 Molecular descriptor-based artificial intelligence frameworks for the estimation of bio-oil yield from agricultural wasteShreya P. Yeole, Tanishq Prasad and Debashis Kundu Renewable Energy, 2025, vol. 239, issue C Abstract: The study highlights the potential of using molecular descriptors and artificial intelligence (AI) frameworks to enhance the predictive accuracy of bio-oil yields, emphasizing the need for AI formulations in handling complex and non-linear data scenarios. An exhaustive dataset of bio-oil yield derived from various feedstocks, including wheat straw, coconut shell, rice husk, bagasse, and sawdust, is collected for the training validation and testing of AI models. Altogether, 2926 molecular descriptors with a combination of two-dimensional and three-dimensional parameters are considered for estimating bio-oil yield using Artificial Neural Network (ANN) and ANN integrated with Grey Wolf Optimization (ANN-GWO) models. Parameters for ANN and ANN-GWO are optimized using a grid approach to demonstrate the correlation coefficient of 0.959 and 0.929, respectively. Among the feedstocks, rice husk and saw dust show remarkable accuracy in the bio-oil estimation, while others perform poorly. Keywords: Bio-oil; Agricultural waste feedstock; Molecular descriptors; ANN; ANN-GWO (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:239:y:2025:i:c:s0960148124021827 DOI: 10.1016/j.renene.2024.122114 Access Statistics for this article Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides More articles in Renewable Energy from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.