Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation

Assessing the sustainable development of green hydrogen and assessing its potential environmental impacts using the Life Cycle Assessment is crucial. Challenges in LCA, like missing environmental data, are often addressed using machine learning, such as artificial neural networks. However, to find a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yajing Chen, Urs Liebau, Shreyas Mysore Guruprasad, Iaroslav Trofimenko, Christine Minke
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Machine Learning and Knowledge Extraction
Subjects:
Online Access:https://www.mdpi.com/2504-4990/6/4/122
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850240923296858112
author Yajing Chen
Urs Liebau
Shreyas Mysore Guruprasad
Iaroslav Trofimenko
Christine Minke
author_facet Yajing Chen
Urs Liebau
Shreyas Mysore Guruprasad
Iaroslav Trofimenko
Christine Minke
author_sort Yajing Chen
collection DOAJ
description Assessing the sustainable development of green hydrogen and assessing its potential environmental impacts using the Life Cycle Assessment is crucial. Challenges in LCA, like missing environmental data, are often addressed using machine learning, such as artificial neural networks. However, to find an ML solution, researchers need to read extensive literature or consult experts. This research demonstrates how customised LLMs, trained with domain-specific papers, can help researchers overcome these challenges. By starting small by consolidating papers focused on the LCA of proton exchange membrane water electrolysis, which produces green hydrogen, and ML applications in LCA. These papers are uploaded to OpenAI to create the LlamaIndex, enabling future queries. Using the LangChain framework, researchers query the customised model (GPT-3.5-turbo), receiving tailored responses. The results demonstrate that customised LLMs can assist researchers in providing suitable ML solutions to address data inaccuracies and gaps. The ability to quickly query an LLM and receive an integrated response across relevant sources presents an improvement over manually retrieving and reading individual papers. This shows that leveraging fine-tuned LLMs can empower researchers to conduct LCAs more efficiently and effectively.
format Article
id doaj-art-9dbc6b28d7684bdcab499e966954489f
institution OA Journals
issn 2504-4990
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Machine Learning and Knowledge Extraction
spelling doaj-art-9dbc6b28d7684bdcab499e966954489f2025-08-20T02:00:43ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902024-11-01642494251410.3390/make6040122Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models AugmentationYajing Chen0Urs Liebau1Shreyas Mysore Guruprasad2Iaroslav Trofimenko3Christine Minke4Institute of Mineral and Waste Processing, Recycling and Circular Economy Systems, Clausthal University of Technology, 38678 Clausthal-Zellerfeld, GermanyCenter for Digital Green Tech, August-Wilhelm-Scheer Institute, 38678 Clausthal-Zellerfeld, GermanyCenter for Digital Green Tech, August-Wilhelm-Scheer Institute, 38678 Clausthal-Zellerfeld, GermanyCenter for Digital Green Tech, August-Wilhelm-Scheer Institute, 38678 Clausthal-Zellerfeld, GermanyInstitute of Mineral and Waste Processing, Recycling and Circular Economy Systems, Clausthal University of Technology, 38678 Clausthal-Zellerfeld, GermanyAssessing the sustainable development of green hydrogen and assessing its potential environmental impacts using the Life Cycle Assessment is crucial. Challenges in LCA, like missing environmental data, are often addressed using machine learning, such as artificial neural networks. However, to find an ML solution, researchers need to read extensive literature or consult experts. This research demonstrates how customised LLMs, trained with domain-specific papers, can help researchers overcome these challenges. By starting small by consolidating papers focused on the LCA of proton exchange membrane water electrolysis, which produces green hydrogen, and ML applications in LCA. These papers are uploaded to OpenAI to create the LlamaIndex, enabling future queries. Using the LangChain framework, researchers query the customised model (GPT-3.5-turbo), receiving tailored responses. The results demonstrate that customised LLMs can assist researchers in providing suitable ML solutions to address data inaccuracies and gaps. The ability to quickly query an LLM and receive an integrated response across relevant sources presents an improvement over manually retrieving and reading individual papers. This shows that leveraging fine-tuned LLMs can empower researchers to conduct LCAs more efficiently and effectively.https://www.mdpi.com/2504-4990/6/4/122life cycle assessmentgreen hydrogenmachine learningcustomised large language model
spellingShingle Yajing Chen
Urs Liebau
Shreyas Mysore Guruprasad
Iaroslav Trofimenko
Christine Minke
Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation
Machine Learning and Knowledge Extraction
life cycle assessment
green hydrogen
machine learning
customised large language model
title Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation
title_full Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation
title_fullStr Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation
title_full_unstemmed Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation
title_short Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation
title_sort advancing life cycle assessment of sustainable green hydrogen production using domain specific fine tuning by large language models augmentation
topic life cycle assessment
green hydrogen
machine learning
customised large language model
url https://www.mdpi.com/2504-4990/6/4/122
work_keys_str_mv AT yajingchen advancinglifecycleassessmentofsustainablegreenhydrogenproductionusingdomainspecificfinetuningbylargelanguagemodelsaugmentation
AT ursliebau advancinglifecycleassessmentofsustainablegreenhydrogenproductionusingdomainspecificfinetuningbylargelanguagemodelsaugmentation
AT shreyasmysoreguruprasad advancinglifecycleassessmentofsustainablegreenhydrogenproductionusingdomainspecificfinetuningbylargelanguagemodelsaugmentation
AT iaroslavtrofimenko advancinglifecycleassessmentofsustainablegreenhydrogenproductionusingdomainspecificfinetuningbylargelanguagemodelsaugmentation
AT christineminke advancinglifecycleassessmentofsustainablegreenhydrogenproductionusingdomainspecificfinetuningbylargelanguagemodelsaugmentation