What are the future trends in natural gas technology to address climate change? Patent analysis through large language model

Mingyu Kim and Juyong Lee

Energy, 2024, vol. 312, issue C

Abstract: Policies to reduce dependence on fossil fuel consumption and increase the share of renewable energy are being pursued worldwide, and in 2020, the European Union highlighted hydrogen as a key priority to achieve its decarbonisation goals. Base on Bidirectional Encoder Representations from Transformers (BERT), a pre-trained transformer-based large language model, this study conducted patent text mining for natural gas utilisation and generation technologies from 2013 to 2022, which are internationally registered patents. As a result of the topic modelling, a topic representation was created with c-TF-IDF that encapsulates all documents in clusters or classes, and 10 related topics and trends were derived. Among the 10 topics, the topics of water reactor and hydrogen-blended gas turbine were found to be increasing rapidly in proportion recently, and in fact, these technologies were found to be the most actively developed technologies in 2023. Therefore, based on the results of patent analysis on natural gas generation technologies, this study demonstrates that applying large language models to traditional patent analysis methodologies that focuses on technology segmentation and topic modelling can be used to predict future trends and innovative technologies, and also suggests the direction of future research on technology prediction.

Keywords: Natural gas; Hydrogen blending; Large language model; Patent analysis; Text mining (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224034224
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:312:y:2024:i:c:s0360544224034224

DOI: 10.1016/j.energy.2024.133644

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().