Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep uncertainty”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Ising-Traffic: Using Ising Machine Learning to Predict Traffic Congestion under Uncertainty

This paper addresses the challenges in accurate and realtime traffic congestion prediction with uncertainty by proposing Ising-Traffic, a novel quantum-inspired dual-model Ising based traffic prediction framework which delivers higher accuracy and lower latency than SOTA solutions. While traditional and deep learning methods face the trade-off between algorithm complexity and computational efficiency, our Ising-based method leverages Ising’s inherent and unique capability of finding the state of a system with the lowest energy and applying it to traffic prediction. In this work, traffic prediction under uncertainty is formulated into two separate Ising models: Reconstruct-Ising and Predict-Ising. Reconstruct-Ising is mapped onto modern Ising machine and handles uncertainty in traffic accurately with negligible latency and energy consumption, while Predict-Ising is mapped onto traditional processors and predicts future congestion precisely with only at most 1.8% computational demands of existing solutions. Our evaluation shows Ising-Traffic delivers on average 98× speedups and 5% accuracy improvement over SOTA.

traffic flow control, Ising↗
DOE OSTI2021

Deep-learning-enabled Bayesian inference of fuel magnetization in magnetized liner inertial fusion

Fuel magnetization in magneto-inertial fusion (MIF) experiments improves charged burn product confinement, reducing requirements on fuel areal density and pressure to achieve self-heating. By elongating the path length of 1.01 MeV tritons produced in a pure deuterium fusion plasma, magnetization enhances the probability for deuterium–tritium reactions producing 11.8-17.1 MeV neutrons. Nuclear diagnostics thus enable a sensitive probe of magnetization. Characterization of magnetization, including uncertainty quantification, is crucial for understanding the physics governing target performance in MIF platforms, such as magnetized liner inertial fusion (MagLIF) experiments conducted at Sandia National Laboratories, Z-facility. We demonstrate a deep-learned surrogate of a physics-based model of nuclear measurements. A single model evaluation is reduced from O ( 10 – 100 ) (10–100) CPU hours on a high-performance computing cluster down to O ( 10 – 100 ) (10) ms on a laptop. This enables a Bayesian inference of magnetization, rigorously accounting for uncertainties from surrogate modeling and noisy nuclear measurements. The approach is validated by testing on synthetic data and comparing with a previous study. We analyze a series of MagLIF experiments systematically varying preheat, resulting in the first ever systematic experimental study of magnetic confinement properties of the fuel plasma as a function of fundamental inputs on any neutron-producing MIF platform. We demonstrate that magnetization decreases from B R ∼ 0.2 ~0.5 to B R ∼ 0.2 ~0.2 MG cm as laser preheat energy deposited increases from E preheat ∼ 460 ~460 J to E preheat ∼ 460 ~1.4 kJ. This trend is consistent with 2D LASNEX simulations showing Nernst advection of the magnetic field out of the hot fuel and diffusion into the target liner.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Deep-Learning-Based Koopman Modeling for Online Control Synthesis of Nonlinear Power System Transient Dynamics

Power system stability and control have become more challenging due to the increasing uncertainty associated with renewable generation. Here, the performance of conventional control is highly driven by the physics-based offline-developed dynamic models that can deviate from the actual system characteristics under different operating conditions and/or configurations. Data-driven approaches based on online measurements can be a better solution to addressing these issues by capturing real-time operation conditions. This article describes a novel fully data-driven probabilistic framework to derive a linear representation of postcontingency grid dynamics and online prescribe control based on the derived model to enhance transient stability. The complex nonlinear power system dynamics is approximated by a linear model by using multiple neural network modules that infer distributions of the observations and introducing a Koopman layer to sample possible Koopman linear models from the inferred distributions. The trained model features linearity that can be easily incorporated into the existing linear control design paradigm and ease the controller design process. The effectiveness of Koopman-based control designs is validated through comparative case studies, which demonstrate increased prediction accuracy and control performance when applied to a power system with heterogeneous generator dynamics.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Multi-Agent Hierarchical Deep Reinforcement Learning for HVAC Control With Flexible DERs

As electricity consumption in commercial and residential buildings continues to rise, reducing energy costs presents an increasing challenge. Heating, ventilating, and air-conditioning (HVAC) systems, which typically account for 40%-50% of a building's energy use, are prime targets for energy savings. Intelligent control of HVAC temperature through the exploitation of HVAC load flexibility brings significant potential to reduce energy consumption and electricity expenses. The nonlinear models of HVAC systems challenge traditional control methods, while the uncertainty introduced by HVAC load flexibility complicates distributed energy resource (DER) management using conventional optimal dispatch techniques. In response to these challenges, we propose a hierarchical multi-agent deep reinforcement learning (DRL) approach. The lower-level agents focus on balancing comfort and energy conservation, while the upper-level DRL agents optimize the use of DERs to reduce peak demand based on the control outcomes of the HVAC by the lower-level agents. Here, in the upper-level agents, we incorporate a multi-agent structure based on ensemble learning, which acts based on historical and current data without relying on precise load forecasting to address the delayed rewarding issue in DRL. This allows for the effective reduction of energy costs. The proposed method is tested using a real-world microgrid comprising 413 buildings in Southern California, and the results demonstrate that our approach can significantly reduce overall electricity bills while ensuring the comfort of consumers and residents.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2013

Ocean Biological Pump Sensitivities and Implications for Climate Change Impacts

The ocean is one of the principal reservoirs of CO2, a greenhouse gas, and therefore plays a crucial role in regulating Earth's climate. Currently, the ocean sequesters about a third of anthropogenic CO2 emissions, mitigating the human impact on climate. At the same time, the deeper ocean represents the largest carbon pool in the Earth System and processes that describe the transfer of carbon from the surface of the ocean to depth are intimately linked to the effectiveness of carbon sequestration.The ocean biological pump (OBP), which involves several biogeochemical processes, is a major pathway for transfer of carbon from the surface mixed layer into the ocean interior. About 75 of the carbon vertical gradient is due to the carbon pump with only 25 attributed to the solubility pump. However, the relative importance and role of the two pumps is poorly constrained. OBP is further divided to the organic carbon pump (soft tissue pump) and the carbonate pump, with the former exporting about 10 times more carbon than the latter through processes like remineralization.Major uncertainties about OBP, and hence in the carbon uptake and sequestration, stem from uncertainties in processes involved in OBP such as particulate organicinorganic carbon sinkingsettling, remineralization, microbial degradation of DOC and uptakegrowth rate changes of the ocean biology. The deep ocean is a major sink of atmospheric CO2 in scales of hundreds to thousands of years, but how the export efficiency (i.e. the fraction of total carbon fixation at the surface that is transported at depth) is affected by climate change remains largely undetermined. These processes affect the ocean chemistry (alkalinity, pH, DIC, particulate and dissolved organic carbon) as well as the ecology (biodiversity, functional groups and their interactions) in the ocean. It is important to have a rigorous, quantitative understanding of the uncertainties involved in the observational measurements, the models and the projections of future changes.

particulates↗
DOE OSTI2022

Evaluating alternative ebullition models for predicting peatland methane emission and its pathways via data–model fusion

Abstract. Understanding the dynamics of peatland methane (CH4) emissions and quantifying sources of uncertainty in estimating peatland CH4 emissions are critical for mitigating climate change. The relative contributions of CH4 emission pathways through ebullition, plant-mediated transport, and diffusion, together with their different transport rates and vulnerability to oxidation, determine the quantity of CH4 to be oxidized before leaving the soil. Notwithstanding their importance, the relative contributions of the emission pathways are highly uncertain. In particular, the ebullition process is more uncertain and can lead to large uncertainties in modeled CH4 emissions. To improve model simulations of CH4 emission and its pathways, we evaluated two model structures: (1) the ebullition bubble growth volume threshold approach (EBG) and (2) the modified ebullition concentration threshold approach (ECT) using CH4 flux and concentration data collected in a peatland in northern Minnesota, USA. When model parameters were constrained using observed CH4 fluxes, the CH4 emissions simulated by the EBG approach (RMSE = 0.53) had a better agreement with observations than the ECT approach (RMSE = 0.61). Further, the EBG approach simulated a smaller contribution from ebullition but more frequent ebullition events than the ECT approach. The EBG approach yielded greatly improved simulations of pore water CH4 concentrations, especially in the deep soil layers, compared to the ECT approach. When constraining the EBG model with both CH4 flux and concentration data in model–data fusion, uncertainty of the modeled CH4 concentration profiles was reduced by 78 % to 86 % in comparison to constraints based on CH4 flux data alone. The improved model capability was attributed to the well-constrained parameters regulating the CH4 production and emission pathways. Our results suggest that the EBG modeling approach better characterizes CH4 emission and underlying mechanisms. Moreover, to achieve the best model results both CH4 flux and concentration data are required to constrain model parameterization.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Training calibration-based counterfactual explainers for deep learning models in medical image analysis

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model’s predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2023

Physics-informed machine learning for fault-leakage reduced-order modeling

Geologic carbon storage (GCS) is a promising technology for mitigating CO 2 emissions. The overall success of GCS depends on safe operations that are informed by risk assessment and have proper mitigation plans in place. Performing quantitative probabilistic risk assessment for a GCS site using traditional reservoir simulators can be challenging due to the high computational costs. To overcome this challenge, the US Department of Energy’s National Risk Assessment Partnership (NRAP) project has developed an integrated assessment modeling approach that utilizes computationally efficient reduced-order models (ROM) for simulating various parts of a GCS storage site to quantify uncertainty. Here, in this study, we develop a reduced-order model for fault leakage risk assessment. We use a deep learning approach to build the reduced-order model. We perform a sensitivity analysis and find that the deep learning model yields high accuracy with a much smaller computational cost than full-physics simulation. We also evaluate the performance of the model in scenarios where simulations are not possible to run, providing analysis not previously performed in fault-leakage ROM analyses. Based on a sensitivity analysis of the model, we suggest a simplified conceptual model for fault leakage and site monitoring.

58 GEOSCIENCES↗
DOE OSTI2021

Distributional Deep Reinforcement Learning-Based Emergency Frequency Control

Emergency frequency control is one of the most critical approaches to maintain power system stability after major disturbances. With the increasing number of grid-connected renewable energy sources, existing model-based methods of frequency control are facing up with challenges of computational speed and scalability for large-scale systems. In this paper, the emergency frequency control problem is formulated as a Markov Decision Process (MDP) and solved through a novel Distributional Deep Reinforcement Learning (DDRL) method, namely the distributional soft actor critic (DSAC) method. Compared with other RL methods that only estimate the mean value, the proposed DSAC model estimates the distribution of value function over returns. This advancement can lead to more insights and knowledge for the agent, with the benefit of a much faster and more stable learning process, and the improved frequency control performance. Here, the simulation results on IEEE 39-bus and IEEE 118-bus systems demonstrate the effectiveness and robustness of proposed models, as well as the advantage compared to other state-of-the-art DRL algorithms.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2012

A Determination of the Intergalactic Redshift Dependent UV-Optical-NIR Photon Density Using Deep Galaxy Survey Data and the Gamma-ray Opacity of the Universe

We calculate the intensity and photon spectrum of the intergalactic background light (IBL) as a function of redshift using an approach based on observational data obtained in many different wavelength bands from local to deep galaxy surveys. This allows us to obtain an empirical determination of the IBL and to quantify its observationally based uncertainties. Using our results on the IBL, we then place 68% confidence upper and lower limits on the opacity of the universe to gamma-rays, free of the theoretical assumptions that were needed for past calculations. We compare our results with measurements of the extragalactic background light and upper limits obtained from observations made by the Fermi Gamma-ray Space Telescope.

Stecker, Floyd W.↗
NASA NTRSDate not supplied

SWIPE: Spectral Water Inversion Processor and Emulator

Degradation of Earth’s inland water resources due to anthropogenic perturbations and climate anomalies at both local and global scales continues to place human health at substantial risk. There is now a growing necessity to develop pragmatic approaches that allow timely and effective extrapolation of local processes, to spatially resolved global products, and to promote operational and sustainable resource policy management. This presentation will be discussing the progress made developing SWIPE: Spectral Water Inversion Processor and Emulator. SWIPE is a platform for advanced modeling of coastal and inland aquatic habitats. The goal is create a comprehensive and cohesive system to leverage recent advancements in computation and machine learning to develop a synthetic training ground for sensitivity studies and algorithm development. The four principal facets of SWIPE include: 1. Advanced two-layer coated sphere bio-optical modeling and GPU radiative transfer modeling, 2. Big Data involving massive synthetic spectral libraries of optical properties of various global aquatic particles, surface reflectance, and top-of-atmosphere reflectance, all at hyperspectral resolution leveraging high-end computing systems at NASA Ames Research Center, 3. Deep Learning for algorithm development for water quality inversion of concentrations of common biogeophysical variables as well as optics, full uncertainty characterization by water type, and forward emulation, and lastly, 4. Image Processing for application of developed retrieval algorithms for both hyperspectral and multispectral sensors with experimental corrections for global adjacency, noise, sunglint, and benthic reflectance. This presentation will demonstrate the Equivalent Algal Populations (EAP) two-layer coated sphere scattering model which has been used develop spectral libraries of hyperspectral inherent optical properties of roughly 80 species of phytoplankton, covering 15 different classes and nine taxonomic functional types. The EAP model was also used to derive spectral properties of 10 different non-algal particle functional types. Examples of how the SMART-G (Speed-up Monte-carlo Advanced Radiative Transfer using GPU) radiative transfer code is used to model optically complex aquatic signals will be presented and discussed in the context of creating a massive synthetic database which can leverage the full power of next generation machine learning techniques and high end computing for water quality inversion. We will discuss our active investigation in things like appropriate model architectures, dimensionality reduction techniques such as PCA and autoencoders, uncertainty quantification and abstaining, and which variables actually benefit most from hyperspectral information versus multispectral resolution. We are also curious about questions relating to cost/benefit analysis in terms of computation resources, neural network complexity, and data volumes. Answers to these questions will hopefully elaborate on cost efficiency for potential future sensor design considerations.

SWIPE↗
DOE OSTI2021

A Deeper Look at DES Dwarf Galaxy Candidates: Grus i and Indus ii

We present deep g- and r-band Magellan/Megacam photometry of two dwarf galaxy candidates discovered in the Dark Energy Survey (DES), Grus i and Indus ii (DES J2038–4609). For the case of Grus i, we resolved the main sequence turn-off (MSTO) and ~2 mags below it. The MSTO can be seen at g 0 ~24 with a photometric uncertainty of 0.03 mag. We show Grus i to be consistent with an old, metal-poor (~13.3 Gyr, [Fe/H] ~ -1.9) dwarf galaxy. We derive updated distance and structural parameters for Grus i using this deep, uniform, wide-field data set. We find an azimuthally-averaged halflight radius more than two times larger (~151 +21 -31 pc; ~$4\buildrel{\,\prime}\over{.} {16}_{-0.74}^{+0.54}$) and an absolute V-band magnitude ~-4.1 that is ~1 magnitude brighter than previous studies. We obtain updated distance, ellipticity, and centroid parameters that are in agreement with other studies within uncertainties. Although our photometry of Indus ii is ~2–3 magnitudes deeper than the DES Y1 public release, we find no coherent stellar population at its reported location. The original detection was located in an incomplete region of sky in the DES Y2Q1 data set and was flagged due to potential blue horizontal branch member stars. The best-fit isochrone parameters are physically inconsistent with both dwarf galaxies and globular clusters. We conclude that Indus ii is likely a false positive, flagged due to a chance alignment of stars along the line of sight.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Vehicle to Grid Frequency Regulation Capacity Optimal Scheduling for Battery Swapping Station Using Deep Q-Network

Battery swapping stations (BSSs) are ideal candidates for fast frequency regulation services (FFRS) due to their large battery stock capacity. In addition, BSSs can precharge batteries for customers and the batteries that are not in charging can provide a stable regulation capacity to the market. However, uncertainties, such as ACE signals and the EV per-hour visit counts, introduce stochastic nonlinear dynamics into the operation of a BSS-based FFRS. Currently, there is no quantification method to ensure its optimal economical operation. To close this gap, in this article, we propose a novel deep Q-learning-based FFRS capacity dynamic scheduling strategy. This method can autonomously schedule the hourly regulation capacity in real time to maximize the BSSx0027;s revenue for providing FFRS. Case studies using real-world data verify the efficacy of the proposed work.

25 ENERGY STORAGE↗
NASA NTRS2015

GCR Simulator Reference Field and a Spectral Approach for Laboratory Simulation

The galactic cosmic ray (GCR) simulator at the NASA Space Radiation Laboratory (NSRL) is intended to deliver the broad spectrum of particles and energies encountered in deep space to biological targets in a controlled laboratory setting. In this work, certain aspects of simulating the GCR environment in the laboratory are discussed. Reference field specification and beam selection strategies at NSRL are the main focus, but the analysis presented herein may be modified for other facilities. First, comparisons are made between direct simulation of the external, free space GCR field and simulation of the induced tissue field behind shielding. It is found that upper energy constraints at NSRL limit the ability to simulate the external, free space field directly (i.e. shielding placed in the beam line in front of a biological target and exposed to a free space spectrum). Second, variation in the induced tissue field associated with shielding configuration and solar activity is addressed. It is found that the observed variation is likely within the uncertainty associated with representing any GCR reference field with discrete ion beams in the laboratory, given current facility constraints. A single reference field for deep space missions is subsequently identified. Third, an approach for selecting beams at NSRL to simulate the designated reference field is presented. Drawbacks of the proposed methodology are discussed and weighed against alternative simulation strategies. The neutron component and track structure characteristics of the simulated field are discussed in this context.

Slaba, Tony C.↗
NASA NTRS2008

Analysis of System Margins on Missions Utilizing Solar Electric Propulsion

NASA's Jet Propulsion Laboratory has conducted a study focused on the analysis of appropriate margins for deep space missions using solar electric propulsion (SEP). The purpose of this study is to understand the links between disparate system margins (power, mass, thermal, etc.) and their impact on overall mission performance and robustness. It is determined that the various sources of uncertainty and risk associated with electric propulsion mission design can be summarized into three relatively independent parameters 1) EP Power Margin, 2) Propellant Margin and 3) Duty Cycle Margin. The overall relationship between these parameters and other major sources of uncertainty is presented. A detailed trajectory analysis is conducted to examine the impact that various assumptions related to power, duty cycle, destination, and thruster performance including missed thrust periods have on overall performance. Recommendations are presented for system margins for deep space missions utilizing solar electric propulsion.

Systems Engineering↗
NASA NTRS2013

An Updated TRMM Composite Climatology of Tropical Rainfall and Its Validation

An updated 15-yr Tropical Rainfall Measuring Mission (TRMM) composite climatology (TCC) is presented and evaluated. This climatology is based on a combination of individual rainfall estimates made with data from the primaryTRMMinstruments: theTRMM Microwave Imager (TMI) and the precipitation radar (PR). This combination climatology of passive microwave retrievals, radar-based retrievals, and an algorithm using both instruments simultaneously provides a consensus TRMM-based estimate of mean precipitation. The dispersion of the three estimates, as indicated by the standard deviation sigma among the estimates, is presented as a measure of confidence in the final estimate and as an estimate of the uncertainty thereof. The procedures utilized by the compositing technique, including adjustments and quality-control measures, are described. The results give a mean value of the TCC of 4.3mm day(exp -1) for the deep tropical ocean beltbetween 10 deg N and 10 deg S, with lower values outside that band. In general, the TCC values confirm ocean estimates from the Global Precipitation Climatology Project (GPCP) analysis, which is based on passive microwave results adjusted for sampling by infrared-based estimates. The pattern of uncertainty estimates shown by sigma is seen to be useful to indicate variations in confidence. Examples include differences between the eastern and western portions of the Pacific Ocean and high values in coastal and mountainous areas. Comparison of the TCC values (and the input products) to gauge analyses over land indicates the value of the radar-based estimates (small biases) and the limitations of the passive microwave algorithm (relatively large biases). Comparison with surface gauge information from western Pacific Ocean atolls shows a negative bias (~16%) for all the TRMM products, although the representativeness of the atoll gauges of open-ocean rainfall is still in question.

(GPCP) Global Precipitation Project analysis↗
NASA NTRS2016

Extending "Deep Blue" Aerosol Retrieval Coverage to Cases of Absorbing Aerosols Above Clouds: Sensitivity Analysis and First Case Studies

Cases of absorbing aerosols above clouds (AACs), such as smoke or mineral dust, are omitted from most routinely processed space-based aerosol optical depth (AOD) data products, including those from the Moderate Resolution Imaging Spectroradiometer (MODIS). This study presents a sensitivity analysis and preliminary algorithm to retrieve above-cloud AOD and liquid cloud optical depth (COD) for AAC cases from MODIS or similar sensors, for incorporation into a future version of the "Deep Blue" AOD data product. Detailed retrieval simulations suggest that these sensors should be able to determine AAC AOD with a typical level of uncertainty approximately 25-50 percent (with lower uncertainties for more strongly absorbing aerosol types) and COD with an uncertainty approximately10-20 percent, if an appropriate aerosol optical model is known beforehand. Errors are larger, particularly if the aerosols are only weakly absorbing, if the aerosol optical properties are not known, and the appropriate model to use must also be retrieved. Actual retrieval errors are also compared to uncertainty envelopes obtained through the optimal estimation (OE) technique; OE-based uncertainties are found to be generally reasonable for COD but larger than actual retrieval errors for AOD, due in part to difficulties in quantifying the degree of spectral correlation of forward model error. The algorithm is also applied to two MODIS scenes (one smoke and one dust) for which near-coincident NASA Ames Airborne Tracking Sun photometer (AATS) data were available to use as a ground truth AOD data source, and found to be in good agreement, demonstrating the validity of the technique with real observations.

aerosols above clouds↗
DOE OSTI2023

Bi-fidelity modeling of uncertain and partially unknown systems using DeepONets

Recent advances in modeling large-scale, complex physical systems have shifted research focuses towards data-driven techniques. However, generating datasets by simulating complex systems can require significant computational resources. Similarly, acquiring experimental datasets can prove difficult. For these systems, often computationally inexpensive, but in general inaccurate models, known as the low-fidelity models, are available. Here in this paper, we propose a bi-fidelity modeling approach for complex physical systems, where we model the discrepancy between the true system's response and a low-fidelity response in the presence of a small training dataset from the true system's response using a deep operator network, a neural network architecture suitable for approximating nonlinear operators. We apply the approach to systems that have parametric uncertainty and are partially unknown. Three numerical examples are used to show the efficacy of the proposed approach to model uncertain and partially unknown physical systems.

MATHEMATICS AND COMPUTING↗