 concluded that the MLP architecture in ANN was the widely used architecture to complete prediction tasks during this period. The common reason behind the MLP outperforming other architectures, across all literature, lies in the MLP’s ability to approximate any relationship between input(s) and output(s) through the typical three layers and its advantage of being easy to use [ 1 , 2 , 6 , 7 , 9 , 31 , 33 , 40 , 42 , 48 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 ]. Therefore, the MLP architecture in ANN is a tested and suitable method for water prediction in a complex system like a river system.…”