Predicting the performance of anaerobic digestion using machine learning algorithms and genomic data

Data-Driven Based In-Depth Interpretation and Inverse Design of Anaerobic Digestion for CH4-Rich Biogas Production

“…Nowadays, data-driven approaches, especially machine learning (ML) algorithms, have been proven to be powerful to assist the design and understanding of waste-to-energy systems. − Additionally, a few studies have been reported on the ML applications in the AD process. , For example, Xu et al found that the extreme gradient boosting (XGBoost) model was the best for predicting CH 4 production, and total solid, soluble chemical oxygen demand (SCOD), and dosages of zero-valent iron (ZVI) are key factors affecting the CH 4 yield from ZVI-based AD . Long et al’s study showed that the ML model obtained a prediction accuracy of 0.82 by considering both operational parameters and genomic data based on 50 samples . Wang et al employed four ML methods to model AD conversion and identify important process parameters with 17 samples, which indicated that k -nearest neighbors (KNN) was the best one and total carbon was a determinant operational parameter .…”

“…18 Long et al's study showed that the ML model obtained a prediction accuracy of 0.82 by considering both operational parameters and genomic data based on 50 samples. 19 Wang et al employed four ML methods to model AD conversion and identify important process parameters with 17 samples, which indicated that k-nearest neighbors (KNN) was the best one and total carbon was a determinant operational parameter. 20 De Clercq et al developed ML models based on an industrial-scale co-AD facility with 1398 samples and claimed that the random forest (RF) and XGBoost showed good accuracy with R 2 values of 0.80−0.88 for CH 4 prediction.…”

Integration of anaerobic digestion with heat Pump: Machine learning-based technical and environmental assessment

“…Referring to the F-table these correspond to the probability value (p-value) of zero, suggesting that the GPR model correctly predicts the data trend (i.e., the correlation is highly significant). The predictive accuracy of the optimal model is competitive with those reported in the literature of ML-based AD modelling with R 2 in the range of 0.8 to 0.9 (Cruz et al, 2022;Long et al, 2021;Wang et al, 2021;Xu et al, 2021). This superior performance of the GPR model when compared to other models is attributed to the capability of probabilistic Gaussian processes to handle datasets with a high degree of variance (see Table 3).…”

“…Following the training procedure, several unseen trial cases (test data) are subjected to the ML model, based on which the accuracy of the model is evaluated. A wide range of ML models has been developed for predicting biogas production from AD processes, among which artificial neural network (ANN) (S ¸enol, 2021), recurrent neural network (RNN) (Park et al, 2021), random forest (RF) (Wang et al, 2021), support vector machine (SVM) (Long et al, 2021), and extreme gradient boost (XGBoost) (Xu et al, 2021) have been popular choices among researchers. Therefore, the work compares the accuracies of five different ML models for predicting biogas yield and methane content for AD processes.…”

Internet of things and machine learning‐based approaches in the urban solid waste management: Trends, challenges, and future directions

“…In SWM, anaerobic digestion is another recycling technique that usually treats biodegradable fractions (Long et al, 2021). However, compared with composting, microorganisms are used to degrade organic material within anaerobic conditions that can create highly energetic biogas, consisting primarily of methane and carbon dioxide (Dahunsi et al, 2016; Ghatak & Ghatak, 2018).…”