“…Integrated deep-learning neural network and desirability analysis in biogas plants [9] 2020 Energy P6 Ingredient analysis of biological wastewater using hybrid multi-stream deep-learning framework [10] 2022 Computers and Chemical Engineering P7 Modelling biogas production from anaerobic wastewater treatment plants using radial basis function networks and differential evolution [11] 2021 Computers and Chemical Engineering P8 Constructing a smart framework for supplying the biogas energy in green buildings using an integration of response surface methodology, artificial intelligence, and petri-net modelling [12] 2021 Energy Conversion and Management…”
Section: P5mentioning
confidence: 99%
“…Datasets can be incomplete due to issues such as equipment failure and measurement errors. This can result in non-aligning data points in the training data, which is unsuitable for model training [10,14]. An important stage is the inclusion or exclusion of outlier values; this can be common due to sensor error (for example, an error reading may be negative or excessively out of the expected range).…”
Section: P18mentioning
confidence: 99%
“…To compensate for the small dataset size, the input data were randomly broadcast into six datasets. In a comparable context of wastewater analysis, a DNN-LSTM hybrid model was developed to predict NO 2 concentrations based on wastewater properties [10]. Historical data lags of NO 2 were utilized for step-ahead predictions in downstream time series analytics.…”
Section: Annmentioning
confidence: 99%
“…The utilization of step-ahead techniques for time-series prediction tasks have been highlighted in [10] for biogas production and [22] for wastewater analysis. These approaches exhibited relatively high performance for downstream prediction tasks; a diagram outlining the training structure is shown in Figure 3.…”
The use of machine learning (ML) in anaerobic digestion (AD) is growing in popularity and improves the interpretation of complex system parameters for better operation and optimisation. This systematic literature review aims to explore how ML is currently employed in AD, with particular attention to the challenges of implementation and the benefits of integrating ML techniques. While both lab and industry-scale datasets have been used for model training, challenges arise from varied system designs and the different monitoring equipment used. Traditional machine-learning techniques, predominantly artificial neural networks (ANN), are the most commonly used but face difficulties in scalability and interpretability. Specifically, models trained on lab-scale data often struggle to generalize to full-scale, real-world operations due to the complexity and variability in bacterial communities and system operations. In practical scenarios, machine learning can be employed in real-time operations for predictive modelling, ensuring system stability is maintained, resulting in improved efficiency of both biogas production and waste treatment processes. Through reviewing the ML techniques employed in wider applied domains, potential future research opportunities in addressing these challenges have been identified.
“…Integrated deep-learning neural network and desirability analysis in biogas plants [9] 2020 Energy P6 Ingredient analysis of biological wastewater using hybrid multi-stream deep-learning framework [10] 2022 Computers and Chemical Engineering P7 Modelling biogas production from anaerobic wastewater treatment plants using radial basis function networks and differential evolution [11] 2021 Computers and Chemical Engineering P8 Constructing a smart framework for supplying the biogas energy in green buildings using an integration of response surface methodology, artificial intelligence, and petri-net modelling [12] 2021 Energy Conversion and Management…”
Section: P5mentioning
confidence: 99%
“…Datasets can be incomplete due to issues such as equipment failure and measurement errors. This can result in non-aligning data points in the training data, which is unsuitable for model training [10,14]. An important stage is the inclusion or exclusion of outlier values; this can be common due to sensor error (for example, an error reading may be negative or excessively out of the expected range).…”
Section: P18mentioning
confidence: 99%
“…To compensate for the small dataset size, the input data were randomly broadcast into six datasets. In a comparable context of wastewater analysis, a DNN-LSTM hybrid model was developed to predict NO 2 concentrations based on wastewater properties [10]. Historical data lags of NO 2 were utilized for step-ahead predictions in downstream time series analytics.…”
Section: Annmentioning
confidence: 99%
“…The utilization of step-ahead techniques for time-series prediction tasks have been highlighted in [10] for biogas production and [22] for wastewater analysis. These approaches exhibited relatively high performance for downstream prediction tasks; a diagram outlining the training structure is shown in Figure 3.…”
The use of machine learning (ML) in anaerobic digestion (AD) is growing in popularity and improves the interpretation of complex system parameters for better operation and optimisation. This systematic literature review aims to explore how ML is currently employed in AD, with particular attention to the challenges of implementation and the benefits of integrating ML techniques. While both lab and industry-scale datasets have been used for model training, challenges arise from varied system designs and the different monitoring equipment used. Traditional machine-learning techniques, predominantly artificial neural networks (ANN), are the most commonly used but face difficulties in scalability and interpretability. Specifically, models trained on lab-scale data often struggle to generalize to full-scale, real-world operations due to the complexity and variability in bacterial communities and system operations. In practical scenarios, machine learning can be employed in real-time operations for predictive modelling, ensuring system stability is maintained, resulting in improved efficiency of both biogas production and waste treatment processes. Through reviewing the ML techniques employed in wider applied domains, potential future research opportunities in addressing these challenges have been identified.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.