Search NASA⌕ Search

SEARCH · Search NASA

Results for “fast machine 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 343 records · Page 19

Fast inference of deep neural networks in FPGAs for particle physics

Here, recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA (Field Programmable Gate Array) hardware has only just begun. FPGA-based trigger and data acquisition systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. A companion compiler package for this work is developed based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models

Image-based evaluation methods are a valuable tool for source rock characterization. The time and resources needed to obtain images has spurred development of machine-learning generative models to create synthetic images of pore structure and rock fabric from limited image data. While generative models have shown success, existing methods for generating 3D volumes from 2D training images are restricted to binary images and grayscale volume generation requires 3D training data. Shale characterization relies on 2D imaging techniques such as scanning electron microscopy (SEM), and grayscale values carry important information about porosity, kerogen content, and mineral composition of the shale. Here, we introduce RockFlow, a method based on generative flow models that creates grayscale volumes from 2D training data. We apply RockFlow to baseline binary micro-CT image volumes and compare performance to a previously proposed model. We also show the extension of our model to 2D grayscale data by generating grayscale image volumes from 2D SEM and dual modality nanoscale shale images. The results show that our method underestimates the porosity and surface area on the binary baseline datasets but is able to generate realistic grayscale image volumes for shales. With improved binary data preprocessing, we believe that our model is capable of generating synthetic porous media volumes for a very broad class of rocks from shale to carbonates to sandstone.

58 GEOSCIENCES↗

Determining Research Priorities for Astronomy Using Machine Learning

We summarize the first exploratory investigation into whether Machine Learning (ML) techniques can augment science strategic planning. We find that an approach based on Latent Dirichlet Allocation (LDA) using abstracts drawn from high-impact astronomy journals may provide a leading indicator of future interest in a research topic. We show two topic metrics that correlate well with the high-priority research areas identified by the 2010 National Academies’ Astronomy and Astrophysics Decadal Survey. One metric is based on a sum of the fractional contribution to each topic by all scientific papers (“counts”) while the other is the Compound Annual Growth Rate (CAGR) of counts. These same metrics also show the same degree of correlation with the whitepapers submitted to the same Decadal Survey. Our results suggest that the Decadal Survey may under-emphasize fast growing research. A preliminary version of our work was presented by Thronson et al. (2021).

Astronomy↗

Toward a smart data transfer node

Scientific computing systems are becoming significantly more complex, with distributed teams and complex workflows spanning resources from telescopes and light sources to fast networks and Internet of Things sensor systems. In such settings, no single, centralized administrative team and software stack can coordinate and manage all resources used by a single application. Indeed, we have reached a critical limit in manageability using current human-in-the-loop techniques. We therefore argue that resources must begin to respond automatically, adapting and tuning their behavior in response to observed properties of scientific workflows. Over time, machine learning methods can be used to identify effective strategies for autonomic, goal-driven management behaviors that can be applied end-to-end across the scientific computing landscape. Using the data transfer nodes that are widely deployed in modern research networks as an example, we explore the architecture, methods, and algorithms needed for a smart data transfer node to support future scientific computing systems that self-tune and self-manage.

97 MATHEMATICS AND COMPUTING↗

Data-driven prediction of battery cycle life before capacity degradation

Accurately predicting the lifetime of complex, nonlinear systems such as lithium-ion batteries is critical for accelerating technology development. However, diverse aging mechanisms, significant device variability and dynamic operating conditions have remained major challenges. We generate a comprehensive dataset consisting of 124 commercial lithium iron phosphate/graphite cells cycled under fast-charging conditions, with widely varying cycle lives ranging from 150 to 2,300 cycles. Using discharge voltage curves from early cycles yet to exhibit capacity degradation, we apply machine-learning tools to both predict and classify cells by cycle life. Our best models achieve 9.1% test error for quantitatively predicting cycle life using the first 100 cycles (exhibiting a median increase of 0.2% from initial capacity) and 4.9% test error using the first 5 cycles for classifying cycle life into two groups. This work highlights the promise of combining deliberate data generation with data-driven modelling to predict the behaviour of complex dynamical systems.

25 ENERGY STORAGE↗

Predictive Data-driven Platform for Subsurface Energy Production

Subsurface energy activities such as unconventional resource recovery, enhanced geothermal energy systems, and geologic carbon storage require fast and reliable methods to account for complex, multiphysical processes in heterogeneous fractured and porous media. Although reservoir simulation is considered the industry standard for simulating these subsurface systems with injection and/or extraction operations, reservoir simulation requires spatio-temporal “Big Data” into the simulation model, which is typically a major challenge during model development and computational phase. In this work, we developed and applied various deep neural network-based approaches to (1) process multiscale image segmentation, (2) generate ensemble members of drainage networks, flow channels, and porous media using deep convolutional generative adversarial network, (3) construct multiple hybrid neural networks such as convolutional LSTM and convolutional neural network-LSTM to develop fast and accurate reduced order models for shale gas extraction, and (4) physics-informed neural network and deep Q-learning for flow and energy production. We hypothesized that physicsbased machine learning/deep learning can overcome the shortcomings of traditional machine learning methods where data-driven models have faltered beyond the data and physical conditions used for training and validation. We improved and developed novel approaches to demonstrate that physics-based ML can allow us to incorporate physical constraints (e.g., scientific domain knowledge) into ML framework. Outcomes of this project will be readily applicable for many energy and national security problems that are particularly defined by multiscale features and network systems.

58 GEOSCIENCES↗

Bridging the gap between experiments and simulations using machine learning

The physics of inertial confinement fusion is rich and complex. Simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this work we use deep learning to build a fast emulator of experiments. To facilitate the development of the deep-learning model, an autoencoder is used to reduce the dimensionality of the input space. Two deep learning models are developed. One model is trained on a vast array of simulation data and is subsequently calibrated to expensive and limited experimental data using a technique known as “transfer learning.” The other model is trained on a statistical model and is subsequently calibrated using experimental data. A comparative study of the two predictive models is carried out. The models potentially reproduce key experimental observables with high accuracy and unprecedented inference times relative to those achieved with simulation codes. These models facilitate rapid exploration of a high dimensional input parameter space.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Hyperplane decision trees as piecewise linear surrogate models for chemical process design

Recent trends in chemical engineering research point towards an increasing reliance on data-driven modeling approaches. Neural networks, for instance, have proven to be accurate when data is plentiful and high-dimensional, but in many cases, they require computationally-intensive training procedures. Here, in this work, we describe hyperplane decision trees (HT) as a highly expressive and low-compute machine learning model architecture. These models are locally linear and have linear decision boundaries, resulting in a piecewise linear model of the data. This property allows them to be converted into mixed-integer linear constraints which can be globally optimized. Our open-source PyTorch implementation of this method is a fast, flexible, and accessible way to build accurate piecewise linear models of data.

Decision trees↗

A Bayesian Approach to Predict Solubility Parameters

Abstract Solubility is a ubiquitous phenomenon in many aspects of material science. While solubility can be determined by considering the cohesive forces in a liquid via the Hansen solubility parameters (HSP), quantitative structure–property relationship models are often used for prediction, notably due to their low computational cost. Here, gpHSP, an interpretable and versatile probabilistic approach to determining HSP, is reported. Our model is based on Gaussian processes, a Bayesian machine learning approach that provides uncertainty bounds to prediction. gpHSP achieves its flexibility by leveraging a variety of input data, such as SMILES strings, COSMOtherm simulations, and quantum chemistry calculations. gpHSP is built on experimentally determined HSP, including a general solvents set aggregated from the literature, and a polymer set experimentally characterized by this group of authors. In all sets, a high degree of agreement is obtained, surpassing well‐established machine learning methods. The general applicability of gpHSP to miscibility of organic semiconductors, drug compounds, and in general solvents is demonstrated, which can be further extended to other domains. gpHSP is a fast and accurate toolbox, which could be applied to molecular design for solution processing technologies.

Sanchez‐Lengeling, Benjamin↗

SRF cavity instability detection with machine learning at CEBAF

During the operation of the Continuous Electron Beam Accelerator Facility (CEBAF), one or more unstable superconducting radio-frequency (SRF) cavities often cause beam loss trips while the unstable cavities themselves do not necessarily trip off. The present RF controls for the legacy cavities report at only 1 Hz, which is too slow to detectfast transient instabilities during these trip events. These challenges make the identification of an unstable cavity out of the hundreds installed at CEBAF a difficult and time-consuming task. To tackle these issues, a fast data acquisition system (DAQ) for the legacy SRF cavities has been developed, which records the sample at 5 kHz. An unsupervised learning framework has been developed to identify anomalous SRF cavity behavior. We will discuss the present status of the DAQ system and our framework, along with recent successes in detecting anomalous cavity behavior. Overall, our method offers a practical solution for identifying unstable SRF cavities, contributing to increased beam availability and machine reliability.

Accelerator Physics↗

Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches

In superconducting magnets, the irreversible transition of a portion of the conductor to resistive state is called a “quench.” Having large stored energy, magnets can be damaged by quenches due to localized heating, high voltage, or large force transients. Unfortunately, current quench protection systems can only detect a quench after it happens, and mitigating risks in Low Temperature Superconducting (LTS) accelerator magnets often requires fast response (down to ms). Additionally, protection of High Temperature Superconducting (HTS) magnets is still suffering from prohibitively slow quench detection. In this study, we lay the groundwork for a quench prediction system using an auto-encoder fully-connected deep neural network. After dynamically trained with data features extracted from acoustic sensors around the magnet, the system detects anomalous events seconds before the quench in most of our data. While the exact nature of the events is under investigation, we show that the system can “forecast” a quench before it happens under magnet training conditions through a randomized experiment. This opens up the way of integrated data processing, potentially leading to faster and better diagnostics and detection of magnet quenches

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Hydrodynamic and Radiographic Toolbox (HART)

With a multi-lab and university team, we propose to develop new methods for a Hydrodynamic and Radiographic Toolbox (HART) that will enable a fuller and more extensive use of experimental radiographic data towards better characterizing and reducing uncertainties in predictive modeling of weapons performance. We will achieve this by leveraging recent developments in areas of computational imaging, statistical and machine learning, and reduced order modeling of hydrodynamics. In terms of software practices, by partnering with XCP (RISTRA Project) we will conform to recent XCP standards that are inline with modern software practices and standards and ensure compatibility and ease of inter-operability with existing codes. Three new activities under this proposal include (a) the development and use of deep learning-based surrogates to accelerate reconstruction and variational inference of density fields from radiographs of hydrotests, (b) a model-data fusion strategy that couples deep learning-based density reconstructions with fast hydrodynamics simulators to better constrain the reconstruction, and (c) a method for treating asymmetries using techniques adopted from limited view tomography. All three new activities will be based on improved treatment of scatter, noise, beam spot movement, detector blur, and flat fielding in the forward model, and a use of sophisticated priors to aid in the re construction. The improvements to the forward model and improved algorithmic design of the reconstruction when complete will be contained in the iterative reconstruction code SHIVA—a code project that we have recently initiated. The many ways in which machine learning can be used in the reconstruction work will be contained in a code HERMES that has been initiated with DTRA support. For example, the significant levels of acceleration that will likely be achieved by the use of machine learning techniques will permit us (and are required) to quantify uncertainties in density retrievals. Next, the two-way coupling between density reconstruction and model-based simulation of the hydrodynamics will be contained in code EREBUS, and will permit a fuller realization of the potential of the data to constrain the hydrodynamic model and better address issues related to asymmetries in the problem. Finally, we anticipate that the better consistency with physics achieved in our reconstructions will allow them to be used by X-Division more so than today.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Exploring new frontiers in type 1 diabetes through advanced mass-spectrometry-based molecular measurements

Type 1 diabetes (T1D) is a devastating autoimmune disease for which advanced mass spectrometry (MS) methods are increasingly used to identify new biomarkers and better understand underlying mechanisms. For example, integration of MS analysis and machine learning has identified multimolecular biomarker panels. In mechanistic studies, MS has contributed to the discovery of neoepitopes, and pathways involved in disease development and identifying therapeutic targets. However, challenges remain in understanding the role of tissue microenvironments, spatial heterogeneity, and environmental factors in disease pathogenesis. Recent advancements in MS, such as ultra-fast ion-mobility separations, and single-cell and spatial omics, can play a central role in addressing these challenges. Here, in this work, we review recent advancements in MS-based molecular measurements and their role in understanding T1D.

60 APPLIED LIFE SCIENCES↗

Moltensaltpropnet

MoltenSaltPropnet is a physics-informed machine learning framework that aims to predict the thermophysical properties of molten fluoride and chloride salt mixtures, which are crucial for the design and safety of Generation IV molten salt reactors. The code processes data from the Molten-Salt Thermal Properties Database (MSTDB-TP) and the Janz compendium, converting critically evaluated correlations into fast, differentiable surrogate models for density, viscosity, thermal conductivity, and heat capacity across 448 distinct salt systems. The implementation consists of several key components: 1. Data Curation: The code parses and cleans the raw data, normalizing elemental mole fractions and extracting relevant regression coefficients for various thermophysical properties. 2. Feature Engineering: It generates fixed-length numerical descriptors that encapsulate the composition and temperature, incorporating polynomial interaction terms and dimensionality-reduction techniques to optimize model performance. 3. Coefficient Learning: Four different machine learning architectures are employed: a deep residual network (ResNet), a Kolmogorov–Arnold network (KAN), a sparsity-inducing neural network (SNN), and classical regression models. Each model learns to predict coefficients that define the temperature-dependent correlations for the thermophysical properties. 4. Property Reconstruction: The predicted coefficients are used to compute temperature-dependent property values, ensuring positivity and monotonic trends through a composite loss function that enforces physical constraints. 5. User Interface: An open-source web application enables users to filter the database, train task-specific models, and visualize the results, allowing for rapid exploration of candidate salt mixtures. MoltenSaltPropnet bridges the gap between limited experimental data and high-fidelity reactor simulations, providing a powerful tool for researchers in the field of molten salt reactors and advanced nuclear energy systems.

Retamales, Mauricio Eduardo Tano [Idaho National L↗

Applying Linear Optics from Closed Orbits Modulation for finding beam-based alignment of harmonic sextupoles

A fast and accurate beam-based alignment (BBA) method for harmonic sextupoles has been devel oped at NSLS-II using Linear Optics from Closed Orbit Modulation (LOCOM). The approach excites the beam with simultaneous sine-wave signals at two fast correctors, chosen with an appropriate phase advance to span the full betatron phase space. This strategy suppresses systematic errors from hysteresis, while additional errors from orbit drift and power-supply calibration are minimized by the short measurement time (a few minutes) and reliance solely on beam-based current-to-field conver sion of the sextupoles, with hysteresis explicitly included. Simulations indicate that Linear Optics from Closed Orbits (LOCO) combined with 0.5 mm local orbit bumps can resolve relative sextupole field offsets (∆k₂) with precision better than 10% of k₂, reflecting to beam-based alignment (BBA) accuracy finer than 50 µm. Moreover, employing machine-learning-optimized local orbit bumps en hances sextupole-induced quadrupole signals in a deterministic manner and maintains orbit stability under large sextupole strength variations (±40%). The proposed method is experimentally validated through proof-of-principle measurements at NSLS-II, demonstrating its potential as a fast, precise, and robust tool for harmonic sextupole alignment.

43 PARTICLE ACCELERATORS↗

Pushing the Limits of Aquatic Remote Sensing: Synthetic Data and Deep Learning for Fast Inverse Emulation of A Coupled Ocean-Atmosphere Radiative Transfer Model

The inversion of electromagnetic information to physical and biological properties of the water column is a notoriously difficult problem, yet fundamental to our ability of understanding aquatic processes on large time and space scales. There is now a growing necessity to develop pragmatic approaches that allow timely and effective extrapolation of local processes, to spatially resolved global products, and to promote operational and sustainable resource policy management. This presentation will discuss research integrating advanced biological and radiative modeling, high-end computation, and machine learning to develop a portable global processor for simultaneous retrieval of atmosphere and water optics for diverse aquatic systems from the open and coastal ocean to optically extreme inland waters and harmful algal blooms. We will discuss some of the basic concepts behind the forward modeling approach including DEAP, the novel Distributed Equivalent Algal Populations model, for developing large spectral libraries of aquatic particle optics to aid in our ability to distinguish phytoplankton functional types (PFTs) and inorganic material, as well as other factors which enable comprehensive modeling from the benthos to top-of-atmosphere (TOA). This information is being used to understand how we can leverage next-generation deep learning methods for maximum information retrieval and rapid image processing, while also providing capabilities to identify minimum sensor spectral requirements necessary for certain aquatic applications. Further, I will touch on how we envision this research to enable the aquatic community for science discovery and how we are moving closer towards the capability for high-fidelity global analysis of aquatic ecosystems.

Jeremy Alan Kravitz↗

Real-time plasma monitoring framework for advanced plasma control and ML-research in DIII-D

Real-time and adaptive plasma control is crucial for robust tokamak operation, requiring sensitivity and tolerance measurements of the plasma state. This paper presents the implementation of an integrated real-time plasma monitoring framework on the DIII-D tokamak to support advanced control approaches, including machine-learning (ML) methods. The system is built on the SHIELD framework, a high-performance modular architecture that provides a unified pipeline for integrating diverse diagnostics. The framework leverages high-bandwidth digitizers, fast numerical processing, and deterministic, low-latency interconnects to stream high-fidelity data from diagnostics such as electron cyclotron emission (ECE), beam emission spectroscopy (BES), CO interferometers, and a visible tangential divertor camera (TangTV). The system’s validity is demonstrated through direct comparisons of real-time and offline data. Furthermore, we present two key applications of the developed plasma monitoring system with ML-based plasma control strategies, including real-time divertor detachment and active Alfvén Eigenmode control. As a result, this work presents a robust and scalable approach for integrating high-frequency, multidimensional diagnostics into advanced control algorithms for future fusion devices.

AI/ML↗

TOWARD CHARACTERIZATION OF THE TYPE IIP SUPERNOVA PROGENITOR POPULATION: A STATISTICAL SAMPLE OF LIGHT CURVES FROM Pan-STARRS1

In recent years, wide-field sky surveys providing deep multiband imaging have presented a new path for indirectly characterizing the progenitor populations of core-collapse supernovae (SNe): systematic light-curve studies. We assemble a set of 76 grizy-band Type IIP SN light curves from Pan-STARRS1, obtained over a constant survey program of 4 yr and classified using both spectroscopy and machine-learning-based photometric techniques. We develop and apply a new Bayesian model for the full multiband evolution of each light curve in the sample. We find no evidence of a subpopulation of fast-declining explosions (historically referred to as ''Type IIL'' SNe). However, we identify a highly significant relation between the plateau phase decay rate and peak luminosity among our SNe IIP. These results argue in favor of a single parameter, likely determined by initial stellar mass, predominantly controlling the explosions of red supergiants. This relation could also be applied for SN cosmology, offering a standardizable candle good to an intrinsic scatter of ≲ 0.2 mag. We compare each light curve to physical models from hydrodynamic simulations to estimate progenitor initial masses and other properties of the Pan-STARRS1 Type IIP SN sample. We show that correction of systematic discrepancies between modeled and observed SN IIP light-curve properties and an expanded grid of progenitor properties are needed to enable robust progenitor inferences from multiband light-curve samples of this kind. This work will serve as a pathfinder for photometric studies of core-collapse SNe to be conducted through future wide-field transient searches.

79 ASTRONOMY AND ASTROPHYSICS↗