Assessing the biochemical oxygen demand using neural networks and ensemble tree approaches in South Korea.

The biochemical oxygen demand (BOD), one of widely utilized variables for water quality assessment, is metric for the ecological division in rivers. Since the traditional approach to predict BOD is time-consuming and inaccurate due to inconstancies in microbial multiplicity, alternative methods have been recommended for more accurate prediction of BOD. This study investigated the capability of a novel deep learning-based model, Deep Echo State Network (Deep ESN), for predicting BOD, based on various water quality variables, at Gongreung and Gyeongan stations, South Korea. The model was compared with the Extreme Learning Machine (ELM) and two ensemble tree models comprising the Gradient Boosting Regression Tree (GBRT) and Random Forests (RF). Diverse water quality variables (i.e., BOD, potential of Hydrogen (pH), electrical conductivity (EC), dissolved oxygen (DO), water temperature (WT), chemical oxygen demand (COD), suspended solids (SS), total nitrogen (T-N), and total phosphorus (T-P)) were utilized for developing the Deep ESN, ELM, GBRT, and RF with five input combinations (i.e., Categories 1-5). These models were evaluated by root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), coefficient of determination (R2), and correlation coefficient (R). Overall evaluations suggested that the Deep ESN5 model provided the most reliable predictions of BOD among all the models at both stations.

Multi-scale dynamics by adjusting the leaking rate to enhance the performance of deep echo state networks.

Introduction: The deep echo state network (Deep-ESN) architecture, which comprises a multi-layered reservoir layer, exhibits superior performance compared to conventional echo state networks (ESNs) owing to the divergent layer-specific time-scale responses in the Deep-ESN. Although researchers have attempted to use experimental trial-and-error grid searches and Bayesian optimization methods to adjust the hyperparameters, suitable guidelines for setting hyperparameters to adjust the time scale of the dynamics in each layer from the perspective of dynamical characteristics have not been established. In this context, we hypothesized that evaluating the dependence of the multi-time-scale dynamical response on the leaking rate as a typical hyperparameter of the time scale in each neuron would help to achieve a guideline for optimizing the hyperparameters of the Deep-ESN. Method: First, we set several leaking rates for each layer of the Deep-ESN and performed multi-scale entropy (MSCE) analysis to analyze the impact of the leaking rate on the dynamics in each layer. Second, we performed layer-by-layer cross-correlation analysis between adjacent layers to elucidate the structural mechanisms to enhance the performance. Results: As a result, an optimum task-specific leaking rate value for producing layer-specific multi-time-scale responses and a queue structure with layer-to-layer signal transmission delays for retaining past applied input enhance the Deep-ESN prediction performance. Discussion: These findings can help to establish ideal design guidelines for setting the hyperparameters of Deep-ESNs.

Estimating the incubated river water quality indicator based on machine learning and deep learning paradigms: BOD5 Prediction.

As an indicator measured by incubating organic material from water samples in rivers, the most typical characteristic of water quality items is biochemical oxygen demand (BOD5) concentration, which is a stream pollutant with an extreme circumstance of organic loading and controlling aquatic behavior in the eco-environment. Leading monitoring approaches including machine leaning and deep learning have been evolved for a correct, trustworthy, and low-cost prediction of BOD5 concentration. The addressed research investigated the efficiency of three standalone models including machine learning (extreme learning machine (ELM) and support vector regression (SVR)) and deep learning (deep echo state network (Deep ESN)). In addition, the novel double-stage synthesis models (wavelet-extreme learning machine (Wavelet-ELM), wavelet-support vector regression (Wavelet-SVR), and wavelet-deep echo state network (Wavelet-Deep ESN)) were developed by integrating wavelet transformation (WT) with the different standalone models. Five input associations were supplied for evaluating standalone and double-stage synthesis models by determining diverse water quantity and quality items. The proposed models were assessed using the coefficient of determination (R2), Nash-Sutcliffe (NS) efficiency, and root mean square error (RMSE). The significance of addressed research can be found from the overall outcomes that the predictive accuracy of double-stage synthesis models were not always superior to that of standalone models. Overall results showed that the SVR with 3th distribution (NS = 0.915) and the Wavelet-SVR with 4th distribution (NS = 0.915) demonstrated more correct outcomes for predicting BOD5 concentration compared to alternative models at Hwangji station, and the Wavelet-SVR with 4th distribution (NS = 0.917) was judged to be the most superior model at Toilchun station. In most cases for predicting BOD5 concentration, the novel double-stage synthesis models can be utilized for efficient and organized data administration and regulation of water pollutants on both stations, South Korea.