SEARCH · Engineering Papers

Results for “Structured Natural Language”

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.

SourceResearch connectionFrom yearThrough year

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

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2013

PACE: Pattern Accurate Computationally Efficient Bootstrapping for Timely Discovery of Cyber-Security Concepts

Public disclosure of important security information, such as knowledge of vulnerabilities or exploits, often occurs in blogs, tweets, mailing lists, and other online sources significantly before proper classification into structured databases. In order to facilitate timely discovery of such knowledge, we propose a novel semi-supervised learning algorithm, PACE, for identifying and classifying relevant entities in text sources. The main contribution of this paper is an enhancement of the traditional bootstrapping method for entity extraction by employing a time-memory trade-off that simultaneously circumvents a costly corpus search while strengthening pattern nomination, which should increase accuracy. An implementation in the cyber-security domain is discussed as well as challenges to Natural Language Processing imposed by the security domain.

Bootstrapping↗

DOE OSTI2018

Predicting Foreign Language Usage from English-Only Social Media Posts

Social media is known for its multicultural and multilingual interactions, a natural product of which is code-mixing. Multilingual speakers mix languages they tweet to address a different audience, express certain feelings, or attract attention. This paper presents a large-scale analysis of 6 million tweets produced by 23 thousand multilingual users speaking 11 other languages besides English. We rely on this multilingual corpus to build predictive models for a novel task – inferring non- English languages that users speak exclusively from their English tweets. We contrast the predictive power of different linguistic signals and report that lexical content and syntactic structure of English tweets are the most predictive of non-English languages that users speak on Twitter. By analyzing cross-lingual transfer – the influence of non-English languages on various levels of linguistic performance in English, we present novel findings on stylistic and syntactic variations across speakers of 11 languages.

code-swicthing↗

DOE OSTI2024

From Data to Knowledge: A Graph-Based Reliability Approach to Assess System Health

With the goal of maximizing plant reliability and availability, complex systems such as nuclear power plants continuously monitor and record the performance and the health status of many components, assets, and systems. Such data may take the form of online monitoring data, condition reports, and maintenance reports and it carries the potential to provide system engineers with insights into anomalous behaviors or degradation trends as well as the possible causes behind them and to predict their direct consequences. The analysis of such data poses however few challenges. While some of these challenges are technical in nature (i.e., data are often distributed over several physical servers or databases), others are conceptual in nature (i.e., data elements come in different formats, numeric or textual), and measured values have different scales (e.g., vibration spectra and oil temperature). This paper directly tackles these challenges, and it focuses on the integration of all these data elements in order to assist plant system engineers in analyzing component, assets, and systems performances and optimize maintenance activities. This is performed by 1) extracting knowledge from textual data via technical language processing methods, and 2) quantifying system, asset, and component health from numeric condition-based data. We rely on model-based system engineering (MBSE) models of systems and assets to identify their architecture and functional (i.e., cause and effect) relations. Numeric and textual data elements are then associated with an MBSE graph element, based on their nature. This bonding of MBSE models and data elements constitutes a first-of-its-kind knowledge graph of a nuclear power plants system, with data elements being organized in a structured manner that enables system engineers to identify cause-effect trends in data elements and carry out appropriate actions in response.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

SHAPER: can you hear the shape of a jet?

The identification of interesting substructures within jets is an important tool for searching for new physics and probing the Standard Model at colliders. Many of these substructure tools have previously been shown to take the form of optimal transport problems, in particular the Energy Mover’s Distance (EMD). In this work, we show that the EMD is in fact the natural structure for comparing collider events, which accounts for its recent success in understanding event and jet substructure. We then present a Shape Hunting Algorithm using Parameterized Energy Reconstruction (SHAPER), which is a general framework for defining and computing shape-based observables. SHAPER generalizes N-jettiness from point clusters to any extended, parametrizable shape. This is accomplished by efficiently minimizing the EMD between events and parameterized manifolds of energy flows representing idealized shapes, implemented using the dual-potential Sinkhorn approximation of the Wasserstein metric. We show how the geometric language of observables as manifolds can be used to define novel observables with built-in infrared-and-collinear safety. We demonstrate the efficacy of the SHAPER framework by performing empirical jet substructure studies using several examples of new shape-based observables.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2026

Sequence-based generative AI design of versatile tryptophan synthases

Enzymes are powerful and sustainable catalysts, but their widespread application is limited by the difficulty of identifying functional starting points for optimization, creating a major bottleneck in early- stage biocatalyst discovery. Designing libraries of such starting enzymes remains particularly challenging. Here, we use the GenSLM protein language model to generate novel β-subunit of tryptophan synthase (TrpB) enzymes that express in Escherichia coli and are both stable and catalytically active. Many generated TrpBs also display significant substrate promiscuity, outperforming their natural counterparts on non-native substrates. Some even surpass laboratory-evolved TrpBs. Comparison of the most-active and most-promiscuous generated TrpB to its closest natural homolog confirms that the enhanced versatility is absent from the natural enzyme, highlighting the creative potential of generative models. These results demonstrate that the generated TrpBs not only preserve natural structure and function but also acquire non-natural properties, establishing generative models as powerful tools for biocatalyst discovery and engineering.

biocatalysis↗

DOE OSTI2018

Tensor networks, p -adic fields, and algebraic curves: arithmetic and the AdS 3 /CFT 2 correspondence

One of the many remarkable properties of conformal field theory in two dimensions is its connection to algebraic geometry. Since every compact Riemann surface is a projective algebraic curve, many constructions of interest in physics (which a priori depend on the analytic structure of the spacetime) can be formulated in purely algebraic language. This opens the door to interesting generalizations, obtained by taking another choice of field: for instance, the p-adics. Herein, we generalize the $\mathrm{AdS} / \mathrm{CFT}$ correspondence according to this principle; the result is a formulation of holography in which the bulk geometry is discrete—the Bruhat–Tits tree for $\mathrm{PGL} (2, \mathbb{Q}_p)$—but the group of bulk isometries nonetheless agrees with that of boundary conformal transformations and is not broken by discretization. We anticipate that this forms the natural geometric setting for tensor networks that have been proposed as models of bulk reconstruction via quantum error correcting codes; in certain cases, geodesics in the Bruhat–Tits tree reproduce those constructed using quantum error correction. Other aspects of holography also hold: Standard holographic results for massive free scalar fields in a fixed background carry over to the tree, whose vertical direction can be interpreted as a renormalization-group scale for modes in the boundary $\mathrm{CFT}$. Higher-genus bulk geometries (the $\mathrm{BTZ}$ black hole and its generalizations) can be understood straightforwardly in our setting, and the Ryu–Takayanagi formula for the entanglement entropy appears naturally

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

A Model Based Approach to Extract Health Information from Textual Data

In current nuclear power plants (NPPs) a large amount of condition-based data is being generated and stored to assess and monitor component health and performance. The format of this data can be either numeric (e.g., pump vibration data) or textual (e.g., condition report which assess component health). While assessing component health from numeric data can be performed with a large variety of methods, the extraction of information from textual data still remains a challenge. Natural language processing (NLP) methods are starting to be deployed in current NPPs mainly to filter out incident reports (IRs) that are not safety related by employing supervised machine learning methods. However, these methods do not really provide the quantitative information that might be contained in IRs. This paper presents an approach to extract information from textual data (e.g., from IRs, maintenance reports) that is based on NLP data analytics methods coupled with model-based system engineer (MBSE) models. NLP methods are employed to perform syntactic and semantic analyses. Syntactic analysis analyzes the grammatical structure of a sentence; such analysis includes: part of speech (POS) tagging (i.e., identification of grammatic elements of each string - e.g., nouns, verbs), named entity recognition (i.e., identification of text entities - e.g., names, dates, events), and relation extraction (e.g., coreference resolution). On the other hand, semantic analysis is designed to analyze the logic structure of a sentence. Through a specific set of rules, our methods can identify whether a sentence contains health information of a component (e.g., degraded performance, anomaly behavior) or the causal relationship between two events (i.e., a cause-effect pair). An innovative element of our approach is that semantic analysis relies on MBSE models to identify links between textual elements. MBSE are diagrams designed to represent system and component dependencies (from both a form and functional point of view). In our approach, MBSE models emulate system engineer knowledge about component/system architecture. This paper presents in detail how the integration of NLP methods and MBSE models is performed. Few analysis examples focusing on centrifugal pumps are presented.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2022

PDFDataExtractor: A Tool for Reading Scientific Text and Interpreting Metadata from the Typeset Literature in the Portable Document Format

The layout of portable document format (PDF) files is constant to any screen, and the metadata therein are latent, compared to mark-up languages such as HTML and XML. No semantic tags are usually provided, and a PDF file is not designed to be edited or its data interpreted by software. However, data held in PDF files need to be extracted in order to comply with opensource data requirements that are now government-regulated. In the chemical domain, related chemical and property data also need to be found, and their correlations need to be exploited to enable data science in areas such as data-driven materials discovery. Such relationships may be realized using text-mining software such as the “chemistry-aware” natural-language-processing tool, ChemDataExtractor; however, this tool has limited data-extraction capabilities from PDF files. This study presents the PDFDataExtractor tool, which can act as a plug-in to ChemDataExtractor. It outperforms other PDF-extraction tools for the chemical literature by coupling its functionalities to the chemical-named entityrecognition capabilities of ChemDataExtractor. The intrinsic PDF-reading abilities of ChemDataExtractor are much improved. The system features a template-based architecture. This enables semantic information to be extracted from the PDF files of scientific articles in order to reconstruct the logical structure of articles. While other existing PDF-extracting tools focus on quantity mining, this template-based system is more focused on quality mining on different layouts. PDFDataExtractor outputs information in JSON and plain text, including the metadata of a PDF file, such as paper title, authors, affiliation, email, abstract, keywords, journal, year, document object identifier (DOI), reference, and issue number. With a self-created evaluation article set, PDFDataExtractor achieved promising precision for all key assessed metadata areas of the document text.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

TransPolymer: a Transformer-based language model for polymer property predictions

Accurate and efficient prediction of polymer properties is of great significance in polymer design. Conventionally, expensive and time-consuming experiments or simulations are required to evaluate polymer functions. Recently, Transformer models, equipped with self-attention mechanisms, have exhibited superior performance in natural language processing. However, such methods have not been investigated in polymer sciences. Herein, we report TransPolymer, a Transformer-based language model for polymer property prediction. Our proposed polymer tokenizer with chemical awareness enables learning representations from polymer sequences. Rigorous experiments on ten polymer property prediction benchmarks demonstrate the superior performance of TransPolymer. Moreover, we show that TransPolymer benefits from pretraining on large unlabeled dataset via Masked Language Modeling. Experimental results further manifest the important role of self-attention in modeling polymer sequences. We highlight this model as a promising computational tool for promoting rational polymer design and understanding structure-property relationships from a data science view.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Understanding Event Trajectories Across Massive Temporal Datasets with Word Embeddings and Visualization

In collaboration with researchers from Virginia Tech, Savannah River National Laboratory has continued development of a natural language processing pipeline to identify and extract events of interest from massive open data sources in the domain of worldwide state-sponsored civil nuclear energy. The foundation of the pipeline is built on compass aligned temporal word embedding models, whereby contextual shifts are automatically identified by comparing keyword embedding vectors across successive time windows. Within the approach, a contextual shift indicates the occurrence of a potential event of interest. However, in such a broad topical domain that captures events at a global scale, across various life cycle stages, and across numerous different technology types, a user that is monitoring events may have broad interests in capturing many different event types with varying degrees of signal. As such, the quantity of information that may be returned from an automated event extraction pipeline can be substantial, requiring manual effort to sift through the information to identify any relevant bits of information. Therefore, a more streamlined workflow that aids in directing a user toward specific information at different points in time is necessary. The workflow presented here has been developed with this concept in mind, built on top of the initial prototype event extraction pipeline, whereby a user can analyze temporal text-based data sources at multiple different contextual levels to isolate key points in time and key subdomains captured within a data corpus. Using multiple corpuses that consist of approximately 7 million Tweets and 7 million news articles, the team has extended compass aligned temporal word embedding models to establish an interconnected and hierarchical structure that relates known key words of interest to documents, local topics (i.e., within a time window), and global topics across the corpuses. All of this information is packaged into a visual analytics system that is linked to the information extraction pipeline and enables a user to identify contextual information that describes the evolution of a high dimensional embedding space across time to isolate changes of interest and explore associated events. This report demonstrates the use of these analytics and a means to fuse information across multiple datasets.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Emulator-Based Bayesian Calibration of the CISNET Colorectal Cancer Models

Purpose To calibrate Cancer Intervention and Surveillance Modeling Network (CISNET)'s SimCRC, MISCAN-Colon, and CRC-SPIN simulation models of the natural history colorectal cancer (CRC) with an emulator-based Bayesian algorithm and internally validate the model-predicted outcomes to calibration targets.Methods We used Latin hypercube sampling to sample up to 50,000 parameter sets for each CISNET-CRC model and generated the corresponding outputs. We trained multilayer perceptron artificial neural networks (ANNs) as emulators using the input and output samples for each CISNET-CRC model. We selected ANN structures with corresponding hyperparameters (i.e., number of hidden layers, nodes, activation functions, epochs, and optimizer) that minimize the predicted mean square error on the validation sample. We implemented the ANN emulators in a probabilistic programming language and calibrated the input parameters with Hamiltonian Monte Carlo-based algorithms to obtain the joint posterior distributions of the CISNET-CRC models' parameters. We internally validated each calibrated emulator by comparing the model-predicted posterior outputs against the calibration targets.Results The optimal ANN for SimCRC had 4 hidden layers and 360 hidden nodes, MISCAN-Colon had 4 hidden layers and 114 hidden nodes, and CRC-SPIN had 1 hidden layer and 140 hidden nodes. The total time for training and calibrating the emulators was 7.3, 4.0, and 0.66 h for SimCRC, MISCAN-Colon, and CRC-SPIN, respectively. The mean of the model-predicted outputs fell within the 95% confidence intervals of the calibration targets in 98 of 110 for SimCRC, 65 of 93 for MISCAN, and 31 of 41 targets for CRC-SPIN.Conclusions Using ANN emulators is a practical solution to reduce the computational burden and complexity for Bayesian calibration of individual-level simulation models used for policy analysis, such as the CISNET CRC models. In this work, we present a step-by-step guide to constructing emulators for calibrating 3 realistic CRC individual-level models using a Bayesian approach.

artificial neural networks↗

DOE OSTI2020

Polarization and Vorticity in the Quark–Gluon Plasma

The quark–gluon plasma (QGP) produced by collisions between ultrarelativistic heavy nuclei is well described in the language of hydrodynamics. Noncentral collisions are characterized by very large angular momentum, which in a fluid system manifests as flow vorticity. This rotational structure can lead to a spin polarization of the hadrons that eventually emerge from the plasma, and thus these collisions provide experimental access to flow substructure at unprecedented detail. Recently, the first observations of Λ hyperon polarization along the direction of collisional angular momentum were reported. These measurements are in broad agreement with hydrodynamic and transport-based calculations and reveal that the QGP is the most vortical fluid ever observed. However, there remain important tensions between theory and observation that might be fundamental in nature. In the relatively mature field of heavy-ion physics, the discovery of global hyperon polarization and 3D simulations of the collision have opened an entirely new direction of research. We discuss the current status of this rapidly developing area and directions for future research.

heavy-ion collisions↗

DOE OSTI2023

The Design and Implementation of a Secure Datastore Based on Ethereum Smart Contract

In this paper, we present a secure datastore based on an Ethereum smart contract. Our research is guided by three research questions. First, we will explore to what extend a smart-contract-based datastore should resemble a traditional database system. Second, we will investigate how to store the data in a smart-contract-based datastore for maximum flexibility while minimizing the gas consumption. Third, we seek answers regarding whether or not a smart-contract-based datastore should incorporate complex processing such as data encryption and data analytic algorithms. The proposed smart-contract-based datastore aims to strike a good balance between several constraints: (1) smart contracts are publicly visible, which may create a confidentiality concern for the data stored in the datastore; (2) unlike traditional database systems, the Ethereum smart contract programming language (i.e., Solidity) offers very limited data structures for data management; (3) all operations that mutate the blockchain state would incur financial costs and the developers for smart contracts must make sure sufficient gas is provisioned for every smart contract call, and ideally, the gas consumption should be minimized. Our investigation shows that although it is essential for a smart-contract-based datastore to offer some basic data query functionality, it is impractical to offer query flexibility that resembles that of a traditional database system. Furthermore, we propose that data should be structured as tag-value pairs, where the tag serves as a non-unique key that describes the nature of the value. We also conclude that complex processing should not be allowed in the smart contract due to the financial burden and security concerns. The tag-based secure datastore designed this way also defines its applicative perimeter, i.e., only applications that align with our strategy would find the proposed datastore a good fit. Those that would rather incur higher financial cost for more data query flexibility and/or less user burden on data pre- and post-processing would find the proposed database too restrictive.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2021

QLiG: Query Like a Graph For Subgraph Matching

A graph is a natural and flexible modeling approach to represent entities and relationships between them in real-world. A Knowledge Graphs (KG) is a specialized graph with formal and structured representation of facts, relationships, annotated with semantic descriptions. Subgraph matching is one of the fundamental graph problems to identify relationships, interactions and activities of interest within a large graph. A query specification is a collection of abstract components, operations, and constraints to express a pattern. The specification can be implemented in different ways based on underlying data model. Various graph query specifications have been developed over the years and have led to the development of different open-sourced and vendor-specific query languages. Such specification are modeled as an extension of relational algebra used to develop relational query languages such as SQL. Such relational concepts do not inherently support graph queries. There is a need to represent graph queries in terms on graph-based components to expedite query construction by non-database experts. We present a graph-based query approach QLiG (pronounced cleeg), to perform subgraph matching in Labeled Property Graph. We present the query specifications, salient features, and a use case to show functional examples.

Purohit, Sumit↗

DOE OSTI2025

From Machine Learning to Machine Reasoning: A Model-based Approach to Analyze Equipment Reliability Data

In current nuclear power plants (NPPs) a large amount of condition-based data which can be used to assess and monitor component health and performance. Assessing component health from such data can be performed with a large variety of methods. While the analysis of numeric data can be performed with several methods, the extraction of information from textual data remains a challenge. Currently employed natural language processing (NLP) methods do not really provide quantitative information that might be contained in IRs. In addition, the integration of numeric and textual data to identify possible causal relationships between data elements is still an unresolved challenge. This paper presents an approach to extract information from textual (e.g., incident or maintenance reports) and numeric data that relies on model based system engineer (MBSE) models. MBSE are diagrams designed to represent system and component dependencies (from both a form and functional point of view). In our approach, MBSE models emulate system engineer knowledge about component/system architecture. NLP methods are employed to perform syntactic and semantic analyses. Syntactic analysis analyzes the grammatical structure of a sentence while semantic analysis is designed to analyze the logic structure of a sentence. An innovative element of our approach is that semantic analysis uses MBSE models to identify links between textual elements. Similarly, numeric data is directly linked to elements of the MBSE models in order to map which functions are being monitored.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2026

A fractional calculus framework for open quantum dynamics: From Liouville to Lindblad to memory kernels

Open quantum systems exhibit dynamics ranging from unitary evolution to irreversible dissipation. While the Gorini–Kossakowski–Sudarshan–Lindblad equation uniquely characterizes Markovian completely positive and trace-preserving (CPTP) evolution, many physical platforms display non-Markovian features such as algebraic relaxation and coherence backflow. Fractional calculus provides a natural way to model such long-memory behavior through power-law temporal kernels introduced by fractional time derivatives. Here, we develop a unified framework that embeds fractional master equations within the broader hierarchy of open-system formalisms. The fractional equation forms a structured subclass of memory-kernel models, reduces to the Lindblad form at unit order, and, through Bochner–Phillips subordination, admits a CPTP representation as an average over Lindblad semigroups. Its resolvent structure further connects fractional dynamics to established non-Markovian approaches, including Nakajima–Zwanzig kernels and hierarchical equations of motion, providing a compact surrogate for long-memory effects. This formulation positions fractional calculus as a rigorous and practical language for modeling non-Markovian quantum dynamics in chemical physics and physical chemistry, providing a CPTP-preserving, computationally efficient surrogate for structured condensed-phase environments where long-time memory and dissipation play a central role.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2017

Characterizing the Benefits of Seismic Isolation of Nuclear Structures in Terms of Reduced Risk and Cost

Seismic isolation is a mature technology that has been implemented in many civil structures, including buildings, bridges, liquid natural gas tanks, and off shore oil platforms, both in the United States and other countries, to mitigate the damaging effects of earthquakes. Seismic isolation has also been used in nuclear structures in France and South Africa, but not yet in the United States: neither in the Department of Energy facilities nor in commercial nuclear power plants (NPPs). This is primarily due to a lack of guidelines, codes and standards for the analysis, design and construction specific to seismically isolated nuclear structures. However, seismic isolation of nuclear structures has seen increased research interest in the recent years and the recently published national consensus standard, America Society of Civil Engineers (ASCE) Standard 4-16 'Seismic analysis of safety related nuclear structures', now incorporates language and commentary (Chapter 12) for seismically isolating surface or near-surface-mounted nuclear facilities, including NPPs. Seismic isolation substantially reduces horizontal seismic loads (demands) on structures, systems, and components. Reduction in demand results in four potential benefits: (1) economic: reduction in capital cost, (2) increased safety: reduction in the mean annual frequency of unacceptable performance, (3) insurance: protection against increases in the known seismic hazard after construction by minimizing the effort to re-qualify and re-certify structures, systems and components, and (4) recertification: the opportunity to certify an existing NPP design for a region of higher seismic hazard. Item (2) above, an increase in safety (reduction of seismic risk), was explored in Huang et al., wherein it was demonstrated that the implementation of seismic isolation reduced seismic risk in nuclear power plant structures. Studies that assess item (1) have not been performed although the use of isolation may lead to large reductions in the capital cost of safety-related nuclear facilities. Funding provided by Nuclear Safety Research and Development in the Department of Energy (DOE) allowed the authors to develop a framework for assessing the economic benefits and reductions in seismic risk afforded by the use of seismic (base) isolation. The framework includes probabilistic risk assessment and estimation of overnight capital costs (OCC's) of a sample generic DOE nuclear facility (GDNF). The project is documented in detail in Bolisetti et al. and Yu et al., and key results are presented here. The GDNF considered in this study is based on a facility constructed at the Idaho National Laboratory. The GDNF is a two-story reinforced concrete building with an embedded basemat and is founded on soft rock at the boundary of Site Class B and Site Class C (B/C boundary) as characterized by ASCE/SEI Standard 7. The GDNF is assumed to handle radiological materials, and its structure, systems and components (SSC's) are designed to effectively confine these materials in the event of an internal failure. The GDNF is populated with components that are generic to safety-related nuclear structures. A single system, which is intended to confine a loss of materials-at-risk (MAR) to the interior of the structure, is chosen for this study. Accordingly, a hypothetical event tree and fault tree are assumed for risk assessment. The isolation system for the GDNF is designed per Chapter 12 of ASCE/SEI 4-16 but is not optimized. The isolation system consists of 38 lead rubber bearings installed in one horizontal plane below the basemat. Details of the GDNF, including the SSC's, event tree and fault tree, and isolation system, are presented in the project report and Yu et al.. This study includes seismic risk assessment and cost estimation for four cases: (1) the GDNF is located at a site of low to moderate seismic hazard and is constructed on a conventional (non-isolated) foundation; (2) the GDNF is located at the same site as case 1, but is seismically isolated; (3) the GDNF is located at a site of high seismic hazard and is constructed on a conventional foundation; and (4) the GDNF is located at the same site of high seismic hazard as case 3, but is seismically isolated. In this study, the DOE site at Idaho National Laboratory (INL) is chosen as the low to moderate seismic hazard site for cases 1 and 2, and the Los Alamos National Laboratory (LANL) is chosen as the high seismic hazard site for cases 3 and 4.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

Causal discovery from data assisted by large language models

Knowledge-driven discovery of novel materials necessitates the development of causal models for property emergence. While in the classical physical paradigm, the causal relationships are deduced based on physical principles or via experiment, the rapid accumulation of observational data necessitates learning causal relationships between dissimilar aspects of material structure and functionalities based on observations. For this, it is essential to integrate experimental data with prior domain knowledge. Here, we demonstrate this approach by combining high-resolution scanning transmission electron microscopy data with insights derived from large language models (LLMs). By applying ChatGPT to domain-specific literature, such as arXiv papers on ferroelectrics, and combining the obtained information with data-driven causal discovery, we construct adjacency matrices for directed acyclic graphs that map the causal relationships between structural, chemical, and polarization degrees of freedom in Sm-doped BiFeO 3 . This approach enables us to hypothesize how synthesis conditions influence material properties and guides experimental validation. Furthermore, the ultimate objective of this work is to develop a unified framework that integrates LLM-driven literature analysis with data-driven discovery, facilitating the precise engineering of ferroelectric materials by establishing clear connections between synthesis conditions and their resulting material properties.

Causal inference↗