Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “scientific deep 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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
NASA NTRS2023

Gateway Program Safety and Mission Assurance Integration - The Future of Safe Deep Space Human Exploration

As a foundational element of the National Aeronautics and Space Administration (NASA) Artemis Campaign, the Gateway is an incrementally built cislunar spacecraft that will serve as a platform for deep space human exploration, science, and technology demonstration. The Gateway will be a unifying catalyst for partners around the world to establish sustained deep space scientific investigations, lunar surface access, and missions to Mars. As human exploration moves farther from Earth, spacecraft designs must optimize mass and volume while minimizing human and spacecraft risk. To accomplish this, the Gateway Program Safety and Mission Assurance (S&MA) office develops, implements, and ensures compliance with requirements, in concert with the accurate characterization and transparent communication of residual hazard risks, for integrated safety, reliability and maintainability, and quality assurance. This paper will detail the evolution of the Gateway Program S&MA integration functions, and provide its current status and lessons learned for future human spaceflight programs.

Helen Vaccaro↗
DOE OSTI2023

Modeling the 4D discharge of lithium-ion batteries with a multiscale time-dependent deep learning framework

The lithium-ion battery (LIB) field is moving towards the direction of investigating spatially resolved physical phenomena in the 3D porous microstructure of electrodes. These pore-scale simulations give new insights into the local dynamics of lithiation/de-lithiation and charge transport, Nevertheless, the computational time of these simulations limits the integration of these models in optimization workflows of cycling conditions or electrode manufacturing processes. Machine learning models present a way of assessing in real-time the performance of materials. While several successful techniques for replicating simulations with machine learning have been proposed, this case study presents a more demanding problem, due to the necessity of understanding the behavior of heterogeneous 3D local data, as it evolves in time: this poses both a scientific and a technical challenge. To this end, we propose an autoregressive multiscale convolutional neural network model to predict relevant quantities at the pore-scale in the solid phase: the lithium concentration (in the active material) and potential (in the active material and carbon binder). Here, these are ultimately used to reconstruct the battery discharge curve. 3D images of the electrode microstructures are the input to the network, trained with a dataset of finite element method simulations to predict the discharge behavior of the cathode side in lithium ion batteries. We propose this machine learning model as a proof-of-concept of the applicability of multiscale networks for time-dependent physics problems. The trained model exhibits very high accuracy (with errors lower than 2 %) in forecasting the discharge behavior of new unseen cathodes.

25 ENERGY STORAGE↗
NASA NTRS2006

Spitzer Space Telescope Sequencing Operations Software, Strategies, and Lessons Learned

The Space Infrared Telescope Facility (SIRTF) was launched in August, 2003, and renamed to the Spitzer Space Telescope in 2004. Two years of observing the universe in the wavelength range from 3 to 180 microns has yielded enormous scientific discoveries. Since this magnificent observatory has a limited lifetime, maximizing science viewing efficiency (ie, maximizing time spent executing activities directly related to science observations) was the key operational objective. The strategy employed for maximizing science viewing efficiency was to optimize spacecraft flexibility, adaptability, and use of observation time. The selected approach involved implementation of a multi-engine sequencing architecture coupled with nondeterministic spacecraft and science execution times. This approach, though effective, added much complexity to uplink operations and sequence development. The Jet Propulsion Laboratory (JPL) manages Spitzer s operations. As part of the uplink process, Spitzer s Mission Sequence Team (MST) was tasked with processing observatory inputs from the Spitzer Science Center (SSC) into efficiently integrated, constraint-checked, and modeled review and command products which accommodated the complexity of non-deterministic spacecraft and science event executions without increasing operations costs. The MST developed processes, scripts, and participated in the adaptation of multi-mission core software to enable rapid processing of complex sequences. The MST was also tasked with developing a Downlink Keyword File (DKF) which could instruct Deep Space Network (DSN) stations on how and when to configure themselves to receive Spitzer science data. As MST and uplink operations developed, important lessons were learned that should be applied to future missions, especially those missions which employ command-intensive operations via a multi-engine sequence architecture.

missions operations↗
DOE OSTI2024

The SciDAC QuantOm Framework: A composable Workflow

As part of the Scientific Discovery through Advanced Computing (SciDAC) program, the Quantum Chromodynamics Nuclear Tomography (QuantOM) project aims to analyze data from Deep Inelastic Scattering (DIS) experiments conducted at Jefferson Lab and the upcoming Electron Ion Collider. The DIS data analysis is performed on an event-level by leveraging nuclear theory models and accounting for experimental conditions. In order to efficiently run multiple analyses under varying conditions, a composable workflow was designed where each section (theory, experiment, objective minimization, etc.) has its own dedicated module. The optimization, i.e. the fit of theory to experimental data is carried out by deep learning techniques, such as Generative Adversarial Networks (GANs) or Reinforcement Learning (RL). This presentation gives an overview of the current status of the workflow, highlights present and future challenges, and highlights possible extensions to other projects with similar requirements.

Lersch, Daniel↗
DOE OSTI2025

Examples of Mission-driven Data Science from Jefferson Lab and ACES

This presentation details mission-driven data science initiatives at Jefferson Lab and the Joint Institute for Advanced Computing on Environmental Studies (ACES). JLab, a U.S. Department of Energy Office of Science national laboratory, operates the Continuous Electron Beam Accelerator Facility (CEBAF), and is the lead institute for the new High Performance Data Facility (HPDF) Hub. The Joint Institute for ACES brings together interdisciplinary teams in health informatics, climate modeling, computer science, and physics to address environmental challenges, including flood modeling. The Hampton Roads region, particularly Norfolk and Virginia Beach, faces increasing flood risks, motivating the need for rapid, reliable, and risk-aware decision support. ACES’s flooding work has a focus on uncertainty quantification (UQ) and machine learning (ML) for coastal flood management. The work is motivated by the increasing vulnerability of communities such as Norfolk and Virginia Beach, Virginia, to frequent coastal flooding events, and the need for rapid, reliable decision support. The research develops computationally efficient ML surrogate models to forecast water levels and flooding risk. A central theme is the quantification and calibration of predictive uncertainty, especially for out-of-distribution (OOD) scenarios, using techniques such as Monte Carlo Dropout, Deep Ensembles, Gaussian Processes, and Deep Quantile Regression (DQR). The study demonstrates that distance-aware UQ is critical for reliable scientific AI, particularly in high-dimensional, safety-critical, and real-time applications.

McSpadden, Diana [Thomas Jefferson National Accele↗
DOE OSTI2026

Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model

Foundation models for astronomical surveys offer powerful learned representations that can be transferred to downstream regression tasks such as galaxy property estimation. However, point predictions alone are insufficient for scientific inference; reliable uncertainty quantification (UQ) is essential. We compare seven UQ methods on galaxy property regression using frozen AION-1 foundation-model embeddings, predicting redshift, stellar mass, stellar-population age, gas-phase metallicity, and specific star-formation rate, from Legacy Survey photometry/imaging and DESI spectra, with PROVABGS-derived labels. Distribution-free conformal methods achieve marginal coverage within $\sim$1 pp of the nominal 90% across all properties, while non-conformal baselines (Deep Ensembles, MC~Dropout) fail to calibrate reliably. Among conformal approaches, Conformalized Quantile Regression (CQR) delivers the best coverage in the bin with the poorest model predictions. More importantly, only the Locally Valid and Discriminative (LVD) framework -- particularly when operating on AION-1 embeddings -- also provides finite-sample \emph{local validity}, producing intervals that adapt to each galaxy's local prediction difficulty rather than relying on marginal guarantees alone. These results establish conformal prediction, and LVD in particular, as the preferred UQ framework for uncertainty-aware inference on foundation-model embeddings in astrophysics.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗
DOE OSTI2020

Deep learning of free boundary and Stefan problems

Free boundary problems appear naturally in numerous areas of mathematics, science and engineering. These problems present a great computational challenge because they necessitate numerical methods that can yield an accurate approximation of free boundaries and complex dynamic interfaces. In this work, we propose a multi-network model based on physics-informed neural networks to tackle a general class of forward and inverse free boundary problems called Stefan problems. Specifically, we approximate the unknown solution as well as any moving boundaries by two deep neural networks. Besides, we formulate a new type of inverse Stefan problems that aim to reconstruct the solution and free boundaries directly from sparse and noisy measurements. We demonstrate the effectiveness of our approach in a series of benchmarks spanning different types of Stefan problems, and illustrate how the proposed framework can accurately recover solutions of partial differential equations with moving boundaries and dynamic interfaces. All code and data accompanying this manuscript are publicly available at https://github.com/PredictiveIntelligenceLab/DeepStefan.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Robotic Planning under Uncertainty in Spatiotemporal Environments in Expeditionary Science

In the expeditionary sciences, spatiotemporally varying environments -- hydrothermal plumes, algal blooms, lava flows, or animal migrations -- are ubiquitous. Mobile robots are uniquely well-suited to study these dynamic, mesoscale natural environments. We formalize expeditionary science as a sequential decision-making problem, modeled using the language of partially-observable Markov decision processes (POMDPs). Solving the expeditionary science POMDP under real-world constraints requires efficient probabilistic modeling and decision-making in problems with complex dynamics and observational models. Previous work in informative path planning, adaptive sampling, and experimental design have shown compelling results, largely in static environments, using data-driven models and information-based rewards. However, these methodologies do not trivially extend to expeditionary science in spatiotemporal environments: they generally do not make use of scientific knowledge such as equations of state dynamics, they focus on information gathering as opposed to scientific task execution, and they make use of decision-making approaches that scale poorly to large, continuous problems with long planning horizons and real-time operational constraints. In this work, we discuss these and other challenges related to probabilistic modeling and decision-making in expeditionary science, and present some of our preliminary work that addresses these gaps. We ground our results in a real expeditionary science deployment of an autonomous underwater vehicle (AUV) in the deep ocean for hydrothermal vent discovery and characterization. Our concluding thoughts highlight remaining work to be done, and the challenges that merit consideration by the reinforcement learning and decision-making community.

Preston, Victoria↗
DOE OSTI2022

Bayesian Active Learning for Scanning Probe Microscopy: From Gaussian Processes to Hypothesis Learning

Recent progress in machine learning methods and the emerging availability of programmable interfaces for scanning probe microscopes (SPMs) have propelled automated and autonomous microscopies to the forefront of attention of the scientific community. However, enabling automated microscopy requires the development of task-specific machine learning methods, understanding the interplay between physics discovery and machine learning, and fully defined discovery workflows. This, in turn, requires balancing the physical intuition and prior knowledge of the domain scientist with rewards that define experimental goals and machine learning algorithms that can translate these to specific experimental protocols. Here, we discuss the basic principles of Bayesian active learning and illustrate its applications for SPM. We progress from the Gaussian process as a simple data-driven method and Bayesian inference for physical models as an extension of physics-based functional fits to more complex deep kernel learning methods, structured Gaussian processes, and hypothesis learning. These frameworks allow for the use of prior data, the discovery of specific functionalities as encoded in spectral data, and exploration of physical laws manifesting during the experiment. Here, the discussed framework can be universally applied to all techniques combining imaging and spectroscopy, SPM methods, nanoindentation, electron microscopy and spectroscopy, and chemical imaging methods and can be particularly impactful for destructive or irreversible measurements.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Solving inverse problems in stochastic models using deep neural networks and adversarial training

Inverse problems associated with stochastic models constitute a significant portion of scientific and engineering applications. In such cases the unknown quantities are distributions. The applicability of traditional methods is limited because of their demanding assumptions or prohibitive computational consumption; for example, maximum likelihood methods require closed-form density functions, and Markov Chain Monte Carlo needs a large number of simulations. We propose a new method that estimates the unknown distribution by matching the statistical properties between observed and simulated random processes. We leverage the expressive power of neural networks to approximate the unknown distribution and use a discriminative neural network for computing the statistical discrepancies between the observed and simulated random processes. Here we demonstrated numerically that the proposed methods can estimate both the model parameters and learn complicated unknown distributions.

42 ENGINEERING↗
DOE OSTI2025

DS-TIDE: Harnessing Dynamical Systems for Efficient Time-Independent Differential Equation Solving

Time-Independent Differential Equations (TIDEs) are central to modeling equilibrium behavior across a wide range of scientific and engineering domains, from electrostatics to porous media flow. Conventional numerical solvers offer reliable solutions but incur significant computational costs due to fine-grained discretization and iterative procedures. Machine learning-based approaches address this by replacing iterative solving processes with one-time inference; however, their sophisticated models require extensive training resources that often exceed those of traditional solvers. Consequently, designing a TIDE solver that achieves high accuracy, broad applicability, and exceptional computational efficiency remains a fundamental challenge. In this paper, we propose DS-TIDE, a novel hardware solver that is inspired by, and subsequently leverages, the intrinsic connection between Dynamical Systems (DS) and Differential Equations (DEs) to efficiently and accurately solve TIDEs. DS-TIDE employs a CMOS-compatible DS-based processor, whose physical states evolve under carefully designed DE-driven dynamics and naturally converge to equilibrium -- the solution of the target TIDE -- within ~1µs on a ~1-watt DS-TIDE processor. To enhance expressivity, DS-TIDE incorporates Heterogeneous Dynamics with Temporal Layering (HDTL), which solves TIDEs through a three-stage DS evolution -- conditioning, solving, and decoding -- each governed by specialized dynamics. The entire evolution process is analogous to an infinitely deep neural network temporally unrolled, offering the system the capability of representing complex equations. Furthermore, DS-TIDE is equipped with an on-device DS-DE Auto-Alignment mechanism that dynamically adapts intrinsic hardware dynamics within milliseconds, effectively aligning the system’s dynamics to diverse target DEs. Experimental results across TIDEs from a wide range of scientific and engineering domains demonstrate that DS-TIDE achieves ~10^3× speedup, ~10^5× energy savings, and competitive or superior accuracy compared to state-of-the-art numerical and ML-based solvers.

Liu, Chuan↗
NASA NTRS2016

Status and Path Forward for the Large Ultraviolet Optical Infrared Surveyor (LUVOIR) Mission Concept Study

In preparation of the 2020 Astrophysics Decadal Survey, National Aeronautics and Space Administration (NASA) has commenced a process for the astronomical community to study several large mission concepts leveraging the lessons learned from past Decadal Surveys. This will enable the Decadal Survey committee to make more informed recommendations to NASA on its astrophysics science and mission priorities with respect to cost and risk. Four astrophysics large mission concepts were identified. Each of them had a Science and Technology Definition Teem(STDT) chartered to produce scientifically compelling, feasible, and executable design reference mission (DRM)concepts to present to the 2020 Decadal Survey. In addition, The Aerospace Corporation will perform an independent cost and technical evaluation (CATE) of each of these mission concept studies in advance of the 2020 Decadal Survey by interacting with the STDTs to provide detailed technical details on certain areas for which deep dives are appropriate. This paper presents the status and path forward for one of the four large mission concepts, namely, the Large UltraViolet, Optical, InfraRed surveyor (LUVOIR).

Study Office: science analyses↗
DOE OSTI2021

Efficient Data Compression for 3D Sparse TPC via Bicephalous Convolutional Autoencoder

Real-time data collection and analysis in large experimental facilities present a great challenge across multiple domains, including high energy physics, nuclear physics, and cosmology. To address this, machine learning (ML)-based methods for real-time data compression have drawn significant attention. However, unlike natural image data, such as CIFAR and ImageNet that are relatively small-sized and continuous, scientific data often come in as three-dimensional 3D data volumes at high rates with high sparsity (many zeros) and non-Gaussian value distribution. This makes direct application of popular ML compression methods, as well as conventional data compression methods, suboptimal. To address these obstacles, this work introduces a dual-head autoencoder to resolve sparsity and regression simultaneously, called Bicephalous Convolutional AutoEncoder (BCAE). This method shows advantages both in compression fidelity and ratio compared to traditional data compression methods, such as MGARD, SZ, and ZFP. To achieve similar fidelity, the best performer among the traditional methods can reach only half the compression ratio of BCAE. Moreover, a thorough ablation study of the BCAE method shows that a dedicated segmentation decoder improves the reconstruction.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRS2018

Digital Technologies at NASA for Science and Engineering

While scientific and engineering advancements used to rely primarily on theoretical studies and physical experiments, today digital technology enabled by petaflops-scale supercomputers is an equal, if not a greater, contributor to such achievements. In addition, computational modeling and simulation serves as a predictive tool that is not otherwise available. As a result, the use of high performance computing is integral to NASA's work in all mission areas such as space exploration, aeronautics, and scientific discovery. But traditional supercomputing alone is not sufficient for all of the space agency's needs. The success of many NASA missions depends on solving complex computing challenges, some of which are NP-hard (decision theory) if using classical solution methods. Quantum computing promises an unprecedented ability to solve such intractable problems by harnessing quantum mechanical effects such as tunneling, superposition, and entanglement. Another disruptive digital technology is neuromorphic computing that uses brain-inspired lessons to generate new architectures that are much more energy efficient, and capable of massive parallel processing and learning in-situ. Finally, with large amounts of observational and computational data sets, the opportunities of big data and data analytics can be leveraged to enable deep learning and knowledge discovery - it's all a massive digital transformation. This talk will be an overview how NASA utilizes digital technologies for its science and engineering efforts.

Biswas, Rupak↗
DOE OSTI2025

A fault-tolerant neutral-atom architecture for universal quantum computation

Quantum error correction (QEC) is essential for the realization of large-scale quantum computers. However, owing to the complexity of operating on the encoded ‘logical’ qubits, understanding the physical principles for building fault-tolerant quantum devices and combining them into efficient architectures is an outstanding scientific challenge. Here we use reconfigurable arrays of up to 448 neutral atoms to implement the key elements of a universal, fault-tolerant quantum processing architecture and experimentally explore their underlying working mechanisms. We first use surface codes to study how repeated QEC suppresses errors, demonstrating 2.14(13)x below-threshold performance in a four-round characterization circuit by leveraging atom loss detection and machine learning decoding. We then investigate logical entanglement using transversal gates and lattice surgery and extend it to universal logic through transversal teleportation with three-dimensional [[15,1,3]] codes, enabling arbitrary-angle synthesis with polylogarithmic overhead. Finally, we develop mid-circuit qubit reuse16, increasing experimental cycle rates by two orders of magnitude and enabling deep-circuit protocols with dozens of logical qubits and hundreds of logical teleportations with [[7,1,3]] and high-rate [[16,6,4]] codes while maintaining constant internal entropy. Our experiments show key principles for efficient architecture design, involving the interplay between quantum logic and entropy removal, judiciously using physical entanglement in logic gates and magic state generation, and leveraging teleportations for universality and physical qubit reset. These results establish foundations for scalable, universal error-corrected processing and its practical implementation in neutral atom systems.

atomic and molecular physics↗
DOE OSTI2022

SULI Research Report Paper

The Intelligence and Space Research Group 4 (ISR-4) at the Los Alamos National Laboratory focuses on signal processing and developing space electronics for various national security missions. The Space and Atmospheric Burst Reporting System (SABRS) is a sensing payload designed for nuclear detonation detection. As the sensors from previous payloads become obsolete, the requirement for a novel payload design increases. SABRS Prime is the successor to the previous SABRS payloads and is scheduled for delivery in 2028. As part of the SABRS Prompt Gamma Instrument Interface Board, high frequency signals from silicon photomultiplier tubes need to be split and subsequently transmitted to the Analog to Digital Converter. Prior to developing the Space Grade Instrument Interface Board, evaluation modules with Commercial off-the-shelf (COTS) components are evaluated and tested under rigorous conditions. Verification of power levels and gain specifications are some of the important steps taken during the evaluation stage. Working on the Signal Splitting Board has enabled me to work with various schematic software applications and learn more about the processes behind designing space grade electronic components. In addition, I conducted research on efficiency improvements for space-based power systems. Changes in design approaches were found to be the most significant sources of improvement. Being able to interact with researchers and peers across various scientific disciplines has given me a better insight into my future pursuits. Working in a R&D environment has cemented my decision to work on space applications for Quantum Sensing and pursue a PhD in Electrical Engineering. The SULI internship program at the Los Alamos National Laboratory has helped me develop the skillset of a researcher, understand the rigorous processes behind developing space grade hardware, and improve my critical thinking abilities to support the development of reliable instrumentation for deep space missions.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2026

Microsecond-latency feedback at a particle accelerator by online reinforcement learning on hardware

The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution due to their ability to dynamically adapt to changing environments and consider delayed consequences. In many real-world applications, RL policies must produce actions in real time, often within microseconds to milliseconds, imposing significant constraints on system latency and computational overhead that conventional machine learning libraries are not designed to handle. To control phenomena in real time at these timescales, RL needs to be deployed on-the-edge, namely on dedicated hardware located near the system it controls, without relying on a host CPU or cloud-based inference. In this work we present the design and deployment of an experience accumulator system in a particle accelerator. In this system, deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of phenomena like beam instabilities. The training uses the collected data offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator, a synchrotron light source, where the system was used to control artificially induced horizontal betatron oscillations in real-time, with a control loop period of just 2.7 μs. The results showed a performance comparable to the commercial feedback system available at the accelerator, demonstrating the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, a seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.

FPGA↗
DOE OSTI2023

Towards On-Chip Learning for Low Latency Reasoning with End-to-End Synthesis

The Software Defined Architectures (SODA) Synthesizer is an open-source compiler-based tool able to automatically generate domain-specialized systems targeting Application-Specific Integrated Circuits (ASICs) or Field Programmable Gate Arrays (FPGAs) starting from high-level programming. SODA is composed of a frontend, SODA-OPT, which leverages the multilevel intermediate representation (MLIR) framework to interface with productive programming tools (e.g., machine learning frame-works), identify kernels suitable for acceleration, and perform high-level optimizations, and of a state-of-the-art high-level synthesis backend, Bambu from the PandA framework, to generate custom accelerators. One specific application of the SODA Synthesizer is the generation of accelerators to enable ultra-low latency inference and control on autonomous systems for scientific discovery (e.g., electron microscopes, sensors in particle accelerators, etc.). This paper provides an overview of the flow in the context of the generation of accelerators for edge processing to be integrated in transmission electron microscopy (TEM) devices, focusing on use cases from precision material synthesis. We show the tool in action with an example of design space exploration for inference on reconfigurable devices with a conventional deep neural network model (LeNet). Finally, we discuss the research directions and opportunities enabled by SODA in the area of autonomous control for scientific experimental workflows.

Castellana, Vito G.↗