Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data reduction methods”

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 919 records · Page 51

Improving IPATS Channel-to-Channel Registration Assessment

The Image Navigation and Registration (INR) Performance Assessment Tool Set (IPATS) is a primary tool for assessing INR performance of GOES-R series ABI images. IPATS assesses five INR metrics: navigation, channel-to-channel registration (CCR), frame-to-frame registration, within-frame registration, and swath-to-swath registration. It was discovered that CCR assessment results between Visible-Near-Infrared (VNIR) channels and Infrared (IR) channels exhibits an annual oscillation in the north-south (NS) direction and a diurnal oscillation in the east-west (EW) direction, with an amplitude of approximately 5 μrad and 2.5 μrad, respectively. However, differences of navigation assessment results between VNIR and IR channels do not exhibit the annual or diurnal oscillations observed in CCR results. This indicates that the observed oscillations are due to measurement errors. The characteristics of the oscillations imply that cloud shadows are a possible cause of these measurement errors. In this study, several methods are explored to minimize the impact of cloud shadows on VNIR to IR CCR assessments: a) assessment at landmark locations only; b) using navigation assessment results to filter CCR assessments; c) using the ABI clear-sky-ratio product as a cloud mask; and d) smaller CCR assessment windows. In this paper, each method and a combination of several methods are evaluated based on assessment accuracy and the number of successful assessments. The selected approach is then used to reprocess GOES-16 ABI CCR data to show reductions in the annual and diurnal measurement error oscillations.

INR↗

Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems

In this work, we present Lift & Learn, a physics-informed method for learning low-dimensional models for large-scale dynamical systems. The method exploits knowledge of a system’s governing equations to identify a coordinate transformation in which the system dynamics have quadratic structure. This transformation is called a lifting map because it often adds auxiliary variables to the system state. The lifting map is applied to data obtained by evaluating a model for the original nonlinear system. This lifted data is projected onto its leading principal components, and low-dimensional linear and quadratic matrix operators are fit to the lifted reduced data using a least-squares operator inference procedure. Analysis of our method shows that the Lift & Learn models are able to capture the system physics in the lifted coordinates at least as accurately as traditional intrusive model reduction approaches. This preservation of system physics makes the Lift & Learn models robust to changes in inputs. Numerical experiments on the FitzHugh–Nagumo neuron activation model and the compressible Euler equations demonstrate the generalizability of our model.

97 MATHEMATICS AND COMPUTING↗

Accurate Prediction of Algal Biomass Lipid, Protein, and Carbohydrate Composition with Machine Learning Regression Modelling of Near-IR Spectra

During large scale algal biomass cultivation, it is difficult to reliably control relative composition to target levels. Rapid determination of chemical composition is feasible by using near infrared (NIR) spectral data. We sought to build and improve on reliable high-throughput screening prediction method based on partial least squares regression (PLSR) by the application of artificial neural networks (ANN) and associated optimization strategies. The algal biomass sample set was designed and created in an iterative process of culturing in physiologically diverse conditions at the GAI field site, followed by compositional analyses at NREL. The workflow allowed us to identify gaps in compositional space for informing the subsequent cultivation and sampling efforts and generated a high quality set of 210 unique samples with chemical analysis results, spectral scanning data, and cultivation metadata. We observed a significant improvement in the performance of carbohydrate content predictions using an optimized ANN model compared to PLSR, with > 16% reduction in mean absolute percent error (MAPE) when tested on the same set of reserved data. The optimized ANN models for FAME and protein prediction performed exceptionally well with 5.99% and 5.09% MAPE, respectively. Application of these methods to detection and quantification of minor biomass constituents that are relevant to certain product streams has shown positive preliminary results, opening the possibility for extensions to the outputs of this powerful data type. All models are accompanied by prediction uncertainties and unsupervised spectral outlier detection to alert an operator to unreliable spectral data. These tools can be deployed for rapid determination of algal culture status, and cultivation and biomass quality improvement.

algal biofuels↗

Smart Meter Data: A Gateway for Reducing Solar Soft Costs with Model-Free Hosting Capacity Maps

Public-facing solar hosting capacity (HC) maps, which show the maximum amount of solar energy that can be installed at a location without adverse effects, have proven to be a key driver of solar soft cost reductions through a variety of pathways (e.g., streamlining interconnection, siting, and customer acquisition processes). However, current methods for generating HC maps require detailed grid models and time-consuming simulations that limit both their accuracy and scalability—today, only a handful out of almost 2,000 utilities provide these maps. This project developed and validated data-driven algorithms for calculating solar HC using data from AMI without the need of detailed grid models or simulations. The algorithms were validated on utility datasets and incorporated as an application into NRECA’s Open Modeling Framework (OMF.coop) for the over 260 coops and vendors throughout the US to use. The OMF is free and open-source for everyone.

14 SOLAR ENERGY↗

SU-F-T-214: Re-Thinking the Useful Clinical Beam Energy in Proton Therapy: An Opportunity for Cost Reduction

Purpose: We conducted a retrospective study of the useful clinical proton beam energy based on the beam range data of patients treated over the last 10 years at Massachusetts General Hospital Proton Therapy Center. Methods: Treatment field information were collected for all patients treated over the last 10 years (2005–2015) in the two gantry treatment rooms at MGH. The beam ranges for these fields were retrieved and categorized per treatment site. The 10 prostate patients that required the highest beam range (lateral fields) were selected. For these patients, anterior oblique beams (30–40 degrees) were simulated in a planning system to obtain the required beam ranges including the margins for potential range uncertainties. Results: There were a total of 4033 patients, treated with combined total of 23603 fields. All treatment indications were considered with the exception of ocular tumors generally treated in a fixed beam room. For all non-prostate treatments (21811 fields), only 5 fields for 4 patients (1-pancreas, 1-lumbar chordoma, 2-spine mets) required beam range greater than 25 cm. There were 446 prostate patients (1792 fields), with the required beam range from 22.3 to 29.0 cm; 386 of them had at least one of their lateral beam range greater than 25 cm. For the 10 prostate patients with highest lateral beam ranges (26 to 29 cm), their treatment with anterior oblique beams would drop the beam ranges below 25 cm (17.3 to 18.5 cm). Conclusion: if prostate patients are treated with anterior fields only, the useful maximum beam range is reduced to 25 cm. Thus a proton therapy system with maximum beam energy of 196 MeV is sufficient to treat all tumors sites with very rare exceptions (<0.1%). Designing such PT system would reduce the cost of proton therapy for hospitals and patients and increase the accessibility to the treatment.

60 APPLIED LIFE SCIENCES↗

Serial femtosecond crystallography of soluble proteins in lipidic cubic phase

Serial femtosecond crystallography (SFX) at X-ray free-electron lasers (XFELs) enables high-resolution protein structure determination using micrometre-sized crystals at room temperature with minimal effects from radiation damage. SFX requires a steady supply of microcrystals intersecting the XFEL beam at random orientations. An LCP–SFX method has recently been introduced in which microcrystals of membrane proteins are grown and delivered for SFX data collection inside a gel-like membrane-mimetic matrix, known as lipidic cubic phase (LCP), using a special LCP microextrusion injector. Here, it is demonstrated that LCP can also be used as a suitable carrier medium for microcrystals of soluble proteins, enabling a dramatic reduction in the amount of crystallized protein required for data collection compared with crystals delivered by liquid injectors. High-quality LCP–SFX data sets were collected for two soluble proteins, lysozyme and phycocyanin, using less than 0.1 mg of each protein.

59 BASIC BIOLOGICAL SCIENCES↗

Unlocking hidden information in sparse small-angle neutron scattering measurements

Hypothesis Small-Angle Neutron Scattering (SANS) is a powerful technique for studying soft matter systems such as colloids, polymers, and lyotropic phases, providing nanoscale structural insights. However, its effectiveness is limited by low neutron flux, leading to long acquisition times and noisy data. Here, we hypothesize that Bayesian statistical inference using Gaussian Process Regression (GPR) can reconstruct high-fidelity scattering data from sparse measurements by leveraging intensity smoothness and continuity. Experiments and Simulations The method was benchmarked computationally and validated through SANS experiments on various soft matter systems, including wormlike micelles, colloidal suspensions, polymeric structures, and lyotropic phases. GPR-based inference was applied to both experimental and synthetic data to evaluate its effectiveness in noise reduction and intensity reconstruction. Findings GPR significantly enhances SANS data quality and therefore reducing measurement times by up to two orders of magnitude. This cost-effective approach maximizes experimental efficiency, enabling high-throughput studies and real-time monitoring of dynamic systems. It is particularly beneficial for weakly scattering and time-sensitive studies. Beyond SANS, this framework applies to other low-SNR techniques, including laboratory-based small-angle X-ray scattering and various dynamical scattering methods. Furthermore, it offers transformative potential for compact neutron sources, enhancing their viability for structural analysis in resource-limited settings.

Small angle neutron scattering↗

SU-E-J-128: Two-Stage Atlas Selection in Multi-Atlas-Based Image Segmentation

Purpose: In the new era of big data, multi-atlas-based image segmentation is challenged by heterogeneous atlas quality and high computation burden from extensive atlas collection, demanding efficient identification of the most relevant atlases. This study aims to develop a two-stage atlas selection scheme to achieve computational economy with performance guarantee. Methods: We develop a low-cost fusion set selection scheme by introducing a preliminary selection to trim full atlas collection into an augmented subset, alleviating the need for extensive full-fledged registrations. More specifically, fusion set selection is performed in two successive steps: preliminary selection and refinement. An augmented subset is first roughly selected from the whole atlas collection with a simple registration scheme and the corresponding preliminary relevance metric; the augmented subset is further refined into the desired fusion set size, using full-fledged registration and the associated relevance metric. The main novelty of this work is the introduction of an inference model to relate the preliminary and refined relevance metrics, based on which the augmented subset size is rigorously derived to ensure the desired atlases survive the preliminary selection with high probability. Results: The performance and complexity of the proposed two-stage atlas selection method were assessed using a collection of 30 prostate MR images. It achieved comparable segmentation accuracy as the conventional one-stage method with full-fledged registration, but significantly reduced computation time to 1/3 (from 30.82 to 11.04 min per segmentation). Compared with alternative one-stage cost-saving approach, the proposed scheme yielded superior performance with mean and medium DSC of (0.83, 0.85) compared to (0.74, 0.78). Conclusion: This work has developed a model-guided two-stage atlas selection scheme to achieve significant cost reduction while guaranteeing high segmentation accuracy. The benefit in both complexity and performance is expected to be most pronounced with large-scale heterogeneous data.

60 APPLIED LIFE SCIENCES↗

The Role of Clear Sky Identification in the Study of Cloud Radiative Effects: Combine Analysis from ISCCP and the Scanner of Radiation Budget (ScaRaB)

Since the effect of clouds on the earth's radiation balance is often estimated as the difference of net radiative fluxes at the top of the atmosphere between all situations and monthly averaged clear sky situations of the same regions, a reliable identification of clear sky is important for the study of cloud radiative effects. The Scanner for Radiation Balance (ScaRaB) radiometer on board the Russian Meteor-3/7 satellite provided earth radiation budget observations from March 1994 to February 1995 with two ERBE-Re broad-band longwave and shortwave channels. Two narrow-band channels, in the infrared atmospheric window and in the visible band, have been added to the ScaRaB instrument to improve the cloud scene identification. The International Satellite Cloud Climatology Project (ISCCP) method for cloud detection and determination of cloud and surface properties uses the same narrow-band channels as ScaRaB, but is employed to a collection of measurements at a better spatial resolution of about 5 km. By applying the original ISCCP algorithms to the ScaRaB data, the clear sky frequency is about 5% lower than the one over quasi-simultaneous original ISCCP data, an indication that the ISCCP cloud detection is quite stable. However, one would expect an about 10 to 20% smaller clear sky occurrence over the larger ScaRaB pixels. Adapting the ISCCP algorithms to the reduced spatial resolution of 60 km and to the different time sampling of the ScaRaB data leads therefore to a reduction of a residual cloud contamination. A sensitivity study with time-space collocated ScaRaB and original ISCCP data at a spatial resolution of 1deg longitude x 1deg latitude shows that the effect of clear sky identification method plays a higher role on the clear sky frequency and therefore on the statistics than on the zonal mean values of the clear sky fluxes. Nevertheless, the zonal outgoing longwave fluxes corresponding to ERBE clear sky are in general about 2 to 10 W/sq m higher than those obtained from the ScaRaB adapted ISCCP clear sky identifications. The latter are close to (about 1 W/sq m higher) fluxes corresponding to clear sky regions from original ISCCP data, whereas ScaRaB clear sky LW fluxes obtained with the original ISCCP identification lie about 1 to 2 W/sq m below. Especially in the tropics where water vapor abundance is high, the ERBE clear sky LW fluxes seem to be systematically overestimated by about 4 W/sq m, and SW fluxes are lower by about 5 to 10 W/sq m. However, the uncertainty in the analysis of monthly mean zonal cloud radiative effects is also produced by the low frequency of clear sky occurrence, illustrated when averaging over pixels or even over regions of 4deg longitude x 5deg latitude, corresponding to the spatial resolution of General Circulation Models. The systematic bias in the clear sky fluxes is not reflected in the zonal cloud radiative effects, because the clear sky regions selected by the different algorithms can occur in different geographic regions with different cloud properties.

Rossow, W. B.↗

Tree-level carbon stock estimations across diverse species using multi-source remote sensing integration

Forests are critical carbon sinks, and remote sensing has been increasingly widely used for forest monitoring and biomass estimations. However, species-specific tree-level studies remain limited. In this study, we demonstrated the feasibility of integrating UAV-based LiDAR with high-resolution optical satellite imagery (0.5 m) to estimate biomass for individual trees across different species. The proposed method accurately estimated biomass for 53 trees (R² = 0.82, rRMSE = 0.44), with species-specific datasets, showing an average 25.2% increase in R² and a 14.8% reduction in rRMSE. A novel vegetation index combining forest structure parameters with vegetation indices (VIs) was developed using high-resolution multispectral satellite data (3 m) to explore its relationship with individual tree biomass. Combining forest structural parameters with VIs further improved estimation accuracy, achieving an R²of 0.89 and an rRMSE of 0.34. Species-specific datasets show an 11.6% increase in R²compared to methods without VIs, and a 22.2% improvement over methods using only VIs. SHapley Additive exPlanations (SHAP) analysis shows that the volume feature played a key role in model performance and remained stable throughout the training process. Altogether, the proposed approach enhances individual tree biomass and carbon sink estimations, showing great potential for large-scale precise forest carbon monitoring using multi-source remote sensing data.

59 BASIC BIOLOGICAL SCIENCES↗

Magnetic Suspension Wind Tunnel Reconstruction Using an Extended Kalman Filter Framework

- Problem Statement: - Magnetic Suspension Balance System (MSBS) allows operation of wind tunnels without sting effect - Small-scale MSBS system has been demonstrated; NASA is building a full-scale MSBS wind tunnel for supersonic speeds - MSBS testing can provide data that addresses mission needs; current data reconstruction methods do not combine all measurement data - Reconstruction methods for aerodynamic coefficients and their uncertainties are piecemeal, and in their infancy - Mission Need: - Enhancement of Entry, Descent, and Landing (EDL) technology during atmospheric flight is a top priority - Accurate dynamic aerodynamic coefficients are necessary for stability and control of entry vehicles - Goal: - Develop an Extended Kalman Filter (EKF) based framework to do reduction of MSBS data that will estimate aerodynamics, trajectory, and uncertainty information, combining data sources from the tunnel

Christopher D. Karlgaard↗

A fast particle-based approach for calibrating a 3-D model of the Antarctic ice sheet

We consider the scientifically challenging and policy-relevant task of understanding the past and projecting the future dynamics of the Antarctic ice sheet. The Antarctic ice sheet has shown a highly nonlinear threshold response to past climate forcings. Triggering such a threshold response through anthropogenic greenhouse gas emissions would drive drastic and potentially fast sea level rise with important implications for coastal flood risks. Previous studies have combined information from ice sheet models and observations to calibrate model parameters. These studies have broken important new ground but have either adopted simple ice sheet models or have limited the number of parameters to allow for the use of more complex models. These limitations are largely due to the computational challenges posed by calibration as models become more computationally intensive or when the number of parameters increases. Here, we propose a method to alleviate this problem: a fast sequential Monte Carlo method that takes advantage of the massive parallelization afforded by modern high-performance computing systems. We use simulated examples to demonstrate how our sample-based approach provides accurate approximations to the posterior distributions of the calibrated parameters. The drastic reduction in computational times enables us to provide new insights into important scientific questions, for example, the impact of Pliocene era data and prior parameter information on sea level projections. These studies would be computationally prohibitive with other computational approaches for calibration such as Markov chain Monte Carlo or emulation-based methods. We also find considerable differences in the distributions of sea level projections when we account for a larger number of uncertain parameters. For example, based on the same ice sheet model and data set, the 99th percentile of the Antarctic ice sheet contribution to sea level rise in 2300 increases from 6.5 m to 13.1 m when we increase the number of calibrated parameters from three to 11. With previous calibration methods, it would be challenging to go beyond five parameters. Here, this work provides an important next step toward improving the uncertainty quantification of complex, computationally intensive and decision-relevant models.

54 ENVIRONMENTAL SCIENCES↗

Winners are not keepers: Characterizing household engagement, gains, and energy patterns in demand response using machine learning in the United States

Demand-response programs can help utilities manage rapidly evolving electric grids, but these programs are subject to the complexities of human behavior. This paper explores a novel method for uncovering heterogeneity in households. In this work, we use a machine-learning method known as a Conditional Inference Tree (c-tree) algorithm to categorize households based on their energy behavior characteristics collected via smart meters, and explore how this translates through into heterogeneity in their real-world response to a DR program. Using data from randomized controlled trial, we generate estimates of the changes in energy use caused by the program within each household group. Our results show that the c-tree approach differentiates households by their energy-use characteristics in a way that increases the spread in enrollment rates and critical peak reduction among household groups, compared with the spreads achieved via several conventional segmentation methods. Thus, the c-tree analysis enables the most tailored targeting of major potential energy savers and could provide the greatest increase in cost-effectiveness of household recruitment into DR programs. Our results also offer fresh insights into the relationships between household energy behavior characteristics – such as peak energy use and “structural winningness” (the ability to save money under a DR program without changing energy-use behaviors) – and household decisions about enrolling in DR programs and reducing energy use. Our research also demonstrates the potential of smart meter data, combined with machine learning and econometric methods, to provide significant value to utilities, program implementers, researchers, and other stakeholders.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Ray Tracing Techniques for the Characterization of Lunar Communication Architectures

This paper provides an overview of the computational techniques used to characterize the viability of different lunar architectures and their ability to provide communication services to the lunar surface. This analysis was done with modern ray tracing techniques that allow for the computations to be done on Graphics Processing Unit (GPU) clusters for a high level of parallelism and severe reduction in computation time. The ray tracing computations were done with the GPU platform Compute Unified Device Architecture (CUDA) provided by NVIDIA which utilizes general-purpose computing on graphics processing units (GPGPU). This new method provides the advantage of being able to characterize a much larger portion of the lunar surface due to its computational efficiency as well as providing a more accurate representation of elevation angle limits instead of the typical and often inaccurate elevation angle mask. The Lunar surface can now be characterized with metrics such as contact time, outage time, and received data rate. With these metrics, different proposed Lunar architectures can be rapidly evaluated. This reduction in computation time not only leads to more accurate results but allows these results to be obtained in a time frame that allows for the complete characterization of the trade space. It is expected that these different architecture comparisons will lead to a conclusive determination of the optimal Lunar architecture and will allow for future Lunar missions to operate as close to real time as possible. In addition, this computation method can be used to recreate visibility figures generated by previous methods but with an increased level of accuracy.

Thomas Montano↗

Active Subspace Methods for Data-Intensive Inverse Problems (Final Report)

Fostered by advances in computing, simulation and data science have emerged as the third and fourth paradigms enabling scientific discovery. Many mathematical challenges arise when integrating these paradigms to produce new knowledge. One of the most important challenges is the inverse or calibration problem: find the inputs of a simulation such that its outputs agree with a given set of measurements. As both the cost of the complex simulations and the volume of measurement data sets increase, intuition-driven trial-and-error methods for calibration quickly become untenable; modern scientists need more computationally efficient and mathematically rigorous methods. When measurements and simulated predictions contain uncertainty, the Bayesian perspective on statistical inference provides a popular mathematical framework for developing computational methods to solve inverse problems. Markov chain Monte Carlo (MCMC) methods are a mainstay of this framework; they characterize a probability distribution on the space of model inputs that is conditioned on the given measurements. However, despite recent advances, MCMC methods remain impractical for expensive simulations with more than a handful of inputs. At its heart, MCMC searches the space of inputs for corresponding outputs that match measurements, and so it is afflicted with the curse of dimensionality. Additionally, MCMC methods become less efficient as the volume of the measurement data increases, particularly if the measurements are redundant. To make MCMC—and Bayesian methods, in general—amenable to today’s computer models with millions of inputs and terabytes of measurement data, one must devise methods to reduce the dimension of both the simulation inputs and the measurements. For many models used in practice, the outputs vary primarily on a low-dimensional manifold of the nominally high-dimensional input space. Recently developed active subspace methods discover this low-dimensional manifold and exploit it to enable analyses typically suited for low-dimensional settings (e.g., statistical inversion of complex systems). We hypothesize that active subspace methods can provide the necessary dimension reduction, enabling existing Bayesian methods to find solutions for a large class of otherwise intractable statistical inverse problems. We will test the hypothesis with a series of mathematical analyses and computational experiments that will proceed along three research veins: (i) integrating active subspace methods into methods for statistical inversion, (ii) addressing current challenges in active subspace methods, and (iii) incorporating methods for nonlinear dimensionality reduction into active subspace methods. We will apply the methods we develop to real inverse problems in chemical kinetics and turbulent flame modeling. Our team combines expertise in methods for inverse problems, dimension reduction, and reduced order modeling. With a history of active collaboration and thoughtful engagement, we bring enthusiasm and fresh perspectives to a well studied subject. We are excited by the potential opportunity to work together to extend and apply active subspace methods to data-intensive inverse problems.

97 MATHEMATICS AND COMPUTING↗

Active Subspace Methods for Data-Intensive Inverse Problems

Fostered by advances in computing, simulation and data science have emerged as the third and fourth paradigms enabling scientific discovery. Many mathematical challenges arise when integrating these paradigms to produce new knowledge. One of the most important challenges is the inverse or calibration problem: find the inputs of a simulation such that its outputs agree with a given set of measurements. As both the cost of the complex simulations and the volume of measurement data sets increase, intuition-driven trial-and-error methods for calibration quickly become untenable; modern scientists need more computationally efficient and mathematically rigorous methods. When measurements and simulated predictions contain uncertainty, the Bayesian perspective on statistical inference provides a popular mathematical framework for developing computational methods to solve inverse problems. Markov chain Monte Carlo (MCMC) methods are a mainstay of this framework; they characterize a probability distribution on the space of model inputs that is conditioned on the given measurements. However, despite recent advances, MCMC methods remain impractical for expensive simulations with more than a handful of inputs. At its heart, MCMC searches the space of inputs for corresponding outputs that match measurements, and so it is afflicted with the curse of dimensionality. Additionally, MCMC methods become less efficient as the volume of the measurement data increases, particularly if the measurements are redundant. To make MCMC—and Bayesian methods, in general—amenable to today’s computer models with millions of inputs and terabytes of measurement data, one must devise methods to reduce the dimension of both the simulation inputs and the measurements. For many models used in practice, the outputs vary primarily on a low-dimensional manifold of the nominally high-dimensional input space. Recently developed active subspace methods discover this low-dimensional manifold and exploit it to enable analyses typically suited for low-dimensional settings (e.g., statistical inversion of complex systems). We hypothesize that active subspace methods can provide the necessary dimension reduction, enabling existing Bayesian methods to find solutions for a large class of otherwise intractable statistical inverse problems. We will test the hypothesis with a series of mathematical analyses and computational experiments that will proceed along three research veins: (i) integrating active subspace methods into methods for statistical inversion, (ii) addressing current challenges in active subspace methods, and (iii) incorporating methods for nonlinear dimensionality reduction into active subspace methods. We will apply the methods we develop to real inverse problems in chemical kinetics and turbulent flame modeling. Our team combines expertise in methods for inverse problems, dimension reduction, and reduced order modeling. With a history of active collaboration and thoughtful engagement, we bring enthusiasm and fresh perspectives to a well studied subject. We are excited by the potential opportunity to work together to extend and apply active subspace methods to data-intensive inverse problems.

97 MATHEMATICS AND COMPUTING↗

Development of Prognostic Models Using Plant Asset Data

The recent growth of machine learning and artificial intelligence technologies provides opportunities for leveraging data-driven algorithms to address the problems of diagnostics and prognostics in the nuclear power industry. The use of machine learning and other statistical methods as prognostic models is of particular interest in the nuclear industry to accurately predict future equipment or plant state given a set of measurements. Such predictive capability will enable predictive assessment of component condition and remaining life and allow for condition-based predictive maintenance. The resulting optimization of maintenance scheduling and reduction in unnecessary maintenance activities will lower overall maintenance costs and improve the economics of nuclear power. This report discusses the various aspects of data processing and model development that are likely to influence the performance of prognostic models. Data from a boiling-water reactor was used to evaluate several prognostic models to identify key considerations for developing such models to predict data-driven plant state and equipment degradation condition. Preliminary results indicate the need for data sets that are relevant to the problem at hand and contain signatures that may be correlated to the prediction problem. Assuming such data exist, development of prognostic models using data-driven methods requires an understanding of the various sources of influence on the prediction accuracy (such as the model architecture, data preprocessing approaches, and potentially external factors influencing the equipment or plant system under assessment). Ongoing research is evaluating these factors in greater detail and examining techniques for calculating prediction uncertainty bounds.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗