| Issue |
E3S Web Conf.
Volume 670, 2025
2nd International Conference on the Agro-Environmental Nexus: Land, Water & Energy for Sustainable Development (IC-AEN 2025)
|
|
|---|---|---|
| Article Number | 05007 | |
| Number of page(s) | 8 | |
| Section | Climate Risk Adaptation and Nature-Based Solutions in Rural Landscapes | |
| DOI | https://doi.org/10.1051/e3sconf/202567005007 | |
| Published online | 01 December 2025 | |
Application of large language models in sustainable structural engineering: Performance and potential
1 Ural Federal University named after the First President of Russia B. N. Yeltsin, Institute of Civil Engineering and Architecture, 620062 Yekaterinburg, Russia
2 Lomonosov Moscow State University, Faculty of Mechanics and Mathematics, 119991 Moscow, Russia
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract
This study evaluates the potential of generative artificial intelligence (AI) large language models (LLMs) in optimizing structural analysis for sustainable construction. The research compares the accuracy, computational efficiency, and reasoning capabilities of six prominent LLMs, including ChatGPT-o1-preview, Claude-3-Opus-200k, and Gemini-1.5-pro, in solving various civil engineering problems. The findings highlight LLMs' potential to enhance energy-efficient building designs, reduce material consumption, and improve structural safety assessments. While their direct application in structural analysis remains in early development, AI-driven approaches show promise in optimizing resource use, supporting sustainable urban development, and mitigating environmental impact in construction engineering.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.