Enhanced Sustainable Concrete Mix Design Using LLMs and Advanced Machine Learning Techniques

Year : 2026 | Volume : 16 | 02 | Page :
    By

    Mr. Rishabh Ray,

  • Mr. Shirshendu Maitra,

  • Ms. Anusri Mukhopadhyay,

Abstract

Large Language Models (LLMs) are emerging as transformative tools in materials science, offering human-like reasoning, zero-shot problem solving, and the ability to integrate fuzzy laboratory knowledge with structured data. This study extends and reinterprets the original systematic benchmark for using LLMs in sustainable concrete design, particularly for Alkali-Activated Concrete (AAC). We introduce an enhanced, multi-model framework combining LLM-based inverse design, Random Forest regression, Gaussian Process Regression (GPR), and a lightweight Artificial Neural Network (ANN). Additional figures and datasets are incorporated to strengthen reproducibility and provide deeper insight into model behavior. Results indicate that LLM-based design assistants can match or outperform classical data-driven approaches without requiring training data, while hybrid LLM–ML models significantly improve stability in predicting 28-day compressive strength.

Keywords: Gen- AI, AAC, sustainable concrete, LLM

How to cite this article:
Mr. Rishabh Ray, Mr. Shirshendu Maitra, Ms. Anusri Mukhopadhyay. Enhanced Sustainable Concrete Mix Design Using LLMs and Advanced Machine Learning Techniques. Recent Trends in Civil Engineering & Technology. 2026; 16(02):-.
How to cite this URL:
Mr. Rishabh Ray, Mr. Shirshendu Maitra, Ms. Anusri Mukhopadhyay. Enhanced Sustainable Concrete Mix Design Using LLMs and Advanced Machine Learning Techniques. Recent Trends in Civil Engineering & Technology. 2026; 16(02):-. Available from: https://journals.stmjournals.com/rtcet/article=2026/view=243808


References

  • Christoph Völker, Tehseen Rug , Kevin Maik Jablonka and Sabine Kruschwitz, “LLMs can Design Sustainable Concrete – a Systematic Benchmark” https://doi.org/10.21203/rs.3.rs-3913272/v1
  • Patel, & Patel, A. (2021). Sustainable green materials in construction. IOP Earth & Environmental Science.J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68–73.
  • Racaza, O. & Cabahug, R. (2016). Coconut husk ash as partial cement substitute. Mindanao Journal of Science & Technology.
  • Claisse, P. (2015). Civil Engineering Materials. Butterworth-Heinemann.
  • Li, M., Zhang, M., & Chen, Y. (2020). Cement production and air quality impacts. Science of the Total Environment.
  • Mohamad, N. et al. (2021). Environmental impacts of cement manufacturing. Materials Today Proceedings.
  • ACI Committee 211. (1991). Concrete Mix Design
  • Kodur, V. (2014). Behavior of concrete under elevated temperatures. ISRN Civil Engineering.
  • Gepulango, & Grio, M. (2003). Compressive strength variation of concrete. Patubas Journal.
  • IBM (2024). Introduction to machine- learning algorithms.
  • Marcos, et al. (2023). Predictive modeling for urban conditions using linear and nonlinear ML. IEEE ICRAIE.
  • Silva, & Marcos, C. (2023). Digital data collection in civil engineering. IEEE ICMSP
  • Marcos, & Silva, D. (2022). ANN-based prediction of structural behavior. IEEE SCM.
  • Gao, et al. (2024). Mix design of sustainable concrete using generative models. Construction Materials Science.
  • Tipu, K. et al. (2025). Optimizing sustainable blended concrete mixes using deep neural networks. Scientific Reports.
  • Erfani, et al. (2025). Applications of multimodal large language models in construction. SSRN.
  • International Journal of Civil (2025). Innovative Concrete Mix Design Incorporating Recycled Aggregates.
  • Journal of Progressive (2024). Review Paper On Concrete Mix Design Optimization Using ML- Based Algorithm.
  • Nature Scientific (2023). Investigation study data to develop sustainable concrete mix using alternative aggregates.
  • Migration Letters (2025). Machine Learning Algorithms for Optimizing Mix Design of Recycled Aggregate Concrete.
Ahead of Print Subscription Original Research
Volume 16
02
Received 10/02/2026
Accepted 13/05/2026
Published 14/05/2026
Publication Time 93 Days
10

Login


My IP

PlumX Metrics