SEARCH · Engineering Papers

Results for “learning rate”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,711 records · Page 95

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Carbon monoxide oxidation expands the known metabolic capacity in anaerobic methanotrophic consortia

Consortia of anaerobic methane-oxidizing archaea (ANME-2) and sulphate-reducing bacteria (SRB) represent globally relevant syntrophic associations capable of growing with minimal amounts of free energy and can persist when methane becomes limiting. Carbon monoxide (CO) has been reported in seep environments and represents a thermodynamically favourable alternative electron donor due to its low reduction potential. Here, we show that environmental ANME-SRB consortia can oxidize CO in the absence of methane, in anoxic microcosm experiments using a combination of stable isotope geochemical tracers, metatranscriptomics, and single cell activity measurements (FISH–nanoSIMS). The oxidation of CO was coupled with sulphate-reduction by syntrophic consortia, and, in the absence of sulphate, through CO 2 reduction to methane by ANME-2. Under these conditions, the production of methane was one ninth the rate of methanotrophy coupled to sulphate-reduction. Paired single cell FISH-nanoSIMS analysis of anabolic activity indicates that CO respiration appears to support cell maintenance rather than active growth, consistent with the observed down-regulation of energy generating complexes in ANME (e.g., mtr, rnf, etc.). The versatile capability of CO oxidation by anaerobic methanotrophic consortia broadens our understanding of carbon cycling in methane seeps and highlights potential mechanisms of resilience by methanotrophic archaea under changing geochemical regimes.

03 NATURAL GAS↗

DOE OSTI2025

Large-scale tearing-mode hazard function analysis with standard matched equilibrium reconstructions

The association between features from standard tokamak equilibrium reconstructions and the onset of n = 1 tearing modes (TMs) is analyzed at scale. The TM onset rate is directly modeled with a ‘hazard’ function which gives the expected number of onsets (per unit time spent) in a given equilibrium parameter region. In particular the different statistical modeling performance achieved for magnetics-only reconstructions and motional Stark effect (MSE) enhanced reconstructions is studied. It is observed that a better hazard model for the TM onset rate can be built with the MSE-enhanced equilibria compared to the matched magnetics-only situation. This advantage disappears if internal profile details are withheld from the matched analysis. Plausibility of the hazard function is further demonstrated with visualizations of global trends in the operational space, and time-traces from specific tokamak discharges. As a result, TMs typically degrade tokamak plasma performance and may lead to plasma termination, motivating this statistical study.

equilibrium↗

DOE OSTI2020

nPINNs: Nonlocal physics-informed neural networks for a parametrized nonlocal universal Laplacian operator. Algorithms and applications

Physics-informed neural networks (PINNs) are effective in solving inverse problems based on differential and integro-differential equations with sparse, noisy, unstructured, and multifidelity data. PINNs incorporate all available information, including governing equations (reflecting physical laws), initial-boundary conditions, and observations of quantities of interest, into a loss function to be minimized, thus recasting the original problem into an optimization problem. In this paper, we extend PINNs to parameter and function inference for integral equations such as nonlocal Poisson and nonlocal turbulence models, and we refer to them as nonlocal PINNs (nPINNs). The contribution of the paper is three-fold. First, we propose a unified nonlocal Laplace operator, which converges to the classical Laplacian as one of the operator parameters, the nonlocal interaction radius $\delta$ goes to zero, and to the fractional Laplacian as $\delta$ goes to infinity. This universal operator forms a super-set of classical Laplacian and fractional Laplacian operators and, thus, has the potential to fit a broad spectrum of data sets. We also provide theoretical convergence rates with respect to $\delta$ and verify them via numerical experiments. Second, we use nPINNs to estimate the two parameters, $\delta$ and $\alpha$, characterizing the kernel of the unified operator. The strong non-convexity of the loss function yielding multiple (good) local minima reveals the occurrence of the operator mimicking phenomenon, that is, different pairs of estimated parameters could produce multiple solutions of comparable accuracy. Third, we propose another nonlocal operator with spatially variable order $\alpha(y)$, which is more suitable for modeling turbulent Couette flow. Our results show that nPINNs can jointly infer this function as well as $\delta$. More importantly, these parameters exhibit a universal behavior with respect to the Reynolds number, a finding that contributes to our understanding of nonlocal interactions in wall-bounded turbulence.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1992

Pre-flight risk assessment in Emergency Medical Service (EMS) helicopters

The Emergency Medical Service (EMS) industry has been the subject of several television and newspaper articles (Harvey and Jensen, 1987) which emphasized the negative aspects, (e.g., fatalities and high accident rates), rather than the life saving services performed. Until recently, the accident rate of the EMS industry has been five times as high as that of other civil helicopters. This high accident rate has been coupled with the dramatic rise in the number of programs. The industry has built from a single service at its inception in 1972, to over 180 in 1987 (Spray, 1987), to the point that 93 percent of the contiguous U.S. is now covered by some type of EMS service. These factors prompted the National Transportation Safety Board (NTSB) to study the accidents that occurred between May 11, 1978 and December 3, 1986 (NTSB, 1988). The NTSB report concluded that 'Sound pilot judgment is central to safe flight operations.' They further stated that '... factors unique to EMS helicopter operations--such as the influence of the mission itself, program competition, and EMS program management perspectives--can drastically influence pilot judgment during the EMS mission.' One of the most difficult decisions that a pilot must make is whether to accept or decline a mission. A pre-flight risk assessment system (SAFE) was developed at NASA-Ames Research Center for civil EMS operations to aid pilots in making this decision objectively. The ability of the SAFE system to predict mission risk profiles was tested at an EMS facility. The results of this field study demonstrated that the usefulness of SAFE was highly dependent on the type of mission flown. SAFE is now being modified so that it can 'learn' with each mission flown. For example, after flying a mission to a particular site, an EMS pilot would input information about this mission into the system, such as new buildings, wires, or approach procedures. Then, the next time a pilot flew a similar mission or one to the same area, this additional information would be taken into account in computing a risk assessment.

Shively, R. J.↗

DOE OSTI2024

Investigating resource-efficient neutron/gamma classification ML models targeting eFPGAs

There has been considerable interest and resulting progress in implementing machine learning (ML) models in hardware over the last several years from the particle and nuclear physics communities. A big driver has been the release of the Python package, hls4ml, which has enabled porting models specified and trained using Python ML libraries to register transfer level (RTL) code. So far, the primary end targets have been commercial field-programmable gate arrays (FPGAs) or synthesized custom blocks on application specific integrated circuits (ASICs). However, recent developments in open-source embedded FPGA (eFPGA) frameworks now provide an alternate, more flexible pathway for implementing ML models in hardware. These customized eFPGA fabrics can be integrated as part of an overall chip design. In general, the decision between a fully custom, eFPGA, or commercial FPGA ML implementation will depend on the details of the end-use application. In this work, we explored the parameter space for eFPGA implementations of fully-connected neural network (fcNN) and boosted decision tree (BDT) models using the task of neutron/gamma classification with a specific focus on resource efficiency. We used data collected using an AmBe sealed source incident on Stilbene, which was optically coupled to an OnSemi J-series silicon photomultiplier (SiPM) to generate training and test data for this study. We investigated relevant input features and the effects of bit-resolution and sampling rate as well as trade-offs in hyperparameters for both ML architectures while tracking total resource usage. The performance metric used to track model performance was the calculated neutron efficiency at a gamma leakage of 10 -3 . The results of the study will be used to aid the specification of an eFPGA fabric, which will be integrated as part of a test chip.

47 OTHER INSTRUMENTATION↗

NASA NTRS2019

Trends in Human Spaceflight: Failure Tolerance, High Reliability and Correlated Failure History

In a half century of human spaceflight, NASA has continuously refined agency safety and reliability requirements in response to mission demands, critical failures, and technology development. Early spacecraft, including Mercury, Gemini and Apollo vehicles, were highly reliant on dissimilar redundancy and demonstrated test margins. Later programs, such as the reusable Space Transportation System (STS) and International Space Station (ISS), introduced probabilistic studies and isolated two-failure tolerance to improve robustness at the expense of added complexity. More recently, the Orion Multi-Program Crew Vehicle (MPCV) program adopted universal single-failure tolerance with two categorical exceptions; Zero-Failure Tolerant (0FT) and Design for Minimum Risk (DFMR) hardware. Failure tolerance variances are defined and managed in accordance with agency human-rating requirements, and require concurrence from program Technical Authorities (TA) as well as the MPCV Safety and Mission Assurance Safety and Engineering Review Panel (MSERP). To understand and reaffirm standards applied to Apollo, Space Shuttle and Orion vehicles, Orion and Deep Space Gateway Safety and Mission Assurance (S&MA) representatives conducted accelerated research to compare unique safety and reliability criteria against ground and flight anomalies, based on information contained in post-mission reports and the Problem Reporting and Corrective Action (PRACA) database. In some cases, high-profile failures and narrow escapes have reinforced decisions to maintain or adapt safety requirements. In others, empirical trends have highlighted the need for vigilance and innovative safety guidelines. Given the inability to achieve absolute compliance with evolving safety and reliability requirements, the team conducted a targeted review of DFMR and 0FT propulsion elements within the framework of changing system design, inspection, materials and process developments to formulate conclusions on technological maturity, failure density, and net changes in safety risk. Based on the aggregate performance of high-reliability and failure-tolerant systems, the authors have attempted to establish best practices and guidelines to inform future program decisions. On a somewhat cautionary note, this study is not intended to direct a universal set of requirements for future missions based on prior lessons learned. Spacecraft safety is a multi-variable problem, and attempts to mitigate past failures will not guarantee future success. However, this assessment offers a retrospective review of policy changes, implementation and effectiveness. In the future, NASA, European Space Agency (ESA) and industry partners may benefit from a more robust correlation between requirements and performance, as space-faring nations work toward more challenging, complex and long-duration commercial and deep-space ventures.

Green, Carrie↗

NASA NTRSDate not supplied

Helmholtz Motor: A Novel Electric Machine That Enables High Temperature Superconducting Armatures

Electrified aircraft are being developed to increase the efficiency and reduce the cost of operating subsonic transport aircraft. Achieving a substantial impact necessitates focusing on single- and twin-aisle aircraft which use propulsion systems with >20 MW ratings. For these aircraft, multi-MW superconducting electric machines are being developed due to their high specific power and high efficiency. Cryogenic electric machines are a promising technology for multi megawatt electric aircraft drivetrains. Second generation high temperature superconductors (HTS) are the ideal conductor for the field winding (typically the rotor) of superconducting machines, and they have attractive features for the armature winding (typically the stator) of these machines. However, their use in armature windings has been severely limited due to excessive AC losses in conventional electric machines. This presentation will present the working principle, design, and a performance trade study of a novel electric machine – termed a Helmholtz machine – that enables HTS armatures by significantly reducing AC losses. The working principle of the patent pending Helmholtz motor is to optimize the rotor-produced magnetic field (i.e., the field winding) so that it produces a magnetic field almost purely in the plane of the HTS. This is accomplished using 2 rotors that contain a set of matched Helmholtz coil pairs (or matched permanent magnet Halbach arrays). The armature (stator) HTS coils are positioned between the rotors and oriented to minimize the out of plane magnetic field. The armature HTS coils are also designed to minimize the out of plane component of their self field. The presentation will include the lessons learned in the sizing and design of this motor, including equations for how to match the magnet arrays. A performance trade study will be presented for a partially superconducting, radial flux version of the motor. The trade study involved an optimization of a motor design code based on analytical calculations (electromagnetic, AC loss, thermofluid, mechanical, and motor sizing) that determine the motor’s total efficiency and total specific power. The design code will be described in the presentation, with an emphasis on the calculation of magnetic fields, AC loss, and temperature distribution.

Superconducting electric machines↗

DOE OSTI2023

Autonomous Inversion of In Situ Deformation Measurement Data for Injection-Induced Stress Change

Geologic carbon storage (GCS) is likely to play a key part of the global effort to dramatically reduce CO2 emissions and perhaps even reduce atmospheric CO2 concentrations through carbon negative operations. A critical part of effort to commercialize and widely deploy this technology is developing the capability to rapidly assimilate real-time monitoring data into a form that will enable site operators to make decisions to manage the safe and efficient operations. Two of the risks associate with GCS are the risk of inducing fractures in the sealing formations that can create leakage pathways and the risk of inducing earthquakes of sufficient magnitude to cause public concern, property damage, or safety risks. To properly manage these risks the site operator needs to know the initial state of stress, the change in stress induced by injection, and the relationship between operational parameters such as injection rate and pressure and the change in stress. Current methods of estimating the change in stress require choosing the type of constitutive model and the model parameters based on core, log, and geophysical data during the characterization phase, with little feedback from operational observations to validate or refine these choices. These characterization methods interrogate the geologic formations using length scales, loading rates or magnitudes that are quite different from those encountered by the actual storage system. It is shown that errors in the assumed constitutive response, even when informed by laboratory tests on core samples, are likely to be common, large, and underestimate the magnitude of stress change caused by injection. Recent advances in borehole-based strain instruments and borehole and surface-based tilt and displacement instruments have now enabled monitoring of the deformation of the storage system throughout its operational lifespan. This data can enable validation and refinement of the knowledge of the geomechanical properties and state of the system, but brings with it a challenge to transform the raw data into actionable knowledge. We demonstrate a method that uses automatic differentiation and a finite-element based geomechanical model perform a gradient-based deterministic inversion of geomechanical monitoring data. This approach allows autonomous integration of the instrument data without the need for time consuming manual interpretation and selection of updated model parameters. Furthermore, only isotropic linear elasticity is considered in this paper, the approach presented is very flexible as to what type of geomechanical constitutive response can be used. The approach is easily adaptable to nonlinear physics-based constitutive models to account for common rock behaviors such as creep and plasticity. The approach also enables training of machine learning-based constitutive models by allowing back propagation of errors through the finite element calculations. This enables strongly enforcing known physics, such as conservation of momentum and continuity, while allowing data-driven models to learn the truly unknown physics such as the constitutive or petrophysical responses.

Burghardt, Jeffrey A.↗

NASA NTRS2014

In-Situ and Remote-Sensing Data Fusion Using Machine Learning Techniques to Infer Urban and Fire Related Pollution Plumes

Airmass type characterization is key in understanding the relative contribution of various emission sources to atmospheric composition and air quality and can be useful in bottom-up model validation and emission inventories. However, classification of pollution plumes from space is often not trivial. Sub-orbital campaigns, such as SEAC4RS (Studies of Emissions, Atmospheric Composition, Clouds and Climate Coupling by Regional Surveys) give us a unique opportunity to study atmospheric composition in detail, by using a vast suite of in-situ instruments for the detection of trace gases and aerosols. These measurements allow identification of spatial and temporal atmospheric composition changes due to various pollution plumes resulting from urban, biogenic and smoke emissions. Nevertheless, to transfer the knowledge gathered from such campaigns into a global spatial and temporal context, there is a need to develop workflow that can be applicable to measurements from space. In this work we rely on sub-orbital in-situ and total column remote sensing measurements of various pollution plumes taken aboard the NASA DC-8 during 2013 SEAC4RS campaign, linking them through a neural-network (NN) algorithm to allow inference of pollution plume types by input of columnar aerosol and trace-gas measurements. In particular, we use the 4STAR (Spectrometer for Sky-Scanning, Sun-Tracking Atmospheric Research) airborne measurements of wavelength dependent aerosol optical depth (AOD), particle size proxies, O3, NO2 and water vapor to classify different pollution plumes. Our method relies on assigning a-priori ground-truth labeling to the various plumes, which include urban pollution, different fire types (i.e. forest and agriculture) and fire stage (i.e. fresh and aged) using cluster analysis of aerosol and trace-gases in-situ and auxiliary (e.g. trajectory) data and the training of a NN scheme to fit the best prediction parameters using 4STAR measurements as input. We explore our misclassification rates as related to our ground-truth labels, and with multi-layered pollution plume cases. The next step in our analysis is to optimize parameter selection for a scheme that can be applied to space-borne aerosol and trace-gas observation platforms such as OMI, and future geostationary satellites such as TEMPO and GEO-CAPE.

Neural-network↗

DOE OSTI2025

Investigating lab-scaled offshore wind aerodynamic testing failure and developing solutions for early anomaly detections

As offshore wind systems become more complex, the risk of human error or equipment malfunction increases during experimental testing. This study investigates a lab-scale incident involving a 1 : 50 scale 5 MW wind turbine, where a generator failure led to rotor overspeed and a blade–tower strike. To improve early fault detection, we propose a data-driven method based on multivariate long short-term memory (LSTM) models. High-frequency measurements are projected onto principal components, and anomalies are identified using reconstruction error and its time derivative. Two models are trained on different healthy datasets and tested using single- and multi-principal component (1PC and MPC) variations. Results show that combining both error and error derivative improves detection accuracy. The 1PC model detects faults faster, has a higher recall rate, and achieves a 43 % improvement in anomaly detection accuracy, while the MPC model yields higher precision. This approach provides a simple and effective tool for early anomaly detection in lab-scale experiments, helping to reduce the risk of future failures during the testing of new technologies.

17 WIND ENERGY↗

NASA NTRSDate not supplied

NASA GPM Status and Future Activities

The joint U.S.-Japan Global Precipitation Measurement (GPM) mission is approaching a decade of operations, and continues to pursue research, dataset production, and outreach related to precipitation. Key activities over the last year were the release of an improved “Version 07” of all GPM precipitation and latent heating products, boosting the orbit of the GPM Core Observatory (GPM CO) to 435 km, and improving quality control on precipitation retrievals from the GPM constellation of passive microwave satellites. This presentation summarizes key improvements to the GPM products and provides some examples of the changes between Versions 06 and 07 in algorithm performance. One important operational change that affected Version 07 is that the scanning strategy for the Ka-band radar channel changed in May 2018; all products that depend on Ka were revised to accommodate this change. For example, in Version 07 the Goddard Profiling (GPROF) algorithm has implemented improvements in regions where orographic enhancement and suppression take place and where the surface is snowy/icy, and again covers radiometers reaching back to 1987. The Combined Radar Radiometer Algorithm (CORRA) now incorporates modified drop-size distribution constraints that substantially reduce bias. Revisions to the Convective-Stratiform Heating (CSH) algorithm employ new radiative transfer retrievals as well as accounting for terrain in the vertical coordinates. Each algorithm was adjusted to ensure continuity for each product across the boundary in 2014 between the predecessor Tropical Rainfall Measuring Mission (TRMM) and the GPM CO. The U.S. Science Team’s Integrated Multi-satellitE Retrievals for GPM (IMERG) was upgraded to account for distortions in the probability density function of regional precipitation rates due to weighted averaging in the Kalman filter used for “morphing” the passive microwave data. Maintaining the GPM CO orbital altitude in the the current very active solar cycle has been forcing the use of more fuel than planned and consequently shortening the forecasted life of the mission from the early 2030's to the late 2020's. It was considered vital to regain some of this lifetime to ensure overlap with the upcoming Atmosphere Observing System mission to provide crosscalibration of instruments. To accomplish this, the orbital altitude was raised from 400 to 435 km on 7-8 November 2023. Thereafter, the primary GPM CO algorithms had to be revised to account for the change in observing parameters. By meeting time this action should be complete. Recently, a screening algorithm based on auto-encoding was developed that uncovered 162 orbits (out of the many thousands of orbits across all years and all satellites) of passive microwave retrievals that had highly anomalous values. Removing these defective retrievals has improved the integrity of both the GPROF and IMERG records. However, the nature of the IMERG processing interacted sufficiently badly with the now-discovered anomalous orbits that it was necessary to completely reprocess the IMERG Final Run record, now labeled Version 07B. The presentation also considers major issues that require continued attention, including the use of machine learning algorithms and the operational challenge of swarms of “small”, perhaps short-lived satellites.

GPM↗

NASA NTRS2014

Nuclear Thermal Propulsion Ground Test History

Nuclear Thermal Propulsion (NTP) was started in ~1955 under the Atomic Energy Commission as project Rover and was assigned to Los Alamos National Laboratory. The Nevada Test Site was selected in 1956 and facility construction began in 1957. The KIWI-A was tested on July 1, 1959 for 5 minutes at 70MW. KIWI-A1 was tested on July 8, 1960 for 6 minutes at 85MW. KIWI-A3 was tested on October 10, 1960 for 5 minutes at 100MW. The National Aeronautics and Space Administration (NASA) was formed in 1958. On August 31, 1960 the AEC and NASA established the Space Nuclear Propulsion Office and named Harold Finger as Director. Immediately following the formation of SNPO, contracts were awarded for the Reactor In Flight Test (RIFT), master plan for the Nuclear Rocket Engine Development Station (NRDS), and the Nuclear Engine for Rocket Vehicle Application (NERVA). From December 7, 1961 to November 30, 1962, the KIWI-B1A, KIWI-B1B, and KIWI-B4A were tested at test cell A. The last two engines were only tested for several seconds before noticeable failure of the fuel elements. Harold Finger called a stop to any further hot fire testing until the problem was well understood. The KIWI-B4A cold flow test showed the problem to be related to fluid dynamics of hydrogen interstitial flow causing fuel element vibrations. President Kennedy visited the NTS one week after the KIWI-B4A failure and got to see the engine starting to be disassembled in the maintenance facility. The KIWI-B4D and KIWI-B4E were modified to not have the vibration problems and were tested in test cell C. The NERVA NRX program started testing in early 1964 with NRX-A1 cold flow test series (unfueled graphite core), NRX-A2 and NRX-A3 power test series up to 1122 MW for 13 minutes. In March 1966, the NRX-EST (Engine System Test) was the first breadboard using flight functional relationship and total operating time of 116 minutes. The NRX-EST demonstrated the feasibility of a hot bleed cycle. The NRX-A5 had multiple start-ups in May-June 1966 with 30.75 minutes accumulative operating time at or above 1GW. The NRX-A6 was tested in December 1969 and ran for 62 minutes at 1100 MW. Each engine had post-test examination and found various structure anomalies which were identified for correction and the fuel element corrosion rate was reduced. The Phoebus series of research reactors began testing at test cell C, in June 1965 with Phoebus 1A. Phoebus 1A operated for 10.5 minutes at 1100 MW before unexpected loss of propellant and leading to an engine breakdown. Phoebus 1B ran for 30 minutes in February of 1967. Phoebus 2A was the highest steady state reactor built at 5GW. Phoebus 2A ran for 12 minutes at 4100 MW demonstrating sufficient power is available. The Peewee test bed reactor was tested November- December 1968 in test cell C for 40 minutes at 500MW with overall performance close to pre-run predictions. The XE' engine was the only engine tested with close to a flight configuration and fired downward into a diffuser at the Engine Test Stand (ETS) in 1969. The XE' was 1100 MW and had ~28 start-ups. The nuclear furnace NF-1 was operated at 44 MW with multiple test runs at 90 minutes in the summer of 1972. The NF-1 was the last NTP reactor tested. The Rover/NERVA program was cancelled in 1973. However, before cancellation, a lot of other engineering work was conducted by Aerojet on a 75, 000 lbf prototype flight engine and by Los Alamos on a ~16,000 lbf "Small Engine" nuclear rocket design. The ground test history of NTP at the NRDS also offers many lessons learned on how best to setup, operate, emergency shutdown, and post-test examine NTP engines. The reactor and engine maintenance and disassembly facilities were used for assembly and inspection of radioactive engines after testing. Most reactor/ engines were run at test cell A or test cell C with open air exhaust. The Rover/NERVA program became aware of a new environmental regulation that would restrict the amount of radioactive particulates allowed to be release in open air and successfully demonstrated a scrubber concept with the NF-1. The ETS stand was the only one with a high altitude test chamber used for XE'. The ETS and other test cells showed the effects the engine's radiation had on the facility materials and instrumentation as well as side effects the ground test facility has back on the engine operation. The breakdown of Phoebus 1A at test cell C showed how the site was cleaned up and back to operation for five more engines before the program was cancelled.

Gerrish, Harold P.↗

DOE OSTI2020

nPINNs: nonlocal Physics-Informed Neural Networks for a parametrized nonlocal universal Laplacian operator. Algorithms and Applications

Physics-informed neural networks (PINNs) are effective in solving inverse problems based on differential and integro-differential equations with sparse, noisy, unstructured, and multifidelity data. PINNs incorporate all available information, including governing equations (reflecting physical laws), initial-boundary conditions, and observations of quantities of interest, into a loss function to be minimized, thus recasting the original problem into an optimization problem. In this paper, we extend PINNs to parameter and function inference for integral equations such as nonlocal Poisson and nonlocal turbulence models, and we refer to them as nonlocal PINNs (nPINNs). The contribution of the paper is three-fold. First, we propose a unified nonlocal Laplace operator, which converges to the classical Laplacian as one of the operator parameters, the nonlocal interaction radius δ goes to zero, and to the fractional Laplacian as δ goes to infinity. This universal operator forms a super-set of classical Laplacian and fractional Laplacian operators and, thus, has the potential to fit a broad spectrum of data sets. We provide theoretical convergence rates with respect to δ and verify them via numerical experiments. Second, we use nPINNs to estimate the two parameters, δ and α, characterizing the kernel of the unified operator. The strong non-convexity of the loss function yielding multiple (good) local minima reveals the occurrence of the operator mimicking phenomenon, that is, different pairs of estimated parameters could produce multiple solutions of comparable accuracy. Third, we propose another nonlocal operator with spatially variable order α(γ), which is more suitable for modeling turbulent Couette flow. Our results show that nPINNs can jointly infer this function as well as δ. More importantly, these parameters exhibit a universal behavior with respect to the Reynolds number, a finding that contributes to our understanding of nonlocal interactions in wall-bounded turbulence.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2023

Prediction of chronic kidney disease progression using recurrent neural network and electronic health records

Chronic kidney disease (CKD) is a progressive loss in kidney function. Early detection of patients who will progress to late-stage CKD is of paramount importance for patient care. To address this, we develop a pipeline to process longitudinal electronic heath records (EHRs) and construct recurrent neural network (RNN) models to predict CKD progression from stages II/III to stages IV/V. The RNN model generates predictions based on time-series records of patients, including repeated lab tests and other clinical variables. Our investigation reveals that using a single variable, the recorded estimated glomerular filtration rate (eGFR) over time, the RNN model achieves an average area under the receiver operating characteristic curve (AUROC) of 0.957 for predicting future CKD progression. When additional clinical variables, such as demographics, vital information, lab test results, and health behaviors, are incorporated, the average AUROC increases to 0.967. In both scenarios, the standard deviation of the AUROC across cross-validation trials is less than 0.01, indicating a stable and high prediction accuracy. Our analysis results demonstrate the proposed RNN model outperforms existing standard approaches, including static and dynamic Cox proportional hazards models, random forest, and LightGBM. The utilization of the RNN model and the time-series data of previous eGFR measurements underscores its potential as a straightforward and effective tool for assessing the clinical risk of CKD patients concerning their disease progression.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Real-Time Artificial Intelligence for Particle Reconstruction and Higgs Physics

With the discovery of the Higgs boson at the CERN LHC, the world's highest-energy particle accelerator complex, scientists have acquired an important tool to study the fundamental building blocks of the universe. Precision measurements of Higgs bosons produced with large momentum allow for unique insights into the structure of the interactions of the Higgs boson with other particles that may shed light on physics beyond the standard model. While experimentally challenging, exploring such interactions with novel artificial intelligence (AI) methods can advance our understanding of the Higgs sector, including the Higgs boson's self-interaction. Moreover, the LHC is undergoing a major upgrade to further increase its particle collision rate and thereby operate for an additional decade. The experimental detectors at the upgraded facility must process at least a factor of ten more data at rates of hundreds of terabytes per second all under challenging conditions. New AI techniques are required to reconstruct and select, or trigger on, the most physics-sensitive events in real-time to handle the resulting avalanche of data. The proposed research will achieve the goals of the LHC program at the CMS experiment by developing a sub-microsecond event reconstruction system using real-time AI algorithms that employ field-programmable gate array technologies. By harnessing sophisticated AI techniques, this research focuses on measuring the production of Higgs bosons at large momentum while enhancing particle reconstruction methods in the trigger and beyond. Overall, the proposed research has broader implications for the use of AI in resource-constrained, low-latency embedded applications across all fields of science.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

Out-of-Distribution Detection and Radiological Data Monitoring Using Statistical Process Control

Abstract Machine learning (ML) models often fail with data that deviates from their training distribution. This is a significant concern for ML-enabled devices as data drift may lead to unexpected performance. This work introduces a new framework for out of distribution (OOD) detection and data drift monitoring that combines ML and geometric methods with statistical process control (SPC). We investigated different design choices, including methods for extracting feature representations and drift quantification for OOD detection in individual images and as an approach for input data monitoring. We evaluated the framework for both identifying OOD images and demonstrating the ability to detect shifts in data streams over time. We demonstrated a proof-of-concept via the following tasks: 1) differentiating axial vs. non-axial CT images, 2) differentiating CXR vs. other radiographic imaging modalities, and 3) differentiating adult CXR vs. pediatric CXR. For the identification of individual OOD images, our framework achieved high sensitivity in detecting OOD inputs: 0.980 in CT, 0.984 in CXR, and 0.854 in pediatric CXR. Our framework is also adept at monitoring data streams and identifying the time a drift occurred. In our simulations tracking drift over time, it effectively detected a shift from CXR to non-CXR instantly, a transition from axial to non-axial CT within few days, and a drift from adult to pediatric CXRs within a day—all while maintaining a low false positive rate. Through additional experiments, we demonstrate the framework is modality-agnostic and independent from the underlying model structure, making it highly customizable for specific applications and broadly applicable across different imaging modalities and deployed ML models.

Zamzmi, Ghada↗

DOE OSTI2026

Advancing Asset Management in Water Infrastructure Systems

Aging water system infrastructure, including drinking water, wastewater, and stormwater, poses a growing challenge for utilities and municipalities. These water systems have well documented challenges with respect to their age, condition, and level of service. ASCE annual report cards consistently rate these infrastructure systems in the United States as underfunded, overcapacity, or past service life (ASCE 2025 Report Card). For example, Chini and Stillwell (2017) estimated that the mean water loss in drinking water systems, i.e., non-revenue water, is approximately 16% across the United States. These concerns are not just relegated to the United States, with Courtenay, British Columbia, identifying 17% of their water main pipes as in a ‘poor’ condition state, defined as a category condition 5 out of 5 (City of Courtenay, 2024). These cases illustrate the challenges utilities are facing to manage extensive networks of infrastructure to deliver a consistent and high level of service. For buried infrastructure such as water systems, studies suggest that preventative interventions can lead to lower maintenance costs and fewer service disruptions (Mazumder et al, 2018; Li et al, 2014). The demonstrated need and benefit of appropriately applied asset management is juxtaposed against the relatively sparse literature that evaluates water systems within an asset management construct. Since 2020, just 37 papers specifically reference asset management in the Journal of Water Resources Planning and Management. Of those, only a few specifically look to develop strategies for improved asset management. Therefore, we highlight four key research areas that represent opportunities for advancement of asset management research for water systems. First, advances in condition assessment and forecasting are needed to better estimate asset deterioration using diverse datasets. Second, machine learning (ML) and artificial intelligence (AI) hold promise for predictive maintenance and investment prioritization, though questions of generalizability and model transparency remain. Third, applying a value of information framework can guide utilities in making cost-effective sensor deployment and data collection decisions, to direct monitoring strategies towards data-informed asset management decisions. Finally, integrated infrastructure management is critical, requiring coordinated planning with other infrastructure systems and stakeholder engagement to reduce costs and enhance service delivery.

Chini, Christopher M.↗

DOE OSTI2025

Graph-Based Prediction of Spatio-Temporal Vaccine Hesitancy From Insurance Claims Data

Growing vaccine hesitancy is contributing to the decline in immunization rates for highly contagious, vaccine-preventable childhood diseases. Therefore, there has been a significant interest in understanding how hesitancy is spreading at higher spatio-temporal resolutions, enabling more targeted interventions. Motivated by this, we study the problem of prediction of vaccine hesitancy at the ZIP Code level, referred to as the VaxHesitancy problem. A significant challenge for this problem is the lack of high-resolution data that indicates hesitancy. Here, we develop a hybrid VaxHesSTL framework that combines a Graph Neural Network (GNN) and a Recurrent Neural Network (RNN) to address the VaxHesitancy problem. The GNN uses a ZIP Code-level network to capture spatial signals from neighboring areas, while the RNN models the temporal dynamics present in the data. We train and evaluate VaxHesSTL using a large dataset, namely the All-Payer Claims Databases (APCD), for Virginia, consisting of insurance claims from over five million individuals for six years. We find that an aggregated contact network or graph, developed from a detailed activity-based population network, plays an important role in the performance of VaxHesSTL, compared to graph models based solely on spatial proximity. Experiments demonstrate that VaxHesSTL outperforms a range of state-of-the-art baselines, which rely solely on historical time series data without accounting for spatial relationships. Since hesitancy data at higher spatial resolution is often unavailable or hard to get, we incorporate an active learning approach with our VaxHesSTL framework to optimize the training set without compromising the prediction performance. We find that hesitancy data for only 18% of ZIP Codes selected by active learning allows us to forecast hesitancy for all the ZIP Codes in the Virginia.

60 APPLIED LIFE SCIENCES↗