Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning based systems”

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 1,117 records · Page 62
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Orion SysML Model, Digital Twin, and Lessons Learned for Artemis I

In 2015 it was recognized by NASA’s Orion Chief Engineer that NASA’s design insight into the Orion subsystems for Artemis I were not sufficient to provide traditional engineering support to flight operations. To address these concerns and provide an opportunity to apply emerging model-based systems engineering and digital twin methodologies and provide opportunities for employees across NASA to get hands-on training, an Orion digital twin pilot project was initiated in 2020. With the increase in complexities of spacecraft, and decreased time to made decisions during missions in critical or emergency situations, digital modeling and integration of design can reduce the time to answer questions by days and required human resources by an order of magnitude over historical approaches and was identified to be critical capability for NASA’s future. This paper describes the genesis of this digital twin pilot project, efforts undertaken, a reproducible methodology to take available system information from a mature program to create an executable SysML model that supports a link to unit-specific data, thus forming a connection to the physical asset, and associated lessons learned and project deliverables.

MBSE↗
DOE OSTI2018

ODDS: Real-Time Object Detection Using Depth Sensors on Embedded GPUs

Detecting objects that are carried when someone enters or exits a room is very useful for a wide range of smart building applications including safety, security, and energy efficiency. While there has been a significant amount of work on object recognition using large-scale RGB image datasets, RGB cameras are too privacy invasive in many smart building applications and they work poorly in the dark. Additionally, deep object detection networks require powerful and expensive GPUs. We propose a novel system that we call ODDS (Object Detector using a Depth Sensor) that can detect objects in real-time using only raw depth data on an embedded GPU, e.g., NVIDIA Jetson TX1. Hence, our solution is significantly less privacy invasive (even if the sensor is compromised) and less expensive, while maintaining a comparable accuracy with state of the art solutions. Specifically, we resort to training a deep convolutional neural network using raw depth images, with curriculum based learning to improve accuracy by considering the complexity and imbalance in object classes and developing a sparse coding based technique that speeds up the system ~2× with minimal loss of accuracy. Based on a complete implementation and real-world evaluation, we see ODDS achieve 80.14% mean average precision in object detection in real-time (5-6 FPS) on a Jetson TX1.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Transfer learning of memory kernels for transferable coarse-graining of polymer dynamics

The present work concerns the transferability of coarse-grained (CG) modeling in reproducing the dynamic properties of the reference atomistic systems across a range of parameters. In particular, we focus on implicit-solvent CG modeling of polymer solutions. The CG model is based on the generalized Langevin equation, where the memory kernel plays the critical role in determining the dynamics in all time scales. Thus, we propose methods for transfer learning of memory kernels. The key ingredient of our methods is Gaussian process regression. By integration with the model order reduction via proper orthogonal decomposition and the active learning technique, the transfer learning can be practically efficient and requires minimum training data. Through two example polymer solution systems, we demonstrate the accuracy and efficiency of the proposed transfer learning methods in the construction of transferable memory kernels. The transferability allows for out-of-sample predictions, even in the extrapolated domain of parameters. Built on the transferable memory kernels, the CG models can reproduce the dynamic properties of polymers in all time scales at different thermodynamic conditions (such as temperature and solvent viscosity) and for different systems with varying concentrations and lengths of polymers.

Ma, Zhan↗
NASA NTRS2008

Development of Improved Aerogels for Spacecraft Hypervelocity Capture

The highly successful NASA Discovery mission Stardust became the first mission to return samples to Earth from a known comet in January 2006 [1]. The samples were captured during a flyby of comet 81P/Wild2 using aerogel, a very low density, silica (SiO2)-based solid with a highly porous structure [2]. Currently, scientists around the world are studying the cometary particles returned by Stardust and reporting fascinating discoveries about the history of comets and the evolution of our solar system. Given the widely acknowledged success of the Stardust mission, additional comet sample return missions are attractive and competitive concepts for future NASA Discovery-class missions; in particular, additional comet sample return missions will allow the first laboratory studies to investigate the naturally occurring diversity among comets, a crucial scientific question for understanding not just the formation of comets but also the very nature of the early solar system. Though Stardust was highly successful, there are important lessons learned from the mission on which advances in aerogel technology can be based

Lisse, C. M.↗
DOE OSTI2019

A real-time machine learning-based disruption predictor in DIII-D

A disruption prediction algorithm, named DPRF (Disruption Prediction using Random Forests), has run in real-time in the DIII-D plasma control system (PCS) over more than 900 discharges. DPRF naturally provides a probability mapping associated to its predictions, i.e. the disruptivity signal, now incorporated in the DIII-D PCS. Here, we report on disruption prediction accomplishments in terms of shot-by-shot performances, by simulating alarms on each discharge as in the PCS framework. Due to the optimised performance metric chosen to evaluate DPRF, we find that almost all disruptive discharges are detected in average with few hundred of milliseconds of warning time, but this comes at a high cost of false alarms produced. Performances are not satisfying ITER requirements, where the success rate has to be higher than 95%, but this is not completely unexpected. DPRF is trained on many years of major disruptions occurring during the flattop phase of the plasma current on DIII-D, but without any differentiation by cause. Furthermore, we find that DPRF is affected by a relatively high fraction of false alarms occurring during the first 500 milliseconds from the flattop onset. This subtle effect, more evident on the discharges where DPRF ran in real-time, can be marginalized by taking specific precautions on the validity range of the predictions, and performances do improve. Even if presently burdened by some limitations, DPRF provides an incredible and novel advantage. Thanks to the feature contribution analysis (e.g., the identification of which signals contributed to triggering an alarm), it is possible to interpret and explain DPRF predictions. It is the first time that such interpretability features is exploited by a disruption predictor: by uncovering the disruption events' causes, a better understanding of disruption dynamics is achieved, and a clear path toward the design of disruption avoidance strategies can be provided.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2018

Generating Exploration Mission-3 Trajectories to a 9:2 NRHO using Machine Learning

The purpose of this thesis is to design a machine learning algorithm platform that provides expanded knowledge of mission availability through a launch season by improving trajectory resolution and introducing launch mission forecasting. The specific scenario addressed in this paper is one in which data is provided for four deterministic translational maneuvers through a mission to a Near Rectilinear Halo Orbit (NRHO) with a 9:2 synodic frequency. Current launch availability knowledge under NASA's Orion Orbit Performance Team is established by altering optimization variables associated to given reference launch epochs. This current method can bean abstract task and relies on an orbit analyst to structure a mission based on an established mission design methodology associated to the performance of Orion and NASA's Space Launch System. Introducing a machine learning algorithm trained to construct mission scenarios within the feasible range of known trajectories reduces the required interaction of the orbit analyst by removing the needed step of optimizing the orbit to fit an expected translational response required of the spacecraft. In this study, k-Nearest Neighbor and Bayesian Linear Regression successfully predicted classical orbital elements for the launch windows observed. However both algorithms had limitations due to their approaches to model fitting. Training machine learning algorithms off of classical orbital elements introduced a repetitive approach to reconstructing mission segments for different arrival opportunities through the launch window and can prove to be a viable method of launch window scan generation for future missions.

Guzman, Esteban↗
DOE OSTI2017

Self-learning Monte Carlo method and cumulative update in fermion systems

In this study, we develop the self-learning Monte Carlo (SLMC) method, a general-purpose numerical method recently introduced to simulate many-body systems, for studying interacting fermion systems. Our method uses a highly efficient update algorithm, which we design and dub “cumulative update”, to generate new candidate configurations in the Markov chain based on a self-learned bosonic effective model. From a general analysis and a numerical study of the double exchange model as an example, we find that the SLMC with cumulative update drastically reduces the computational cost of the simulation, while remaining statistically exact. Remarkably, its computational complexity is far less than the conventional algorithm with local updates.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Temporal Characterization and Filtering of Sensor Data to Support Anomaly Detection

Here, we present an approach for characterizing complex temporal behavior in the sensor measurements of a system in order to support detection of anomalies in that system. We first characterize typical behavior by extending a hidden Markov model-based approach to time series alignment. We then use a trace of that learned behavior to develop a particle filter that enables efficient estimation of the filtering distribution on the state space. This produces filtered residuals that can then be used in an anomaly detection framework. Our motivating example is the daily behavior of a building’s heating, ventilation, and air conditioning (HVAC) system, using sensor measurements that arrive every minute and induce a state space with 15,120 states. We provide an end-to-end demonstration of our approach showing improved performance of anomaly detection after application of alignment and filtering compared to the unaligned data. The proposed model is implemented as a computationally efficient R package alignts (align time series) built with R and Fortran 95 with OpenMP support.

47 OTHER INSTRUMENTATION↗
NASA NTRSDate not supplied

Designing Autonomy into Interfaces for Long-Duration Missions

As NASA develops technologies for long-duration crewed missions, we must understand how communication between ground control teams and astronauts differs from the current dynamic to adapt new concepts for long-duration mission operations. Today, ground control teams support astronauts with immediate availability to answer questions, resolve issues, and manage activities. In the near future, however, extended communication delays during long-duration missions will require astronauts to become more autonomous. As many of the responsibilities shift from the ground control teams to the astronauts on-board, the concept of operations must also change from how it functions today. With increased astronaut autonomy, software tools must be developed that enable efficient completion of mission tasks without increased mental workload. Designing software tools to facilitate crew autonomy requires development teams to know which data will enhance quick decision making while providing necessary context for situational awareness of systems being managed on-board. NASA's Autonomous Systems and Operations (ASO) team is presently developing a software interface tool, EXPRESS (EXpedite the PRocessing of Experiments for Space Station) 2.5 to enable a long-duration crew to schedule activities for and operate autonomous systems. This paper describes details of the integrated human factors approach that drove the design of the elements of the software tool, including self-managed scheduling, constraint-driven planning, autonomous system fault recovery, and recommended troubleshooting actions. Additionally, this paper will chronicle ASO modifications of the user interface after the team's first flight demonstration, how it was based on lessons learned during software development, as well as from crew feedback in order to develop the current version which will be demonstrated on ISS in 2021. In the upcoming ISS demonstration, the astronaut crew will be given scenarios for scheduling and operating autonomous system activities, including off-nominal scenarios and autonomous system recoveries. The demonstration of the EXPRESS 2.5 tool is a step towards improved levels of autonomy as our new journeys take us farther into space.

autonomy↗
DOE OSTI2021

Development of Digital Twin Predictive Model for PWR Components: Updates on Multi Times Series Temperature Prediction Using Recurrent Neural Network, DMW Fatigue Tests, System Level Thermal-Mechanical-Stress Analysis

The long-term operation (LTO) of nuclear power plant (NPP) beyond their original design life of 40 years, can lead to more material damage associated with cyclic fatigue under thermal-mechanical loading cycles and associated long-term exposure of reactor material to the deleterious reactor-coolant environments. However, under this LTO condition the reactor components can still safely operate but may require more frequent Nondestructive Evaluation (NDE) of reactor components. Frequent NDE requirement may lead to frequent shutdown of the NPP. This in turn can lead to power outage and additional NDE-inspection-cost related economic loss. The economic loss can be minimized by reducing uncertainty in life estimation of safety-critical pressure boundary components and by implementing more digital approach such as by using upcoming digital-twin (DT) technology for predicting the structural states (e.g., time and location dependent inside/outside thickness temperature, stress, strain, plastic deformation, etc.) and associated fatigue life of a component in real time. Towards this goal Argonne National Laboratory (ANL) with the sponsorship of DOE Light Water Reactor Sustainability (LWRS) program is working on the development of a DT framework that can be used for real time environmental fatigue prediction of reactor components. The DT framework is based on limited experiment-data, Artificial-intelligence (AI) – Machine-Learning (ML) - Deep-Learning (DL) based techniques and Multiphysics-computational-mechanics such as finite element (FE) based modeling tools. Towards this overall goal, following are some of the major contributions made during the FY21: 1) Multiple 82/182 dissimilar metal weld (DMW) specimens (both solid-weld and joint-weld representing the actual reactor multi-metal nozzles) were fatigue tested. The resulting fatigue lives were compared to the NUREG-6909 based best-fit and design fatigue curves. Additionally, the results of 52/152 DMW fatigue specimens (which were recently tested at Republic of Korea under the sponsorship of International Nuclear Energy Research Initiative - INERI program) were compared to the NUREG-6909 based best-fit and design fatigue curves. From the comparison of 82/182 and 52/152 DMW test data with NUREG-6909 best-fit curve, most of the reported test data fall way away from the NUREG-6909 suggested best-fit or mean curve. The NUREG-6909 suggested best-fit curve is the best-fit curve of austenitic stainless steel and due to lack of enough data on Nickel-based welds, this is currently being used for predicting the life of Nickel-alloy-based welded components. However, the above observation may require higher scaling factor (e.g., ASME suggested factor of 20 on cycles rather than the current NUREG-6909 suggested factor of 12 on cycles) for scaling the austenitic-stainless-steel best-fit-curve for estimating the design or safe-life of a welded component. Accordingly, for example, if a DMW component experience a strain amplitude of 0.6% the PWR-water life of the component would be 52 cycles instead of 85 cycles. However, more DMW tests are required to further ascertain the above-mentioned observations. 2) A system level CAD and finite element model were developed which consists of reactor pressure vessel (RPV), part of steam generator (SG), part of pressurizer (PRZ), hot leg (HL), and surge line (SL). This is with detailed nozzle geometry and thermal-mechanical material properties of different metals to simulate realistic thermal-mechanical stress under connected system global thermal-mechanical boundary conditions. 3) Different system level heat transfer analyses were performed with estimation of relevant heat transfer coefficients. The resulting data were used in subsequent system level thermal-mechanical stress analysis and for generating spatial-temporal training and validation data for a system level digital-twin based temperature predictor. Transient heat transfer analyses were performed considering thermal boundary condition under design-basis (DB) loading and EDF (Électricité de France) data-based grid-load-following (EDF-GLF) loading cycles. 4) System level thermal-mechanical stress analysis was performed for identifying damage-prone hotspots and for future extension of the model for cyclic state prediction. From the system-level model simulation under DB loading cycle it is found that HL and the SL nozzle that connect to the HL can experience significant stress and strain and could be one of the weakest links in the overall reactor coolant system (RCS). 5) An AI/ML based DT model was developed for multi-time-series temperature prediction at any inside/outside thickness locations of PWR pressure boundary components. This is by using Recurrent-neural-network (RNN) and keras machine learning libraries. The RNN model was validated against two laboratory test-based data sets with one obtained through ANL’s in-air fatigue test system and other through PWR-water test loop. The experimentally validated DT model further validated against FE model results to predict thermal scarification related spatialtemporal temperatures at random locations of a component. The well validated DT model was then used for demonstrating spatial-temporal temperature prediction under 100+ years of reactor operation subjected to combined DB, EDF-GLF and randomized grid-load-following (RANDOMGLF) loading Cycles. The expert-elicitation DT model framework was developed assuming field/input/process measurements can be available from a few existing plant sensors and can readily be used by the NPP operators. The above temperature prediction model will feed to the next-step stress analysis model based on which the life of a component can be predicted in realtime, which is one of our future works.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

DiffLense: a conditional diffusion model for super-resolution of gravitational lensing data

Abstract Gravitational lensing data is frequently collected at low resolution due to instrumental limitations and observing conditions. Machine learning-based super-resolution techniques offer a method to enhance the resolution of these images, enabling more precise measurements of lensing effects and a better understanding of the matter distribution in the lensing system. This enhancement can significantly improve our knowledge of the distribution of mass within the lensing galaxy and its environment, as well as the properties of the background source being lensed. Traditional super-resolution techniques typically learn a mapping function from lower-resolution to higher-resolution samples. However, these methods are often constrained by their dependence on optimizing a fixed distance function, which can result in the loss of intricate details crucial for astrophysical analysis. In this work, we introduce DiffLense , a novel super-resolution pipeline based on a conditional diffusion model specifically designed to enhance the resolution of gravitational lensing images obtained from the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP). Our approach adopts a generative model, leveraging the detailed structural information present in Hubble space telescope (HST) counterparts. The diffusion model, trained to generate HST data, is conditioned on HSC data pre-processed with denoising techniques and thresholding to significantly reduce noise and background interference. This process leads to a more distinct and less overlapping conditional distribution during the model’s training phase. We demonstrate that DiffLense outperforms existing state-of-the-art single-image super-resolution techniques, particularly in retaining the fine details necessary for astrophysical analyses.

Computer Science↗
NASA NTRS2003

Flight Test of an Intelligent Flight-Control System

The F-15 Advanced Controls Technology for Integrated Vehicles (ACTIVE) airplane (see figure) was the test bed for a flight test of an intelligent flight control system (IFCS). This IFCS utilizes a neural network to determine critical stability and control derivatives for a control law, the real-time gains of which are computed by an algorithm that solves the Riccati equation. These derivatives are also used to identify the parameters of a dynamic model of the airplane. The model is used in a model-following portion of the control law, in order to provide specific vehicle handling characteristics. The flight test of the IFCS marks the initiation of the Intelligent Flight Control System Advanced Concept Program (IFCS ACP), which is a collaboration between NASA and Boeing Phantom Works. The goals of the IFCS ACP are to (1) develop the concept of a flight-control system that uses neural-network technology to identify aircraft characteristics to provide optimal aircraft performance, (2) develop a self-training neural network to update estimates of aircraft properties in flight, and (3) demonstrate the aforementioned concepts on the F-15 ACTIVE airplane in flight. The activities of the initial IFCS ACP were divided into three Phases, each devoted to the attainment of a different objective. The objective of Phase I was to develop a pre-trained neural network to store and recall the wind-tunnel-based stability and control derivatives of the vehicle. The objective of Phase II was to develop a neural network that can learn how to adjust the stability and control derivatives to account for failures or modeling deficiencies. The objective of Phase III was to develop a flight control system that uses the neural network outputs as a basis for controlling the aircraft. The flight test of the IFCS was performed in stages. In the first stage, the Phase I version of the pre-trained neural network was flown in a passive mode. The neural network software was running using flight data inputs with the outputs provided to instrumentation only. The IFCS was not used to control the airplane. In another stage of the flight test, the Phase I pre-trained neural network was integrated into a Phase III version of the flight control system. The Phase I pretrained neural network provided realtime stability and control derivatives to a Phase III controller that was based on a stochastic optimal feedforward and feedback technique (SOFFT). This combined Phase I/III system was operated together with the research flight-control system (RFCS) of the F-15 ACTIVE during the flight test. The RFCS enables the pilot to switch quickly from the experimental- research flight mode back to the safe conventional mode. These initial IFCS ACP flight tests were completed in April 1999. The Phase I/III flight test milestone was to demonstrate, across a range of subsonic and supersonic flight conditions, that the pre-trained neural network could be used to supply real-time aerodynamic stability and control derivatives to the closed-loop optimal SOFFT flight controller. Additional objectives attained in the flight test included (1) flight qualification of a neural-network-based control system; (2) the use of a combined neural-network/closed-loop optimal flight-control system to obtain level-one handling qualities; and (3) demonstration, through variation of control gains, that different handling qualities can be achieved by setting new target parameters. In addition, data for the Phase-II (on-line-learning) neural network were collected, during the use of stacked-frequency- sweep excitation, for post-flight analysis. Initial analysis of these data showed the potential for future flight tests that will incorporate the real-time identification and on-line learning aspects of the IFCS.

Davidson, Ron↗
NASA NTRS2016

Estimation of Optimum Stimulus Amplitude for Balance Training using Electrical Stimulation of the Vestibular System

Sensorimotor changes such as posture and gait instabilities can affect the functional performance of astronauts after gravitational transitions. Sensorimotor Adaptability (SA) training can help alleviate decrements on exposure to novel sensorimotor environments based on the concept of 'learning to learn' by exposure to varying sensory challenges during posture and locomotion tasks (Bloomberg 2015). Supra-threshold Stochastic Vestibular Stimulation (SVS) can be used to provide one of many challenges by disrupting vestibular inputs. In this scenario, the central nervous system can be trained to utilize veridical information from other sensory inputs, such as vision and somatosensory inputs, for posture and locomotion control. The minimum amplitude of SVS to simulate the effect of deterioration in vestibular inputs for preflight training or for evaluating vestibular contribution in functional tests in general, however, has not yet been identified. Few studies (MacDougall 2006; Dilda 2014) have used arbitrary but fixed maximum current amplitudes from 3 to 5 mA in the medio-lateral (ML) direction to disrupt balance function in healthy adults. Giving this high level of current amplitude to all the individuals has a risk of invoking side effects such as nausea and discomfort. The goal of this study was to determine the minimum SVS level that yields an equivalently degraded balance performance. Thirteen subjects stood on a compliant foam surface with their eyes closed and were instructed to maintain a stable upright stance. Measures of stability of the head, trunk, and whole body were quantified in the ML direction. Duration of time they could stand on the foam surface was also measured. The minimum SVS dosage was defined to be that level which significantly degraded balance performance such that any further increase in stimulation level did not lead to further balance degradation. The minimum SVS level was determined by performing linear fits on the performance variable at different stimulation levels. Results from the balance task suggest that there are inter-individual differences and the minimum SVS amplitude was found to be in the range of 1 mA to 2.5 mA across subjects. SVS resulted in an average decrement of balance task performance in the range of 62%-73% across different measured variables at the minimum SVS amplitude in comparison to the control trial (no stimulus). Training using supra-threshold SVS stimulation is one of the sensory challenges used for preflight SA training designed to improve adaptability to novel gravitational environments. Inter-individual differences in response to SVS can help customize the SA training paradigms using minimal dosage required. Another application of using SVS is to simulate acute deterioration of vestibular sensory inputs in the evaluation of tests for assessing vestibular function.

Goel, R.↗
DOE OSTI2022

Deep Reinforcement Learning From Demonstrations to Assist Service Restoration in Islanded Microgrids

Microgrids can be operated in island mode during utility grid outages to support service restoration and improve system resilience. To schedule and dispatch distributed energy resources (DERs) in an islanded microgrid, conventional model-based methods rely on accurate distribution network models and lack generalization and adaptability. Data-driven methods are promising for DER coordination but face practical challenges such as potential hazards to microgrids during online training and insufficient online training opportunities due to low outage rates. This paper presents a novel two-stage learning framework that builds on the deep deterministic policy gradient from demonstrations to identify an optimal restoration strategy. At the pre-training stage, imitation learning is applied to equip the control agent with expert experiences to guarantee acceptable initial performance. At the online training stage, action clipping, reward shaping, and expert demonstrations are leveraged to ensure safe exploration while accelerating the training process. In conclusion, the proposed method is illustrated using the IEEE 123-node system and compared with a representative model-based method and the standard deep deterministic policy gradient method to prove solution accuracy and demonstrate increased computational efficiency.

Du, Yan↗
DOE OSTI2023

The effect of relative humidity on eddy covariance latent heat flux measurements and its implication for partitioning into transpiration and evaporation

While the eddy covariance (EC) technique is a well-established method for measuring water fluxes (i.e., evaporation or 'evapotranspiration’, ET), the measurement is susceptible to many uncertainties. One such issue is the potential underestimation of ET when relative humidity (RH) is high (> 70%), due to low-pass filtering with some EC systems. Yet, this underestimation for different types of EC systems (e.g. open-path or closed-path sensors) has not been characterized for synthesis datasets such as the widely used FLUXNET2015 dataset. Here, we assess the RH-associated underestimation of latent heat fluxes (LE, or ET) from different EC systems for 163 sites in the FLUXNET2015 dataset. We found that the LE underestimation is most apparent during hours when RH is higher than 70%, predominantly observed at sites using closed-path EC systems, but the extent of the LE underestimation is highly site-specific. We then propose a machine learning based method to correct for this underestimation, and compare it to two energy balance closure based LE correction approaches (Bowen ratio correction, BRC, and attributing all errors to LE). Our correction increases LE by 189% for closed-path sites at high RH (> 90%), while BRC increases LE by around 30% for all RH conditions. Additionally, we assess the influence of these corrections on ET-based transpiration (T) estimates using two different ET partitioning methods. Results show opposite responses (increasing vs. slightly decreasing T-to-ET ratios, T/ET) between the two methods when comparing T based on corrected and uncorrected LE. Overall, our results demonstrate the existence of a high RH bias in water fluxes in the FLUXNET2015 dataset and suggest that this bias is a pronounced source of uncertainty in ET measurements to be considered when estimating ecosystem T/ET and WUE.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Operator inference for non-intrusive model reduction with quadratic manifolds

This paper proposes a novel approach for learning a data-driven quadratic manifold from high-dimensional data, then employing this quadratic manifold to derive efficient physics-based reduced-order models. The key ingredient of the approach is a polynomial mapping between high-dimensional states and a low-dimensional embedding. This mapping consists of two parts: a representation in a linear subspace (computed in this work using the proper orthogonal decomposition) and a quadratic component. The approach can be viewed as a form of data-driven closure modeling, since the quadratic component introduces directions into the approximation that lie in the orthogonal complement of the linear subspace, but without introducing any additional degrees of freedom to the low-dimensional representation. Combining the quadratic manifold approximation with the operator inference method for projection-based model reduction leads to a scalable non-intrusive approach for learning reduced-order models of dynamical systems. Further, applying the new approach to transport-dominated systems of partial differential equations illustrates the gains in efficiency that can be achieved over approximation in a linear subspace.

42 ENGINEERING↗
DOE OSTI2024

SPARC-X: Quantum simulations at extreme scale - reactive dynamics from first principles

We have developed the massively parallel electronic structure code SPARC-X: a computational framework for performing Kohn-Sham Density Functional Theory (DFT) calculations that can scale linearly with the number of atoms in the system, while being able to leverage petascale and emerging exascale parallel computers to study chemical phenomena at unprecedented length and time scales. SPARC-X exploits a recent breakthrough in electronic structure methodologies: systematically improvable, strictly local, orthonormal, discontinuous real-space bases that efficiently and systematically capture the local chemistry of the system. With further adaptation using new machine-learning techniques and the use of the massively parallel Spectral Quadrature (SQ) electronic structure method, the algorithmic complexity and prefactor associated with DFT calculations involving semilocal as well as hybrid functionals are dramatically reduced. Using petascale computational resources, SPARC-X enables quantum mechanical simulations at length and time scales previously accessible only by empirical approaches, e.g., 1,000,000 atoms for a few picoseconds using semilocal functionals or 1,000 atoms for a few picoseconds using hybrid functionals. Using exascale resources, the sizes and times targeted are two orders of magnitude larger. Such a capability has applications in a wide variety of chemical sciences, including reactive interfaces where large length- and/or long time-scales are needed and traditional force fields fail. This is particularly important in dynamic catalysis, where bond breaking and formation must be understood in detail. We developed, tested, and employed the SPARC-X framework to understand the photocatalytic properties of TiO 2 nanoparticles, revealing finite size effects that cannot be captured with standard model systems or functionals. This integrated development and application strategy ensures that SPARC-X remains a robust, efficient, and scalable software package for quantum simulations on current petascale and emerging exascale computing resources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Real-Time Inference For MI/RR Deblending

The Fermilab Main Injector (MI) and Recycler Ring (RR) share a common beam loss monitor (BLM) system, making loss events difficult to attribute to their source machine when beam is present in both simultaneously. The Real-time Edge AI for Distributed Systems (READS) project addresses this by deblending BLM readings in real time using machine learning (ML). The current FPGA based implementation meets the sub-3 ms latency requirement but carries a resource intensive hls4ml development cycle, motivating exploration of GPU based deployment. This paper characterizes inference latency on an NVIDIA Jetson Orin Nano and introduces a packet organization scheme for assembling synchronized event frames from seven distributed BLM DAQ streams. Using a Python based DAQ simulation with injected timing jitter in place of unavailable live beam data, the pipeline achieved an average end to end latency of 0.456 ms (σ = 0.122 ms) across 167,000 test frames, comfortably meeting the timing constraint. Early outliers were attributed to TensorRT warm-up rather than steady state limitations, suggesting GPU based inference is a viable alternative to the existing FPGA implementation.

Yu, Kellen [Cornell U.]↗