An efficient strategy for predicting river dissolved oxygen concentration: application of deep recurrent neural network model

Predicting dissolved oxygen level using Young's double-slit experiment optimizer-based weighting model

Accurate prediction of the dissolved oxygen level (DOL) is important for enhancing environmental conditions and facilitating water resource management. However, the irregularity and volatility inherent in DOL pose significant challenges to achieving precise forecasts. A single model usually suffers from low prediction accuracy, narrow application range, and difficult data acquisition. This study proposes a new weighted model that avoids these problems, which could increase the prediction accuracy of the DOL. The weighting constructs of the proposed model (PWM) included eight neural networks and one statistical method and utilized Young's double-slit experimental optimizer as an intelligent weighting tool. To evaluate the effectiveness of PWM, simulations were conducted using real-world data acquired from the Tualatin River Basin in Oregon, United States. Empirical findings unequivocally demonstrated that PWM outperforms both the statistical model and the individual machine learning models, and has the lowest mean absolute percentage error among all the weighted models. Based on two real datasets, the PWM can averagely obtain the mean absolute percentage errors of 1.0216%, 1.4630%, and 1.7087% for one-, two-, and three-step predictions, respectively. This study shows that the PWM can effectively integrate the distinctive merits of deep learning methods, neural networks, and statistical models, thereby increasing forecasting accuracy and providing indispensable technical support for the sustainable development of regional water environments.

Long short-term memory models of water quality in inland water environments

Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse and seasonal changes. Deep learning models have demonstrated predictive power of water quality due to the superior ability to automatically learn complex patterns and relationships from variables. Long short-term memory (LSTM), one of deep learning models for water quality prediction, is a type of recurrent neural network that can account for longer-term traits of time-dependent data. It is the most widely applied network used to predict the time series of water quality variables. First, we reviewed applications of a standalone LSTM and discussed its calculation time, prediction accuracy, and good robustness with process-driven numerical models and the other machine learning. This review was expanded into the LSTM model with data pre-processing techniques, including the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise method and Synchrosqueezed Wavelet Transform. The review then focused on the coupling of LSTM with a convolutional neural network, attention network, and transfer learning. The coupled networks demonstrated their performance over the standalone LSTM model. We also emphasized the influence of the static variables in the model and used the transformation method on the dataset. Outlook and further challenges were addressed. The outlook for research and application of LSTM in hydrology concludes the review.

Alternative states in microbial communities during artificial aeration: Proof of incubation experiment and development of recurrent neural network models

Artificial aeration, a widely used method of restoring the aquatic ecological environment by enhancing the re-oxygenation capacity, typically relies upon empirical models to predict ecological dynamics and determine the operating scheme of the aeration equipment. Restoration through artificial aeration is involved in oxic-anoxic transitions, whether these transitions occurred in the form of a regime shift, making the development of predictive models challenging. Here, we confirmed the existence of alternative states in microbial communities during artificial aeration through aeration incubation experiment for the first time and considered its existence in neural network modeling in order to improve model performance. By aeration incubation experiment, it was confirmed that the alternative states exist in microbial communities during artificial aeration by two independent approaches, potential analysis and "enterotyping" approach. Comparing neural network models with and without considering the existence of alternative states, it was found that considering the existence of alternative states in modeling could improve the performance of neural network model. Our study provides a reference for the prediction of systems containing time series data where the current state will have an impact on later states. The developed model could be used for optimizing the operating scheme of the artificial aeration.

Research progress of the artificial intelligence application in wastewater treatment during 2012-2022: a bibliometric analysis

This study identified literatures from the Web of Science Core Collection on the application of artificial intelligence in wastewater treatment from 2011 to 2022, through bibliometrics, to summarize achievements and capture the scientific and technological progress. The number of papers published is on the rise, and especially, the number of papers issued after 2018 has increased sharply, with China contributing the most in this regard, followed by the US, Iran and India. The University of Tehran has the largest number of papers, WATER is the most published journal, and Nasr M has the largest number of articles. Collaborative network has been developed mainly through cooperation between European countries, China and the US. Remote sensing in developing countries needs to be further integrated with water quality monitoring programs. It is worth noting that artificial neural network is a research hotspot in recent years. Through keyword clustering analysis, 'machine learning' and 'deep learning' are hot keywords that have emerged since 2019. The use of neural networks for predicting the effectiveness of treatment of difficult to degrade wastewater is a future research trend. The rapid advancement of deep learning provides the opportunity to build automated pipeline defect detection systems through image recognition.

A spatiotemporal dissolved oxygen prediction model based on graph attention networks suitable for missing data

The accurate prediction of dissolved oxygen concentration is crucial for the effective prevention and control of water pollution. A spatiotemporal prediction model for dissolved oxygen content that is suitable for missing data is proposed in this study. The model utilizes a module based on neural controlled differential equations (NCDEs) to handle missing data and graph attention networks (GATs) to capture the spatiotemporal relationship of dissolved oxygen content. To enhance the performance of model, it is optimized from three aspects: an iterative optimization method based on the k-nearest neighbor graph is proposed to enhance the quality of graph; Shapley additive explanations model (SHAP) is used to select the main features into model, enabling it to handle multiple features; and a fusion graph attention mechanism is introduced to improve the robustness of model to noise. The model is evaluated using data from water quality monitoring sites in Hunan Province, China, from January 14, 2021, to June 16, 2022. The proposed model outperforms other models in long-term prediction (step = 18), with MAE of 0.194, NSE of 0.914, RAE of 0.219, and IA of 0.977. The results demonstrate that constructing appropriate spatial dependencies can enhance the accuracy of dissolved oxygen prediction models, and the NCDE module confers robustness to missing data in the model.

Mid- to Long-Term Runoff Prediction Based on Deep Learning at Different Time Scales in the Upper Yangtze River Basin

Deep learning models are essential tools for mid- to long-term runoff prediction. However, the influence of the input time lag and output lead time on the prediction results in deep learning models has been less studied. Based on 290 schemas, this study specified different time lags by sliding windows and predicted the runoff process by RNN (Recurrent Neural Network), LSTM (Long–short-term Memory), and GRU (Gated Recurrent Unit) models at five hydrological stations in the upper Yangtze River during 1980–2018 at daily, ten-day, and monthly scales. Different models have different optimal time lags; therefore, multiple time lags were analyzed in this paper to find out the relationship between the time intervals and the accuracy of different river runoff predictions. The results show that the optimal time-lag settings for the RNN, LSTM, and GRU models in the daily, ten-day, and monthly scales were 7 days, 24 ten days, 27 ten days, 24 ten days, 24 months, 27 months, and 21 months, respectively. Furthermore, with the increase of time lags, the simulation accuracy would stabilize after a specific time lag at multiple time scales of runoff prediction. Increased lead time was linearly related to decreased NSE at daily and ten-day runoff prediction. However, there was no significant linear relationship between NSE and lead time at monthly runoff prediction. Choosing the smallest lead time could have the best prediction results at different time scales. Further, the RMSE of the three models revealed that RNN was inferior to LSTM and GRU in runoff prediction. In addition, RNN, LSTM, and GRU models could not accurately predict extreme runoff events at different time scales. This study highlights the influence of time-lag setting and lead-time selection in the mid- to long-term runoff prediction results for the upper Yangtze River basin. It is recommended that researchers should evaluate the effect of time lag before using deep learning models for runoff prediction, and to obtain the best prediction, the shortest lead-time length can be chosen as the best output for different time scales.

Modeling Multistep Ahead Dissolved Oxygen Concentration Using Improved Support Vector Machines by a Hybrid Metaheuristic Algorithm

Dissolved oxygen (DO) concentration is an important water-quality parameter, and its estimation is very important for aquatic ecosystems, drinking water resources, and agro-industrial activities. In the presented study, a new support vector machine (SVM) method, which is improved by hybrid firefly algorithm–particle swarm optimization (FFAPSO), is proposed for the accurate estimation of the DO. Daily pH, temperature (T), electrical conductivity (EC), river discharge (Q) and DO data from Fountain Creek near Fountain, the United States, were used for the model development. Various combinations of pH, T, EC, and Q were used as inputs to the models to estimate the DO. The outcomes of the proposed SVM–FFAPSO model were compared with the SVM–PSO, SVM–FFA, and standalone SVM with respect to the root mean square errors (RMSE), the mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and determination coefficient (R2), and graphical methods, such as scatterplots, and Taylor and violin charts. The SVM–FFAPSO showed a superior performance to the other methods in the estimation of the DO. The best model of each method was also assessed in multistep-ahead (from 1- to 7-day ahead) DO, and the superiority of the proposed method was observed from the comparison. The general outcomes recommend the use of SVM–FFAPSO in DO modeling, and this method can be useful for decision-makers in urban water planning and management.

Machine learning algorithm as a sustainable tool for dissolved oxygen prediction: a case study of Feitsui Reservoir, Taiwan

Water quality status in terms of one crucial parameter such as dissolved oxygen (D.O.) has been an important concern in the Fei-Tsui reservoir for decades since it's the primary water source for Taipei City. Therefore, this study aims to develop a reliable prediction model to predict D.O. in the Fei-Tsui reservoir for better water quality monitoring. The proposed model is an artificial neural network (ANN) with one hidden layer. Twenty-nine years of water quality data have been used to validate the accuracy of the proposed model. A different number of neurons have been investigated to optimize the model's accuracy. Statistical indices have been used to examine the reliability of the model. In addition to that, sensitivity analysis has been carried out to investigate the model's sensitivity to the input parameters. The results revealed the proposed model capable of capturing the dissolved oxygen's nonlinearity with an acceptable level of accuracy where the R-squared value was equal to 0.98. The optimum number of neurons was found to be equal to 15-neuron. Sensitivity analysis shows that the model can predict D.O. where four input parameters have been included as input where the d-factor value was equal to 0.010. This main achievement and finding will significantly impact the water quality status in reservoirs. Having such a simple and accurate model embedded in IoT devices to monitor and predict water quality parameters in real-time would ease the decision-makers and managers to control the pollution risk and support their decisions to improve water quality in reservoirs.