Mapping the Landscape of Artificial Intelligence in Life Cycle Assessment Using Large Language Models

Anastasija Mensikova; Donna M. Rizzo; Kathryn Hinkelman

cs.AIFeb 26, 2026

Mapping the Landscape of Artificial Intelligence in Life Cycle Assessment Using Large Language Models

Authors: Anastasija Mensikova, Donna M. Rizzo, Kathryn Hinkelman

Organizations: University of Vermont Burlington, VT, USA

Abstract

Integration of artificial intelligence (AI) into life cycle assessment (LCA) has accelerated in recent years, with numerous studies successfully adapting machine learning algorithms to support various stages of LCA. Despite this rapid development, comprehensive and broad synthesis of AI-LCA research remains limited. To address this gap, this study presents a detailed review of published work at the intersection of AI and LCA, leveraging large language models (LLMs) to identify current trends, emerging themes, and future directions. Our analyses reveal that as LCA research continues to expand, the adoption of AI technologies has grown dramatically, with a noticeable shift toward LLM-driven approaches, continued increases in ML applications, and statistically significant correlations between AI approaches and corresponding LCA stages. By integrating LLM-based text-mining methods with traditional literature review techniques, this study introduces a dynamic and effective framework capable of capturing both high-level research trends and nuanced conceptual patterns (themes) across the field. Collectively, these findings demonstrate the potential of LLM-assisted methodologies to support large-scale, reproducible reviews across broad research domains, while also evaluating pathways for computationally-efficient LCA in the context of rapidly developing AI technologies. In doing so, this work helps LCA practitioners incorporate state-of-the-art tools and timely insights into environmental assessments that can enhance the rigor and quality of sustainability-driven decisions and decision-making processes.

Figures & tables

Figure 1: Review protocol to identify, screen, and collect documents based on PRISMA 2020 [ 10 ] .

Figure 2: UMAP projections, their respective HDBSCAN-produced clusters, and LLM-generated cluster titles (

n=209

$C$	Key TF-IDF Phrases	LLM-Generated Title
0	carbon emissions, recycled aggregates	Sustainable Construction Materials and Processes Optimization
1	product development, sustainable manufacturing	Sustainable Product Development and Circular Economy
2	wastewater treatment, human health	Life Cycle Assessment of Water Treatment Technologies
3	biodiesel production, ghg emissions	Sustainable Biosynthesis and Circular Economy
4	water use, resource recovery	Life Cycle Assessment of Sustainable Agriculture and Energy Systems
5	energy consumption, machine learning	Integrating AI and LCA for Sustainable Decision-Making

Table 1: Summary of identified AI–LCA clusters including term extraction and LLM-generated approaches.

Figure 3: Evolution of the top terms in abstracts (

n=538

) over 4-year time periods with heights normalized by number of terms per period.

Term	Specificity $\chi^{2}$	$f$
renewable energy	228	8
power generation	215	8
output energy	214	5
operational efficiency	211	11
biodiesel production	209	3
energy systems	199	17

Table 2: Most frequently occurring terms in abstracts (

n=538

) related to energy based on specificity.

Figure 4: Distribution of AI topics over time extracted from full texts with an LLM. All papers where the LLM could not find any AI methodologies were excluded. Number of documents in each year are listed across the top.

Figure 5: Distribution of AI topics, LCA stages and LCIA methodologies over time (

n=209

Figure 6: Contingency between AI/ML and LCA terms across abstracts ( $n=538$ ) indicating highly statistically significant differences ( $p=0.00262$ ) across all terms. Cells with an asterisk are significant ( $p<0.05$ ).

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

$C$	LLM-Generated Title	LLM-Generated AI Methods	Top Ranked Citations
0	Sustainable Construction Materials and Processes Optimization	Machine learning models, such as neural networks and genetic algorithms, are used to predict and optimize various performance metrics, including energy consumption, carbon emissions, and cost	[ 19 , 20 ]
1	Sustainable Product Development and Circular Economy	Machine learning algorithms are used in some papers to analyze data and predict outcomes, while others employ AI-powered decision support systems for optimizing resource efficiency	[ 21 , 22 ]
2	Life Cycle Assessment of Water Treatment Technologies	Machine learning models are used to predict chemical toxicity and expand species sensitivity distributions, while deep neural networks enhance environmental impact assessment accuracy for constructed wetlands	[ 23 , 24 ]
3	Sustainable Biosynthesis and Circular Economy	Machine learning (ML) techniques, such as transformer-based language models and natural gradient boosting, are used to optimize processes, predict yields, and analyze LCA data	[ 25 , 26 ]
4	Life Cycle Assessment of Sustainable Agriculture and Energy Systems	Machine learning models such as random forest regression, Gaussian kernel regression, and neural networks are used to predict missing data, optimize datasets, and improve the accuracy of life cycle climate emissions predictions	[ 27 , 28 ]
5	Integrating AI and LCA for Sustainable Decision-Making	Papers in this cluster employ AI/ML techniques such as generative design, predictive modeling, and semantic interoperability to analyze and improve the environmental performance of buildings, infrastructure, and manufacturing systems	[ 29 , 30 ]

Appendix

Table 3: Summary of identified AI–LCA clusters including term extraction and LLM-generated approaches for validation and refinement.

Life Cycle Assessment

See all 10 papers

LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation
Jun 25, 2026Georgios Tsironis, Juan D. Medrano-Garcia, Gonzalo Guillen-GosalbezRetrieval-Augmented Generation LLM Grounding
Institute for Chemical and Bioengineering, Department of Chemistry and Applied Biosciences, ETH Zürich, Vladimir Prelog Weg 1, Zürich 8093, Switzerland · NCCR Catalysis, Zurich 8093, Switzerland
PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews
Sep 10, 2026Miguel Zabaleta, Baihan LinLLM Auditing Systematic Review Automation
Department of AI and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, USA
Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment
May 31, 2026Jared Fernandez, Clara Na, Yonatan Bisk +2Energy-Efficient ML Responsible AI
Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA · Department of Civil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, PA, USA · Wilton E. Scott Institute for Energy Innovation, Carnegie Mellon University, Pittsburgh, PA, USA

Jun 25, 2026J/K move · Enter open · S save

LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation

Georgios Tsironis, Juan D. Medrano-Garcia, Gonzalo Guillen-Gosalbez

Institute for Chemical and Bioengineering, Department of Chemistry and Applied Biosciences, ETH Zürich, Vladimir Prelog Weg 1, Zürich 8093, Switzerland · NCCR Catalysis, Zurich 8093, Switzerland

Retrieval-Augmented Generation LLM Grounding Life Cycle Assessment Data Fusion

Open paper AskPDF arXiv

The interpretation phase of life cycle assessment often lacks structured mechanisms for translating quantified improvement opportunities addressing environmental hotspots into actionable strategic pathways under technological, social, and policy uncertainty. To overcome this limitation, this study introduces a perspective-conditioned retrieval-augmented generation framework for LCA interpretation, where a multi-perspective retrieval and controlled synthesis is incorporated in the artificial intelligence (AI)-assisted LCA. To operationalise large language models in LCA interpretation, a perspective fusion RAG architecture was developed, covering academic, industry, public discourse, and European union (EU) funding datasets. Our approach comprises three steps: (1) a scenario anchor defining system boundaries and decarbonization targets, (2) a set of perspective-specific micro-queries with constrained retrieval, and (3) a neutral synthesis step integrating only ledger-stored outputs without further retrieval. The framework is demonstrated through a hydrogen-enabled diesel reduction use case in an Italian apple production facility using GPT-5 nano as the reasoning model. Overall, the structured retrieval and constrained synthesis are designed to mitigate the risk of hallucination while preserving cross-domain diversity. The approach presented can support more disciplined translation of impact results into strategic pathways and opens up new avenues for the use of advanced AI tools in LCA studies, particularly those focused on technologies that could be deployed at scale. This proof-of-concept demonstrates how AI-assisted, evidence-grounded interpretation can support implementation-oriented decision-making beyond conventional LCA studies.

Abstract

Life Cycle Assessment

Explore similar work

LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews

Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment