Machine learning-based optimization of catalytic hydrodeoxygenation of biomass pyrolysis oil

Chen, Xiangmeng; Shafizadeh, Alireza; Shahbeik, Hossein; Rafiee, Shahin; Golvirdizadeh, Milad; Moradi, Aysooda; Peng, Wanxi; Tabatabaei, Meisam; Aghbashlo, Mortaza

doi:10.1016/j.jclepro.2024.140738

Cited by 9 publications

(3 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this frame, ML has been used for the development of stable and efficient catalysts and selecting optimum operating conditions for the pyrolysis of guaiacol, chosen as a bio-oil model compound. 205 The technology allowed the navigation of complex data relationships and optimization of process parameters. The flowchart of the research methodology is shown in Fig.…”

Section: Sustainability and Future Green Protocolsmentioning

confidence: 99%

“…Through multi-objective optimization, a 92.26% guaiacol conversion was achieved at 365 °C, 2.72 MPa H 2 pressure, 37% crystallinity index of the catalyst with a surface area of 756.9 m 2 g −1 . 205…”

Section: Sustainability and Future Green Protocolsmentioning

confidence: 99%

“…This correlation method considers the probability that the observed correlation strength may occur by chance, where a value of +1, 0, and −1 means perfect positive, weak, and complete negative correlation. 205 Fig. 8b shows the Spearman correlation matrix, built based on input descriptors and output responses across the dataset.…”

Section: Sustainability and Future Green Protocolsmentioning

confidence: 99%

See 2 more Smart Citations

Biomass-derived carbon-based catalysts for lignocellulosic biomass and waste valorisation: a circular approach

Belluati,

Tabasso,

Calcio Gaudino

et al. 2024

Green Chem.

View full text Add to dashboard Cite

show abstract

Section: Sustainability and Future Green Protocolsmentioning

confidence: 99%

Section: Sustainability and Future Green Protocolsmentioning

confidence: 99%

Section: Sustainability and Future Green Protocolsmentioning

confidence: 99%

See 1 more Smart Citation

Biomass-derived carbon-based catalysts for lignocellulosic biomass and waste valorisation: a circular approach

Belluati,

Tabasso,

Calcio Gaudino

et al. 2024

Green Chem.

View full text Add to dashboard Cite

show abstract

Data-Driven Framework for the Techno-Economic Assessment of Sustainable Aviation Fuel from Pyrolysis

Okolie,

Moradi,

Rogachuk

et al. 2024

Bioenerg. Res.

View full text Add to dashboard Cite

The aviation sector plays a vital role in global transportation, economic growth, and social integration. However, its rapid expansion has led to increased emissions. Sustainable aviation fuel (SAF) provides a promising solution by offering a clean-burning, renewable alternative to conventional jet fuel. SAF can be produced through various processes and feedstocks, significantly reducing the aviation industry’s environmental footprint. Fast pyrolysis (FP) presents a cost-effective and scalable approach for SAF production due to its low-cost feedstocks, rapid reaction times, and simpler technology. However, estimating the economic viability of FP for SAF production is complex and labor-intensive, requiring detailed process models and numerous assumptions. Furthermore, determining the relationship between feedstock properties and the minimum selling price (MSP) of the fuel can be challenging. To address these challenges, this study developed a data-driven framework for the preliminary estimation of SAF's MSP from FP. Synthetic data was generated using Generative Adversarial Networks (GAN) and Variational Autoencoders (VAE), and hyperparameter optimization was performed using Grid Search to enhance model accuracy and predictions. Five surrogate models were evaluated: linear regression, gradient boost regression (GBR), random forest (RF), extreme boost regression (XGBoost), and elastic net. Among these, GBR and RF showed the most promise, based on metrics such as R2, RMSE, and MAE for both original and synthetic datasets. Specifically, GBR achieved a Train R2 of 0.9999 and a Test R2 of 0.9277, while RF recorded Train and Test R2 scores of 0.9789 and 0.9255, respectively. The use of data from the VAE further improved model accuracy. Additionally, a publicly accessible graphical user interface was developed, enabling researchers to estimate the MSP of SAF based on biomass properties, plant capacity, and location.

show abstract

Machine learning-based prediction of non-aeration linear alkylbenzene sulfonate mineralization in an oxygenic microalgal-bacteria biofilm

Xia,

Wu,

Cui

et al. 2025

Bioresource Technology

View full text Add to dashboard Cite

Machine learning-based optimization of catalytic hydrodeoxygenation of biomass pyrolysis oil

Cited by 9 publications

References 60 publications

Biomass-derived carbon-based catalysts for lignocellulosic biomass and waste valorisation: a circular approach

Biomass-derived carbon-based catalysts for lignocellulosic biomass and waste valorisation: a circular approach

Data-Driven Framework for the Techno-Economic Assessment of Sustainable Aviation Fuel from Pyrolysis

Machine learning-based prediction of non-aeration linear alkylbenzene sulfonate mineralization in an oxygenic microalgal-bacteria biofilm

Contact Info

Product

Resources

About