Search NASA⌕ Search

SEARCH · Search NASA

Results for “representation learning”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Comparison of Machine Learning Approaches for Prediction of the Equivalent Alkane Carbon Number for Microemulsions Based on Molecular Properties

The chemical properties of oils are vital in the design of microemulsion systems. The hydrophilic–lipophilic difference equation used to predict microemulsions’ phase behavior expresses the oils’ physiochemical properties as the equivalent alkane carbon number (EACN). The experimental determination of EACN requires knowledge of the temperature dependence of the microemulsion system and the effects of different surfactant concentrations. Thus, the experimental determination is time-intensive and tedious, requiring days to months for proper separations. Furthermore, the experiments require high purity of chemicals because microemulsions are sensitive to impurities. Our work focuses on the quick and reliable predictions of the EACN with machine learning (ML) models. Due to the immaturity of ML chemical predictions, we compare three graph neural networks (GNNs) and a gradient-boosted tree algorithm, known as XGBoost. The GNNs use the molecular structures represented as simplified molecular-input line-entry system (SMILES) codes for the initial input, which allows us to assess whether geometry optimization is necessary for reliable results. The XGBoost model also begins with the SMILES representations of the molecules but uses molecular descriptors instead of geometry optimizations. As a result, the best model tested (crystal graph convolutional neural network with Merck molecular force field-94) has an error of 1.15 EACN units of the true EACN for unknown data with the errors skewed toward zero and an R² score of 0.9

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Transforming the bootstrap: using Transformers to compute scattering amplitudes in planar N = 4 Super Yang-Mills theory

Abstract We pursue the use of deep learning methods to improve state-of-the-art computations in theoretical high-energy physics. Planar N = 4 Super Yang-Mills theory is a close cousin to the theory that describes Higgs boson production at the Large Hadron Collider; its scattering amplitudes are large mathematical expressions containing integer coefficients. In this paper, we apply Transformers to predict these coefficients. The problem can be formulated in a language-like representation amenable to standard cross-entropy training objectives. We design two related experiments and show that the model achieves high accuracy (> 98%) on both tasks. Our work shows that Transformers can be applied successfully to problems in theoretical physics that require exact solutions.

Cai, Tianji (ORCID:0000000232359486)↗
DOE OSTI2024

Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory

We pursue the use of deep learning methods to improve state-of-the-art computations in theoretical high-energy physics. Planar N = 4 Super Yang-Mills theory is a close cousin to the theory that describes Higgs boson production at the Large Hadron Collider; its scattering amplitudes are large mathematical expressions containing integer coefficients. In this paper, we apply Transformers to predict these coefficients. The problem can be formulated in a language-like representation amenable to standard cross-entropy training objectives. We design two related experiments and show that the model achieves high accuracy (> 98%) on both tasks. Our work shows that Transformers can be applied successfully to problems in theoretical physics that require exact solutions.

Lance, Dixon↗
DOE OSTI2025

From PINNs to PIKANs: recent advances in physics-informed machine learning

Physics-Informed Neural Networks (PINNs) have emerged as a key tool in Scientific Machine Learning since their introduction in 2017, enabling the efficient solution of ordinary and partial differential equations using sparse measurements. Over the past few years, significant advancements have been made in the training and optimization of PINNs, covering aspects such as network architectures, adaptive refinement, domain decomposition, and the use of adaptive weights and activation functions. A notable recent development is the Physics-Informed Kolmogorov-Arnold Networks (PIKANS), which leverage a representation model originally proposed by Kolmogorov in 1957, offering a promising alternative to traditional PINNs. In this review, we provide a comprehensive overview of the latest advancements in PINNs, focusing on improvements in network design, feature expansion, optimization techniques, uncertainty quantification, and theoretical insights. We also survey key applications across a range of fields, including biomedicine, fluid and solid mechanics, geophysics, dynamical systems, heat transfer, chemical engineering, and beyond. Lastly, we review computational frameworks and software tools developed by both academia and industry to support PINN research and applications.

Kolmogorov-Arnold networks↗
DOE OSTI2024

Updates to the Alliance of Genome Resources central infrastructure

The Alliance of Genome Resources (Alliance) is an extensible coalition of knowledgebases focused on the genetics and genomics of intensively studied model organisms. The Alliance is organized as individual knowledge centers with strong connections to their research communities and a centralized software infrastructure, discussed here. Model organisms currently represented in the Alliance are budding yeast, Caenorhabditis elegans, Drosophila, zebrafish, frog, laboratory mouse, laboratory rat, and the Gene Ontology Consortium. The project is in a rapid development phase to harmonize knowledge, store it, analyze it, and present it to the community through a web portal, direct downloads, and application programming interfaces (APIs). Here, we focus on developments over the last 2 years. Specifically, we added and enhanced tools for browsing the genome (JBrowse), downloading sequences, mining complex data (AllianceMine), visualizing pathways, full-text searching of the literature (Textpresso), and sequence similarity searching (SequenceServer). We enhanced existing interactive data tables and added an interactive table of paralogs to complement our representation of orthology. To support individual model organism communities, we implemented species-specific “landing pages” and will add disease-specific portals soon; in addition, we support a common community forum implemented in Discourse software. We describe our progress toward a central persistent database to support curation, the data modeling that underpins harmonization, and progress toward a state-of-the-art literature curation system with integrated artificial intelligence and machine learning (AI/ML).

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Learning from metastable symmetric-tilt grain boundaries using physics-based descriptors

Grain boundaries (GBs) govern critical properties of polycrystalline materials. Although significant advancements have been made in characterizing minimum energy and ordered GBs, real GBs are seldom found in such well-defined states. This diversity of atomic arrangements in metastable states makes it challenging to establish structure-property relationships with physical insights. Here, to address this challenge, we use data-driven methods to explore these relationships and examine the underlying physics. In this study, we utilize a large atomistic database (~5000) of minimum energy and metastable states of symmetric-tilt copper GBs, combined with physically motivated local atomic environment (LAE) descriptors [strain functional descriptors (SFDs)], to predict GB properties and gain physical insights. Our regression models exhibit robust predictive capabilities using only 19 descriptors, generalizing to atomic environments in nanocrystals. A significant highlight of our work is the integration of an unsupervised method with SFDs to elucidate LAEs at GBs and their role in determining properties. The model, trained on these minimum energy and metastable GBs using SFDs, predicts the properties of unseen nanocrystals with good accuracy. Our research underscores the role of a physics-based representation of LAEs and the efficacy of data-driven methods in establishing GB structure-property relationships.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Automating the Analysis of Large Language Models Responses through Zero-Shot Question Answering

Recent advancements in Large Language Models (LLMs) have shown significant potential in various applications, yet their evaluation, particularly in zero-shot question answering scenarios, remains a challenging task. In this study, our objective was to explore precision metrics for Large Language Models (LLM) and design and implement a software pipeline to automatically evaluate LLMs' outputs under zero-shot question answering. Zero-shot question answering involves a model providing answers to questions about topics it hasn't seen during training. It leverages the principles of zero-shot learning by relying on semantic understanding and generalization from related knowledge. The data used was metadata from medical databases on congenital heart disease. We explored eleven LLM metrics and selected three for our evaluation: BLEU, BERTScore, and MoverScore. BLEU calculates a score based on the overlap of n-grams (contiguous sequences of n items, typically words) between the machine-generated translation and the reference translations. Higher BLEU scores indicate better correspondence between the machine-generated and human-generated translations. BERTScore is a metric used to evaluate the quality of machine-generated text by measuring the similarity of token embeddings produced by BERT (Bidirectional Encoder Representations from Transformers) between the generated text and reference text. MoverScore is a metric that quantifies the dissimilarity between the distributions of word embeddings from machine-generated text and reference text, emphasizing semantic similarity over exact token overlap. We also introduced HBKI, a composite metric summarizing these approaches. We tested five models —GPT-3, Llama-2, Gemini 1.5 Pro, Solar 10.7B, and Mixtral-8x7b. Our software pipeline, designed and implemented using Object-Oriented Programming principles, allows users to customize the selection and extraction of features for topics of interest in their own research. Our results show that MoverScore delivered the most precise evaluation of the LLM's outputs, while Mixtral-8x7b achieved the best overall performance in extracting metadata from the databases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Harnessing distributed GPU computing for generalizable graph convolutional networks in power grid reliability assessments

Although machine learning (ML) has emerged as a powerful tool for rapidly assessing grid contingencies, prior studies have largely considered a static grid topology in their analyses. This limits their application, since they need to be re-trained for every new topology. Here, this paper explores the development of generalizable graph convolutional network (GCN) models by pre-training them across a range of grid topologies and contingency types. We found that a GCN model with auto-regressive moving average (ARMA) layers with a line graph representation of the grid offered the best predictive performance in predicting voltage magnitudes (VM) and voltage angles (VA). We introduced the concept of phantom nodes to consider disparate grid topologies with a varying number of nodes and lines. For pre-training the GCN ARMA model across a variety of topologies, distributed graphics processing unit (GPU) computing afforded us significant training scalability. The predictive performance of this model on grid topologies that were part of the training data is substantially better than the direct current (DC) approximation. Although direct application of the pre-trained model to topologies that are not part of the grid is not particularly satisfactory, fine-tuning with small amounts of data from a specific topology of interest significantly improves predictive performance. In general, this paper highlights the feasibility of training large-scale GNN models to assess the reliability of power grids by considering a wide variety of grid topologies and contingency types. With the advent of foundational models in ML and the exponential increase in GPU computing clusters, generalizable ML models will significantly enhance how utilities manage power systems and make decisions in real-time or near-real-time.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Generative Models for Crystalline Materials

Understanding structure-property relationships in materials is fundamental in condensed matter physics and materials science. Over the past few years, machine learning (ML) has emerged as a powerful tool for advancing this understanding and accelerating materials discovery. Early ML approaches primarily focused on constructing and screening large material spaces to identify promising candidates for various applications. More recently, research efforts have increasingly shifted toward generating crystal structures using end-to-end generative models. This review analyzes the current state of generative modeling for crystal structure prediction and de novo generation. It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations. Furthermore, the review highlights experimental considerations for evaluating generated structures and provides recommendations for suitable existing software tools. Emerging topics, such as modeling disorder and defects, integration in advanced characterization, incorporating synthetic feasibility constraints, and model explainability are explored. Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.

Metni, Houssam [Karlsruhe Inst. of Technology (KIT↗
DOE OSTI2025

Unsupervised discovery of extreme weather events using universal representations of emergent organization

Spontaneous self-organization is ubiquitous in systems far from thermodynamic equilibrium. While organized structures that emerge dominate transport properties, universal representations that identify and describe these key objects remain elusive. Here, we introduce a theoretically grounded framework for describing emergent organization that, via data-driven algorithms, is constructive in practice. Its building blocks are spacetime lightcones that embody how information propagates across a system through local interactions. We show that predictive equivalence classes of lightcones—local causal states—capture organized behaviors in complex spatiotemporal systems. Employing an unsupervised physics-informed machine learning algorithm and a high-performance computing implementation, we demonstrate automatically discovering organized structures in two real-world domain science problems. We show that local causal states identify vortices and track their power-law decay behavior in two-dimensional fluid turbulence. We then show how to detect and track familiar extreme weather events—hurricanes and atmospheric rivers—and discover other novel structures associated with precipitation extremes in high-resolution climate data at the grid-cell level.

Rupe, Adam [Pacific Northwest National Laboratory ↗
DOE OSTI2024

LossLens: Diagnostics for Machine Learning Through Loss Landscape Visual Analytics

Modern machine learning often relies on optimizing a neural network's parameters using a loss function to learn complex features. Beyond training, examining the loss function with respect to a network's parameters (i.e., as a loss landscape) can reveal insights into the architecture and learning process. While the local structure of the loss landscape surrounding an individual solution can be characterized using a variety of approaches, the global structure of a loss landscape, which includes potentially many local minima corresponding to different solutions, remains far more difficult to conceptualize and visualize. To address this difficulty, we introduce LossLens, a visual analytics framework that explores loss landscapes at multiple scales. LossLens integrates metrics from global and local scales into a comprehensive visual representation, enhancing model diagnostics. Here we demonstrate LossLens through two case studies: visualizing how residual connections influence a ResNet-20, and visualizing how physical parameters influence a physics-informed neural network (PINN) solving a simple convection problem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Advancing the Representation of Human Actions in Large‐Scale Hydrological Models: Challenges and Future Research Directions

Characterizing the impact of human actions on terrestrial water fluxes and storages at multi-basin, continental, and global scales has long been on the agenda of scientists engaged in climate science, hydrology, and water resources systems analysis. This need has resulted in a variety of modeling efforts focused on the representation of water infrastructure operations. Yet, the representation of human-water interactions in large-scale hydrological models is still relatively crude, fragmented across models, and often achieved at coarse resolutions (~10–100 km) that cannot capture local water management decisions. In this commentary, we argue that the concomitance of four drivers and innovations is poised to change the status quo: “hyper-resolution” hydrological models (~0.1–1 km), multi-sector modeling, satellite missions able to monitor the outcome of human actions, and machine learning are creating a fertile environment for human-water research to flourish. We then outline four challenges that chart future research in hydrological modeling: (a) creating hyper-resolution global data sets of water management practices, (b) improving the characterization of anthropogenic interventions on water quantity, stream temperature, and sediment transport, (c) improving model calibration and diagnostic evaluation, and (d) reducing the computational requirements associated with the successful exploration of these challenges. Overcoming them will require addressing modeling, computational, and data development needs that cut across the hydrology community, thereby requiring a major communal effort.

catchment hydrology↗
DOE OSTI2024

Geothermal Power Systems Analysis: Outcome of Industry Stakeholders Workshop: Preprint

Geothermal cost and performance evaluation implemented via technoeconomic assessment (TEA) modeling is critical for the Department of Energy (DOE) and other geothermal industry stakeholders in assessing the current state of geothermal technologies and to identify existing hurdles to commercially viable geothermal development. The Geothermal Electricity Technology Evaluation Model (GETEM) is a major TEA tool used in estimating the economic feasibility and levelized cost of energy (LCOE) of conventional hydrothermal systems and enhanced geothermal systems (EGS). Since 2021, GETEM has been transitioning from an intricate spreadsheet model to a user-friendly tool within the System Advisor Model (SAM) developed by the National Renewable Energy Laboratory (NREL). Apart from enabling an expanded visibility of the geothermal model among other renewable resources, having GETEM in SAM has the advantage of simulation automation, better usability, updates tracking, active user inputs/feedback, and extended financial modeling. GETEM is used in developing supply curves for the Annual Technology Baseline (ATB). The ATB data are inputs to the Renewable Energy Potential (reV) and the Regional Energy Deployment System (ReEDS) models. The geothermal module in NREL’s reV model assesses the geothermal energy potential in the conterminous United States by defining the geospatial intersection of geothermal resources with existing grid infrastructure within the constraint of land use characteristics. The ReEDS model is a capacity expansion model used for simulating the long-term build-out and operation of the US generation and transmission system based on current energy costs and policies. To ensure enhanced representation of current industry trends in our model transitions and development, we organized a two-day virtual workshop to elicit geothermal industry stakeholder input and recommendations on our current approaches and assumptions on technoeconomic, resource assessment, and deployment scenarios modeling of geothermal technologies. Participants included developers, operators, investors, regulatory agencies, system modelers, national laboratory researchers, consultants, and other stakeholders. In this workshop, we gained stakeholder insights on current geothermal plant performance (i.e., capacity factors), updated drilling costs and learning curves, and next generation technologies such as closed loop and superhot rock geothermal. Other outcomes from this workshop and its impact on future geothermal development feasibility, resource availability, and capacity expansion studies are compiled and discussed.

Annual Technology Baseline↗
DOE OSTI2024

ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks

Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present study investigates the influence of different activation functions—ReLU, leaky ReLU, GELU, and Mish—on the accuracy, robustness, and encoding properties of convolutional neural networks (CNNs) and multi-layer perceptrons (MLPs) trained to estimate self-motion from optic flow. Our results demonstrate that networks with ReLU and leaky ReLU activation functions not only achieved superior accuracy in self-motion estimation from novel optic flow patterns but also exhibited greater robustness under challenging conditions. The advantages offered by ReLU and leaky ReLU may stem from their ability to induce sparser representations than GELU and Mish do. Our work characterizes the encoding of optic flow in neural networks and highlights how the sparseness induced by ReLU may enhance robust and accurate self-motion estimation from optic flow.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Robust Spectral Anomaly Detection in EELS Spectral Images via 3D Convolutional Variational Autoencoders

Abstract A 3D Convolutional Variational Autoencoder (3D‐CVAE) is introduced for automated anomaly detection in electron energy‐loss spectroscopy spectrum imaging (EELS‐SI) data. This approach leverages the full 3D structure of EELS‐SI data to detect subtle spectral anomalies while preserving both spatial and spectral correlations across the datacube. By employing cross‐entropy loss and training on bulk spectra, the model learns to reconstruct bulk features characteristic of the defect‐free material. In exploring methods for anomaly detection, both the 3D‐CVAE approach and principal component analysis (PCA) are evaluated, testing their performance using FeL‐edge ΔEpeak shifts designed to simulate material defects. These results show that 3D‐CVAE achieves superior anomaly detection and maintains consistent performance across various shift magnitudes. The method demonstrates clear bimodal separation between bulk and anomalous spectra, enabling reliable classification. Further analysis verifies that lower‐dimensional representations are robust to anomalies in the data. While performance advantages over PCA diminish with decreasing anomaly concentration, our method maintains high reconstruction quality even in challenging, noise‐dominated spectral regions. This approach provides a robust framework for unsupervised automated detection of spectral anomalies in EELS‐SI data, particularly valuable for analyzing complex material systems.

Chemistry↗
DOE OSTI2025

Mapping wall-to-wall fractional cover of Arctic tundra plant functional types in Alaska using 20-m spatial resolution satellite imagery and harmonized plot observations

Estimates of fractional cover (fCover) across given land surfaces are used to assess, and often model, vegetation composition and diversity, which are crucial for understanding the health and functioning of terrestrial ecosystems. Remote sensing provides a useful means for scaling local, plot-measured fCover estimates to regional scales. Leveraging a recently synthesized and harmonized plot database, this study generated wall-to-wall maps of fCover for six Alaskan-Arctic plant functional types (PFT), including non-vascular plants, forbs, graminoids, and deciduous and evergreen shrubs, using 20-m satellite data (Sentinel-1, Sentinel-2, ArcticDEM) using a machine learning regression approach, specifically the random forest (RF) algorithm, which is well-suited for handling nonlinear relationships and high-dimensional satellite datasets. This study additionally addressed the spatio-temporal inconsistencies e.g., sampling scale, plot size, and collection year in plot measured fCover by adopting a multivariate outlier detection approach—Cook’s distance—to identify high-quality plots for model training and validation. Our approach achieves high accuracy (R 2 = 0.59–0.93, root mean squared errors = 0.02–0.10 for all PFTs) between plot-observed and satellite-derived fCover when using high-quality plot samples. The mapped fCover characterizes the spatial patterns of different PFTs across the tundra biome at a 20-m resolution, providing key information needed for improved representation of Arctic tundra vegetation in terrestrial biosphere models to better understand climate-vegetation feedback across the Arctic tundra.

Arctic tundra↗
DOE OSTI2025

A Comprehensive Machine Learning Model for Metal–Ligand Binding Prediction: Applications in Chemistry and Biology

A machine-learning (ML) model that predicts metal–ligand binding constants was developed using the open-source Chemprop software. The model was trained on over 30,000 experimental log K 1 values, which include both protonation and metal–ligand stability constants, comprising over 3500 ligands and 10 2 metal ions from 73 total elements, thus generalizing beyond existing limited approaches, which focus only on specific metals or ligand families. The best-performing model included a combination of SMILES-based molecular representations along with descriptors for the metal ion and experimental conditions. It had an external test R 2 value of 0.942, and MAE value of 0.834. A “SMILES-only” simpler version also produced accurate predictions and preserved the binding trends, serving as a quick and easily accessible alternative for users without computational expertise. The SMILES-only model performed comparably to density functional theory (DFT) calculations but utilized a fraction of the computational resources. The model was successfully applied across diverse domains, including bioinorganic chemistry, heavy metal remediation, and sensor development and demonstrated its effectiveness as a rapid and reliable screening tool for both academic and industrial uses.

Ligands↗
DOE OSTI2026

Integrated System Planning: Emerging Software Requirements in the Power Industry

Power system planning software remains fragmented across organizational boundaries, with specialized tools for capacity expansion, production cost modeling, power flow, and dynamic analysis operating on incompatible data models and assumptions. This article argues that the fragmentation is not merely a technical problem but a predictable consequence of Conway's law: software architectures mirror the departmental structures within which they are developed. Regulatory milestones like Federal Energy Regulatory Commission (FERC) Order 888 formalized these divisions, but the roots trace back to the distinct engineering disciplines-mechanical, chemical, and electrical-that staffed generation and transmission planning departments in vertically integrated utilities. As the industry moves toward integrated system planning (ISP) that coordinates generation, transmission, and distribution investment decisions, the software ecosystem must evolve accordingly. We identify five categories of software requirements to enable this transition: coherent data inputs decoupled from individual applications, unified and extensible data schemas, modular component representations that support multiple abstraction levels, lifecycle management of planning datasets, and well-defined application programming interface (API) contracts that separate data exchange from algorithmic control. We examine how these requirements interact with three common workflow patterns-serial gate clearing, sequential multiapplication, and convergence oriented-and discuss the interface design principles each demands. We then outline a vision for platform-based planning architectures where specialized analytical services compose through standardized interfaces and where artificial intelligence (AI)/machine learning (ML) tools augment decision support within a disciplined software infrastructure. The practices proposed here offer a path from today's siloed tool collections toward collaborative planning ecosystems capable of handling the complexity of modern power system transformation.

24 POWER TRANSMISSION AND DISTRIBUTION↗