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.

A point-to-point communication network is represented by (G,C), where G=(V,/spl epsiv/) is a directed graph with vertex set V and edge set /spl epsiv/, and C=[C/sub ij/,(i,j)/spl isin//spl epsiv/] is a nonnegative-valued vector. A vertex in V represents a node in the communication network, and an edge (i,j) represents a point-to-point discrete memoryless channel (DMC) from node i to node j whose capacity is C/sub ij/. We assume that the channels in the network are independent of each other. An information source with entropy rate h is generated at source node /spl delta/ and recovered at sink node t with arbitrarily small probability of error. We show that the value of a max-flow from node /spl delta/ to node t in (G,C) must be greater than or equal to h. This results implies a separation theorem for network coding and channel coding in such a communication network.