Filtern
Dokumenttyp
Sprache
- Englisch (3)
Schlagworte
- Concrete (1)
- Hackathon (1)
- Inverse Design (1)
- Large Language model (1)
- Orchestration (1)
- Prediction (1)
- Product certification (1)
- Test method validation (1)
- Volatile organic compounds (1)
Organisationseinheit der BAM
Product emissions chamber testing involves a complex protocol with several sources of measurement uncertainty (ASTM, 2010; ISO, 2006). Despite the potential for significant variability in measurement results within and among laboratories, there is no Standard method available to assess the accuracy of emissions chamber test results. Recently, Germany’s Federal Institute for Materials Research and Testing (BAM) started a program to evaluate the performance of laboratories testing for the AgBB (German Committee for Health-related Evaluation of Building Products) labelling scheme (Wilke et al., 2009). Test method validation was conducted through interlaboratory studies (ILS) with over 30 participants. Simultaneously, the National Institute of Standards and Technology (NIST) and Virginia Tech (VT) started a program to develop a series of reference materials that mimic real building products, can be tested in typical emissions chambers, and have independently known emission rates (Cox et al., 2010). BAM, NIST and VT subsequently joined forces to conduct a series of inter-laboratory studies using the prototype reference material. A pilot ILS was conducted with BAM and NIST followed by an expanded ILS with several participating countries. Results from these interlaboratory studies have the potential to define an internationally-accepted Standard approach to validate results from product emissions tests.
Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, we organized a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications. The diverse topics and the fact that working prototypes could be generated in less than two days highlight that LLMs will profoundly impact the future of our fields. The rich collection of ideas and projects also indicates that the applications of LLMs are not limited to materials science and chemistry but offer potential benefits to a wide range of scientific disciplines.