Modeling and optimization of process parameters in co-composting of tea waste and food waste: Radial basis function neural networks and genetic algorithm

Yılmaz, Elif Ceren; Temel, Fulya Aydın; Yolcu, Özge Cağcağ; Turan, Nurdan Gamze

doi:10.1016/j.biortech.2022.127910

Cited by 27 publications

(10 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks can efficiently process a large amount of data, learn from a large amount of data, constantly change their own weights and thresholds, and gradually improve their ability to fit and predict the data, which is very helpful for the interpretation of some nonlinear problems; moreover, they can be better than RSM models. When the problem changes, the artificial neural network can adjust the structure and parameters according to the true conditions to adapt to different environments [37] . Three artificial neural networks were trained to fit the extraction process and the kinetics of AMRP in this experiment.…”

Section: Discussionmentioning

confidence: 99%

Artificial neural network model- and response surface methodology-based optimization of Atractylodis Macrocephalae Rhizoma polysaccharide extraction, kinetic modelling and structural characterization

Qiu

Shi

et al. 2023

Ultrasonics Sonochemistry

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Artificial neural network model- and response surface methodology-based optimization of Atractylodis Macrocephalae Rhizoma polysaccharide extraction, kinetic modelling and structural characterization

Qiu

Shi

et al. 2023

Ultrasonics Sonochemistry

View full text Add to dashboard Cite

“…Recent studies have used ML for composting processes to predict CO2 output from the process [15], for improving compost quality [16], for monitoring moisture content in composting systems [17] and for classifying the maturity of compost [18]. A recent critical review by Temel et al, 2023, [[19] evaluated the advantages and limitations of different ML and AI algorithms used in the composting process, which is an important bioprocess.…”

Section: Introductionmentioning

confidence: 99%

Development of a model composting process for food waste in an island community and use of machine learning models to predict its performance

Lytras,

Lyberatos,

Lytras

et al. 2024

Preprint

View full text Add to dashboard Cite

Purpose: A novel composting process suitable for handling food waste in an island community is developed. Food waste collection exhibits a substantial variation in quantities over the year and is based on separate disposal of food waste from residents and shops at the source. Methods: The food waste is properly mixed with recycled compost and bulking material, consisting of a mixture of prunings, leaves and sawdust and placed in one of 24 1m3 closed container. After approximately one month, it is transferred to a second 1m3 container and after one more month to a final 1m3 container. Then it is sieved using an automated sieve and separated into two fractions. The net product is bagged and returned to the citizens, while the “reject” fraction is mixed with the feed. Approximately 15 tons of food waste were processed in 44 batches and produced approximately 3.4 tons of compost product. During the composting batches the composting mixture temperature and volume were monitored, the mixture was stirred 2-3 times weekly and water was added as needed to maintain a good level of moisture. For each of the 44 batches, the mean and maximum temperature reached, the mean ambient temperature, the process duration and the amounts of crude and net compost obtained after sieving are presented. Results: Five machine learning models (Linear Regression, Decision tree regressor, K-Neighbors Regressor, Support Vector Regression, XGBoost Regression) were developed capable of predicting these outputs, using as inputs ambient temperature and the mixture amount and composition with excellent results. Conclusion: The developed machine learning models are useful for predicting the outcome of composting food waste and could be used for optimal designing compost plant operations.

show abstract

“…During the composting process, harmful substances and pathogens in sludge can be eliminated, and nutrients such as nitrogen and phosphorus can be recovered and converted into organic fertilizers [9]. The physical and chemical properties of sludge are unsuitable for direct composting, meaning it can only be recycled into high-quality products through co-composting [10]. Many studies have added improved materials to sludge compost to achieve synergistic effects in stabilizing waste, and in recent years, significant achievements have been made in cocomposting sludge with various additives to improve the quality and maturity of compost, such as rice husks, earthworms, biochar, and sawdust.…”

Section: Introductionmentioning

confidence: 99%

Bacterial Community Succession in Earthworm Mucus and Sludge Compost and Its Relationship with Environmental Factors

Wang,

Zhang,

Fan

et al. 2024

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

This study investigated the effects of adding earthworm mucus on the changes in sludge compost bacterial community structure and its response to environmental factors. The results showed that adding earthworm mucus improved the composting effect of sludge, reducing nitrogen loss and increasing nutrients; nitrogen loss decreased by 5.55%, and potassium and phosphorus increased by 10.23 and 16.28%, respectively. Firmicutes, Chloroflexi, Actinobacteria, and Proteobacteria were the main bacterial phyla in the sludge, with a combined relative abundance of over 60%. The addition of earthworm mucus significantly impacted bacterial community structure and composting activity, increasing the relative abundance of dominant bacteria during the process. Redundancy analysis showed that environmental factors significantly impacted the changes in bacterial community structure during composting. The results indicate that the addition of earthworm mucus increases the relative abundance of advantageous bacteria playing essential roles in sludge composting, enhancing the fertility and maturity of sludge composting products by significantly reducing nitrogen loss and increasing potassium and phosphorus. Based on the response relationship between environmental factors and bacterial communities, the bacterial community structure in sludge composting can be improved by regulating environmental factors (such as pH and moisture content), enhancing the effectiveness of sludge composting.

show abstract

Modeling and optimization of process parameters in co-composting of tea waste and food waste: Radial basis function neural networks and genetic algorithm

Cited by 27 publications

References 45 publications

Artificial neural network model- and response surface methodology-based optimization of Atractylodis Macrocephalae Rhizoma polysaccharide extraction, kinetic modelling and structural characterization

Artificial neural network model- and response surface methodology-based optimization of Atractylodis Macrocephalae Rhizoma polysaccharide extraction, kinetic modelling and structural characterization

Development of a model composting process for food waste in an island community and use of machine learning models to predict its performance

Bacterial Community Succession in Earthworm Mucus and Sludge Compost and Its Relationship with Environmental Factors

Contact Info

Product

Resources

About