An Integrated First Principal and Deep Learning Approach for Modeling Nitrous Oxide Emissions from Wastewater Treatment Plants

Data-driven differentiable model for dynamic prediction and control in wastewater treatment

Wastewater treatment plants, while critical for environmental protection, face mounting challenges in operational efficiency and sustainability due to increasing urbanization and stricter environmental standards. In this study, we introduce an innovative continuous-time neural framework based on Neural Ordinary Differential Equations (Neural ODEs) to enhance the modeling of sewage treatment processes. Addressing the dual challenges of operational efficiency and sustainable development in urban wastewater treatment plants (WWTPs), our methodology marks a significant departure from traditional approaches by implementing a continuous-time neural framework that captures the inherent dynamics of wastewater treatment processes while reducing computational demands by 95 % compared to discrete-time models. We analyzed operational data from three full-scale WWTPs over a year, demonstrating that our model not only achieves superior prediction accuracy (R² > 0.95) with various input window sizes but also significantly reduces memory usage-from 111.88-12,484.59 MB to just 17.74-50.92 MB. Notably, our framework exhibits robust performance even with up to 30 % missing data, uncovering new process insights through interpretable feature attribution. Further integration with reinforcement learning has led to a 21.9 % reduction in aeration energy consumption compared to conventional open-loop control strategies while adhering to effluent quality standards. This research establishes a novel paradigm for intelligent wastewater management that optimizes operational efficiency and promotes environmental sustainability.

Comprehensive assessment, intelligent prediction, and precise mitigation strategies for greenhouse gas emissions in full-scale wastewater treatment plants

Wastewater treatment plants (WWTPs) are major contributors to global anthropogenic greenhouse gas (GHG) emissions, with China ranks among the leading emitters. In the context of China's "dual-carbon" journey, precision quantification and predictive forecasting of GHG fluxes, particularly methane (CH4) and nitrous oxide (N2O)-are crucial for developing advanced mitigation strategies of WWTPs. To accurately assess GHG emissions, this study firstly introduced customized emission factors (EFs) to precisely evaluate the GHG emissions of a full - scale A2O - based WWTP in Beijing. This approach addressed the overestimation of emissions when using the IPCC's standard EFs. Additionally, the study proposed machine learning (ML) techniques to predict GHG fluxes based on routine wastewater quality parameters. Specifically, Long Short-Term Memory (LSTM) and Random Forest (RF) models showed the strong performance in predicting CH4 and N2O emissions, respectively. Moreover, our findings revealed distinct spatiotemporal patterns of GHG emission: CH4 emissions peak during the summer solstice, while N2O emissions rise during the winter months. For the first time, this study identified the nitrification biofilter in the advanced treatment unit as a significant direct source of N2O emissions. Eventhough, indirect CO2 emissions account for a dominant 57%-90% of the total GHG emissions. Scenario analyses revealed a strategic mitigation approach. Energy conservation emerged as the most effective measure, capable of reducing emissions by 23.41%, followed by heat recovery, which could cut emissions by 10.15%. In practical applications, improving energy efficiency is of utmost importance in real - world mitigation strategies. This highlights the significance of integrated approaches for achieving the sustainable development of WWTPs in the "dual - carbon" background.

Effective evaluation of greenhouse gases (GHGs) emissions from anoxic/oxic (A/O) process of regenerated papermaking wastewater treatment through hybrid deep learning techniques: Leveraging the critical role of water quality indicators

Accurate accounting of greenhouse gases (GHGs) emissions from industrial wastewater treatment processes/plants with high organic concentration and fluctuating inflows is crucial for the calculation and management of carbon emissions. The impacts of water quality indicators on GHGs emissions within the biological nutrient removal process are still unclear, which deserves intensive attention. Here, a lab-scale anoxic/oxic (A/O) process was constructed for raw regenerated papermaking wastewater treatment with different low/high-concentration influent stages for about 110 days to evaluate GHGs emissions. A high-quality dataset included 295 sets of the multi-factors (including COD, suspended solid (SS), NH4+-N, NO3--N, NO2--N, and pH/DO/Temperature) was built. Moreover, the corresponding proportion of GHGs emissions were analyzed and a novel hybrid deep learning model TCNA, which integrated the Temporal Convolutional Network (TCN) and Attention Mechanism (AM), was developed to explore the trends and predictions of GHGs emissions based on the dataset. A series of comparisons with model Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and Temporal Convolutional Networks (TCN) were also conducted under the same conditions. The TCNA model showed an outstanding performance for CO2, CH4, and N2O emissions prediction, achieving the highest value of R2 score (CO2, 0.8014; CH4, 0.8839; N2O, 0.9354) and the lowest value of root mean squared error (RMSE) and mean absolute error (MAE) (CO2: 2.6137,1.9366; CH4: 1.929,0.7214; N2O: 0.8897, 0.5777) among the five models above. The results highlight the potential of the TCNA model for accurate and robust prediction of GHGs emissions from industrial wastewater treatment plants with the A/O treatment process, contributing to effective GHGs mitigation strategies and carbon management of industrial wastewater treatment.

Deciphering and Mitigating of Dynamic Greenhouse Gas Emission in Urban Drainage Systems with Knowledge-Infused Graph Neural Network

Deciphering and mitigating dynamic greenhouse gas (GHG) emissions under environmental fluctuation in urban drainage systems (UDGSs) is challenging due to the absence of a high-prediction model that accurately quantifies the contributions of biological production pathways. Here we infused biological production pathways into the graph neural network (GNN) model architecture, developing ecological knowledge-infused GNN (EcoGNN-GHG) models to evaluate methane (CH4) and nitrous oxide (N2O) production in sewers and wastewater treatment plants (WWTPs). The EcoGNN-GHG model demonstrated high predictive accuracy, achieving an R2 of 0.96 for CH4 in sewers and 0.82 for N2O in WWTPs. Model interpretability analysis revealed fluctuations in contributions of the anaerobic hydrolysis acidification pathway to CH4 production and the nitrification-denitrification pathway to N2O production under dynamic environmental conditions, guiding the formulation of a precise dissolved oxygen control strategy targeting critical water quality parameters (acetate for CH4 production and nitrite for N2O production). Implementing this strategy to control DO thereby regulating biological production pathway contributions, CH4 production in sewers and N2O production in WWTPs were reduced by 35.50% and 29.94%, respectively. Our findings offer a robust, accurate method for predicting GHG emissions, quantifying production pathway contributions, and developing effective control strategies in UDGSs.

Small-data-trained model for predicting nitrate accumulation in one-stage partial nitritation-anammox processes controlled by oxygen supply rate

Nitrate (NO3--N) accumulation is the biggest obstacle for wastewater treatment via partial nitritation-anammox process. Dissolved oxygen (DO) control is the most used strategy to prevent NO3--N accumulation, but the performance is usually unstable. This study proposes a novel strategy for controlling NO3--N accumulation based on oxygen supply rate (OSR). In comparison, limiting the OSR is more effective than limiting DO in controlling NO3--N accumulation through mathematical simulation. A laboratory-scale one-stage partial nitritation-anammox system was continuously operated for 135 days, which was divided into five stages with different OSRs. A novel deep learning model integrating Gated Recurrent Unit and Multilayer Perceptron was developed to predict NO3--N accumulation load. To tackle with the general obstacle of limited environmental samples, a generic evaluation was proposed to optimise the model structure by leveraging predictive performance and overfitting risk. The developed model successfully predicted the NO3--N accumulation in the system ten days in advance, showcasing its potential contribution to system design and performance enhancement.

Microbial-Guided prediction of methane and sulfide production in Sewers: Integrating mechanistic models with Machine learning

Accurate modeling of methane (CH4) and sulfide (H2S) production in sewer systems was constrained by insufficient consideration of microbial processes under dynamic environmental conditions. This study introduces a microbial-guided machine learning (ML) framework (Micro-ML), which integrates microbial process representations from mechanistic models (microbial information) with ML models. Results indicate that Micro-ML model enhanced predictions of CH4 and H2S production, where microbial information provides more information for model optimization. The feature importance of microbial information performed comparable weightings for 58.12 % and 55.16 %, respectively, but their relative significance in influencing Micro-ML model performance varies considerably. The application of Micro-ML performed great potential in reducing CH4 and H2S production (decreased ∼ 80 % and 90 %). The integrated model not only improves the accuracy of CH4 and H2S predictions but also offers a valuable tool for effective management strategies for sewer systems.

Augmented machine learning for sewage quality assessment with limited data

Physical, chemical, and biological processes within sewers significantly alter sewage composition during conveyance. This leads to the formation of sulfide and methane-compounds that contribute to sewer corrosion and greenhouse gas emissions. Reliable modeling of these compounds is essential for effective sewer management, but the development of machine learning (ML) models is hindered by differences in data accessibility and sampling frequencies of water quality variables. Here we present a mechanistically enhanced hybrid (ME-Hybrid) model that combines mechanistic modeling with data-driven approaches. This model harmonizes datasets with varying sampling frequencies and generates synthetic samples for ML training, thereby enhancing the monitoring of methane and sulfide in sewers. The optimal ME-Hybrid model integrates the backpropagation neural network with mechanistic frequency harmonization. We demonstrate that the ME-Hybrid model outperforms pure ML and linear interpolation in capturing fluctuating trends and extremes of sulfide concentrations, achieving a coefficient of determination (R2) of 0.94. Synthetic samples generated through mechanistic augmentation closely approximate real samples in modeling performance, statistical distribution, and data structure. This enables the model to maintain high predictive accuracy (R2 > 0.76) for sulfide even when trained on only 50 % of the dataset. Additionally, the ME-Hybrid model successfully assesses sewer methane concentrations with an R2 of 0.94, validating its applicability and generalization ability. Our results provide a reliable methodological framework for modeling and prediction under data scarcity. By facilitating better monitoring and management of sewer systems, the ME-Hybrid model aids in the development of strategies that minimize environmental impacts, enhance urban resilience, and ultimately lead to sustainable urban water systems.

A novel hybrid variable cross layer-based machine learning model improves the accuracy and interpretation of energy intensity prediction of wastewater treatment plant

Energy intensity (EI) prediction in wastewater treatment plants (WWTPs) suffers from inaccuracy and non-interpretability due to poor data quality, complex mechanisms and various confounding variables. In this study, the novel hybrid variable cross layer-based machine learning (VCL-ML) model was devised, which generates new knowledge with monitoring indicators (e.g., COD, etc.) and then embeds both domain knowledge and monitoring indicators into the ML model. This novel hybrid VCL-ML model achieves a root-mean-square error (RMSE) of 0.021 kW h/m³ with an 8.7% improvement over the conventional ML (Con-ML) model. The Shapley additive explanation demonstrated that domain knowledge features are ranked high and have important interpretable implications for the model, such as capacity utilization (CU), which measures the efficiency of resource use, and total nitrogen remaining rate (TN_rr), which indicates the nitrogen retention in a system. Partially dependent interactions between domain knowledge (e.g., sludge yield) and monitoring indexes (e.g., influent pH) could contribute to the interpretation of reality. By comparing the feature categorization between VCL-ML and Con-ML models, temporal information (e.g., month) and removal information (e.g., TN_rr) played an important role in the model's performance improvement. This result highlights the strong correlation between wastewater treatment plant energy intensity with pollutant removal and temporal information while weakening the contribution of other redundant features. This VCL-ML model improves the predicting accuracy and interpretation of the EI of WWTPs, which can be used in the optimal operation and sustainable management of WWTPs.

Development and application of an intelligent nitrogen removal diagnosis and optimization framework for WWTPs: Low-carbon and stable operation

Optimizing nitrogen removal is crucial for ensuring the efficient operation of wastewater treatment plants (WWTPs), but it is susceptible to variations in influent conditions and operational parameter constraints, and conflicts with the energy-saving and carbon emission reduction goals. To address these issues, this study proposes a hybrid framework integrating process simulation, machine learning, and multi-objective genetic algorithms for nitrogen removal diagnosis and optimization, aiming to predict the total nitrogen in effluent, diagnose nitrogen over-limit risks, and optimize the control strategies. Taking a full-scale WWTP as a case study, a process time-lag simulation-enhanced machine learning model (PTLS-ML) was developed, achieving R2 values of 0.94 and 0.79 for the training and testing sets, respectively. The proposed model successfully identified the potential reasons of nitrogen over-limit risks under different influent conditions and operational parameters, and accordingly provided optimization suggestions. In addition, the multi-objective optimization (MOO) algorithms analysis further demonstrated that maintaining 4-6 mg/L total nitrogen concentration in effluent by adjusting process operational parameters can effectively balance multiple objectives (i.e., effluent water quality, operating costs, and greenhouse gas emissions), achieving coordinated optimization. This framework can serve as a reference for stable operation, energy-saving, and emission reduction in the nitrogen removal of WWTPs.

Forecasting nitrous oxide emissions from a full-scale wastewater treatment plant using LSTM-based deep learning models

Nitrous oxide (N2O) emissions from wastewater treatment plants (WWTPs) exhibit significant seasonal variability, making accurate predictions with conventional biokinetic models difficult due to complex and poorly understood biochemical processes. This study addresses these challenges by exploring data-driven alternatives, using long short-term memory (LSTM) based encoder-decoder models as basis. The models were developed for future integration into a model predictive control framework, aiming to reduce N2O emissions by forecasting these over varying prediction horizons. The models were trained on 12 months and tested on 3 months of data from a full-scale WWTP in Amsterdam West, the Netherlands. The dataset encompasses seasonal peaks in N2O emissions typical for winter and spring months. The best performing model, featuring a 256-256 LSTM architecture, achieved the highest accuracy with test R2 values up to 0.98 across prediction horizons spanning 0.5 to 6.0 h ahead. Feature importance analysis identified past N2O emissions, influent flowrate, NH4+, NOx, and dissolved oxygen (DO) in the aerobic tank as most significant inputs. The observed decreasing influence of historical N2O emissions over extended prediction horizons highlights the importance and significance of process variables for the model's performance. The model's ability to accurately forecast short-term N2O emissions and capture immediate trends highlights its potential for operational use in controlling emissions in WWTPs. Further research incorporating diverse datasets and biochemical process inputs related to microbial activities in the N2O production pathways could improve the model's accuracy for longer forecasting horizons. These findings advocate for hybridising deep learning models with biokinetic and mechanistic insights to enhance prediction accuracy and interpretability.

Supporting data-enhanced hybrid ordinary differential equation model for phosphate dynamics in municipal wastewater treatment

A parallel hybrid ordinary differential equation (ODE) integrating the Activated Sludge Model No. 2d (ASM2d) and an artificial neural network (ANN) was developed to simulate biological phosphorus removal (BPR) with high accuracy and interpretability. Two novelties were introduced; first, the involved supporting data (i.e., phosphate-release activity) were incorporated as an input in the ANN. Second, the outputs of the ANN were selective. Three models were implemented using different ANN outputs, and all three outperformed ASM2d in phosphate estimation for anaerobic/aerobic sequencing batch reactor operation. In particular, the incorporation of four variables responsible for BPR into the ANN enabled the highest performance (R2 = 0.93) owing to the capture of increasing phosphate-accumulating organisms (PAOs). The ANN with the supporting data worked satisfactorily to compensate for ASM2d by adding proper PAOs, resulting in improvement in phosphate estimation. The novel parallel hybrid ODE can simulate BPR while maintaining physical meaning.

Novel extended hybrid tool for real time control and practically support decisions to reduce GHG emissions in full scale wastewater treatment plants

In this paper, a novel methodology and extended hybrid model for the real time control, prediction and reduction of direct emissions of greenhouse gases (GHGs) from wastewater treatment plants (WWTPs) is proposed to overcome the lack of long-term data availability in several full-scale case studies. A mechanistic model (MCM) and a machine learning (ML) model are combined to real time control, predict the emissions of nitrous oxide (N2O) and carbon dioxide (CO2) as well as effluent quality (COD - chemical oxygen demand, NH4-N - ammonia, NO3-N - nitrate) in activated sludge method. For methane (CH4), using the MCM model, predictions are performed on the input data (VFA, CODs for aerobic and anaerobic compartments) to the MLM model. Additionally, scenarios were analyzed to assess and reduce the GHGs emissions related to the biological processes. A real WWTP, with a population equivalent (PE) of 125,000, was studied for the validation of the hybrid model. A global sensitivity analysis (GSA) of the MCM and a ML model were implemented to assess GHGs emission mechanisms the biological reactor. Finally, an early warning tool for the prediction of GHGs errors was implemented to assess the accuracy and the reliability of the proposed algorithm. The results could support the wastewater treatment plant operators to evaluate possible mitigation scenarios (MS) that can reduce direct GHG emissions from WWTPs by up to 21%, while maintaining the final quality standard of the treated effluent.

An ensemble model for accurate prediction of key water quality parameters in river based on deep learning methods

Deep learning models provide a more powerful method for accurate and stable prediction of water quality in rivers, which is crucial for the intelligent management and control of the water environment. To increase the accuracy of predicting the water quality parameters and learn more about the impact of complex spatial information based on deep learning models, this study proposes two ensemble models TNX (with temporal attention) and STNX (with spatio-temporal attention) based on seasonal and trend decomposition (STL) method to predict water quality using geo-sensory time series data. Dissolved oxygen, total phosphorus, and ammonia nitrogen were predicted in short-step (1 h, and 2 h) and long-step (12 h, and 24 h) with seven water quality monitoring sites in a river. The ensemble model TNX improved the performance by 2.1%-6.1% and 4.3%-22.0% relative to the best baseline deep learning model for the short-step and long-step water quality prediction, and it can capture the variation pattern of water quality parameters by only predicting the trend component of raw data after STL decomposition. The STNX model, with spatio-temporal attention, obtained 0.5%-2.4% and 2.3%-5.7% higher performance compared to the TNX model for the short-step and long-step water quality prediction, and such improvement was more effective in mitigating the prediction shift patterns of long-step prediction. Moreover, the model interpretation results consistently demonstrated positive relationship patterns across all monitoring sites. However, the significance of seven specific monitoring sites diminished as the distance between the predicted and input monitoring sites increased. This study provides an ensemble modeling approach based on STL decomposition for improving short-step and long-step prediction of river water quality parameter, and understands the impact of complex spatial information on deep learning model.

Complete long-term monitoring of greenhouse gas emissions from a full-scale industrial wastewater treatment plant with different cover configurations

The greenhouse gas (GHG) emissions from wastewater treatment plants (WWTPs), consisting mainly of methane (CH4) and nitrous oxide (N2O), have been constantly increasing and become a non-negligible contributor towards carbon neutrality. The precise evaluation of plant-specific GHG emissions, however, remains challenging. The current assessment approach is based on the product of influent load and emission factor (EF), of which the latter is quite often a single value with huge uncertainty. In particular, the latest default Tier 1 value of N2O EF, 0.016 ± 0.012 kgN2O-N kgTN-1, is estimated based on the measurement of 30 municipal WWTPs only, without involving any industrial wastewater. Therefore, to resolve the pattern of GHG emissions from industrial WWTPs, this work conducted a 14-month monitoring campaign covering all the process units at a full-scale industrial WWTP in Shanghai, China. The total CH4 and N2O emissions from the whole plant were, on average, 447.7 ± 224.5 kgCO2-eq d-1 and 1605.3 ± 2491.0 kgCO2-eq d-1, respectively, exhibiting a 5.2- or 3.9-times more significant deviation than the influent loads of chemical oxygen demand (COD) or total nitrogen (TN). The resulting EFs, 0.00072 kgCH4 kgCOD-1 and 0.00211 kgN2O-N kgTN-1, were just 0.36% of the IPCC recommended value for CH4, and 13.2% for N2O. Besides, the parallel anoxic-oxic (A/O) lines of this industrial WWTP were covered in two configurations, allowing the comparison of GHG emissions from different odor control setup. Unit-specific analysis showed that the replacement of enclosed A/open O with enclosed A/O reduced the CH4 EF by three times, from 0.00159 to 0.00051 kgCH4 kgCOD-1, and dramatically decreased the N2O EF by an order of magnitude, from 0.00376 to 0.00032 kgN2O-N kgTN-1, which was among the lowest of all full-scale WWTPs.

Adaptive prediction for effluent quality of wastewater treatment plant: Improvement with a dual-stage attention-based LSTM network

The accurate effluent prediction plays a crucial role in providing early warning for abnormal effluent and achieving the adjustment of feedforward control parameters during wastewater treatment. This study applied a dual-staged attention mechanism based on long short-term memory network (DA-LSTM) to improve the accuracy of effluent quality prediction. The results showed that input attention (IA) and temporal attention (TA) significantly enhanced the prediction performance of LSTM. Specially, IA could adaptively adjust feature weights to enhance the robustness against input noise, with R2 increased by 13.18%. To promote its long-term memory ability, TA was used to increase the memory span from 96 h to 168 h. Compared to a single LSTM model, the DA-LSTM model showed an improvement in prediction accuracy by 5.10%, 2.11%, 14.47% for COD, TP, and TN. Additionally, DA-LSTM demonstrated excellent generalization performance in new scenarios, with the R2 values for COD, TP, and TN increasing by 22.67%, 20.06%, and 17.14% respectively, while the MAPE values decreased by 56.46%, 63.08%, and 42.79%. In conclusion, the DA-LSTM model demonstrated excellent prediction performance and generalization ability due to its advantages of feature-adaptive weighting and long-term memory focusing. This has forward-looking significance for achieving efficient early warning of abnormal operating conditions and timely management of control parameters.

Direct and indirect monitoring methods for nitrous oxide emissions in full-scale wastewater treatment plants: A critical review

Mitigation of nitrous oxide (N2O) emissions in full-scale wastewater treatment plant (WWTP) has become an irreversible trend to adapt the climate change. Monitoring of N2O emissions plays a fundamental role in understanding and mitigating N2O emissions. This paper provides a comprehensive review of direct and indirect N2O monitoring methods. The techniques, strengths, limitations, and applicable scenarios of various methods are discussed. We conclude that the floating chamber technique is suitable for capturing and interpreting the spatiotemporal variability of real-time N2O emissions, due to its long-term in-situ monitoring capability and high data acquisition frequency. The monitoring duration, location, and frequency should be emphasized to guarantee the accuracy and comparability of acquired data. Calculation by default emission factors (EFs) is efficient when there is a need for ambiguous historical N2O emission accounts of national-scale or regional-scale WWTPs. Using process-specific EFs is beneficial in promoting mitigation pathways that are primarily focused on low-emission process upgrades. Machine learning models exhibit exemplary performance in the prediction of N2O emissions. Integrating mechanistic models with machine learning models can improve their explanatory power and sharpen their predictive precision. The implementation of the synergy of nutrient removal and N2O mitigation strategies necessitates the calibration and validation of multi-path mechanistic models, supported by long-term continuous direct monitoring campaigns.

A Review of Computational Modeling in Wastewater Treatment Processes

Wastewater treatment companies are facing several challenges related to the optimization of energy efficiency, meeting more restricted water quality standards, and resource recovery potential. Over the past decades, computational models have gained recognition as effective tools for addressing some of these challenges, contributing to the economic and operational efficiencies of wastewater treatment plants (WWTPs). To predict the performance of WWTPs, numerous deterministic, stochastic, and time series-based models have been developed. Mechanistic models, incorporating physical and empirical knowledge, are dominant as predictive models. However, these models represent a simplification of reality, resulting in model structure uncertainty and a constant need for calibration. With the increasing amount of available data, data-driven models are becoming more attractive. The implementation of predictive models can revolutionize the way companies manage WWTPs by permitting the development of digital twins for process simulation in (near) real-time. In data-driven models, the structure is not explicitly specified but is instead determined by searching for relationships in the available data. Thus, the main objective of the present review is to discuss the implementation of machine learning models for the prediction of WWTP effluent characteristics and wastewater inflows as well as anomaly detection studies and energy consumption optimization in WWTPs. Furthermore, an overview considering the merging of both mechanistic and machine learning models resulting in hybrid models is presented as a promising approach. A critical assessment of the main gaps and future directions on the implementation of mathematical modeling in wastewater treatment processes is also presented, focusing on topics such as the explainability of data-driven models and the use of Transfer Learning processes.

Calculation of carbon emissions in wastewater treatment and its neutralization measures: A review

As the pursuit of "carbon neutrality" gains momentum, the emphasis on low-carbon solutions, emphasizing energy conservation and resource reuse, has introduced fresh challenges to conventional wastewater treatment approaches. Precisely evaluating carbon emissions in urban water supply and drainage systems, wastewater treatment plants, and establishing carbon-neutral operating models has become a pivotal concern in the future of wastewater treatment. Regrettably, limited research has been devoted to carbon accounting and the development of carbon-neutral strategies for wastewater treatment. In this review, to facilitate comprehensive carbon accounting, we initially recognizes direct and indirect carbon emission sources in the wastewater treatment process. We then provide an overview of several major carbon accounting methods and propose a carbon accounting framework. Furthermore, we advocate for a systemic perspective, highlighting that achieving carbon neutrality in wastewater treatment extends beyond the boundaries of wastewater treatment plants. We assess current technical measures both within and outside the plants that contribute to achieving carbon-neutral operations. Encouraging the application of intelligent algorithms for the multifaceted monitoring and control of wastewater treatment processes is paramount. Supporting resource and energy recycling is also essential, as is recognizing the benefits of synergistic wastewater treatment technologies. We advocate a systematic, multi-level planning approach that takes into account a wide range of factors. Our goal is to offer valuable insights and support for the practical implementation of water environment management within the framework of carbon neutrality, and to advance sustainable socio-economic development and contribute to a more environmentally responsible future.

Prediction of nitrous oxide emission of a municipal wastewater treatment plant using LSTM-based deep learning models

Accurate assessment of greenhouse gas emissions from wastewater treatment plants is crucial for mitigating climate change. N2O is a potent greenhouse gas that is emitted from wastewater treatment plants during the biological denitrification process. In this study, we developed and evaluated deep learning models for predicting N2O emissions from a WWTP in Switzerland. Six key parameters were selected to obtain the optimal LSTM model by adjusting experimental parameter conditions. The optimal parameter condition was achieved with 150 neurons, the tanh activation function, the RMSprop optimization algorithm, a learning rate of 0.001, no dropout regularization, and a batch size of 128. Under the same conditions, we compared the performance of recurrent neural networks (RNNs) and Long Short-Term Memory (LSTM) networks. We found that LSTM models outperformed RNN models in predicting N2O emissions. The optimal LSTM model achieved a 36% improvement in mean absolute error (MAE), a 19% improvement in root mean squared error (RMSE), and a 6.92% improvement in R2 score compared to the RNN model. Additionally, LSTM models demonstrated better resilience to sudden changes in the target sequence, exhibiting a 9.54% higher percentage of explained variance compared to RNNs. These results highlight the potential of LSTM models for accurate and robust prediction of N2O emissions from wastewater treatment plants, contributing to effective greenhouse gas mitigation strategies.

How to Provide Nitrite Robustly for Anaerobic Ammonium Oxidation in Mainstream Nitrogen Removal

Innovation in decarbonizing wastewater treatment is urgent in response to global climate change. The practical implementation of anaerobic ammonium oxidation (anammox) treating domestic wastewater is the key to reconciling carbon-neutral management of wastewater treatment with sustainable development. Nitrite availability is the prerequisite of the anammox reaction, but how to achieve robust nitrite supply and accumulation for mainstream systems remains elusive. This work presents a state-of-the-art review on the recent advances in nitrite supply for mainstream anammox, paying special attention to available pathways (forward-going (from ammonium to nitrite) and backward-going (from nitrate to nitrite)), key controlling strategies, and physiological and ecological characteristics of functional microorganisms involved in nitrite supply. First, we comprehensively assessed the mainstream nitrite-oxidizing bacteria control methods, outlining that these technologies are transitioning to technologies possessing multiple selective pressures (such as intermittent aeration and membrane-aerated biological reactor), integrating side stream treatment (such as free ammonia/free nitrous acid suppression in recirculated sludge treatment), and maintaining high activity of ammonia-oxidizing bacteria and anammox bacteria for competing oxygen and nitrite with nitrite-oxidizing bacteria. We then highlight emerging strategies of nitrite supply, including the nitrite production driven by novel ammonia-oxidizing microbes (ammonia-oxidizing archaea and complete ammonia oxidation bacteria) and nitrate reduction pathways (partial denitrification and nitrate-dependent anaerobic methane oxidation). The resources requirement of different mainstream nitrite supply pathways is analyzed, and a hybrid nitrite supply pathway by combining partial nitrification and nitrate reduction is encouraged. Moreover, data-driven modeling of a mainstream nitrite supply process as well as proactive microbiome management is proposed in the hope of achieving mainstream nitrite supply in practical application. Finally, the existing challenges and further perspectives are highlighted, i.e., investigation of nitrite-supplying bacteria, the scaling-up of hybrid nitrite supply technologies from laboratory to practical implementation under real conditions, and the data-driven management for the stable performance of mainstream nitrite supply. The fundamental insights in this review aim to inspire and advance our understanding about how to provide nitrite robustly for mainstream anammox and shed light on important obstacles warranting further settlement.

Machine learning for modeling N2O emissions from wastewater treatment plants: Aligning model performance, complexity, and interpretability

Nitrous oxide (N2O) emissions may account for up to 80 % of a wastewater treatment plant's (WWTP) total carbon footprint. Given the complexity of the pathways involved, estimating N2O emissions through mechanistic models still often fails to precisely depict process dynamics. Alternatively, data-driven methods for predicting N2O emissions hold substantial potential. However, so far, a comprehensive approach is still overlooked, impeding the advancement of full-scale application. Therefore, this study develops a comprehensive approach for using machine learning to perform online process modeling of N2O emissions. The approach is tested on a long-term N2O emission dataset from a full-scale WWTP. Uniquely, the proposed approach emphasizes not just model accuracy, but it also considers model complexity, computational speed, and interpretability, equipping operators with the insights needed for informed corrective actions. Algorithms with varying levels of complexity and interpretability including k-Nearest Neighbors (kNN), decision trees, ensemble learning models, and deep neural networks (DNN) were considered. Furthermore, a parametric multivariate outlier removal method was adjusted to account for data statistical distributions, significantly reducing data loss. By employing an effective feature selection methodology, a trade-off between data acquisition, model performance, and complexity was found, reducing the number of features by 40 % and decreasing data collection cost, model complexity and computational burden without significant effect on modeling accuracy. The best performing models are kNN (R2 = 0.88), AdaBoost (R2 = 0.94), and DNN (R2 = 0.90). Feature importance of models was analyzed and compared with process knowledge to test interpretability, guiding N2O mitigation decisions.

Deep learning in wastewater treatment: a critical review

Modeling wastewater processes supports tasks such as process prediction, soft sensing, data analysis and computer assisted design of wastewater systems. Wastewater treatment processes are large, complex processes, with multiple controlling mechanisms, a high degree of disturbance variability and non-linear (generally stable) behavior with multiple internal recycle loops. Semi-mechanistic biochemical models currently dominate research and application, with data-driven deep learning models emerging as an alternative and supplementary approach. But these modeling approaches have grown in separate communities of research and practice, and so there is limited appreciation of the strengths, weaknesses, contrasts and similarities between the methods. This review addresses that gap by providing a detailed guide to deep learning methods and their application to wastewater process modeling. The review is aimed at wastewater modeling experts who are familiar with established mechanistic modeling approach, and are curious about the opportunities and challenges afforded by deep learning methods. We conclude with a discussion and needs analysis on the value of different ways of modeling wastewater processes and open research problems.

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.

Physics-informed neural network-based serial hybrid model capturing the hidden kinetics for sulfur-driven autotrophic denitrification process

Sulfur-driven autotrophic denitrification (SdAD) is a biological process that can remove nitrate from low carbon/nitrogen (C/N) ratio wastewater. Although this process has been intensively researched, the mechanism whereby its intermediates (i.e., elemental sulfur and nitrite ions) are generated and accumulated remains elusive. Existing mathematical models developed for SdAD cannot accurately predict the intermediates in SdAD because of the incomplete knowledge of process kinetic resulting from changes in the environmental conditions and electron competition during SdAD. To address this limitation, we proposed a novel serial hybrid model structure based on a physics-informed neural network (PINN) to capture the dynamics of the process kinetics and predict the substrate concentrations in SdAD. In this study, we evaluated the model through numerical experiments and applied it to real case studies involving batch and continuous-flow reactor scenarios. By leveraging the PINN approach, the hybrid model yielded accurate predictions at both the state (i.e. substrate concentration) and kinetic levels in the numerical experiments and performed better than both mechanistic and purely data-driven models in the case studies. Furthermore, we used the trained hybrid model to design control strategies for SdAD and a novel integrated process involving SdAD and anammox for energy-efficient nitrogen removal. Finally, we discuss the advantages and application scope of the PINN-based hybrid model.

Automatic control and optimal operation for greenhouse gas mitigation in sustainable wastewater treatment plants: A review

In order to promote low-carbon sustainable operational management of the wastewater treatment plants (WWTPs), automatic control and optimal operation technologies, which devote to improving effluent quality, operational costs and greenhouse gas (GHG) emissions, have flourished in recent years. There is no consensus on the design procedure for optimal control/operation of sustainable WWTPs. In this review, we summarize recent researches on developing control and optimization strategies for GHG mitigation in WWTPs. Faced with the fact that direct carbon dioxide (CO₂) emissions (considered biological origin) are generally not included in the carbon footprint of WWTPs, direct emissions (nitrous oxide (N₂O), methane (CH₄)) and indirect emissions are paid much attention. Firstly, the plant-wide models with GHG dynamic simulation, which are employed to design and evaluate the automatic control schemes as well as representative studies on identifying key factors affecting GHG emissions or comprehensive performance are outlined. Then, both traditional and advanced control methods commonly used in GHG mitigation are reviewed in detail, followed by the multi-objective optimization practices of control/operational parameters. Based on the mentioned control and (or) optimization strategies, a novel design framework for the optimal control/operation of sustainable WWTPs is proposed. The findings and design framework proposed in the paper will provide guidance for GHG mitigation and sustainable operation in WWTPs. It is foreseeable that more accurate and appropriate plant-wide models together with flexible control methods and intelligent optimization strategies will be developed to satisfy the upgrading requirements of WWTPs in the future.

Contribution of nitrous oxide to the carbon footprint of full-scale wastewater treatment plants and mitigation strategies- a critical review

Nitrous oxide (N₂O), a potent greenhouse gas, significantly contributes to the carbon footprint of wastewater treatment plants (WWTPs) and contributes significantly to global climate change and to the deterioration of the natural environment. Our understanding of N₂O generation mechanisms has significantly improved in the last decade, but the development of effective N₂O emission mitigation strategies has lagged owing to the complexity of parameter regulation, substandard monitoring activities, and inadequate policy criteria. Based on critically screened published studies on N₂O control in full-scale WWTPs, this review elucidates N₂O generation pathway identifications and emission mechanisms and summarizes the impact of N₂O on the total carbon footprint of WWTPs. In particular, a linear relationship was established between N₂O emission factors and total nitrogen removal efficiencies in WWTPs located in China. Promising N₂O mitigation options were proposed, which focus on optimizing operating conditions and implementation of innovative treatment processes. Furthermore, the sustainable operation of WWTPs has been anticipated to convert WWTPs into absolute greenhouse gas reducers as a result of the refinement and improvement of on-site monitoring activities, mitigation mechanisms, regulation of operational parameters, modeling, and policies.

Nitrous Oxide Emission from Full-Scale Anammox-Driven Wastewater Treatment Systems

Wastewater treatment plants (WWTPs) are important contributors to global greenhouse gas (GHG) emissions, partly due to their huge emission of nitrous oxide (N₂O), which has a global warming potential of 298 CO₂ equivalents. Anaerobic ammonium-oxidizing (anammox) bacteria provide a shortcut in the nitrogen removal pathway by directly transforming ammonium and nitrite to nitrogen gas (N₂). Due to its energy efficiency, the anammox-driven treatment has been applied worldwide for the removal of inorganic nitrogen from ammonium-rich wastewater. Although direct evidence of the metabolic production of N₂O by anammox bacteria is lacking, the microorganisms coexisting in anammox-driven WWTPs could produce a considerable amount of N₂O and hence affect the sustainability of wastewater treatment. Thus, N₂O emission is still one of the downsides of anammox-driven wastewater treatment, and efforts are required to understand the mechanisms of N₂O emission from anammox-driven WWTPs using different nitrogen removal strategies and develop effective mitigation strategies. Here, three main N₂O production processes, namely, hydroxylamine oxidation, nitrifier denitrification, and heterotrophic denitrification, and the unique N₂O consumption process termed nosZ-dominated N₂O degradation, occurring in anammox-driven wastewater treatment systems, are summarized and discussed. The key factors influencing N₂O emission and mitigation strategies are discussed in detail, and areas in which further research is urgently required are identified.