A RAG-Based Framework for Material Matching in LCA: Integrating Semantic and Character Similarity with AI-Driven Explanations

In early building planning, appropriate material selection is crucial for emission reduction. To address the inefficiency of manual searches in Life Cycle Assessment (LCA) databases, prior studies have proposed automated matching methods that are based on Natural Language Processing (NLP). However, the outputs typically provide only matching results without explanations, which limits their usability for non-experts. This study proposes a Retrieval Augmented Generation (RAG)-based material matching framework that incorporates a hybrid scoring of semantic similarity and edit distance to search similar material and employs GPT-2 to generate natural language explanations. Besides retrieving matching materials efficiently, this approach also enhances result interpretability with explanations. In the case study, accuracy ranges from 27.73% to 78.13%, with notable structure category variance. Excluding extremes, average accuracy reaches 60%. This RAG-based framework offers more instructive material recommendations and effective support for non-experts in decision-making.      «

In early building planning, appropriate material selection is crucial for emission reduction. To address the inefficiency of manual searches in Life Cycle Assessment (LCA) databases, prior studies have proposed automated matching methods that are based on Natural Language Processing (NLP). However, the outputs typically provide only matching results without explanations, which limits their usability for non-experts. This study proposes a Retrieval Augmented Generation (RAG)-based material matchi...     »