Predicting methane yield by linear regression models: A validation study for grassland biomass

Characterizing the influence of wastewater composition and lignin content on anaerobic biodegradability

“…Hashimoto et al 14 tested the Chandler et al 10 model and found good agreement with his data, but reported that lignin was not the only factor controlling the methanogenic biodegradable fraction ( f D ). Rodrigues et al 15 and Dandikas 11 arrived at similar conclusions for the influence of lignin on the methane yields, but also suggested that lignin alone was not a good predictor.…”

Tree-Based Automated Machine Learning to Predict Biogas Production for Anaerobic Co-digestion of Organic Waste

“…25 Given the fact that AD is often a nonlinear process, traditional statistical models (e.g., linear regression) have shown deficient performance for a generalized prediction of biogas production. 26 When mechanistic modeling is not feasible or sufficient, and training data is available, machine learning (ML) can be the best option for developing predictive models and developing insights into the influence of key parameters. In the past decade, different ML techniques (summarized in Table S1) have been leveraged to predict biogas production, including connectivism learning (e.g., artificial neural network, ANN) and statistical learning (e.g., random forest, extreme gradient boosting, support vector machine).…”

“…However, the ADM1 model requires knowledge of many concentration state variables (i.e., the concentrations for detail components of substrates), which necessitates extensive ongoing analysis of substrates, thus limiting its applicability in industrial facilities where this data is not regularly collected. − Also, the complicated microbial and physicochemical process of AD substantially affects the prediction accuracy of mechanistic models . Given the fact that AD is often a nonlinear process, traditional statistical models (e.g., linear regression) have shown deficient performance for a generalized prediction of biogas production . When mechanistic modeling is not feasible or sufficient, and training data is available, machine learning (ML) can be the best option for developing predictive models and developing insights into the influence of key parameters.…”

Solving Regression Problems with Intelligent Machine Learner for Engineering Informatics

“…Chou (2009) [31] developed a generalized linear model-based expert system for estimating the cost of transportation projects. Dandikas et al (2018) [32] assessed the advantages and disadvantages of regression models for predicting potential of biomethane. The results indicated that the regression method could predict variations in the methane yield and could be used to rank substrates for production quality.…”