Search NASA⌕ Search

SEARCH · Search NASA

Results for “Regularization”

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

CRISPRi functional genomics in bacteria and its application to medical and industrial research

SUMMARY Functional genomics is the use of systematic gene perturbation approaches to determine the contributions of genes under conditions of interest. Although functional genomic strategies have been used in bacteria for decades, recent studies have taken advantage of CRISPR (clustered regularly interspaced short palindromic repeats) technologies, such as CRISPRi (CRISPR interference), that are capable of precisely modulating expression of all genes in the genome. Here, we discuss and review the use of CRISPRi and related technologies for bacterial functional genomics. We discuss the strengths and weaknesses of CRISPRi as well as design considerations for CRISPRi genetic screens. We also review examples of how CRISPRi screens have defined relevant genetic targets for medical and industrial applications. Finally, we outline a few of the many possible directions that could be pursued using CRISPR-based functional genomics in bacteria. Our view is that the most exciting screens and discoveries are yet to come.

Microbiology↗
DOE OSTI2024

Improved Zika virus plaque assay using Vero/TMPRSS2 cell line

Plaque assay is the gold standard for the quantification of viable cytopathic viruses like Zika virus (ZIKV). Some strains of ZIKV produce plaques that are very difficult to accurately visualize and count on the commonly used Vero cell line. From data generated in our lab, we became curious if Vero/TMPRSS2 cells may be a better alternative; therefore, we compared the plaque forming units of two strains of ZIKV on Vero/TMPRSS2 cells to those produced by Vero cells. We also compared the virus stock titer generated on Vero/TMPRSS2 cells to that generated by the Vero cell line. Although the Vero cells generated higher quantity of ZIKV stocks, the Vero/TMPRSS2 cells produced plaques with significantly improved morphology and visibility and may, therefore, be a better alternative to use for performing plaque assays for strains of ZIKV that are more difficult to titer on regular Vero cells.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Predictive analytics to direct clinical attention to complex patients with elevated suicide risk: enhancement of the Veterans Health Administration REACH VET model

Suicide is a major public health concern, particularly among Veterans. The U.S. Department of Veterans Affairs Veterans Health Administration (VHA) employs the Recovery Engagement and Coordination for Health–Veterans Enhanced Treatment (REACH VET) model to prioritise high-risk patients for targeted clinical attention. REACH VET 1.0 (RV 1.0) was developed on 2008–2011 data. To reflect changes in clinical practice and populations, VHA updated it to REACH VET 2.0 (RV 2.0). This study describes its development and validation. RV 2.0 used longitudinal data from 7,248,170 VHA patients (4,967 suicide deaths) in 2018–2019, with 650 time-varying demographic, clinical and area-level predictors derived from a 2-year lookback (2016–2019). An ensemble of Elastic-Net logistic regression models was trained on 2018 data and evaluated monthly at the population level in 2019, focusing on the top 0.1% intervention risk tier. Analyses assessed model discrimination, suicide detection, risk concentration, subgroup consistency (sex, age and race/ethnicity) and performance relative to RV 1.0 using the same percentile-based risk strata. RV 2.0 outperformed RV 1.0 across all risk strata, with better discrimination (C-statistic 0.76 vs 0.69) and consistent performance across demographic subgroups. Within the top 0.1% of predicted risk, RV 2.0 identified more deaths, higher suicide rates and greater mortality risk concentration both when averaged across the 12 monthly 2019 test sets (5.6 vs 3.6; 83.6 vs 53.7 per 100,000 person-years; 21.0 vs 14.1) and when annualised for 2019 (67 vs 43; 2.7% vs 1.7%; 1,003 vs 644 per 100,000 person-years; 26.7 vs 17.1). RV 2.0 improves suicide risk stratification among Veterans, demonstrating better performance and consistent prediction across subgroups and highlighting the need for regular model updates and evaluation.

Peluso, Alina [Oak Ridge National Laboratory (ORNL↗
DOE OSTI2025

Hierarchical Bayesian Inverse Problems: A High-Dimensional Statistics Viewpoint

This paper analyzes hierarchical Bayesian inverse problems using techniques from highdimensional statistics. Furthermore, our analysis leverages a property of hierarchical Bayesian regularizers that we call approximate decomposability to obtain non-asymptotic bounds on the reconstruction error attained by maximum a posteriori estimators. The new theory explains how hierarchical Bayesian models that exploit sparsity, group sparsity, and sparse representations of the unknown parameter can achieve accurate reconstructions in high-dimensional settings.

MAP estimation↗
DOE OSTI2025

Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inference

In this work, we present two neural network approaches that approximate the solutions of static and dynamic conditional optimal transport (COT) problems. Both approaches enable conditional sampling and conditional density estimation, which are core tasks in Bayesian inference—particularly in the simulation-based (“likelihood-free”) setting. Our methods represent the target conditional distribution as a transformation of a tractable reference distribution. Obtaining such a transformation, chosen here to be an approximation of the COT map, is computationally challenging even in moderate dimensions. To improve scalability, our numerical algorithms use neural networks to parameterize candidate maps and further exploit the structure of the COT problem. Our static approach approximates the map as the gradient of a partially input convex neural network. It uses a novel numerical implementation to increase computational efficiency compared to state-of-the-art alternatives. Our dynamic approach approximates the conditional optimal transport via the flow map of a regularized neural ODE; compared to the static approach, it is slower to train but offers more modeling choices and can lead to faster sampling. We demonstrate both algorithms numerically, comparing them with competing state-of-the-art approaches, using benchmark datasets and simulation-based Bayesian inverse problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Multiscale Neural Networks for Approximating Green’s Functions

Neural networks (NNs) have been widely used to solve partial differential equations (PDEs) in the applications of physics, biology, and engineering. One effective approach for solving PDEs with a fixed differential operator is learning Green’s functions. However, Green’s functions are notoriously difficult to learn due to their poor regularity, which typically requires larger NNs and longer training times. In this work, we address these challenges by leveraging multiscale NNs to learn Green’s functions. Through theoretical analysis using multiscale Barron space methods and experimental validation, we show that the multiscale approach significantly reduces the necessary NN size and accelerates training.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Understanding GPU Memory Corruption at Extreme Scale: The Summit Case Study

GPU memory corruption and in particular double-bit errors (DBEs) remain one of the least understood aspects of HPC system reliability. Albeit rare, their occurrences always lead to job termination and can potentially cost thousands of node-hours, either from wasted computations or as the overhead from regular checkpointing needed to minimize the losses. As supercomputers and their components simultaneously grow in scale, density, failure rates, and environmental footprint, the efficiency of HPC operations becomes both an imperative and a challenge. We examine DBEs using system telemetry data and logs collected from the Summit supercomputer, equipped with 27,648 Tesla V100 GPUs with 2nd-generation high-bandwidth memory (HBM2). Using exploratory data analysis and statistical learning, we extract several insights about memory reliability in such GPUs. We find that GPUs with prior DBE occurrences are prone to experience them again due to otherwise harmless factors, correlate this phenomenon with GPU placement, and suggest manufacturing variability as a factor. On the general population of GPUs, we link DBEs to short- and long-term high power consumption modes while finding no significant correlation with higher temperatures. We also show that the workload type can be a factor in memory’s propensity to corruption.

Oles, Vlad↗
DOE OSTI2024

Algorithm 1049: The Delaunay Density Diagnostic

Accurate approximation of a real-valued function depends on two aspects of the available data: the density of inputs within the domain of interest and the variation of the outputs over that domain. There are few methods for assessing whether the density of inputs is sufficient to identify the relevant variations in outputs—i.e., the “geometric scale” of the function—despite the fact that sampling density is closely tied to the success or failure of an approximation method. In this article, we introduce a general purpose, computational approach to detecting the geometric scale of real-valued functions over a fixed domain using a deterministic interpolation technique from computational geometry. The algorithm is intended to work on scalar data in moderate dimensions (2–10). Our algorithm is based on the observation that a sequence of piecewise linear interpolants will converge to a continuous function at a quadratic rate (in L 2 norm) if and only if the data are sampled densely enough to distinguish the feature from noise (assuming sufficiently regular sampling). We present numerical experiments demonstrating how our method can identify feature scale, estimate uncertainty in feature scale, and assess the sampling density for fixed (i.e., static) datasets of input–output pairs. Finally, we include analytical results in support of our numerical findings and have released lightweight code that can be adapted for use in a variety of data science settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling

Sparse observations and coarse-resolution climate models limit effective regional decision-making, underscoring the need for robust downscaling. However, existing AI methods struggle with generalization across variables and geographies and are constrained by the quadratic complexity of Vision Transformer (ViT) self-attention. We introduce ORBIT-2, a scalable foundation model for global, hyper-resolution climate 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 [ORNL] (ORCID:0000000165451943)↗
DOE OSTI2026

ObstacleSense: Low-Power Neuromorphic Vision for Corridor Obstacle Awareness in Low-Level ADAS

The automotive industry’s pursuit of Level 5 autonomy is constrained by substantial perception-compute power requirements, often reaching 1, 000 + watts in full autonomy stacks. Reducing this energy burden requires rethinking perception not only at the high-end autonomy level, but also at the foundational Advanced Driver Assistance Systems (ADAS) level where low-power, safety-critical sensing can have broad impact. Neuromorphic vision provides a promising starting point: HD Dynamic Vision Sensors (DVS) can operate below 100 mW at the sensor level by reporting only asynchronous brightness changes. However, low-power sensing alone is insufficient if downstream perception reintroduces dense, energy-intensive computation. In particular, many event-driven object-detection pipelines still rely on CNN backbones, while purely spiking alternatives often trade away accuracy or ignore deployment constraints. We introduce ObstacleSense, a highly compact, CNN-free hybrid ANN–SNN framework for Level 0–1 forward-corridor obstacle awareness. Instead of performing full-scene object detection with a convolutional feature backbone, ObstacleSense targets the safety-critical question of whether the ego corridor is occupied and how far the nearest obstacle is. The architecture combines polarity-conditioned event encoding, lightweight temporal spiking dynamics, axial spatial mixing, and coarse-to-fine range estimation within a regular fixed-grid compute pattern. This design avoids the dense CNN backbone commonly used in event-based detection while maintaining a small state footprint suitable for eventual small-FPGA deployment. Before hardware mapping, we evaluate the software implementation using a model-side power proxy derived from MACs, weight and activation traffic, and spiking state updates under shared FP16 assumptions. On simulated CARLA event corpora, the deployment-oriented model achieves 0.9464 objectness F1, 0.9978 grid-level mAP, and 0.8987 m distance Mean Absolute Error at an estimated 1.92 mW proxy cost, while maintaining performance on unseen generalization test sequences.

Johnson-Scott, Zac [ORNL]↗
DOE OSTI2025

Metabolomic and transcriptomic remodeling of bone marrow myeloid cells in response to maternal obesity

Maternal obesity puts the offspring at high risk of developing obesity and cardiometabolic diseases in adulthood. Here, we utilized a mouse model of maternal high-fat diet (HFD)-induced obesity that recapitulates metabolic perturbations seen in humans. We show increased adiposity in the offspring of HFD-fed mothers (Off-HFD) when compared with the offspring of regular diet-fed mothers (Off-RD). We have previously reported significant immune perturbations in the bone marrow of newly weaned Off-HFD. Here, we hypothesized that lipid metabolism is altered in the bone marrow of Off-HFD versus Off-RD. To test this hypothesis, we investigated the lipidomic profile of bone marrow cells collected from 3-week-old Off-RD and Off-HFD. Diacylglycerols (DAGs), triacylglycerols (TAGs), sphingolipids, and phospholipids were remarkably different between the groups, independent of fetal sex. Levels of cholesteryl esters were significantly decreased in Off-HFD, suggesting reduced delivery of cholesterol. These were accompanied by age-dependent progression of mitochondrial dysfunction in bone marrow cells. We subsequently isolated CD11b+ myeloid cells from 3-wk-old mice and conducted metabolomic, lipidomic, and transcriptomic analyses. The lipidomic profiles of myeloid cells were similar to those of bone marrow cells and included increases in DAGs and decreased TAGs. Transcriptomics revealed altered expression of genes related to immune pathways, including macrophage alternative activation, B-cell receptors, and transforming growth factor-β signaling. All told, this study revealed lipidomic, metabolomic, and gene expression abnormalities in bone marrow cells broadly, and in bone marrow myeloid cells particularly, in the newly weaned offspring of mothers with obesity, which might at least partially explain the progression of metabolic and cardiovascular diseases in their adulthood.

RNA sequencing↗
DOE OSTI2024

Fusion Neutron Generator

The proposed code, named FROG (Fusion neutron Generator) is built upon the open-source particle transport Monte Carlo toolkit Geant4. Geant4 provides C++ classes that can be leveraged to build application-specific codes dealing with the transport of particles through matter. Geant4-based codes are applied in high-energy particle physics experiments, medical applications, shielding, and space applications for example. The FROG code allows the user to define the geometry of a neutron converter device shaped as a hollow cylinder, where a neutron breeding material such as lithium deuteride (LiD) is cladded by two concentric cylinders. Such neutron converter is then placed inside a regular nuclear fission reactor, where thermal neutrons will react with the neutron breeder material (typically, Lithium 6), and through a series of reactions, will generate high-energy neutrons – neutrons whose kinetic energy are around 14 MeV. The hollowed central portion can hold a specimen that will be bombarded by high-energy neutrons created inside the neutron breeding material. Figuratively speaking, this type of device transforms neutrons from thermal (~0.625 eV) to fusion (~14 MeV) energies and is sometimes termed “fusion-to-thermal neutron converters” in the literature. The code consists of C++ source file compiled and linked to generate an executable. The user can select the dimensions of the converter (radius, length, and thickness of the breeder material), the breeder material type, the cladding material, and the specimen material that will be activated or irradiated. As input, the neutron flux for a specific location inside a reactor, for instance, positions in ATR, is required. As output, the code predicts the number of high-energy neutrons produced, the total neutron flux and fluence as well as its detailed spectrum. The physics involved in such device is very complex, as it requires modeling neutron transport, light-ion (tritons) transport, as well as fusion reactions. The Geant4 toolkit provides the required physical models.

Martin, NicholasP. [Idaho National Laboratory (INL↗
DOE OSTI2024

LATTE: Los Alamos TravelTime package based on Eikonal equation

This Fortran code focuses on traveltime computation and tomography based on eikonal equation. Specifically, the package provides three major functionalities: (1) forward modeling of traveltime from single-point or ensemble source based on factorized eikonal equation, (2) adjoint-state first-arrival traveltime tomography based on picked first arrival traveltime using steepest descent, conjugate gradient, or limited-memory BFGS inversion scheme, and (3) adjoint-state joint transmission-reflection tomography based on picked first-arrival and reflection traveltimes. The package applies to forward modeling and tomography based on traveltime in 2D and 3D isotropic regular-grid models. We name this package LATTE – Los Alamos TravelTime package based on Eikonal equation. * The code is for accompanying a journal paper under preparation. The paper will be submitted via LA-UR separately later.

Gao, Kai↗
DOE OSTI2024

ninterp: N-dimensional interpolation Rust crate [SWR-25-25]

The ninterp crate provides multivariate interpolation over a regular, sorted, nonrepeating grid of any dimensionality. A variety of interpolation strategies are implemented, however more are likely to be added. Extrapolation beyond the range of the supplied coordinates is supported for 1-D linear interpolators, using the slope of the nearby points. There are hard-coded interpolators for lower dimensionalities (up to N = 3) for better runtime performance. All interpolation is handled through instances of the Interpolator enum, with the selected tuple variant containing relevant data. Interpolation is executed by calling Interpolator::interpolate.

Carow, Kyle↗
DOE OSTI2024

Sentinel

Network intrusion detection systems (NIDS) are commonplace in network security but they frequently employ algorithms that are computational demanding requiring hardware and software with significant power requirements. Two examples of such resource-intensive algorithms used for network security are regular expression matching and broader signature pattern matching which are commonly used in deep packet inspection (DPI). Network security algorithms that have large power requirements may be a challenge for low-power internet-of-things (IoT) environments, which generally lack the power resources to implement complex security measures like computationally expensive DPI at the edge. Furthermore, IoT environments incorporating 5G standalone networks have network latency constraints beyond just power that make DPI at the edge even more difficult. Programmable logic is ideally suited for machine learning inference for DPI because of its deep instruction level parallelism and single-cycle memory access. Machine learning approaches for DPI have been explored before using the programmable logic of field programmable gate arrays (FPGA) as a potential solution for NIDS approaches that would be power-suitable for IoT. However, those previous programmable logic NIDS approaches utilize either a supervised or unsupervised learning model. Sentinel utilizes the ensemble of these two machine learning approaches known as a semi-supervised approach which has shown promise in NIDS implementations. Sentinel provides a programmable logic implementation of a semi-supervised approach for DPI which operates at much lower power and latency than a GPU implementation with negligible loss of accuracy due to quantization through a logistic regressor.

Anderson, MatthewW [Idaho National Laboratory (INL↗
DOE OSTI2025

hdsullivan/ResSR

This is the official implementation of ResSR [1]. ResSR is a computationally efficient MSI-SR method that achieves high-quality reconstructions by using a closed-form spectral decomposition along with a spatial residual correction. ResSR applies singular value decomposition to identify correlations across spectral bands, uses pixel-wise computation to upsample the MSI, and then applies a residual correction process to correct the high-spatial frequency components of the upsampled bands. While ResSR is formulated as the solution to a spatially-coupled optimization problem, we use pixel-wise regularization and derive an approximate closed-form solution, resulting in a pixel-wise algorithm with a dramatic reduction in computation that achieves state-of-the-art reconstructions. [1] Duba-Sullivan, H., Reid, E. J., Voisin, S., Bouman, C. A., & Buzzard, G. T. (2024). ResSR: A Computationally Efficient Residual Approach to Super-Resolving Multispectral Images. arXiv preprint arXiv:2408.13225.

Duba-Sullivan, Haley [Oak Ridge National Laborator↗
DOE OSTI2025

NNFDivergence

The code implements f divergence regularization for neural networks in the Python-based Pytorch framework. The methods are the main focus but the repository will also contain examples that operate on purely synthetic "toy" data or on openly available, public data from NASA.

Klein, Natalie [@lanl]↗
DOE OSTI2025

SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification

SInkhorn Dynamic Domain Adaptation (SIDDA) supplements the experiments presented in 2501.14048, SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks. SIDDA introduces a semi-supervised, automatic domain adaptation method that leverages Sinkhorn divergences to dynamically adjust the regularization in the optimal transport plan and the weighting between classification and domain adaptation loss terms during training.

Pandya, Sneh [Fermi National Accelerator Laborator↗