Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “knowledge discovery”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 343 records · Page 19

Isolation, enzyme-bound structure and antibacterial activity of platencin A[subscript 1] from Streptomyces platensis

Natural products continue to serve as one of the best sources for discovery of antibacterial agents as exemplified by the recent discoveries of platensimycin and platencin. Chemical modifications as well as discovery of congeners are the main sources for gaining knowledge of structure-activity relationship of natural products. Screening for congeners in the extracts of the fermentation broths of Streptomyces platensis led to the isolation of platencin A{sub 1}, a hydroxy congener of platencin. The hydroxylation of the tricyclic enone moiety negatively affected the antibacterial activity and appears to be consistent with the hydrophobic binding pocket of the FabF. Isolation, structure, enzyme-bound structure and activity of platencin A{sub 1} and two other congeners have been described.

59 BASIC BIOLOGICAL SCIENCES↗

ADIOS Visualization Schema: A First Step Towards Improving Interdisciplinary Collaboration in High Performance Computing

Scientific communities have benefitted from a significant increase of available computing and storage resources in the last few decades. For science projects that have access to leadership scale computing resources, the capacity to produce data has been growing exponentially. Teams working on such projects must now include, in addition to the traditional application scientists, experts in various disciplines including applied mathematicians for development of algorithms, visualization specialists for large data, and I/O specialists. Sharing of knowledge and data is becoming a requirement for scientific discovery, providing useful mechanisms to facilitate this sharing is a key challenge for e-Science. Our hypothesis is that in order to decrease the time to solution for application scientists we need to lower the barrier of entry into related computing fields. We aim at improving users' experience when interacting with a vast software ecosystem and/or huge amount of data, while maintaining focus on their primary research field. In this context we present our approach to bridge the gap between the application scientists and the visualization experts through a visualization schema as a first step and proof of concept for a new way to look at interdisciplinary collaboration among scientists dealing with big data. The key to our approach is recognizing that our users are scientists who mostly work as islands. They tend to work in very specialized environment but occasionally have to collaborate with other researchers in order to take full advantage of computing innovations and get insight from big data. We present an example of identifying the connecting elements between one of such relationships and offer a liaison schema to facilitate their collaboration.

Computer Science↗

Domestication in dry-cured meat Penicillium fungi: Convergent specific phenotypes and horizontal gene transfers without strong genetic subdivision

Some fungi have been domesticated for food production, with genetic differentiation between populations from food and wild environments, and food populations often acquiring beneficial traits through horizontal gene transfers (HGTs). Studying their adaptation to human-made substrates is of fundamental and applied importance for understanding adaptation processes and for further strain improvement. We studied here the population structures and phenotypes of two distantly related Penicillium species used for dry-cured meat production, P. nalgiovense, the most common species in the dry-cured meat food industry, and P. salamii, used locally by farms. Both species displayed low genetic diversity, lacking differentiation between strains isolated from dry-cured meat and those from other environments. Nevertheless, the strains collected from dry-cured meat within each species displayed slower proteolysis and lipolysis than their wild conspecifics, and those of P. nalgiovense were whiter. Phenotypically, the non-dry-cured meat strains were more similar to their sister species than to their conspecific dry-cured meat strains, indicating an evolution of specific phenotypes in dry-cured meat strains. A comparison of available Penicillium genomes from various environments revealed HGTs, particularly between P. nalgiovense and P. salamii (representing almost 1.5 Mb of cumulative length). HGTs additionally involved P. biforme, also found in dry-cured meat products. We further detected positive selection based on amino acid changes. Our findings suggest that selection by humans has shaped the P. salamii and P. nalgiovense populations used for dry-cured meat production, which constitutes domestication. Several genetic and phenotypic changes were similar in P. salamii, P. nalgiovense and P. biforme, indicating convergent adaptation to the same human-made environment. Our findings have implications for fundamental knowledge on adaptation and for the food industry: the discovery of different phenotypes and of two mating types paves the way for strain improvement by conventional breeding, to elucidate the genomic bases of beneficial phenotypes and to generate diversity.

60 APPLIED LIFE SCIENCES↗

Crown group Oxyphotobacteria postdate the rise of oxygen

Abstract The rise of oxygen ca. 2.3 billion years ago (Ga) is the most distinct environmental transition in Earth history. This event was enabled by the evolution of oxygenic photosynthesis in the ancestors of Cyanobacteria. However, long‐standing questions concern the evolutionary timing of this metabolism, with conflicting answers spanning more than one billion years. Recently, knowledge of the Cyanobacteria phylum has expanded with the discovery of non‐photosynthetic members, including a closely related sister group termed Melainabacteria, with the known oxygenic phototrophs restricted to a clade recently designated Oxyphotobacteria. By integrating genomic data from the Melainabacteria, cross‐calibrated Bayesian relaxed molecular clock analyses show that crown group Oxyphotobacteria evolved ca. 2.0 billion years ago (Ga), well after the rise of atmospheric dioxygen. We further estimate the divergence between Oxyphotobacteria and Melainabacteria ca. 2.5–2.6 Ga, which—if oxygenic photosynthesis is an evolutionary synapomorphy of the Oxyphotobacteria—marks an upper limit for the origin of oxygenic photosynthesis. Together, these results are consistent with the hypothesis that oxygenic photosynthesis evolved relatively close in time to the rise of oxygen.

Shih, P. M.↗

Metamaterials as a Platform for the Development of Novel Materials for Energy Applications

To explore the fundamental properties of metamaterials (MMs) / metasurfaces and their potential for control of energy at the sub‐wavelength scale in support of the mission of the Department of Energy and the office of Basic Energy Sciences. Electromagnetic metamaterials provide a platform for the discovery and design of new materials with novel structures, functions, and properties. The PI proposes to advance the knowledge base of these materials through fundamental investigations of the experimental and theoretical properties of metamaterials for the discovery, prediction and design of new materials with novel structures, functions, and properties. The proposed research activities emphasize a complete basic research program including the conceptual / computational design, fabrication / synthesis of the materials, and the characterization and analysis of their electromagnetic properties. The proposed project explores the fundamental properties of metamaterials / metasurfaces and their potential for energy applications. There are three main topics which will be investigated: 1) Dispersion engineering with metamaterials and metasurfaces, 2) Epsilon near zero metamaterial absorbers and emitters, and 3) All dielectric metamaterials. The program implements a complete basic research program consisting of theory / design, modeling, characterization, and analysis, in order to fully characterize metamaterials and metasurfaces, while at the same time minimizing iterations necessary to achieve the proposal goals.

36 MATERIALS SCIENCE↗

Building on the Cornerstone: Destinations for Nearside Sample Return

Discoveries from LRO (Lunar Reconnaissance Orbiter) have transformed our knowledge of the Moon, but LRO's instruments were originally designed to collect the measurements required to enable future lunar surface exploration. Compelling science questions and critical resources make the Moon a key destination for future human and robotic exploration. Lunar surface exploration, including rovers and other landed missions, must be part of a balanced planetary science and exploration portfolio. Among the highest planetary exploration priorities is the collection of new samples and their return to Earth for more comprehensive analysis than can be done in-situ. The Moon is the closest and most accessible location to address key science questions through targeted sample return. The Moon is the only other planet from which we have contextualized samples, yet critical issues need to be addressed: we lack important details of the Moon's early and recent geologic history, the full compositional and age ranges of its crust, and its bulk composition.

Lawrence, S. J.↗

Utilization of machine learning to accelerate colloidal synthesis and discovery

Machine learning techniques are seeing increased usage for predicting new materials with targeted properties. However, widespread adoption of these techniques is hindered by the relatively greater experimental efforts required to test the predictions. Furthermore, because failed synthesis pathways are rarely communicated, it is difficult to find prior datasets that are sufficient for modeling. This work presents a closed-loop machine learning-based strategy for colloidal synthesis of nanoparticles, assuming no prior knowledge of the synthetic process, in order to show that synthetic discovery can be accelerated despite limited data availability.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

High Temperature Chemistry of Aromatic Hydrocarbons. Final Technical Report

The primary goal of this research was to uncover the principal reaction channels available to polycyclic aromatic hydrocarbons (PAHs) at high temperatures in the gas phase and to establish the factors that determine which channels will be followed in varying circumstances. New structure-property relationships for PAHs were also studied. The efficient production of clean energy from fossil fuels will remain a major component of the DOE mission until alternative sources of energy eventually displace coal and petroleum. Hydrocarbons constitute the most basic class of compounds in all of organic chemistry, and as the dominant species in fossil fuels, they figure prominently into the programs of the DOE. Much is already known about the normal chemistry of hydrocarbons under ambient conditions, but far less is known about their intrinsic chemistry at temperatures close to those reached during combustion. An understanding of the fundamental molecular transformations, rearrangements, and interconversions of PAHs at high temperatures in the gas phase, as revealed by careful studies on small, well-designed, molecular systems, provides insights into the underlying chemistry of many important processes that are more complex, such as the generation of energy by the combustion of fossil fuels, the uncatalyzed gasification and liquefaction of coal, the production of fullerenes in fuel-rich flames, and the formation of soot and carcinogenic pollutants in smoke (e.g., benzo[a]pyrene). The rational control of any of these processes, whether it be the optimization of a desirable process or the minimization of an undesirable one, requires a clear knowledge of the basic chemistry that governs the fate of the species involved. Advances in chemistry at the most fundamental level come about primarily from the discovery of new reactions and from new insights into how reactions occur. Harnessing that knowledge is the key to new technologies. The recent commercialization of a combustion synthesis of C 60 and other fullerenes depended critically on a knowledge of hydrocarbon reactions at high temperatures in the gas phase, and the research supported by this project enabled further advances in the realm of carbon-rich materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

ElectroCat: DOE's approach to PGM-free catalyst and electrode R&D

The successful development of high-performance, durable platinum group metal-free (PGM-free) electrocatalysts and electrodes for polymer electrolyte membrane fuel cells (PEMFCs) will ultimately improve the cost-competiveness of fuel cells in a wide range of applications. This is considered to be a critical development especially for automotive fuel cell applications in order to bring the system cost of an automotive fuel cell system down to the $30/kW cost target set by the U.S. Department of Energy (DOE). The platinum group metal (PGM) electrocatalysts are a major contributor to the system cost. Addressing the technical challenges to PGM-free electrocatalyst and electrode development, therefore, represents one of DOE's most pressing research and development (R&D) priorities. ElectroCat was formed by the DOE as part of the Energy Materials Network (EMN) in early 2016, and shares with other EMN consortia the goal of decreasing the time to market for advanced materials related to clean energy technologies, in the context of increasing U.S. fuel cell electric vehicle (FCEV) manufacturing competitiveness. To accomplish this, the consortium performs core research and development and provides universities and companies streamlined access to the unique, world-class set of tools and expertise relevant to early-stage applied PGM-free catalyst R&D of the member national laboratories. Moreover, ElectroCat fosters a systematic methodology by which prospective catalysts and electrodes are prepared and analyzed rapidly and comprehensively using high-throughput, combinatorial methods. Catalyst discovery is augmented by theory as well as foundational electrocatalysis and materials knowledge at the participating national laboratories. Furthermore, ElectroCat has developed a data sharing framework, requisite of all EMN consortia, for disseminating its findings to the public via a searchable database, to further expedite incorporation of PGM-free electrocatalysts into next-generation fuel cells by advancing the general understanding of the PGM-free electrocatalyst field.

Thompson, Simon T.↗

Skluma: An extensible metadata extraction pipeline for disorganized data

To mitigate the effects of high-velocity data expansion and to automate the organization of filesystems and data repositories, we have developed Skluma-a system that automatically processes a target filesystem or repository, extracts content-and context-based metadata, and organizes extracted metadata for subsequent use. Skluma is able to extract diverse metadata, including aggregate values derived from embedded structured data; named entities and latent topics buried within free-text documents; and content encoded in images. Skluma implements an overarching probabilistic pipeline to extract increasingly specific metadata from files. It applies machine learning methods to determine file types, dynamically prioritizes and then executes a suite of metadata extractors, and explores contextual metadata based on relationships among files. The derived metadata, represented in JSON, describes probabilistic knowledge of each file that may be subsequently used for discovery or organization. Skluma's architecture enables it to be deployed both locally and used as an on-demand, cloud-hosted service to create and execute dynamic extraction workflows on massive numbers of files. It is modular and extensible-allowing users to contribute their own specialized metadata extractors. Thus far we have tested Skluma on local filesystems, remote FTP-accessible servers, and publicly-accessible Globus endpoints. We have demonstrated its efficacy by applying it to a scientific environmental data repository of more than 500,000 files. We show that we can extract metadata from those files with modest cloud costs in a few hours.

data swamp↗

CO2 Sensors Based on Nanocrystalline SnO2 Doped with CuO

Nanocrystalline tin oxide (SnO2) doped with copper oxide (CuO) has been found to be useful as an electrical-resistance sensory material for measuring the concentration of carbon dioxide in air. SnO2 is an n-type semiconductor that has been widely used as a sensing material for detecting such reducing gases as carbon monoxide, some of the nitrogen oxides, and hydrocarbons. Without doping, SnO2 usually does not respond to carbon dioxide and other stable gases. The discovery that the electrical resistance of CuO-doped SnO2 varies significantly with the concentration of CO2 creates opportunities for the development of relatively inexpensive CO2 sensors for detecting fires and monitoring atmospheric conditions. This discovery could also lead to research that could alter fundamental knowledge of SnO2 as a sensing material, perhaps leading to the development of SnO2-based sensing materials for measuring concentrations of oxidizing gases. Prototype CO2 sensors based on CuO-doped SnO2 have been fabricated by means of semiconductor-microfabrication and sol-gel nanomaterial-synthesis batch processes that are amendable to inexpensive implementation in mass production.

Xu, Jennifer C.↗

Charting the chemical space of Zintl phases with graph neural networks and bonding insights

A large number of Zintl phases have been discovered by solid-state chemists driven by empirical knowledge, chemical intuition and in some cases, through serendipitous accidents. These discoveries have only scratched the surface, given the vast compositional and structural diversity that Zintl phases can accommodate. The large chemical space of Zintl phases, as well as intermetallic compounds in general, remain under-explored. Here, we use graph neural networks and the upper bound energy minimization approach to efficiently scan a large chemical space of >90 000 hypothetical Zintl phases and accurately discover 1810 new thermodynamically stable phases with 90% precision, as validated with first-principles calculations. We show that our approach is more than 2× more accurate in predicting DFT stability than M3GNet (40% precision) on the same dataset. Using a random forest model and SHAP analysis, we demonstrate the critical role of ionic bonding in the thermodynamic stability of Zintl phases. Our results not only expand the known chemical landscape of Zintl phases but also highlight the efficacy of machine learning frameworks combined with domain knowledge in uncovering chemically meaningful insights across complex intermetallics.

36 MATERIALS SCIENCE↗

Enhancing NASA Earth Science Data Discovery from Scientific Publications

Earth observations from space borne instruments have evolved explosively in the past decades. Following closely are reanalysis systems assimilating model and observational data, yielding even longer records and larger number of variables. Thanks to advances in internet technology, it is now easier than ever to visualize and analyze these data using web interfaces. On the other hand, it also becomes an increasingly daunting task to build upon the existing knowledge published in various peer reviewed sources, and navigate toward the most relevant data, analysis, and visualization. We present an analysis of a subset of publications that utilized a popular visualization web interface at the NASA Goddard Earth Science Data and Information Services Center. Known as "Giovanni", it allows researchers from wide backgrounds to work with hundreds of variables from space observations and assimilation systems. Since coming online more than a decade ago, Giovanni has been credited in more than 100 papers per year, and the total count now is estimated to be nearly 1,500. Many of these papers contain valuable information about when, where and how Giovanni has been used, and hence forge an opportunity to learn and share the knowledge of which variables were used for what research projects. The purpose of our work is to retrieve the information from the papers and organize it as a knowledge repository which links together datasets, variables, places, dates and phenomena all of which reflect the essence of the published research. Since the publications are unstructured texts, we use natural language processing along with machine learning methods in the retrieval process. One of the challenges is deciphering the dataset names, because in many cases researchers refer to variables, rather than the datasets containing them. To constrain the number of terms, we deploy Earth Science ontologies as dictionaries for the term extraction. We demonstrate that storing these terms and underlying ontologies, along with datasets, variables and papers in the knowledge graph database, enables various linkages between all these entities facilitating the data discovery. Thus, we are setting a qualitatively new stage in improvements of web data interfaces, where machine learning techniques are used to establish and optimize usage-based discovery of data.

Irina V Gerasimov↗

Developing Concepts of Operations Using Multi-Step Tool Techniques With Large Language Models

The National Aeronautics and Space Administration (NASA) Air Mobility Pathfinders (AMP) project is developing and evaluating concepts of operations (ConOps) for safe, secure, and scalable Urban Air Mobility (UAM) operations. The AMP project’s Operational Concepts, Architecture, and Requirements Integration (OCARI) Team is using a Model Based System Engineering (MBSE) approach for integration, interoperability, and traceability of Advanced Air Mobility (AAM) ecosystems centered around urban air taxi services. The team’s goal is to define structures and behaviors needed for system feasibility, readiness, and interoperability, establish a UAM knowledge base, and trace and validate assumptions and requirements relevant to AAM. NASA Langley Research Center (LaRC) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of multi-modal transportation systems. The Knowledge-based Digital Platform (KbDP) is a concept being developed that ties the workflows of Project Managers (PM), Principal Investigators (PI), and System Engineers together across organizational boundaries. It does so through the management of an information database defined by mathematical, data science, and system engineering principles. Machine Learning (ML) algorithms play a key role in this concept by extracting meaningful knowledge from relational and graph databases, document repositories, and system artifacts, which the human user leverages to greatly improve the efficiency and effectiveness of their research. Recent advancements in the field of Large Language Models (LLMs), specifically models trained for tool use, such as Command-R , now allow for the reliable implementation of single-step and multi-step tool-centric systems. These techniques provide the LLM with a set of tools, in our case Python functions, that can be called on to answer a much wider range of questions compared to LLMs implemented using a traditional single-source or Retrieval Augmented Generation (RAG) approach. Through this method, the LLM can pull information from multiple data sources, such as relational or graph databases, document repositories, application programming interfaces (APIs), and SysML artifacts depending on the user’s question. The LLM can also output the information in a variety of different formats, using output generation tools, such as CSV, UML, or SysML artifacts. Additionally, tools can be assigned roles and can work together to provide answers to queries in an “agent” like approach, similar to that implemented by Microsoft’s AutoGen framework where different agents can converse with each other to accomplish tasks. Previously, our team developed a chatbot system with “agent like” functionality in the form of different “modes” the user could select from a user interface (UI), this architecture can be seen on the left in figure 1. Three different modes were implemented, the first mode allowed the LLM to utilize the structures and algorithms within a graph database to trace UAM requirements. The second mode gave the LLM access to a vector search capable of providing relevant information from thousands of document pages related to UAM ConOps and requirements. The third mode served as a general assistant where users could enter open-ended questions and custom prompts to utilize the LLM for different use-cases. This system improved the process surrounding generating and analyzing information related to UAM requirements, however, the implementation provided a clunky user experience. Users were required to know what mode to select within the UI in advance before entering their question to the selected tool. Moreover, the different tools were isolated from each other, they lacked bidirectional links that would allow for tools to collaborate to generate better responses. Our team is working on a new architecture, seen on the right in the below figure, with the goal to address many of the UX shortcomings of our original system while improving the accuracy and depth of responses from the LLM. This new system will automatically select the appropriate tool to use based off the user’s question. Each tool will be capable of calling on any of the other tools available to the LLM, resulting in a collaborative pipeline where tools can pass data between other tools until enough data is received to generate an answer to the user’s question. Using a locally deployed, open-source, LLM, the NASA OCARI team, in collaboration with Collins Aerospace, will implement a prototype application that will bridge knowledge across multiple sources to assist System Engineers (SEs) with requirements discovery and tracing, research question and use case identification, and assumption validation. Such a system will also allow SEs to more easily, and intuitively, explore the AAM ecosystem, ultimately improving the efficiency and effectiveness of the SE's research and decision-making processes surrounding ConOps development and validation. In this session, our team will provide a video demonstration of our new prototype architecture in action. We will also present an overview of our prototype system architecture and talk about its advantages over traditional LLM deployments along with how those advantages can provide additional value to the field of System Engineering.

systems engineering↗

Exploring soybean metabolic pathways based on probabilistic graphical model and knowledge-based methods

Soybean (Glycine max) is a major source of vegetable oil and protein for both animal and human consumption. The completion of soybean genome sequence led to a number of transcriptomic studies (RNA-seq), which provide a resource for gene discovery and functional analysis. Several data-driven (e.g., based on gene expression data) and knowledge-based (e.g., predictions of molecular interactions) methods have been proposed and implemented. In order to better understand gene relationships and protein interactions, we applied probabilistic graphical methods, based on Bayesian network and knowledgebase constraints using gene expression data to reconstruct soybean metabolic pathways. The results show that this method can predict new relationships between genes, improving on traditional reference pathway maps.

54 ENVIRONMENTAL SCIENCES↗

A MODERN SEARCH FOR WOLF–RAYET STARS IN THE MAGELLANIC CLOUDS. II. A SECOND YEAR OF DISCOVERIES

The numbers and types of evolved massive stars found in nearby galaxies provide an exacting test of stellar evolution models. Because of their proximity and rich massive star populations, the Magellanic Clouds have long served as the linchpins for such studies. Yet the continued accidental discoveries of Wolf–Rayet (WR) stars in these systems demonstrate that our knowledge is not as complete as usually assumed. Therefore, we undertook a multi-year survey for WRs in the Magellanic Clouds. Our results from our first year (reported previously) confirmed nine new LMC WRs. Of these, six were of a type never before recognized, with WN3-type emission combined with O3-type absorption features. Yet these stars are 2–3 mag too faint to be WN3+O3 V binaries. Here we report on the second year of our survey, including the discovery of four more WRs, two of which are also WN3/O3s, plus two “slash” WRs. This brings the total of known LMC WRs to 152, 13 (8.2%) of which were found by our survey, which is now ∼60% complete. We find that the spatial distribution of the WN3/O3s is similar to that of other WRs in the LMC, suggesting that they are descended from the same progenitors. We call attention to the fact that 5 of the 12 known SMC WRs may in fact be similar WN3/O3s rather than the binaries they have often assumed to be. We also discuss our other discoveries: a newly discovered Onfp-type star, and a peculiar emission-line object. Finally, we consider the completeness limits of our survey.

79 ASTRONOMY AND ASTROPHYSICS↗

Bayesian Active Learning for Scanning Probe Microscopy: From Gaussian Processes to Hypothesis Learning

Recent progress in machine learning methods and the emerging availability of programmable interfaces for scanning probe microscopes (SPMs) have propelled automated and autonomous microscopies to the forefront of attention of the scientific community. However, enabling automated microscopy requires the development of task-specific machine learning methods, understanding the interplay between physics discovery and machine learning, and fully defined discovery workflows. This, in turn, requires balancing the physical intuition and prior knowledge of the domain scientist with rewards that define experimental goals and machine learning algorithms that can translate these to specific experimental protocols. Here, we discuss the basic principles of Bayesian active learning and illustrate its applications for SPM. We progress from the Gaussian process as a simple data-driven method and Bayesian inference for physical models as an extension of physics-based functional fits to more complex deep kernel learning methods, structured Gaussian processes, and hypothesis learning. These frameworks allow for the use of prior data, the discovery of specific functionalities as encoded in spectral data, and exploration of physical laws manifesting during the experiment. Here, the discussed framework can be universally applied to all techniques combining imaging and spectroscopy, SPM methods, nanoindentation, electron microscopy and spectroscopy, and chemical imaging methods and can be particularly impactful for destructive or irreversible measurements.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

AtomSets as a hierarchical transfer learning framework for small and large materials datasets

Abstract Predicting properties from a material’s composition or structure is of great interest for materials design. Deep learning has recently garnered considerable interest in materials predictive tasks with low model errors when dealing with large materials data. However, deep learning models suffer in the small data regime that is common in materials science. Here we develop the AtomSets framework, which utilizes universal compositional and structural descriptors extracted from pre-trained graph network deep learning models with standard multi-layer perceptrons to achieve consistently high model accuracy for both small compositional data (<400) and large structural data (>130,000). The AtomSets models show lower errors than the graph network models at small data limits and other non-deep-learning models at large data limits. They also transfer better in a simulated materials discovery process where the targeted materials have property values out of the training data limits. The models require minimal domain knowledge inputs and are free from feature engineering. The presented AtomSets model framework can potentially accelerate machine learning-assisted materials design and discovery with less data restriction.

Chen, Chi (ORCID:0000000180087043)↗