Ensemble machine learning prediction of anaerobic co-digestion of manure and thermally pretreated harvest residues

Bioresource Technology, Год журнала: 2024, Номер 402, С. 130793 - 130793

Опубликована: Май 3, 2024

Язык: Английский

---

Machine learning-aided unveiling the relationship between chemical pretreatment and methane production of lignocellulosic waste

Waste Management, Год журнала: 2024, Номер 187, С. 235 - 243

Опубликована: Июль 27, 2024

Язык: Английский

---

A novel dual-way inference modeling method for coal coking: Predicting H2 and CH4 concentrations in coke oven gas and inferring optimal reaction conditions

Fuel, Год журнала: 2024, Номер 381, С. 133325 - 133325

Опубликована: Окт. 5, 2024

Язык: Английский

---

Trustworthy and Human Centric neural network approaches for prediction of landfill methane emission and sustainable waste management practices

Waste Management, Год журнала: 2025, Номер 195, С. 44 - 54

Опубликована: Янв. 30, 2025

Landfills rank third among the anthropogenic sources of methane gas in atmosphere, hence there is a need for greater emphasis on quantification landfill emission mitigating environmental degradation. However, estimation and prediction challenge as modeling complexity generation involves different chemical, biological physical reactions. Various machine learning techniques lacks providing explainability context addressing uncertainties emission. This work presents novel artificial neural network (ANN) based approach enhancing interpretation prediction. A trustworthy ANN (TANN) using SHapley Additive exPlanations (SHAP) presented this research improving predicted values data seven major producing countries like India, China, Russia, Indonesia, US, EU, Brazil. Further, Human-Centric (HCANN) model two approaches: risks indication physics informed are developed. The HCANN was capable scientific principles well-known LandGEM data. results exhibited close agreement with those produced by LandGEM. Likewise developed factors production rates (MPR), capture system efficiency (GCSE), monitoring reliability (MSR) able to offer intuitive contextual decision understand risk associated unmanaged methane. Proposed TANN approaches valuable tool assessment sustainable waste management practices.

Язык: Английский

---

Comparative Evaluation of Ensemble Machine Learning Models for Methane Production from Anaerobic Digestion

Fermentation, Год журнала: 2025, Номер 11(3), С. 130 - 130

Опубликована: Март 7, 2025

This study provides a comparative evaluation of several ensemble model constructions for the prediction specific methane yield (SMY) from anaerobic digestion. From authors’ knowledge based on existing research, present their accuracy and utilization in digestion modeling relative to individual machine learning methods is incomplete. Three input datasets compiled samples using agricultural forestry lignocellulosic residues previous studies were used this study. A total six five evaluated per dataset, whose was assessed robust 10-fold cross-validation 100 repetitions. Ensemble models outperformed one out three terms accuracy. They also produced notably lower coefficients variation root-mean-square error (RMSE) than most accurate (0.031 0.393 dataset A, 0.026 0.272 B, 0.021 0.217 AB), being much less prone randomness training test data split. The optimal generally benefited higher number included, as well diversity principles. Since reporting final fitting single split-sample approach highly randomness, adoption multiple repetitions proposed standard future studies.

Язык: Английский

---

Harnessing Fruit and Vegetable Waste for Biofuel Production: Advances and Scope for Future Development

eFood, Год журнала: 2025, Номер 6(2)

Опубликована: Апрель 1, 2025

ABSTRACT Extreme exploitation of petroleum fuels has raised concerns around global warming due to increased greenhouse gas emissions, which by the year 2040 are expected rise 43 billion metric tons. Biofuels have gained popularity in recent years because their renewable and environmentally friendly prospects. Second‐generation biodiesel is generated from nonedible raw materials such as food waste, suggested lesser negative impacts on environment does not threaten security. Edible fruit waste (7.65 kg/person) edible vegetable (16 highest contribution 38% waste. Annually, this corresponds 15.78 m 2 cropland usage, 1.358 kg CO equivalent, 232.87 g nitrogen 3810.6 L freshwater 38.544 phosphorus usage per person for agricultural production. FVW includes peels, seeds, crops, leaves, straw, stems, roots, or tubers. This can be utilized feedstock biofuel instead burning, dumping, landfilling, leads economic, environmental, health issues water‐borne diseases, respiratory lung diseases. Converting lignocellulosic mass into green energy including biogas, bioethanol, biohydrogen help management while also contributing carbon‐neutral model. Past studies shown potential using generation, jet fuels, general diesel engines. review focuses latest advances production technology, with an emphasis new pretreatments, technologies, works improve biomass.

Язык: Английский

---

Carmna: classification and regression models for nitrogenase activity based on a pretrained large protein language model

Briefings in Bioinformatics, Год журнала: 2025, Номер 26(2)

Опубликована: Март 1, 2025

Abstract Nitrogen-fixing microorganisms play a critical role in the global nitrogen cycle by converting atmospheric into ammonia through action of nitrogenase (EC 1.18.6.1). In this study, we employed six machine learning algorithms to model classification and regression activity (Carmna). Carmna utilized pretrained large-scale ProtT5 for feature extraction from sequences incorporated additional features, such as gene expression codon preference, training. The optimal model, based on XGBoost, achieved an average area under receiver operating characteristic curve 0.9365 F1 score 0.85 five-fold cross-validation. For regression, best-performing was stacking approach support vector with R2 0.5572 mean absolute error 0.3351. Further interpretability analysis revealed that not only proportion preferences standard amino acids, but also levels spatial distance genes were associated activity. We obtained minimum nitrogen-fixing nif cluster. This study deepens our understanding complex mechanisms regulating contributes development efficient bio-fertilizers.

Язык: Английский

---

Interpretable Machine Learning for Optimizing Carbon Source Design to Enhance Bioethanol Yield in Gas Fermentation

Fuel, Год журнала: 2025, Номер 400, С. 135738 - 135738

Опубликована: Май 22, 2025

Язык: Английский

---

City scale urban flooding risk assessment using multi-source data and machine learning approach

Journal of Hydrology, Год журнала: 2024, Номер unknown, С. 132626 - 132626

Опубликована: Дек. 1, 2024

Язык: Английский

---

Exploring interactive effects of environmental and microbial factors on food waste anaerobic digestion performance: Interpretable machine learning models

Bioresource Technology, Год журнала: 2024, Номер 416, С. 131762 - 131762

Опубликована: Ноя. 7, 2024

Язык: Английский

---