Van Krevelen diagrams based on machine learning visualize feedstock-product relationships in thermal conversion processes

Aug 5, 2026

Feedstock properties strongly influence thermal conversion performance, and optimizing both feedstock selection and process design requires understanding how H/C and O/C ratios relate to final products. This study constructs van Krevelen diagrams for six thermal conversion techniques—torrefaction, hydrothermal carbonization, hydrothermal liquefaction, hydrothermal gasification, pyrolysis, and gasification—using machine learning built from data and results reported in the literature. Reliability of the generated diagrams is evaluated to verify dependability, providing a visual decision-support framework for process and feedstock selection.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Overview

Objective and rationale

Machine-learning workflow and diagram generation

Thermal conversion techniques covered

Reliability assessment and outcomes

UC Berkeley UC Berkeley Previously Published Works Title Van Krevelen diagrams based on machine learning visualize feedstock-product relationships in thermal conversion processes. Permalink [https://escholarship.org/uc/item/3qx99782](https://escholarship.org/uc/item/3qx99782) Journal Communications Chemistry, 6(1) Authors Wang, Shule Wang, Yiying Shi, Ziyi et al. Publication Date 2023-12-13 DOI 10.1038/s42004-023-01077-z Peer reviewed [eScholarship.org](eScholarship.org) Powered by the California Digital Library University of California ARTICLE [https://doi.org/10.1038/s42004-023-01077-z](https://doi.org/10.1038/s42004-023-01077-z) OPEN Van Krevelen diagrams based on machine learning visualize feedstock-product relationships in thermal conversion processes Shule Wang 1,2,14, Yiying Wang3,14, Ziyi Shi4,14, Kang Sun1,2,14, Yuming Wen 3✉, Lukasz Niedzwiecki 5,6, Ruming Pan 7,8, Yongdong Xu9, Ilman Nuran Zaini4, Katarzyna Jagodzińska4, Christian Aragon-Briceno10, Chuchu Tang11, Thossaporn Onsree12, Nakorn Tippayawong13, Halina Pawlak-Kruczek5, Pär Göran Jönsson4, Weihong Yang4, Jianchun Jiang 1,2✉, Sibudjing Kawi 3✉ & Chi-Hwa Wang3✉ Feedstock properties play a crucial role in thermal conversion processes, where understanding the inﬂuence of these properties on treatment performance is essential for optimizing both feedstock selection and the overall process. In this study, a series of van Krevelen diagrams were generated to illustrate the impact of H/C and O/C ratios of feedstock on the products obtained from six commonly used thermal conversion techniques: torrefaction, hydrothermal carbonization, hydrothermal liquefaction, hydrothermal gasiﬁcation, pyrolysis, and gasiﬁcation. Machine learning methods were employed, utilizing data, methods, and results from corresponding studies in this ﬁeld. Furthermore, the reliability of the constructed van Krevelen diagrams was analyzed to assess their dependability. The van Krevelen diagrams developed in this work systematically provide visual representations of the relationships between feedstock and products in thermal conversion processes, thereby aiding in optimizing the selection of feedstock and the choice of thermal conversion technique. 1 Jiangsu Province Key Laboratory of Biomass Energy and Materials, National Engineering Laboratory for Biomass Chemical Utilization, Institute of Chemical Industry of Forest Products, Chinese Academy of Forestry (CAF), 210042 Nanjing, China. 2 Jiangsu Co-Innovation Center for Efﬁcient Processing and Utilization of Forest Resources, College of Chemical Engineering, Nanjing Forestry University, Longpan Road 159, 210037 Nanjing, China. 3 Department of Chemical and Biomolecular Engineering, National University of Singapore, 4 Engineering Drive 4, Singapore 117585, Singapore. 4 Department of Materials Science and Engineering, KTH Royal Institute of Technology, SE-100 44 Stockholm, Sweden. 5 Department of Energy Conversion Engineering, Wroclaw University of Science and Technology, 27 wybrzeże Stanisława Wyspiańskiego st. 50-370, Wroclaw, Poland. 6 Energy Research Centre, Centre for Energy and Environmental Technologies, VŠB-Technical University of Ostrava, 708 00 Ostrava, Poruba, Czech Republic. 7 School of Energy Science and Engineering, Harbin Institute of Technology, 150001 Harbin, China. 8 Institut de Mécanique des Fluides de Toulouse (IMFT) - Université de Toulouse, CNRS-INPT-UPS, 31400 Toulouse, France. 9 Laboratory of Environment-Enhancing Energy (E2E), Key Laboratory of Agricultural Engineering in Structure and Environment of Ministry of Agriculture and Rural Affairs, China Agricultural University, 100083 Beijing, China. 10 Department of Industry and Energy, CIRCE-Research Centre for Energy Resources and Consumption, 50018 Zaragoza, Spain. 11 Faculty of Creative Arts, University of Malaya, 50603 Kuala Lumpur, Malaysia. 12 Department of Chemical Engineering, University of South Carolina, 301 Ma

FAQs

What problem do the van Krevelen diagrams address in thermal conversion research?

They visualize how feedstock properties relate to products formed during thermal conversion, helping researchers understand the impact of H/C and O/C ratios on performance.

Which thermal conversion techniques are included in the study?

Torrefaction, hydrothermal carbonization, hydrothermal liquefaction, hydrothermal gasification, pyrolysis, and gasification.

How does the study use machine learning?

Machine learning models are trained using data, methods, and results reported in relevant studies to generate van Krevelen diagrams connecting feedstock and product relationships.

What is evaluated to ensure the diagrams are dependable?

The reliability of the constructed van Krevelen diagrams is analyzed to assess their dependability before using them as a guidance tool.

Aug 5, 2026

Upload by Emma Wilson