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

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.

Research data infrastructure for high-throughput experimental materials science.

The High-Throughput Experimental Materials Database (HTEM-DB, htem.nrel.gov) is a repository of inorganic thin-film materials data collected during combinatorial experiments at the National Renewable Energy Laboratory (NREL). This data asset is enabled by NREL's Research Data Infrastructure (RDI), a set of custom data tools that collect, process, and store experimental data and metadata. Here, we describe the experimental data flow from the RDI to the HTEM-DB to illustrate the strategies and best practices currently used for materials data at NREL. Integration of the data tools with experimental instruments establishes a data communication pipeline between experimental researchers and data scientists. This work motivates the creation of similar workflows at other institutions to aggregate valuable data and increase their usefulness for future machine learning studies. In turn, such data-driven studies can greatly accelerate the pace of discovery and design in the materials science domain.

Graph network based deep learning of bandgaps.

Recent machine learning models for bandgap prediction that explicitly encode the structure information to the model feature set significantly improve the model accuracy compared to both traditional machine learning and non-graph-based deep learning methods. The ongoing rapid growth of open-access bandgap databases can benefit such model construction not only by expanding their domain of applicability but also by requiring constant updating of the model. Here, we build a new state-of-the-art multi-fidelity graph network model for bandgap prediction of crystalline compounds from a large bandgap database of experimental and density functional theory (DFT) computed bandgaps with over 806 600 entries (1500 experimental, 775 700 low-fidelity DFT, and 29 400 high-fidelity DFT). The model predicts bandgaps with a 0.23 eV mean absolute error in cross validation for high-fidelity data, and including the mixed data from all different fidelities improves the prediction of the high-fidelity data. The prediction error is smaller for high-symmetry crystals than for low symmetry crystals. Our data are published through a new cloud-based computing environment, called the "Foundry," which supports easy creation and revision of standardized data structures and will enable cloud accessible containerized models, allowing for continuous model development and data accumulation in the future.

Synergistic plasma-assisted electrochemical reduction of nitrogen to ammonia.

A nitrogen plasma was incorporated into the cathode side of an electrolyzer to provide energetically activated N2 species to the electrocatalyst surface. At an applied bias of ∼3.5 V across the electrolyzer, plasma-assisted operation was observed to produce 47% more ammonia than the combination of plasma-without-bias and bias-without-plasma conditions.

An open experimental database for exploring inorganic materials.

The use of advanced machine learning algorithms in experimental materials science is limited by the lack of sufficiently large and diverse datasets amenable to data mining. If publicly open, such data resources would also enable materials research by scientists without access to expensive experimental equipment. Here, we report on our progress towards a publicly open High Throughput Experimental Materials (HTEM) Database (htem.nrel.gov). This database currently contains 140,000 sample entries, characterized by structural (100,000), synthetic (80,000), chemical (70,000), and optoelectronic (50,000) properties of inorganic thin film materials, grouped in >4,000 sample entries across >100 materials systems; more than a half of these data are publicly available. This article shows how the HTEM database may enable scientists to explore materials by browsing web-based user interface and an application programming interface. This paper also describes a HTE approach to generating materials data, and discusses the laboratory information management system (LIMS), that underpin HTEM database. Finally, this manuscript illustrates how advanced machine learning algorithms can be adopted to materials science problems using this open data resource.