Knowledge Graph for Methane Selective Conversion: Revisiting and Predicting Product Selectivity and Methane Conversion

Boyu Xu; Gaoyang Li; Bohan Wang; Jiawei Bian; Hui Pan; Yulin Min; Guodong Qi; Jun Xu; Feng Deng; Feng Ju; Hao Ling; Zhendong Wang

doi:10.1002/advs.202514601

Knowledge Graph for Methane Selective Conversion: Revisiting and Predicting Product Selectivity and Methane Conversion

Boyu Xu
, Gaoyang Li
, Bohan Wang
, Jiawei Bian
, Hui Pan^*
, Yulin Min
, Guodong Qi^*
, Jun Xu
, Feng Deng
, Feng Ju^*
, Hao Ling
, Zhendong Wang

^*Corresponding author for this work

Sub Visualisation and Graphics

Shanghai University of Electric Power
East China University of Science and Technology
Chinese Academy of Sciences
SINOPEC

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Selective conversion of methane to carbon-based compounds is promising but currently limited by issues related to scale. Unraveling the interconnected relationships between products selectivity and methane conversion plays a pivotal role in understanding of this complex process. In this work, a knowledge graph (KG) is constructed for methane conversion with the help of a robust large language model basing on the literature reported methane conversion over different catalysts under various conditions. This KG, structured around 11 entity types and 32 relationship types, allows to effectively analyze advancements in methane conversion - including identifying optimal catalytic processes, evaluating reaction conditions, and tracking development trends. A deep neural network analysis of the KG highlighted catalysts with metal active sites and multifunctional supports as particularly effective for methanol production under conditions suitable for industrial-scale applications. These findings provide valuable insights for targeted catalyst development and industrial applications.

Original language	English
Article number	e14601
Number of pages	13
Journal	Advanced Science
Volume	12
Issue number	48
Early online date	6 Oct 2025
DOIs	https://doi.org/10.1002/advs.202514601
Publication status	Published - 29 Dec 2025

Bibliographical note

Publisher Copyright:
© 2025 The Author(s). Advanced Science published by Wiley-VCH GmbH.

Funding

This work was supported by Sinopec Foundation (224250), the National Key R&D Program of China (2022YFA1504500 and 2023YFA1509102), the Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0540000), the National Natural Science Foundation of China (22378131, 22478239 and 22272185), Shanghai Pujiang Programme (23PJD021), and Science and Technology Commission of Shanghai Municipality (No.19DZ2271100).

Funders	Funder number
Shanghai Pujiang Programme	23PJD021
Chinese Academy of Sciences	XDB0540000
Sinopec Foundation	224250
Science and Technology Commission of Shanghai Municipality	19DZ2271100
National Natural Science Foundation of China	22378131, 22272185, 22478239
National Key Research and Development Program of China	2023YFA1509102, 2022YFA1504500

Keywords

Deep neural networks
Knowledge graph
Large language models
Methane selective conversion
Predicting catalytic performance

Access to Document

10.1002/advs.202514601Licence: CC BY

Advanced Science - 2025 - Xu - Knowledge Graph for Methane Selective Conversion Revisiting and Predicting ProductFinal published version, 6.36 MBLicence: CC BY

Cite this

@article{e8c9bc824f7749dba456b7c67ca91493,

title = "Knowledge Graph for Methane Selective Conversion: Revisiting and Predicting Product Selectivity and Methane Conversion",

abstract = "Selective conversion of methane to carbon-based compounds is promising but currently limited by issues related to scale. Unraveling the interconnected relationships between products selectivity and methane conversion plays a pivotal role in understanding of this complex process. In this work, a knowledge graph (KG) is constructed for methane conversion with the help of a robust large language model basing on the literature reported methane conversion over different catalysts under various conditions. This KG, structured around 11 entity types and 32 relationship types, allows to effectively analyze advancements in methane conversion - including identifying optimal catalytic processes, evaluating reaction conditions, and tracking development trends. A deep neural network analysis of the KG highlighted catalysts with metal active sites and multifunctional supports as particularly effective for methanol production under conditions suitable for industrial-scale applications. These findings provide valuable insights for targeted catalyst development and industrial applications.",

keywords = "Deep neural networks, Knowledge graph, Large language models, Methane selective conversion, Predicting catalytic performance",

author = "Boyu Xu and Gaoyang Li and Bohan Wang and Jiawei Bian and Hui Pan and Yulin Min and Guodong Qi and Jun Xu and Feng Deng and Feng Ju and Hao Ling and Zhendong Wang",

note = "Publisher Copyright: {\textcopyright} 2025 The Author(s). Advanced Science published by Wiley-VCH GmbH.",

year = "2025",

month = dec,

day = "29",

doi = "10.1002/advs.202514601",

language = "English",

volume = "12",

journal = "Advanced Science",

issn = "2198-3844",

publisher = "John Wiley and Sons Inc.",

number = "48",

}

TY - JOUR

T1 - Knowledge Graph for Methane Selective Conversion

T2 - Revisiting and Predicting Product Selectivity and Methane Conversion

AU - Xu, Boyu

AU - Li, Gaoyang

AU - Wang, Bohan

AU - Bian, Jiawei

AU - Pan, Hui

AU - Min, Yulin

AU - Qi, Guodong

AU - Xu, Jun

AU - Deng, Feng

AU - Ju, Feng

AU - Ling, Hao

AU - Wang, Zhendong

PY - 2025/12/29

Y1 - 2025/12/29

N2 - Selective conversion of methane to carbon-based compounds is promising but currently limited by issues related to scale. Unraveling the interconnected relationships between products selectivity and methane conversion plays a pivotal role in understanding of this complex process. In this work, a knowledge graph (KG) is constructed for methane conversion with the help of a robust large language model basing on the literature reported methane conversion over different catalysts under various conditions. This KG, structured around 11 entity types and 32 relationship types, allows to effectively analyze advancements in methane conversion - including identifying optimal catalytic processes, evaluating reaction conditions, and tracking development trends. A deep neural network analysis of the KG highlighted catalysts with metal active sites and multifunctional supports as particularly effective for methanol production under conditions suitable for industrial-scale applications. These findings provide valuable insights for targeted catalyst development and industrial applications.

AB - Selective conversion of methane to carbon-based compounds is promising but currently limited by issues related to scale. Unraveling the interconnected relationships between products selectivity and methane conversion plays a pivotal role in understanding of this complex process. In this work, a knowledge graph (KG) is constructed for methane conversion with the help of a robust large language model basing on the literature reported methane conversion over different catalysts under various conditions. This KG, structured around 11 entity types and 32 relationship types, allows to effectively analyze advancements in methane conversion - including identifying optimal catalytic processes, evaluating reaction conditions, and tracking development trends. A deep neural network analysis of the KG highlighted catalysts with metal active sites and multifunctional supports as particularly effective for methanol production under conditions suitable for industrial-scale applications. These findings provide valuable insights for targeted catalyst development and industrial applications.

KW - Deep neural networks

KW - Knowledge graph

KW - Large language models

KW - Methane selective conversion

KW - Predicting catalytic performance

UR - https://www.scopus.com/pages/publications/105018321791

U2 - 10.1002/advs.202514601

DO - 10.1002/advs.202514601

M3 - Article

C2 - 41053516

SN - 2198-3844

VL - 12

JO - Advanced Science

JF - Advanced Science

IS - 48

M1 - e14601

ER -

Knowledge Graph for Methane Selective Conversion: Revisiting and Predicting Product Selectivity and Methane Conversion

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this