This Research Topic will explore machine learning/deep learning in the field of sustainable energy and chemicals derived from biomass. Our Topic uncovers the power of harnessing datasets to revolutionize the way we understand and optimize feedstock properties, biomass processing, and fuel/product correlations in renewable applications.
Machine learning allows scientists to unlock the potential of datasets rich with information on biomass feedstocks and processing conditions. These researchers also leverage algorithms to discern non-intuitive correlations, allowing the prediction and optimization of feedstock properties or processes for sustainable energy and chemical production. Analyzing these correlations can result in the development of advanced models that enable precise fuel property predictions necessary for optimizing renewable energy systems.
The application of machine learning and deep learning techniques to improve the speed, breadth, and depth of insights that researchers can generate from biomass feedstock, processing, and products data is still nascent. As of December 2023, a Web of Science search using the title of this Research Topic resulted in only 21 publications. Dropping “deep learning” as a key word resulted in 36 titles, with 5 highly cited papers and 17 reviews, and recent publication years, ranging from 2021 to 2023. This research area has much promise, attracting interest from both domain science and data science experts. It is the aim of this Research Topic to solicit high quality scientific publications to further seed and contribute to the growth of this promising and exciting field.
Our goal is to develop a collection highlighting the span of the nascent and current research in sustainable energy and chemicals production from biomass using the power of machine learning and deep learning.
Types of accepted manuscripts include Reviews and Original Research. Specific themes that potential contributors can address may include, but are not limited to:
• Data considerations in biopower, bioenergy, and biochemical machine learning/deep learning applications
• Use of machine learning techniques, such as classification, regression, and optimization to predict relevant biopower, bioenergy, or bioproducts parameters (e.g. yield and purity)
• Identification of catalysts and process parameters to efficiently convert biomass from datasets
• Explainability of ML/DL techniques applied to biorefineries
Keywords:
Machine learning, Deep learning, Datasets, Bioenergy, Biofuels and bioproducts, Prediction
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
This Research Topic will explore machine learning/deep learning in the field of sustainable energy and chemicals derived from biomass. Our Topic uncovers the power of harnessing datasets to revolutionize the way we understand and optimize feedstock properties, biomass processing, and fuel/product correlations in renewable applications.
Machine learning allows scientists to unlock the potential of datasets rich with information on biomass feedstocks and processing conditions. These researchers also leverage algorithms to discern non-intuitive correlations, allowing the prediction and optimization of feedstock properties or processes for sustainable energy and chemical production. Analyzing these correlations can result in the development of advanced models that enable precise fuel property predictions necessary for optimizing renewable energy systems.
The application of machine learning and deep learning techniques to improve the speed, breadth, and depth of insights that researchers can generate from biomass feedstock, processing, and products data is still nascent. As of December 2023, a Web of Science search using the title of this Research Topic resulted in only 21 publications. Dropping “deep learning” as a key word resulted in 36 titles, with 5 highly cited papers and 17 reviews, and recent publication years, ranging from 2021 to 2023. This research area has much promise, attracting interest from both domain science and data science experts. It is the aim of this Research Topic to solicit high quality scientific publications to further seed and contribute to the growth of this promising and exciting field.
Our goal is to develop a collection highlighting the span of the nascent and current research in sustainable energy and chemicals production from biomass using the power of machine learning and deep learning.
Types of accepted manuscripts include Reviews and Original Research. Specific themes that potential contributors can address may include, but are not limited to:
• Data considerations in biopower, bioenergy, and biochemical machine learning/deep learning applications
• Use of machine learning techniques, such as classification, regression, and optimization to predict relevant biopower, bioenergy, or bioproducts parameters (e.g. yield and purity)
• Identification of catalysts and process parameters to efficiently convert biomass from datasets
• Explainability of ML/DL techniques applied to biorefineries
Keywords:
Machine learning, Deep learning, Datasets, Bioenergy, Biofuels and bioproducts, Prediction
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.