Data driven design of alkali-activated concrete using sequential learning

Völker, Christoph; Torres, Benjamí Moreno; Rug, Tehseen; Firdous, Rafia; Zia, Ghezal Ahmad Jan; Lüders, Stephan; Scaffino, Horacio Lisdero; Höpler, Michael; Böhmer, Felix; Pfaff, Matthias; Stephan, Dietmar; Kruschwitz, Sabine

doi:10.1016/j.jclepro.2023.138221

Cited by 12 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In an effort to validate and identify optimal data-driven routes for optimization of such concrete, Völker et al used a set of 131 experimental data from the literature to conduct computational benchmarks, exploring the effect of algorithm choice and parallelization on the efficiency with which high compression strength materials can be identified. 603 Notably, this is one of the only studies that shows modern adaptive experimentation being used in the context of concrete optimization.…”

Section: Concrete Formulationsmentioning

confidence: 99%

Self-Driving Laboratories for Chemistry and Materials Science

Tom,

Schmid,

Baird

et al. 2024

Preprint

View full text Add to dashboard Cite

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through the automation of experimental workflows, along with the autonomization of experiment planning, SDLs hold the potential to greatly accelerate research in chemistry and materials discovery. This review article provides an in-depth analysis of the state-of-the-art in SDL technology, its applications across various scientific disciplines, and the potential implications for research, and industry. This review additionally provides an overview of the enabling technologies for SDLs, including their hardware, software, and integration with laboratory infrastructure. Most importantly, this review explores the diverse range of scientific domains where SDLs have made significant contributions, from drug discovery and materials science to genomics and chemistry. We provide a comprehensive review of existing real-world examples of SDLs, their different levels of automation, and the challenges and limitations associated with each domain.

show abstract

Section: Concrete Formulationsmentioning

confidence: 99%

Self-Driving Laboratories for Chemistry and Materials Science

Tom,

Schmid,

Baird

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Much research is focused on formulations of concrete that are less CO 2 intensive. 50 To expedite the design process, e.g., by prioritizing experiments using MLpredictions, data-driven methods have been investigated by Völker et al 51 The Text2Concrete team (Sabine Kruschwitz, Christoph Völker, and Ghezal Ahmad Zia) explored, based on data reported by Rao and Rao, 52 whether LLMs can be used for this task. This data set provides 240 alternative, more sustainable, concrete formulations and their respective compressive strengths.…”

Section: Predictive Modelingmentioning

confidence: 99%

14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon

Jablonka,

Ai,

Al-Feghali

et al. 2023

Digital Discovery

View full text Add to dashboard Cite

show abstract

“…Traditional development methods for cementitious materials, such as AAC, are often inefficient and limited due to their empirical and prescriptive nature, struggling to effectively handle the material's extensive range of compositional variations [6]. The introduction of Data-Driven Design (DDD) methods, such as Sequential Learning (SL) and Bayesian Optimization (BO) marked a significant improvement [7,8,9,10,11], yet they are dependent on initial data collection: The high variability of the precursor materials, where each batch can have different properties, means that it is simply not practical to use pre-existing data. Consequently, this approach often necessitates a preliminary phase of re-establishing fundamental relationships through experimental data, delaying the onset of novel formulation development.…”

Section: Introductionmentioning

confidence: 99%

“…This percentile marks the lower bound performance limit that was achieved in 90% of the design runs, indicating a high robustness of the method in attaining such compressive strengths at a given number of development cycles. The methodologies underlying the benchmarking approach and the baseline methods are described in more detail in [9].…”

mentioning

confidence: 99%

LLMs can Design Sustainable Concrete – a Systematic Benchmark

Völker,

Rug,

Jablonka

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

In the context of a circular building material economy, the complexity of resource flows and the variability of material composition pose significant challenges. This study demonstrates how Large Language Models (LLMs) can advance material design by adopting a Knowledge-Driven Design (KDD) approach that outperforms traditional Data-Driven Design (DDD) methods. Our focus is on designing alkali-activated concrete (AAC) mix designs, an environmentally friendly alternative to conventional Portland cement-based concrete. GPT-3.5 Turbo and GPT-4 Turbo enable using fuzzy design knowledge as previously untapped input data modality. A key aspect of our research is to improve the performance of the LLMs in post-training. We use strategies such as refining prompt context, extending test time, and including a verifier.The study's systematic benchmarks are based on 240 AAC formulations extracted from the literature. The target was on achieving maximum compressive strength through an adaptive design approach over multiple development cycles. We compare these results to the traditional DDD baseline methods. KDD outperforms conventional methods by providing robust initial predictions and demonstrating effective adaptability informed by laboratory validation data, culminating in the development of high-quality AAC formulations. These results provide valuable insight into the capabilities of chat-based LLMs in managing complex material formulations, which are particularly beneficial in situations where traditional DDD is impractical due to data collection issues. With natural language as the basis the KDD is intuitively accessible to domain experts. The methodology and results of this study have significant implications for the field of materials science, particularly in the context of a circular economy, and pave the way for innovative applications of LLMs in various scientific fields.

show abstract

Data driven design of alkali-activated concrete using sequential learning

Cited by 12 publications

References 34 publications

Self-Driving Laboratories for Chemistry and Materials Science

Self-Driving Laboratories for Chemistry and Materials Science

14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon

LLMs can Design Sustainable Concrete – a Systematic Benchmark

Contact Info

Product

Resources

About