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

Ouderji, Zahra Hajabdollahi; Gupta, Ravi; McKeown, Andrew; Yu, Zhibin; Smith, Cindy J.; Sloan, William; You, Siming

doi:10.1016/j.biortech.2022.128485

Cited by 15 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An analysis of regression was conducted using the root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination ( R 2 ), which are commonly used metrics for regression analysis. Equation ( 6 )–( 9 ) provides the equations for these metrics (Hajabdollahi Ouderji et al 2023 ). …”

Section: Methodsmentioning

confidence: 99%

Future prediction of biogas potential and CH4 emission with boosting algorithms: the case of cattle, small ruminant, and poultry manure from Turkey

Pence,

Kumaş,

Cesmeli

et al. 2024

Environ Sci Pollut Res

View full text Add to dashboard Cite

Animal waste can be converted into a renewable energy source using biogas technology. This process has an impact on greenhouse gas emissions and is a sustainable source of energy for countries. It can reduce the effects of climate change and protect the planet for future generations. Tier1 and tier2 approaches are commonly used in the literature to calculate emissions factors. With boosting algorithms, this study estimated each animal category’s biogas potential and CH4 emissions (tier1 and tier2 approach) for 2004–2021 in all of Turkey’s provinces. Two different scenarios were created in the study. For scenario-1, the years 2020–2021 were predicted using data from 2004 to 2019, while for scenario-2, the years 2022–2024 were predicted using data from 2004 to 2021. According to the scenario-1 analysis, the eXtreme Gradient Boosting Regressor (XGBR) algorithm was the most successful algorithm with an R2 of 0.9883 for animal-based biogas prediction and 0.9835 and 0.9773 for animal-based CH4 emission predictions (tier1 and tier2 approaches) for the years 2020–2021. When the mean absolute percentage error was evaluated, it was found to be relatively low at 0.46%, 1.07%, and 2.78%, respectively. According to the scenario-2 analysis, the XGBR algorithm predicted the log10 values of the animal-based biogas potential of five major cities in Turkey for the year 2024, with 11.279 for Istanbul, 12.055 for Ankara, 12.309 for Izmir, 11.869 for Bursa, and 12.866 for Antalya. In the estimation of log10 values of CH4 emission, the tier1 approach yielded estimates of 3.080, 3.652, 3.929, 3.411, and 3.321, respectively, while the tier2 approach yielded estimates of 1.810, 2.806, 2.757, 2.552 and 2.122, respectively. Graphical Abstract

show abstract

Section: Methodsmentioning

confidence: 99%

Future prediction of biogas potential and CH4 emission with boosting algorithms: the case of cattle, small ruminant, and poultry manure from Turkey

Pence,

Kumaş,

Cesmeli

et al. 2024

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…The waste products that are accessible include animal manure as well as food wastages, both of which comprises a considerable quantity of organic matter which is capable of being fermented without the presence of oxygen. Anaerobic digestion (AD) has been shown to be an effective approach for minimizing the amount of organic waste produced while simultaneously the recovery of valuable byproducts such as digestate and biogas [5]. There is a considerable relationship between the kind of waste that is utilized as a feedstock in the AD process and the performance of the process.…”

Section: Introductionmentioning

confidence: 99%

Estimating the Potential of Biogas Yield from Anaerobic Co-digestion of Organic Waste with Ensemble Machine learning

Le,

Dong

2024

COMIEN

View full text Add to dashboard Cite

The biogas has the potential to serve as a substitute as fossil derived fuel. The present study investigates anaerobic co-digestion of organic waste for predictive modelling. Several co-digestion studies were performed with different pH, solid concentration, temperature, and co-digestion ratios. A water displacement apparatus was used to test biogas yield, and data was collected meticulously. Linear regression (LR) and Random Forest (RF) based models were built with Python-based tools and tested using statistical measures for the prediction of biogas yield. The LR showed a strong linear association, with R and R2 values of 0.9892 and 0.9785, respectively. However, RF surpassed LR, with higher R and R2 values of 0.9919 and 0.9826, respectively. Furthermore, RF had lower MSE and MAE values, indicating higher prediction accuracy and precision. RF consistently scored well in tests, demonstrating its ability to capture complicated relationships while minimizing prediction mistakes. Taylor's diagrams further demonstrated RF's excellent performance during both the training and testing periods. Overall, RF emerges as the optimum model for reliably estimating biogas output in anaerobic co-digestion systems, with important implications for waste-to-energy processes.

show abstract

Detailed analysis of Türkiye's agricultural biomass-based energy potential with machine learning algorithms based on environmental and climatic conditions

Pence,

Kumas,

Siseci Cesmeli

et al. 2024

Clean Techn Environ Policy

View full text Add to dashboard Cite

In the study, the biomass and energy potential of each province of Türkiye was calculated for the years 2010–2021, using data from 15 different fields and 16 different horticultural crops. The total theoretical energy potential obtained from field and garden products was calculated as 222,620 Terajoule (TJ) and 61,737 TJ for 2010 and 308,888 TJ and 77,002 TJ for 2021, respectively. The agricultural biomass potential for 2021 was estimated using machine learning algorithms, depending on the environmental and climate data covering 2010–2020, which has not been studied in the literature. In this study, agricultural biomass potential for Türkiye was tried to be modeled by using Random Forest, K-Nearest Neighbors (KNN), Gradient Boosting, and eXtreme Gradient Boosting Regressor (XGBR) from machine learning methods. Agricultural biomass potential was tested in a tenfold cross-validation analysis and prediction for 2021 using only climatic and agricultural area data. In addition, by applying feature selection, it has been tried to reduce the features to be used and increase the success rate. Accordingly, when the results of the Random Forest algorithm were generalized, it achieved an R2 value of 0.9328 using all features for the tenfold cross-validation analysis. At the same time, it reached an R2 value of 0.9434 using four features in the prediction of 2021 and was found to be successful. Considering only the 2021 forecast, the KNN algorithm reached the highest result with an R2 value of 0.9560 using only four features. Also, the Wilcoxon rank-sum test result at p = 0.05 shows no significant difference between the predictions and the actual values. Graphical abstract

show abstract

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

Cited by 15 publications

References 28 publications

Future prediction of biogas potential and CH4 emission with boosting algorithms: the case of cattle, small ruminant, and poultry manure from Turkey

Future prediction of biogas potential and CH4 emission with boosting algorithms: the case of cattle, small ruminant, and poultry manure from Turkey

Estimating the Potential of Biogas Yield from Anaerobic Co-digestion of Organic Waste with Ensemble Machine learning

Detailed analysis of Türkiye's agricultural biomass-based energy potential with machine learning algorithms based on environmental and climatic conditions

Contact Info

Product

Resources

About