Search NASA⌕ Search

Engineering topics

Dunn, Alexander

Publications and source records attributed to Dunn, Alexander.

Structured information extraction from scientific text with large language models

Extracting structured knowledge from scientific text remains a challenging task for machine learning models. Here, we present a simple approach to joint named entity recognition and relation extraction and demonstrate how pretrained large language models (GPT-3, Llama-2) can be fine-tuned to extract useful records of complex scientific knowledge. We test three representative tasks in materials chemistry: linking dopants and host materials, cataloging metal-organic frameworks, and general composition/phase/morphology/application information extraction. Records are extracted from single sentences or entire paragraphs, and the output can be returned as simple English sentences or a more structured format such as a list of JSON objects. This approach represents a simple, accessible, and highly flexible route to obtaining large databases of structured specialized scientific knowledge extracted from research papers.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Gapped metals as thermoelectric materials revealed by high-throughput screening

The typical strategy to design high performance thermoelectric materials is to dope a semiconducting material until optimal properties are obtained. However, some known thermoelectric materials such as La 3 Te 4 , Mo 3 Sb 7 , Yb 14 MnSb 11 , and NbCoSb are actually gapped metals,i.e., their band structure displays a gap slightly above or below the band crossed by the Fermi level. This key feature makes these metals comparable to degenerate semiconductors and thus suitable for thermoelectric applications. In this work, we perform a computational high-throughput search for such gapped metals exhibiting attractive thermoelectric properties. Several thousands of metals are found to present this key feature, and about one thousand of them show decent thermoelectric properties as evaluated by a computed zT. We present the different chemistry of gapped metals we discovered such as clathrates, Chevrel phases, or transition metal dichalcogenides and discuss their previous studies as thermoelectric and their potential as new thermoelectric materials.

36 MATERIALS SCIENCE↗

Machine Learning Chemical Guidelines for Engineering Electronic Structures in Half-Heusler Thermoelectric Materials

Half-Heusler materials are strong candidates for thermoelectric applications due to their high weighted mobilities and power factors, which is known to be correlated to valley degeneracy in the electronic band structure. However, there are over 50 known semiconducting half-Heusler phases, and it is not clear how the chemical composition affects the electronic structure. While all the n-type electronic structures have their conduction band minimum at either the Γ - or X -point, there is more diversity in the p-type electronic structures, and the valence band maximum can be at either the Γ -, L -, or W -point. Here, we use high throughput computation and machine learning to compare the valence bands of known half-Heusler compounds and discover new chemical guidelines for promoting the highly degenerate W -point to the valence band maximum. We do this by constructing an “orbital phase diagram” to cluster the variety of electronic structures expressed by these phases into groups, based on the atomic orbitals that contribute most to their valence bands. Then, with the aid of machine learning, we develop new chemical rules that predict the location of the valence band maximum in each of the phases. These rules can be used to engineer band structures with band convergence and high valley degeneracy.

36 MATERIALS SCIENCE↗

Unsupervised word embeddings capture latent knowledge from materials science literature

The overwhelming majority of scientific knowledge is published as text, which is difficult to analyse by either traditional statistical analysis or modern machine learning methods. By contrast, the main source of machine-interpretable data for the materials research community has come from structured property databases, which encompass only a small fraction of the knowledge present in the research literature. Beyond property values, publications contain valuable knowledge regarding the connections and relationships between data items as interpreted by the authors. To improve the identification and use of this knowledge, several studies have focused on the retrieval of information from scientific literature using supervised natural language processing, which requires large hand-labelled datasets for training. Here we show that materials science knowledge present in the published literature can be efficiently encoded as information-dense word embeddings (vector representations of words) without human labelling or supervision. Without any explicit insertion of chemical knowledge, these embeddings capture complex materials science concepts such as the underlying structure of the periodic table and structure-property relationships in materials. Furthermore, we demonstrate that an unsupervised method can recommend materials for functional applications several years before their discovery. This suggests that latent knowledge regarding future discoveries is to a large extent embedded in past publications. Lastly, our findings highlight the possibility of extracting knowledge and relationships from the massive body of scientific literature in a collective manner, and point towards a generalized approach to the mining of scientific literature.

36 MATERIALS SCIENCE↗

MISSE-11 Ground Experiment Control

Back during the Apollo missions, when astronauts were being sent to the moon to explore and further scientific knowledge by conducting experiments and collecting samples for scientists back on Earth, they were faced with a surprising problem. It was discovered that the moon’s surface is covered with dust that has electrostatic properties, which would stick to suit and equipment. This hindered the functionality of the astronauts’ space suits, solar panels, optical instruments, among other exposed surfaces due to the jagged geometry of the dust which would damage said equipment. To resolve this issue, the Electrostatics and Surface Physics Laboratory (ESPL) came up with the solution of using an Electrodynamic Dust Shield (EDS)1 that uses electrostatic forces to move particles across a surface. Varieties of this dust shield have been developed for different applications. The purpose of the Materials International Space Station Experiments 11 (MISSE-11) is to experiment a payload that contains the dust mitigation technology to be flown to space for one year and an identical payload will be on earth, under vacuum, in the Electrostatics and Surface Physics Laboratory. The space payload was prepared prior to our arrival and shipped to fly on the International Space Station (ISS). The payload staying on the ground is going to act as a control for the experiment so that we may compare it to the payload that was flown in space. During our time at Kennedy Space Center, we were tasked with building and start testing the ground control unit of the MISSE-11 payload. To complete our task for the ground control unit, we constructed a new vacuum chamber setup and added automated aspects, procured the necessary flight electronics, designed and communicated for the machining of the payload frame, and performed functional and thermal testing on the electronics to the same original operational standards. Some modifications were made where possible, without affecting the performance of the samples, to be efficient with the production of the control unit while keeping important aspects identical. The experiment is now nearly complete, and testing will be starting within the next few weeks.

MISSE↗

Matminer: An open source toolkit for materials data mining

As materials data sets grow in size and scope, the role of data mining and statistical learning methods to analyze these materials data sets and build predictive models is becoming more important. This manuscript introduces matminer, an open-source, Python-based software platform to facilitate data-driven methods of analyzing and predicting materials properties. Matminer provides modules for retrieving large data sets from external databases such as the Materials Project, Citrination, Materials Data Facility, and Materials Platform for Data Science. It also provides implementations for an extensive library of feature extraction routines developed by the materials community, with 47 featurization classes that can generate thousands of individual descriptors and combine them into mathematical functions. Finally, matminer provides a visualization module for producing interactive, shareable plots. These functions are designed in a way that integrates closely with machine learning and data analysis packages already developed and in use by the Python data science community. We explain the structure and logic of matminer, provide a description of its various modules, and showcase several examples of how matminer can be used to collect data, reproduce data mining studies reported in the literature, and test new methodologies.

97 MATHEMATICS AND COMPUTING↗