SpiderGen: Towards Procedure Generation For Carbon Life Cycle Assessments with Generative AI

TL;DR

SpiderGen leverages large language models to automate the generation of process flow graphs for life cycle assessments of consumer products, significantly reducing time and cost while maintaining accuracy.

Contribution

The paper introduces SpiderGen, a novel LLM-based workflow that integrates traditional LCA methodology with AI reasoning to generate key procedural information efficiently.

Findings

Achieves an F1-Score of 65% in accuracy, outperforming one-shot prompting.

Reduces LCA process estimation cost to less than $1 USD and under 10 minutes.

Demonstrates potential to cut human effort and costs substantially.

Abstract

Investigating the effects of climate change and global warming caused by GHG emissions have been a key concern worldwide. These emissions are largely contributed to by the production, use and disposal of consumer products. Thus, it is important to build tools to estimate the environmental impact of consumer goods, an essential part of which is conducting Life Cycle Assessments (LCAs). LCAs specify and account for the appropriate processes involved with the production, use, and disposal of the products. We present SpiderGen, an LLM-based workflow which integrates the taxonomy and methodology of traditional LCA with the reasoning capabilities and world knowledge of LLMs to generate graphical representations of the key procedural information used for LCA, known as Product Category Rules Process Flow Graphs (PCR PFGs). We additionally evaluate the output of SpiderGen by comparing it with 65 real-world LCA documents. We find that SpiderGen provides accurate LCA process information that is either fully correct or has minor errors, achieving an F1-Score of 65% across 10 sample data points, as compared to 53% using a one-shot prompting method. We observe that the remaining errors occur primarily due to differences in detail between LCA documents, as well as differences in the "scope" of which auxiliary processes must also be included. We also demonstrate that SpiderGen performs better than several baselines techniques, such as chain-of-thought prompting and one-shot prompting. Finally, we highlight SpiderGen's potential to reduce the human effort and costs for estimating carbon impact, as it is able to produce LCA process information for less than \$1 USD in under 10 minutes as compared to the status quo LCA, which can cost over \$25000 USD and take up to 21-person days.