Search NASA⌕ Search

SEARCH · Search NASA

Results for “Scalable Model”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Advancing Urban Water Resilience: Coproducing Knowledge through Civic–Academic Global Partnerships on Water and Climate

As extreme weather events become more pronounced, the vulnerabilities associated with the urban water supply and wastewater systems in megacities are intensified in multiple interconnected dimensions. These multifaceted water challenges can benefit from enhanced cross-sectoral collaboration and sharing of critical knowledge, which are essential for sustainable and adaptive water governance frameworks. In this context, the Megacity Alliance for Water and Climate (MAWAC)–Europe and North America Region (ENAR) Working Group convened a workshop in March 2023, followed by a subsequent workshop in London, United Kingdom, from 11 to 13 September 2024. These workshops aimed to investigate and devise solutions for the cascading hazards with water systems. The solutions examined various aspects focused on climate adaptation and mitigation, stormwater management, and the governance of water and wastewater systems. Additionally, discussions highlighted the importance of community engagement, economic considerations, equity, and effective communication in addressing these pressing challenges. Over the course of 3 days, experts from academia, government agencies, and industry engaged in meaningful discussions on digital modeling for integrated water management, climate-informed urban planning, and public–private–academic partnerships (Fig. 1). Case studies from cities such as New York, Los Angeles, London, Paris, and Chicago highlighted innovative governance strategies for managing water and wastewater systems, promoting water reuse, planning infrastructure, and fostering stakeholder-driven and stakeholder-informed adaptation. The workshop participants emphasized the need for data-driven decision-making, scalable governance models, and knowledge-sharing networks to enhance urban water governance for sustainability and resilience. This workshop report presents the key takeaways from the 3-day convening, providing a roadmap for integrating scientific research, policy frameworks, and emerging technologies to address water challenges faced by megacities.

Hydrologic models↗
DOE OSTI2025

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

DP-TwoLevel: two-stage gradient subspace learning for differentially private federated learning

Federated learning (FL) enables collaborative model training across distributed data sources without sharing raw data, but faces fundamental challenges in communication efficiency and privacy. Differentially private (DP) training mitigates information leakage but introduces noise that degrades model performance, especially in high-dimensional settings. We propose DP-TwoLevel, a hierarchical gradient projection method that improves utility under fixed DP constraints by exploiting low-dimensional structure in model updates. Our approach learns a two-level PCA-based representation of gradients and applies DP noise in a reduced-dimensional subspace, thereby lowering the effective noise magnitude while preserving dominant signal components. We evaluate the method across three datasets (MNIST, Fashion-MNIST, CIFAR-10) and three privacy regimes (ϵ∈0.5, 1.0, 2.0). Across nine experimental settings, DP-TwoLevel consistently outperforms DP-FedAvg, achieving an average accuracy improvement of 9.44%, with larger gains observed in lower ϵ(higher-noise) regimes (up to +22.31%). We further analyze scalability across models ranging from 100K to 1.49M parameters and identify a variance-based success criterion: performance remains strong when the projection preserves more than 75% of gradient variance, degrades in a marginal regime (65–75%), and fails below this threshold. Our results demonstrate that structure-aware dimensionality reduction can significantly improve the privacy–utility tradeoff in FL without modifying formal privacy guarantees. We also provide empirical evidence of scaling limitations for global projections and motivate per-layer extensions for larger models.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2026

Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis

Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT), a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self-attention. The QGT models variable-length sentences as token graphs, where both the embedding encoding and the self-attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and 𝑘 -nearest-neighbor graph structures and evaluate it on five benchmark sentiment-classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving 29.4 × fewer parameters while requiring 3–5 × fewer samples to reach comparable performance. These findings highlight the potential of graph-based quantum models as scalable and data-efficient architectures for natural language understanding.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Performance evaluation of automated data-driven feature extraction and selection methods for practical and scalable building energy consumption prediction models

Here, this study quantifies the impact of automated feature engineering methods (feature extraction and selection) on the quality and accuracy of machine learning models that predict building energy consumption. The case study compares model performance for three main scenarios: baseline (no feature extraction and selection), feature extraction only, and feature extraction combined with feature selection (filter and/or wrapper methods) for fully trained machine learning models for 200 metered/sub-metered energy measurements across 118 real buildings. For consistency, the same machine learning model architecture (a black box deep learning neural network with probabilistic forecast output) was used for all scenarios. Based on results, all feature engineering methods provided noticeable prediction accuracy improvements (e.g., 29%-68% median prediction improvement) compared to baseline scenarios. However, in this application, feature selection methods provide little practical value due to their limited performance gains and high computational cost. Smarter algorithm development supported by better computational environments will be needed before feature selection methods can reliably and efficiently improve predictive model performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Architecting the Third Dimension of Electrochemical Energy Storage

Three-dimensional (3D) architectural design has emerged as a powerful strategy to push electrochemical energy storage (EES) devices beyond the intrinsic limitations of conventional two-dimensional (2D) electrodes. While planar architectures enable high packing density and mature manufacturing, they suffer from limited ion transport and low active-material loading. In contrast, 3D architectures introduce low-tortuosity networks and high surface area that enhance charge and mass transport while supporting thick, high mass-loading electrodes. However, their practicality remains hindered by challenges in volumetric density, mechanical stability, and large-scale manufacturability. Here, this Perspective examines the key evaluation and design principles that govern 3D device performance. We discuss the fundamental trade-offs between porosity, volumetric density, and mechanical stability that shape 3D design and highlight emerging strategies for integrating materials engineering, structural optimization, device integration, computational modeling, and scalable manufacturing. By aligning structural functionality with manufacturability, 3D architectures can evolve from laboratory prototypes to commercially viable energy storage systems.

25 ENERGY STORAGE↗
DOE OSTI2026

Dark Energy Survey Year 3 results: Simulation-based 𝑤CDM inference from weak lensing and galaxy clustering maps with deep learning: Analysis design

Data-driven approaches using deep learning are emerging as powerful techniques to extract non-Gaussian information from cosmological large-scale structure. Here, this work presents the first simulation-based inference (SBI) pipeline that combines weak lensing and galaxy clustering maps in a realistic Dark Energy Survey Year 3 (DES Y3) configuration and serves as preparation for a forthcoming analysis of the survey data. We develop a scalable forward model based on the CosmoGridV1 suite of N-body simulations to generate over one million self-consistent mock realizations of DES Y3 at the map level. Leveraging this large dataset, we train deep graph convolutional neural networks on the full survey footprint in spherical geometry to learn low-dimensional features that approximately maximize mutual information with target parameters. These learned compressions enable neural density estimation of the implicit likelihood via normalizing flows in a ten-dimensional parameter space spanning cosmological 𝑤CDM, intrinsic alignment, and linear galaxy bias parameters, while marginalizing over baryonic, photometric redshift, and shear bias nuisances. To ensure robustness, we extensively validate our inference pipeline using synthetic observations derived from both systematic contaminations in our forward model and independent Buzzard galaxy catalogs. Our forecasts yield significant improvements in cosmological parameter constraints, achieving 2−3× higher figures of merit in the 𝛺 𝑚 − 𝑆 8 plane relative to our implementation of baseline two-point statistics and effectively breaking parameter degeneracies through probe combination. These results demonstrate the potential of SBI analyses powered by deep learning for upcoming Stage-IV wide-field imaging surveys.

Thomsen, A. [Zurich, ETH] (ORCID:0000000203099021)↗
DOE OSTI2025

Computing virtual dark-field X-ray microscopy images of complex discrete dislocation structures from large-scale molecular dynamics simulations

Dark-field X-ray microscopy (DFXM) is a novel diffraction-based imaging technique that non-destructively maps the local deformation from crystalline defects in bulk materials. While studies have demonstrated that DFXM can spatially map 3D defect geometries, it is still challenging to interpret DFXM images of the high-dislocation-density systems relevant to macroscopic crystal plasticity. This work develops a scalable forward model to calculate virtual DFXM images for complex discrete dislocation structure(s) (DDS) obtained from atomistic simulations. Our new DDS-DFXM model integrates a non-singular formulation for calculating the local strain from the DDS and an efficient geometrical optics algorithm for computing the DFXM image from the strain field. We apply the model to complex DDS obtained from a large-scale mol­ecular dynamics simulation of compressive loading on single-crystal silicon. Simulated DFXM images exhibit prominent contrast for dislocation features between the multiple slip systems, demonstrating the potential of DFXM to resolve features from dislocation multiplication. In conclusion, the integrated DDS-DFXM model provides a toolbox for DFXM experimental design and image interpretation in the context of bulk crystal plasticity for a range of measurements across shock plasticity and the broader materials science community.

X-ray imaging↗
DOE OSTI2025

ORBIT-2 Weather and Climate Downscaling Software Repository

ORBIT-2 is a scalable foundation model for global, hyper-resolution climate and weather downscaling. ORBIT-2 incorporates two key innovations: (1) Residual Slim ViT (Reslim), a lightweight architecture with residual learning and Bayesian regularization for efficient, robust prediction; and (2) TILES, a tile-wise sequence scaling algorithm that reduces self-attention complexity from quadratic to linear, enabling long-sequence processing and massive parallelism. ORBIT-2 scales to 10 billion parameters across 65,536 GPUs, achieving up to 4.1 ExaFLOPS sustained throughput and 74–98% strong scaling efficiency. It supports downscaling to 0.9 km global resolution and processes sequences up to 4.2 billion tokens. On 7 km resolution benchmarks, ORBIT-2 achieves high accuracy with 𝑅2 scores in range of 0.98–0.99 against observation data.

Wang, Xiao [Oak Ridge National Laboratory]↗
DOE OSTI2026

Livewire: A Model Platform for Data Quality Assessment and AI Readiness Across DOE Missions

High-quality, well-governed data is essential for accelerating discovery and achieving operational excellence across DOE and national laboratory missions. The Livewire Data Platform is a DOE-supported platform that offers automated assessments of data quality, standardization, provenance, and Artificial Intelligence (AI) readiness. It allows researchers and data practitioners to systematically and easily evaluate datasets against established governance criteria and prepare them for advanced analytics. Livewire addresses critical challenges in DOE's data ecosystem with integrated capabilities for metadata validation, provenance tracking, and schema alignment. This platform's automated workflows assist users in identifying data quality gaps, enhancing interoperability between datasets collected from various stakeholders, and ensuring compliance with DOE data standards, all while reducing manual curation efforts. Additionally, we will discuss its AI readiness framework, which is being developed to prepare datasets for training models, developing advanced analytic tools, and machine learning applications. Using some of the more than one hundred tabular datasets on Livewire, processed with this open-source methodology, we will demonstrate how Livewire can serve as a model for scalable, standards-driven data management. This approach provides a pathway to leverage existing and future datasets within the DOE, boosting innovation and efficiency across national laboratories.

33 - ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2026

Scalable Federated Learning for Scientific Foundation Models on Leadership-Class Systems

Federated learning (FL) at leadership-class HPC systems remains largely unexplored, despite growing interest in deploying federated workflows on modern HPC systems. This paper provides the first system-level empirical characterization of federated fine-tuning of pretrained foundation models on an exascale supercomputer under a multi-node deployment. Using up to 96 concurrent FL clients deployed across Frontier nodes, we study the impact of client scale, model size, data heterogeneity, partial participation, and differential privacy on runtime, communication overhead, and convergence stability. Our results show that pretrained transformer models remain robust to heterogeneity, client dropout, and privacy noise, while system efficiency degrades rapidly with scale as synchronizat and orchestration dominate runtime. We further demonstrate that system-aware execution strategies, including intra-node aggregation and early aggregation, significantly reduce wall-clock time without degrading model quality. These findings establish a practical performance baseline and inform the design of communication-efficient FL systems on leadership-class HPC platforms.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2024

Scalability of Real-time Distribution Models

This work will focus on developing the capabilities and validating the models for a sub transmission network with multiple feeders and microgrids. To achieve this scale of Hardware-in-the-loop (HitL) simulation, it is necessary to federate and collaborate. The work aims to design the large-scale feeder models to allow federation with complementary testbeds in the future. The feeder would be designed to be reconfigurable to put the system into a variety of modes. Aggregators models will be included in each distribution network’s federate to take control actions and interact with the management systems. Lastly, the feeder model will support large scale resilience studies involving complex Distributed Energy Resources (DER) controls, microgrid studies and emulation of complex data flows in future grid architectures.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Optimal Membrane Cascade Design for Critical Mineral Recovery through Logic-based Superstructure Optimization

In this work, we extend the superstructure model proposed by Wamble et al. (2022) that considers feed input locations, recycling strategies, split fractions, stage numbers, and membrane area. We include the total number of stages as a decision variable, which might be particularly useful when there is cost as- sociated with adding additional stages. We propose a Generalized Disjunctive Programming (GDP) superstructure model that integrates all the design variables of the system. We also investigate the scalability of the model by varying the number of stages and the number of finite elements per stage to determine the impact on recovery and solution time.

Tran, Norman↗