Data-driven method based on deep learning algorithm for detecting fat, oil, and grease (FOG) of sewer networks in urban commercial areas

A hybrid deep learning approach to improve real-time effluent quality prediction in wastewater treatment plant

Wastewater treatment plant (WWTP) operation is usually intricate due to large variations in influent characteristics and nonlinear sewage treatment processes. Effective modeling of WWTP effluent water quality can provide valuable decision-making support to facilitate their operations and management. In this study, we developed a novel hybrid deep learning model by combining the temporal convolutional network (TCN) model with the long short-term memory (LSTM) network model to improve the simulation of hourly total nitrogen (TN) concentration in WWTP effluent. The developed model was tested in a WWTP in Jiangsu Province, China, where the prediction results of the hybrid TCN-LSTM model were compared with those of single deep learning models (TCN and LSTM) and traditional machine learning model (feedforward neural network, FFNN). The hybrid TCN-LSTM model could achieve 33.1 % higher accuracy as compared to the single TCN or LSTM model, and its performance could improve by 63.6 % comparing to the traditional FFNN model. The developed hybrid model also exhibited a higher power prediction of WWTP effluent TN for the next multiple time steps within eight hours, as compared to the standalone TCN, LSTM, and FFNN models. Finally, employing model interpretation approach of Shapley additive explanation to identify the key parameters influencing the behavior of WWTP effluent water quality, it was found that removing variables that did not contribute to the model output could further improve modeling efficiency while optimizing monitoring and management strategies.

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.

Tackling fat, oil, and grease (FOG) build-up in sewers: Insights into deposit formation and sustainable in-sewer management techniques

The increasing global demand for fatty products, population growth, and the expansion of food service establishments (FSEs) present significant challenges for the wastewater industry. This is often due to the build-up of fat, oil and grease (FOG) in sewers, which reduces capacity and leads to sanitary sewer overflows. It is crucial to develop economic and sustainable in-sewer FOG management techniques to minimise maintenance costs and service disruptions caused by the removal of FOG deposits from sewers. This study aims to understand the process of FOG deposit formation in both concrete and non-concrete sewers. Compared to fresh cooking oil, disposal of used cooking oil in households and FSE sinks results in the formation of highly adhesive and viscous FOG deposits. This occurs due to hydrolysis during frying, which increases the concentration of fatty acids, particularly palmitic acid, in the used cooking oil. Furthermore, metal ions from food waste, wastewater, and dishwashing detergents contribute to the saponification and aggregation reactions which cause FOG deposition in both concrete and non-concrete sewers. However, the leaching of Ca2+ ions exacerbates FOG deposition in cement-concrete sewers. The article concludes by suggesting future research perspectives and proposes implementation strategies for microbially induced concrete corrosion (MICC) control to manage FOG deposition in sewers. One such strategy involves applying superhydrophobic coating materials with low surface free energy and high surface roughness to the interior surfaces of the sewer. This approach would help repel wastewater carrying FOG deposit components, potentially disrupting the interaction between FOG components, and reducing the adhesion of FOG deposits to sewer surfaces.

Research on predicting the diffusion of toxic heavy gas sulfur dioxide by applying a hybrid deep learning model to real case data

Toxic heavy gas sulfur dioxide (SO2) is a specific life and environmental hazard. Predicting the diffusion of SO2 has become a research focus in fields such as environmental and safety studies. However, traditional methods, such as kinetic models, cannot balance precision and time. Thus, they do not meet the needs of emergency decision-making. Deep learning (DL) models are emerging as a highly regarded solution, providing faster and more accurate predictions of gas concentrations. To this end, this study proposes an innovative hybrid DL model, the parallel-connected convolutional neural network-gated recurrent unit (PC CNN-GRU). This model utilizes two CNNs connected in parallel to process gas release and meteorological datasets, enabling the automatic extraction of high-dimensional data features and handling of long-term temporal dependencies through the GRU. The proposed model demonstrates good performance (RMSE, MAE, and R2 of 20.1658, 10.9158, and 0.9288, respectively) with real data from the Project Prairie Grass (PPG) case. Meanwhile, to address the issue of limited availability of raw data, in this study, time series generative adversarial network (TimeGAN) are introduced for SO2 diffusion studies for the first time, and their effectiveness is verified. To enhance the practicality of the research, the contribution of drivers to SO2 diffusion is quantified through the utilization of the permutation importance (PIMP) and Sobol' method. Additionally, the maximum safe distance downwind under various conditions is visualized based on the SO2 toxicity endpoint concentration. The results of the analyses can provide a scientific basis for relevant decisions and measures.

Time series prediction of the chemical components of PM2.5 based on a deep learning model

Modeling-based prediction methods enable rapid, reagent-free air pollution detection based on inexpensive multi-source data than traditional chemical reaction-based detection methods in order to quickly understand the air pollution situation. In this study, a convolutional neural network (CNN) and long and short-term memory (LSTM) neural networks are integrated to create a CNN-LSTM time series prediction model to predict the concentration of PM2.5 and its chemical components (i.e., heavy metals, carbon component, and water-soluble ions) using meteorological data and air pollutants (PM2.5, SO2, NO2, CO, and O3). In the integrated CNN-LSTM model, the CNN uses convolutional and pooling layers to extract features from the data, whereas the powerful nonlinear mapping and learning capabilities of LSTM enable the time series prediction of air pollution. The experimental results showed that the CNN-LSTM exhibited good generalization ability in the prediction of As, Cd, Cr, Cu, Ni, and Zn, with a mean R2 above 0.9. Mean R2 predicted for PM2.5, Pb, Ti, EC, OC, SO42-, and NO3- ranged from 0.85 to 0.9. Shapley value showed that PM2.5, NO2, SO2, and CO had a greater influence on the predicted heavy metal results of the model. Regarding water-soluble ions, the predicted results were dominantly influenced by PM2.5, CO, and humidity. The prediction of the carbon fraction was affected mainly by the PM2.5 concentration. Additionally, several input variables for various components were eliminated without affecting the prediction accuracy of the model, with R2 between 0.70 and 0.84, thereby maximizing modeling efficiency and lowering operational costs. The fully trained model prediction results showed that most predicted components of PM2.5 were lower during January to March 2020 than those in 2018 and 2019. This study provides insight into improving the accuracy of modeling-based detection methods and promotes the development of integrated air pollution monitoring toward a more sustainable direction.

Water Quality Prediction Based on Machine Learning and Comprehensive Weighting Methods

In the context of escalating global environmental concerns, the importance of preserving water resources and upholding ecological equilibrium has become increasingly apparent. As a result, the monitoring and prediction of water quality have emerged as vital tasks in achieving these objectives. However, ensuring the accuracy and dependability of water quality prediction has proven to be a challenging endeavor. To address this issue, this study proposes a comprehensive weight-based approach that combines entropy weighting with the Pearson correlation coefficient to select crucial features in water quality prediction. This approach effectively considers both feature correlation and information content, avoiding excessive reliance on a single criterion for feature selection. Through the utilization of this comprehensive approach, a comprehensive evaluation of the contribution and importance of the features was achieved, thereby minimizing subjective bias and uncertainty. By striking a balance among various factors, features with stronger correlation and greater information content can be selected, leading to improved accuracy and robustness in the feature-selection process. Furthermore, this study explored several machine learning models for water quality prediction, including Support Vector Machines (SVMs), Multilayer Perceptron (MLP), Random Forest (RF), XGBoost, and Long Short-Term Memory (LSTM). SVM exhibited commendable performance in predicting Dissolved Oxygen (DO), showcasing excellent generalization capabilities and high prediction accuracy. MLP demonstrated its strength in nonlinear modeling and performed well in predicting multiple water quality parameters. Conversely, the RF and XGBoost models exhibited relatively inferior performance in water quality prediction. In contrast, the LSTM model, a recurrent neural network specialized in processing time series data, demonstrated exceptional abilities in water quality prediction. It effectively captured the dynamic patterns present in time series data, offering stable and accurate predictions for various water quality parameters.

Water quality assessment of deep learning-improved comprehensive pollution index: a case study of Dagu River, Jiaozhou Bay, China

In the past few decades, with the country's rapid development, water pollution has become a significant problem many countries face. Most of the existing water quality evaluation uses a single time-invariant model to simulate the evolution process, which cannot directly describe the complex behavior of long-term water quality evolution. In addition, the traditional comprehensive index method, fuzzy comprehensive evaluation, and gray pattern recognition have more subjective factors. It can lead to an inevitable subjectivity of the results and weak applicability. Given these shortcomings, this paper proposes a deep learning-improved comprehensive pollution index method to predict future water quality development. As a first processing step, the historical data is normalized. Three deep learning models, multilayer perceptron (MLP), recurrent neural network (RNN), and long short-term memory (LSTM), are used to train historical data. The optimal data prediction model is selected through simulation and comparative analysis of relevant measured data, and the improved entropy weight comprehensive pollution index method is applied to evaluate future water quality changes. Compared with the traditional time-invariant evaluation model, the feature of this model is that it can effectively reflect the development of water quality in the future. Moreover, the entropy weight method is introduced to balance the errors caused by subjective weight. The result shows that LSTM performs well in accurately identifying and predicting water quality. And the deep learning-improved comprehensive pollution index method can provide helpful information and enlightenment for water quality change, which can help improve the water quality prediction and scientific management of coastal water resources.

A bilevel data-driven method for sewer deposit prediction under uncertainty

Deposit accumulation is one of the predominant causes of sewer blockage and overflow. Nevertheless, the traditional detection methods are costly and time-consuming, and the accuracy of the mathematical models for deposit prediction is usually affected by some uncertain factors (e.g., pipe properties and flow velocity of water). This paper proposes a framework of global sensitivity analysis (GSA) to identify the most sensitive indicators for sewer deposit prediction by (i) developing a data-driven bilevel (i.e., catchment level and segment level) model to map the relation between input and output indicators and (ii) employing three different GSA methods, namely, the Morris method, Sobol method, and Borgonovo index method to identify the indicators as important or unimportant (insensitive). The results show that the likelihood of combined sewer overflow occurrences (LCSOO), pipe age (PA), and pipe material (PM) are influential parameters for the thickness of deposits. Here, we pay close attention to the most influential parameters, which can help improve forecast prediction accuracy.

A critical review of wastewater quality variation and in-sewer processes during conveyance in sewer systems

In-sewer physio-biochemical processes cause significant variations of wastewater quality during conveyance, which affects the influent to a wastewater treatment plant (WWTP) and arguably the microbial community of biological treatment units in a WWTP. In wet weather, contaminants stored in sewer deposits can be resuspended and migrate downstream or be released during combined sewer overflows to the urban water bodies, posing challenges to the treatment facilities or endangering urban water quality. Therefore, in-sewer transformation and migration of contaminants have been extensively studied. The compiled results from representative research in the past few decades showed that biochemical reactions are both cross-sectionally and longitudinally organized in the deposits and the sewage, following the redox potential as well as the sequence of macromolecule/contaminant degradation. The sewage organic contents and sewer biofilm microorganisms were found to covary but more systematic studies are required to examine the temporal stability of the feature. Besides, unique communities can be developed in the sewage phase. The enrichment of the major sewage-associated microorganisms can be explained by the availability of biodegradable organic contents in sewers. The sewer deposits, including biofilms, harbor both microorganisms and contaminants and usually can provide longer residence time for in-sewer transformation than wastewater. However, the interrelationships among contaminant transformation, microorganisms in the deposits/biofilms, and those in the sewage are largely unclear. Specifically, the formation and migration of FOG (fat, oil, and grease) deposits, generation and transport of contaminants in the sewer atmosphere (e.g., H₂S, CH₄, volatile organic compounds, bioaerosols), transport and transformation of nonconventional contaminants, such as pharmaceuticals and personal care products, and wastewater quality variation during the biofilm rehabilitation period after damages caused by rains/storms are some topics for future research. Moreover, systematic and standardized field analysis of real sewers under dynamic wastewater discharge conditions is necessary. We believe that an improved understanding of these processes would assist in sewer management and better prepare us for the challenges brought about by climate change and water shortage.

The next generation of soil and water bodies heavy metals prediction and detection: New expert system based Edge Cloud Server and Federated Learning technology

Heavy metals (HMs) in soil and water bodies greatly threaten human health. The wide separation of HMs urges the necessity to develop an expert system for HMs prediction and detection. In the current perspective, several propositions are discussed to design an innovative intelligence system for HMs prediction and detection in soil and water bodies. The intelligence system incorporates the Edge Cloud Server (ECS) data center, an innovative deep learning predictive model and the Federated Learning (FL) technology. The ECS data center is based on satellite sensing sources under human expertise ruling and HMs in-situ measurement. The FL system comprises a machine learning (ML) technique that trains an algorithm across multiple decentralized edge servers holding local data samples without exchanging them or breaching data privacy. The expected outcomes of the intelligence system are to quantify the soil and water bodies' HMs, develop new modified HMs pollution contamination indices and provide decision-makers and environmental experts with an appropriate vision of soil, surface water, and crop health.

TLT: Recurrent fine-tuning transfer learning for water quality long-term prediction

The water quality long-term prediction is essential to water environment management decisions. In recent years, although water quality prediction methods based on deep learning have achieved excellent performance in short-term prediction, these methods are unsuitable for long-term prediction because the accumulation use of short-term prediction will easily introduce noise. Furthermore, The long-term prediction task requires a large amount of data to train the model to obtain accurate prediction results. For some monitoring stations with limited historical data, it is challenging to fully exploit the performance of deep learning models. To this end, we introduce a transfer learning framework into water quality prediction to improve the prediction performance in data-constrained scenarios. We propose a deep Transfer Learning based on Transformer (TLT) model to enable time dependency perception and facilitate long-term water quality prediction. In TLT, we innovatively introduce a recurrent fine-tuning transfer learning method, which can transfer the knowledge learned from source monitoring stations to the target station, while preventing the deep learning model from overfitting the source data during the pre-training phase. So, TLT can fully exert the performance of deep learning models with limited samples. We conduct experiments on data from 120 monitoring stations in major rivers and lakes in China to verify the effectiveness of TLT. The results show that TLT can effectively improve the long-term prediction accuracy of four water quality indicators (pH, DO, NH₃-N, and COD_Mn) from monitoring stations with limited samples.

Deep learning model based on urban multi-source data for predicting heavy metals (Cu, Zn, Ni, Cr) in industrial sewer networks

The high concentrations of heavy metals in municipal industrial sewer networks will seriously impact the microorganisms of the activated sludge in the wastewater treatment plant (WWTP), thus deteriorating the effluent quality and destroying the stability of sewage treatment. Therefore, timely prediction and early warning of heavy metal concentrations in industrial sewer networks is crucial. However, due to the complex sources of heavy metals in industrial sewer networks, traditional physical modeling and linear methods cannot establish an accurate prediction model. Herein, we developed a Gated Recurrent Unit (GRU) neural network model based on a deep learning algorithm for predicting the concentrations of heavy metals in industrial sewer networks. To train the GRU model, we used low-cost and easy-to-obtain urban multi-source data, including socio-environmental indicator data, air environmental indicator data, water quantity indicator data, and easily measurable water quality indicator data. The model was applied to predict the concentrations of heavy metals (Cu, Zn, Ni, and Cr) in the sewer networks of an industrial area in southern China. The results are compared with the commonly used Artificial Neural Network (ANN) model. In this study, it was shown that the GRU had better prediction performance for Cu, Zn, Ni, and Cr concentrations, with the average R² significantly increased by 12.35%, 11.94%, 9.21%, and 8.13%, respectively, compared to ANN predictions. The sensitivity analysis based on Shapley (SHAP) values revealed that conductivity (σ), temperature (T), pH, and sewage flow (Flow) contributed significantly to the prediction results of the model. Furthermore, the three input variables including air pressure (AP), land area (A), and population (Pop.) were removed without affecting the prediction performance of the model, which maximized the modeling efficiency and reduced the operational cost. This study provides an economical and feasible technical method for early warning of abnormal heavy metal concentrations in urban industrial sewer networks.