Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning framework”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

SmileyLlama: modifying large language models for directed chemical space exploration

Here we show that large language models (LLMs) can be transformed via supervised fine-tuning of engineered prompts into SmileyLlama for exploring the chemical space of drug molecules. We benchmark SmileyLlama against pretrained LLMs and chemical language models trained from scratch for generating valid and novel drug-like molecules, and use direct preference optimization to both improve SmileyLlama’s adherence to a prompt and as part of the iMiner reinforcement learning framework to predict molecules with optimized three-dimensional conformations and high binding affinity to drug targets. By training an LLM to speak directly as a chemical language model, while retaining most of its natural language capabilities, we show that SmileyLlama can reliably generate molecules with user-specified properties rather than acting only as a chatbot with knowledge of chemistry or as a virtual assistant. While SmileyLlama is geared toward drug discovery, the supervised fine-tuning/direct preference optimization/LLM framework can be extended to other chemical, biological and materials applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Toward accelerating rare-earth metal extraction using equivariant neural networks

The separation of rare-earth metals, vital for numerous advanced technologies, is hampered by their similar chemical properties, making ligand discovery a significant challenge. Traditional experimental and quantum chemistry approaches for identifying effective ligands are often resource-intensive. We introduce a machine learning protocol based on an equivariant neural network, Allegro, for the rapid and accurate prediction of binding energies in rare-earth complexes. Key to this work is our newly curated dataset of rare-earth metal complexes—made publicly available to foster further research—systematically generated using the Architector program. This dataset distinctively features functionalized derivatives of proven rare-earth-chelating scaffolds, hydroxypyridinone (HOPO), catecholamide (CAM), and their thio-analogues, selected for their established efficacy in binding these elements. Trained on this valuable resource, our Allegro models demonstrate excellent performance, particularly when trained to directly predict DFT-level binding energies, yielding highly accurate results that closely correlate with theoretical calculations on a diverse test set. Furthermore, this strategy exhibited strong out-of-sample generalization, accurately predicting binding energies for an isomeric HOPO-derivative ligand not seen during training. By substantially reducing computational demands, this machine learning framework, alongside the provided dataset, represent powerful tools to accelerate the high-throughput screening and rational design of novel ligands for efficient rare-earth metal separation.

Gupta, Ankur K. [Lawrence Berkeley National Labora↗
DOE OSTI2025

A hybrid neural architecture: Online attosecond x-ray characterization

The emergence of high-repetition-rate x-ray free-electron lasers (XFELs), such as SLAC’s LCLS-II, serves as our canonical example for autonomous controls that necessitate high-throughput diagnostics paired with streaming computational pipelines capable of single-shot analysis with extremely low latency. We present the deterministic characterization with an integrated parallelizable hybrid resolver architecture, a hybrid machine learning framework designed for fast, accurate analysis of XFEL diagnostics using angular streaking-based sinogram images. This architecture integrates convolutional neural networks and bidirectional long short-term memory models to denoise input, identify x-ray sub-spike features, and extract sub-spike relative delays with sub-30 attosecond temporal resolution. Deployed on low-latency hardware, it achieves over 10 kHz throughput with 168.3 μs inference latency, indicating scalability to 14 kHz with field-programmable gate array integration. By transforming regression tasks into classification problems and leveraging optimized error encoding, we achieve high precision with low-latency performance that is critical for real-time streaming event selection and experimental control feedback signals. This represents a key development in real-time control pipelines for next-generation autonomous science, generally, and high repetition-rate x-ray experiments in particular.

Accelerator Physics (physics.acc-ph)↗
DOE OSTI2024

Enhanced plasma performance in C-2W advanced beam-driven field-reversed configuration experiments

TAE Technologies’ fifth-generation fusion device, C-2W (also called ‘Norman’), is the world’s largest compact-toroid device and has made significant progress in field-reversed configuration (FRC) plasma performance. C-2W produces record breaking, macroscopically stable, high-temperature advanced beam-driven FRC plasmas, dominated by injected fast particles and sustained in steady state, which is primarily limited by neutral-beam (NB) pulse duration. The NB power supply system has recently been upgraded to extend the pulse length from 30 ms to 40 ms, which allows for a longer plasma lifetime and thus better characterization and further enhancement of FRC performance. An active plasma control system is routinely used in C-2W to produce consistent FRC performance as well as for reliable machine operations using magnet coils, edge-biasing electrodes, gas injection and tunable-energy NBs. Google’s machine learning framework for experimental optimization has also been routinely used to enhance plasma performance. D

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Uncovering obscured phonon dynamics from powder inelastic neutron scattering using machine learning

The study of phonon dynamics is pivotal for understanding material properties, yet it faces challenges due to the irreversible information loss inherent in powder inelastic neutron scattering spectra and the limitations of traditional analysis methods. In this study, we present a machine learning framework designed to reveal obscured phonon dynamics from powder spectra. Using a variational autoencoder, we obtain a disentangled latent representation of spectra and successfully extract force constants for reconstructing phonon dispersions. Notably, our model demonstrates effective applicability to experimental data even when trained exclusively on physics-based simulations. The fine-tuning with experimental spectra further mitigates issues arising from domain shift. Analysis of latent space underscores the model’s versatility and generalizability, affirming its suitability for complex system applications. Furthermore, our framework’s two-stage design is promising for developing a universal pre-trained feature extractor. This approach has the potential to revolutionize neutron measurements of phonon dynamics, offering researchers a potent tool to decipher intricate spectra and gain valuable insights into the intrinsic physics of materials.

domain adaptation↗
DOE OSTI2025

Detecting anomalous SRF cavity behavior with unsupervised learning

We present an unsupervised learning framework for detecting anomalous superconducting radio-frequency (SRF) cavity behavior at the Continuous Electron Beam Accelerator Facility (CEBAF), emphasizing its initial performance and effectiveness. Key to the system’s success was the development of data acquisition systems (DAQs) that capture fast-sampled, information-rich signals, essential for detecting transient effects. The approach involves creating daily cavity-specific models using principal component analysis to handle variations in rf signal behavior and mitigate performance degradation from data drift. This unsupervised method eliminates the need for expensive labeling by continuously updating models with recent data. Deployed and operational for 3 months before a scheduled shutdown, the system successfully identified several issues with DAQ signals, confirming its effectiveness. Despite access to only a fraction of CEBAF’s SRF cavity signals, the framework efficiently detected several instances requiring intervention, demonstrating a significant improvement over traditional, labor-intensive methods of manual plot inspection. Published by the American Physical Society 2025

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Current status of the light neutralino thermal dark matter in the phenomenological MSSM

In a previous publication, we studied the parameter space of the phenomenological minimal Supersymmetric standard model with a light neutralino thermal dark matter ( M χ ˜ 1 0 ≤ M h / 2 ) and observed that the recent results from the dark matter and collider experiments put strong constraints on this scenario. In this work, we present in detail the arguments behind the robustness of this result against scanning over the large number of parameters in phenomenological minimal Supersymmetric standard model. The Run 3 of LHC will be crucial in probing the surviving regions of the parameter space. We further investigate the impact of light staus on our parameter space and also provide benchmarks that can be interesting for Run 3 of LHC. We analyze these benchmarks at the LHC using the machine learning framework of . Finally, we also discuss the effect of nonstandard cosmology on the parameter space. Published by the American Physical Society 2025

Barman, Rahool Kumar↗
DOE OSTI2024

Model orthogonalization and Bayesian forecast mixing via principal component analysis

One can improve predictability in the unknown domain by combining forecasts of imperfect complex computational models using a Bayesian statistical machine learning framework. In many cases, however, the models used in the mixing process are similar. In addition to contaminating the model space, the existence of such similar, or even redundant, models during the multimodeling process can result in misinterpretation of results and deterioration of predictive performance. In this paper we describe a method based on the principal component analysis that eliminates model redundancy. We show that by adding model orthogonalization to the proposed Bayesian model combination framework, one can arrive at better prediction accuracy and reach excellent uncertainty quantification performance.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

Adaptive Graph Learning with Transformer for Multi-Reservoir Inflow Prediction

Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for multi-reservoir inflow forecasting. AdaTrip constructs dynamic graphs where reservoirs are nodes with directed edges reflecting hydrological connections, employing attention mechanisms to automatically identify crucial spatial and temporal dependencies. Evaluation on thirty reservoirs in the Upper Colorado River Basin demonstrates superiority over existing baselines, with improved performance for reservoirs with limited records through parameter sharing. Additionally, AdaTrip provides interpretable attention maps at edge and time-step levels, offering insights into hydrological controls to support operational decision-making. Our code is available at https://github.com/humphreyhuu/AdaTrip.

Hu, Pengfei [ORNL] (ORCID:0009000367130950)↗
DOE OSTI2026

A Benchmark Suite for Evaluating Scientific AI Workloads on GPUs

AI applications have been steadily increasing in the allocation portfolio among leadership computing facilities. These applications depend on deep learning frameworks with hardware acceleration and underlying software systems. With the rapid development of applications, software stacks, and hardware devices, it is essential to evaluate the performance of core operations in AI workloads for direction of optimizations and procurement of next-generation high-performance computing (HPC) infrastructures. Currently, most benchmarks lack scientific AI workloads. So, we present DeepKernelBench and the experimental results of evaluating the benchmark suite for early observations and performance comparisons on datacenter GPUs using representative workloads for scientific AI, including Attentions, General matrix multiplications, Geometrics and Fourier neural operations.

Jin, Zheming [Advanced Micro Devices (AMD)]↗
DOE OSTI2025

A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching

Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2024

Accelerated Depth Computation for Surface Boxplots with Deep Learning

Functional depth is a well-known technique used to derive descriptive statistics (e.g., median, quartiles, and outliers) for 1D data. Surface boxplots extend this concept to ensembles of images, helping scientists and users identify representative and outlier images. However, the computational time for surface boxplots increases cubically with the number of ensemble members, making it impractical for integration into visualization tools. In this paper, we propose a deep-learning solution for efficient depth prediction and computation of surface boxplots for time-varying ensemble data. Our deep learning framework accurately predicts member depths in a surface boxplot, achieving average speedups of 6X on a CPU and 15X on a GPU for the 2D Red Sea dataset with 50 ensemble members compared to the traditional depth computation algorithm. Our approach achieves at least a 99% level of rank preservation, with order flipping occurring only at pairs with extremely similar depth values that pose no statistical differences. This local flipping does not significantly impact the overall depth order of the ensemble members.

Han, Mengjiao↗
DOE OSTI2024

Deep Learning-based Non-Stationary Bias Correction (NSBC)

This work develops the NSBC (non-stationary bias correction) methodology to correct temperature projection bias from E3SM. The NSBC deep learning framework consists of a three-part architecture: an auto-encoder for compressing the spatial information, an LSTM for predicting annual temperature mean, and a U-Net for capturing the residual bias in temperature. The non-stationary bias correction (NSBC) framework can correct the non-stationarity of the biases of the climate models, which significantly improves the accuracy of future temperature prediction and improves the overestimation of extreme high temperatures that many existing bias correction methods suffer from. Getting started 1. Obtain the historical climate simulation and observation data. The E3SM simulation data are available through https://aims2.llnl.gov/search/cmip6/. The pseudo observations, the Geophysical Fluid Dynamics Laboratory (GFDL)-ESM4 model (Krasting et al., 2018) are available through https://aims2.llnl.gov/search/cmip6/. The spatial resolution of E3SM and pseudo observation datasets are both regridded to a common 1° resolution grid using conservative interpolation. The regridded E3SM and pseudo observation with 1° resolution can be found throught ./data/. 2. Train the Auto-encoder model. Python 0-autoencoder.py 3. Train the LSTM Python 1-LSTM.py 4. Generate the annual mean temperature based on trained LSTM Python 2-generate_annual_mean_LSTM.py 5. Train the U-Net. Python 3-unet.py 6. Evaluation and compared with the baseline Python 4_evaluation.py Is there a deadline approaching that requires the release of yo

Lucas, Donald↗
DOE OSTI2025

pnnl/glad

The Graph-based Learning of Aerosol Dynamics (GLAD) package implements a Graph Network-based Simulator (GNS), a machine learning framework that has been used to simulate particle-based fluid dynamics models

Smith, Ian [@pnnl]↗
DOE OSTI2024

UFNet: Joint U-Net and Fully Connected Neural Network to Bias Correct Precipitation Predictions from

Paper information. Shuang Yu, Indrasis Chakraborty, Gemma J. Anderson, Donald D. Lucas, Yannic Lops, and Daniel Galea. UFNet: Joint U-Net and fully connected neural network to bias correct precipitation predictions from climate models. Artificial Intelligence for the Earth Systems, 2024. Overview. This work develops the UFNet methodology to correct E3SM historical precipitation projection bias. The UFNet deep learning framework consists of a two-part architecture: a U-Net convolutional network to capture the spatiotemporal distribution of precipitation and a fully connected network to capture the distribution of higher-order statistics. The joint network, termed UFNet, can simultaneously improve the spatial structure of the modeled precipitation and capture the distribution of extreme precipitation values. Below we provide guidance for applying UFNet to correct the Energy Exascale Earth System Model (E3SM; Golaz et al. 2019) daily precipitation projection over the contiguous United States (CONUS). Getting started 1. Obtain the historical climate simulation and observation data. The E3SM historical simulation data are available through https://aims2.llnl.gov/search/cmip6/. The CPC unified gauge-based analysis of daily precipitation can be found through https://psl.noaa.gov/data/gridded/data.cpc.globalprecip.html. The ECMWF atmospheric reanalysis of the 20th century (ERA-20C) data are available through https://www.ecmwf.int/en/forecasts/datasets/reanalysis-datasets/era-20c. The spatial resolution of E3SM and observed datasets are both regridded to a common 1° resolution grid using conservative interpolation. The regridded E3SM, CPC and ERA-20C with 1° resolution can be found throught ./data/. 2. Train the fully connected network (DNN) Python train_dnn.py 3. Train the UFNet Python train_ufnet.py 4. Evaluation and compared with the baseline Python evaluation.py

Lucas, DonaldD↗
DOE OSTI2026

OPEN ALPHADIFFRACT

Open-source release of the AlphaDiffract data generation and training system. Includes only the public Materials Project dataset retrievers.AlphaDiffract is a deep learning framework that achieves state-of-the-art performance in predicting the crystal system, space group, and lattice parameters directly from PXRD patterns. AlphaDiffract utilizes a 1D adaptation of the ConvNeXt architecture, a modern convolutional neural network that integrates key design principles from transformers, coupledwith dedicated prediction heads for each crystallographic property.

Prince, Michael [Argonne National Laboratory (ANL)↗
DOE OSTI2026

Transplatformer: translating toxicogenomic profiles between generations of platforms

Background Transcriptomic profiling technologies have advanced the analysis of biological and toxicological responses. However, substantial differences in probe design, dynamic range, gene coverage, and preprocessing pipelines across platforms introduce artifacts that limit cross-study integration and hinder the reuse of historical datasets. We aim to develop computational methods for accurate cross-platform translation to maximize the value of legacy resources. Results We present TransPlatformer a deep learning framework for translating gene expression profiles across heterogeneous toxicogenomics platforms. TransPlatformer employs a novel attention-based architecture to map high-dimensional fold-change vectors from legacy microarray technologies to current platforms. Models are trained and evaluated using DrugMatrix, spanning three technological generations. We investigate mixed-tissue, single-tissue, and cross-tissue training paradigms and benchmark performance against multilayer perceptron and matrix-completion baselines. In mixed-tissue training, TransPlatformer achieves a greater than 50% reduction in mean absolute error (0.043 vs. 0.09) and nearly doubles Pearson correlation ( ≈ 0.71 vs. 0.37) relative to baseline methods. Importantly, TransPlatformer preserves rare but biologically meaningful over- and under-expressed signals, with mean absolute error below 0.22. Single-tissue models yield further improvements for well-represented organs, such as a 10% reduction in liver mean absolute error, while underscoring the need for data augmentation strategies in low-sample tissues.ra Conclusions TransPlatformer provides an effective and scalable computational solution for cross-platform transcriptomic translation. By enabling biologically faithful harmonization of gene expression data, the proposed approach facilitates the reuse of legacy toxicogenomics datasets, enhances downstream biomarker discovery, and supports more reproducible predictive modeling in toxicology.

59 BASIC BIOLOGICAL SCIENCES↗