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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Uncertainty Quantification for Data-Driven Machine Learning Models in Nuclear Engineering Applications: Where We Are and What Do We Need?

Machine learning (ML) has been leveraged to tackle a diverse range of tasks in almost all branches of nuclear engineering. Many of the successes in ML applications can be attributed to the recent performance breakthroughs in deep learning, the growing availability of computational power, data, and easy-to-use ML libraries. However, these empirical successes have often outpaced our formal understanding of the ML algorithms. An important but under-rated area is uncertainty quantification (UQ) of ML. ML-based models are subject to approximation uncertainty when they are used to make predictions, due to sources including but not limited to, data noise, data coverage, extrapolation, imperfect model architecture and the stochastic training process. The goal of this paper is to clearly explain and illustrate the importance of UQ of ML. We will elucidate the differences in the basic concepts of UQ of physics-based models and data-driven ML models. Various sources of uncertainties in physical modeling and data-driven modeling will be discussed, demonstrated, and compared. We will also present and demonstrate a few techniques to quantify the ML prediction uncertainties, including Monte Carlo dropout, deep ensemble, Bayesian neural networks, Gaussian Processes and conformal prediction. Lastly, we will discuss the need for building a verification, validation and UQ framework to establish ML credibility.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Evaluating uncertainty-based active learning for accelerating the generalization of molecular property prediction

Deep learning models have proven to be a powerful tool for the prediction of molecular properties for applications including drug design and the development of energy storage materials. However, in order to learn accurate and robust structure–property mappings, these models require large amounts of data which can be a challenge to collect given the time and resource-intensive nature of experimental material characterization efforts. Additionally, such models fail to generalize to new types of molecular structures that were not included in the model training data. The acceleration of material development through uncertainty-guided experimental design has the promise to significantly reduce the data requirements and enable faster generalization to new types of materials. To evaluate the potential of such approaches for electrolyte design applications, we perform comprehensive evaluation of existing uncertainty quantification methods on the prediction of two relevant molecular properties - aqueous solubility and redox potential. We develop novel evaluation methods to probe the utility of the uncertainty estimates for both in-domain and out-of-domain data sets. Finally, we leverage selected uncertainty estimation methods for active learning to evaluate their capacity to support experimental design.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Estimation, UQ, and Sensitivity Analysis for a New Diagnostic Setup [Slides]

This is for an early career talk I am giving at the Association for Women in Math’s Research Symposium. It provides a general overview of three projects: the first focuses on velocity measurements from optical laser diagnostics, the second focuses on probe alignment and location (metrology), and the third is my Site-Directed Research and Development (SDRD) which focuses on neural networks for image datasets. All three projects have strong uncertainty quantification components.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2024

Spectral Correlation in MODIS Water-Leaving Reflectance Retrieval Uncertainty

Spectral remote sensing reflectance, Rrs(λ) (sr−1), is the fundamental quantity used to derive a host of bio-optical and biogeochemical properties of the water column from satellite ocean color measurements. Estimation of uncertainty in those derived geophysical products is therefore dependent on knowledge of the uncertainty in satellite-retrieved R rs . Furthermore, since the associated algorithms require R rs at multiple spectral bands, the spectral (i.e., band-to-band)error covariance in R rs is needed to accurately estimate the uncertainty in those derived properties. This study establishes a derivative-based approach for propagating instrument random noise, instrument systematic uncertainty, and forward model uncertainty into R rs as retrieved using NASA’s multiple-scattering epsilon (MSEPS) atmospheric correction algorithm, to generate pixel-level error covariance in R rs . The approach is applied to measurements from Moderate Resolution Imaging Spectroradiometer (MODIS) on the Aqua satellite and verified using Monte Carlo (MC) analysis. We also make use of this full spectral error covariance in R rs to calculate uncertainty in phytoplankton pigment chlorophyll-a concentration (chl a , mg/m 3 ) and diffuse attenuation coefficient of downwelling irradiance at 490 nm (K d (490), m -1 ). Accounting for the error covariance in R rs generally reduces the estimated relative uncertainty in chl a by ∼1-2% (absolute value) in waters with chl a < 0.25 mg/m 3 where the color index (CI) algorithm is used. The reduction is ∼5-10% in waters with chl a > 0.35 mg/m 3 where the blue-green ratio (OCX) algorithm is used. Such reduction can be higher than 30% in some regions. For K d (490), the reduction by error covariance is generally ∼2%, but can be higher than 20% in some regions. The error covariance in R rs is further verified through forward-calculating chl a from MODIS-retrieved and in situ R rs and comparing estimated uncertainty with observed differences. An 8-day global composite of propagated uncertainty shows that the goal of 35% uncertainty in chl a can be achieved over deep ocean waters (chl a ≤ 0.1 mg/m3). While the derivative-based approach generates reasonable error covariance in R rs some assumptions should be updated as our knowledge improves. These include the inter-band error correlation in top-of-atmosphere reflectance, and uncertainties in the calibration of MODIS 869 nm band, in ancillary data, and in the in situ data used for system vicarious calibration.

Ocean color↗
DOE OSTI2021

Underestimated marine stratocumulus cloud feedback associated with overly active deep convection in models

Cloud feedback remains the largest source of uncertainty in equilibrium climate sensitivity (ECS). Many studies have attempted to narrow uncertainties in cloud feedback and ECS by proposing observable metrics with high skill at predicting future climate, referred to as emergent constraints. These constraints are often associated with clouds, convection, and circulation, and are interrelated. However, physical explanations for these connections remain unclear. Here, we propose a new mechanism relating convection and clouds across multiple climate models. Some models show overly active deep convection on daily timescales in the subtropical low cloud regions, which contributes to weaker subsidence inversion and smaller amounts of low-level clouds. Such models predict smaller shortwave (SW) cloud feedback. Using precipitation frequency in these regions as an emergent constraint, encapsulating this mechanism, models with lower SW cloud feedback (<0.50 W m -2 °C - 1) are found to exhibit erroneously frequent convection. Our results suggest that further improvements in understanding and better modeling of cloud and convective systems are necessary for accurate climate predictions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Emulation of the calculations of final r -process abundance patterns with a neural network

This work explores the construction of a fast emulator for the calculation of the final pattern of nucleosynthesis in the rapid neutron capture process (the r-process). An emulator is built using a feed-forward artificial neural network (ANN). We train the ANN with nuclear data and relative abundance patterns. We take as input the β-decay half-lives and the one-neutron separation energy of the nuclei in the rare-earth region. The output is the final isotopic abundance pattern. In this work, we focus on the nuclear data and abundance patterns in the rare-earth region to reduce the dimension of the input and output space. We show that the ANN can capture the effect of the changes in the nuclear physics inputs on the final r-process abundance pattern in the adopted astrophysical conditions. We employ the deep ensemble method to quantify the prediction uncertainty of the neural network emulator. The emulator achieves a speed-up by a factor of about 20 000 in obtaining a final abundance pattern in the rare-earth region. The emulator may be utilized in statistical analyses such as uncertainty quantification, inverse problems, and sensitivity analysis.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Uncertainty Quantification and Sensitivity Analysis of Low-Dimensional Manifold via Co-Kurtosis PCA in Combustion Modeling

For multi-scale multi-physics applications e.g., the turbulent combustion code Pele, robust and accurate dimensionality reduction is crucial to solving problems at exascale and beyond. A recently developed technique, Co-Kurtosis based Principal Component Analysis (CoK-PCA) which leverages principal vectors of co-kurtosis, is a promising alternative to traditional PCA for complex chemical systems. To improve the effectiveness of this approach, we employ Artificial Neural Networks for reconstructing thermo-chemical scalars, species production rates, and overall heat release rates corresponding to the full state space. Our focus is on bolstering confidence in this deep learning based non-linear reconstruction through Uncertainty Quantification (UQ) and Sensitivity Analysis (SA). UQ involves quantifying uncertainties in inputs and outputs, while SA identifies influential inputs. One of the noteworthy challenges is the computational expense inherent in both endeavors. To address this, we employ the Monte Carlo methods to effectively quantify and propagate uncertainties in our reduced spaces while managing computational demands. Our research carries profound implications not only for the realm of combustion modeling but also for a broader audience in UQ. By showcasing the reliability and robustness of CoK-PCA in dimensionality reduction and deep learning predictions, we empower researchers and decision-makers to navigate complex combustion systems with greater confidence.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Enhancing generative molecular design via uncertainty-guided fine-tuning of variational autoencoders

In recent years, deep generative models have been successfully applied to various molecular design tasks, particularly in the life and materials sciences. One critical challenge for pre-trained generative molecular design (GMD) models is to fine-tune them to be better suited for downstream design tasks that aim at optimizing specific molecular properties. However, redesigning and training an existing effective generative model from scratch for each new design task are impractical. Furthermore, the black-box nature of typical downstream tasks that involve property prediction makes it nontrivial to optimize the generative model in a task-specific manner. In this work, we propose an uncertainty-guided fine-tuning strategy that can effectively enhance a pre-trained variational autoencoder (VAE) for GMD through performance feedback in an active learning setting. The strategy begins by quantifying the model uncertainty of the generative model using an efficient active subspace-based UQ (uncertainty quantification) scheme. Next, the decoder diversity within the characterized model uncertainty class is explored to expand the viable space of molecular generation. The low-dimensionality of the active subspace makes this exploration tractable using a black-box optimization scheme, which in turn enables us to identify and leverage a diverse set of high-performing models to generate enhanced molecules. Empirical results across six target molecular properties using multiple VAE-based generative models demonstrate that our uncertainty-guided fine-tuning strategy consistently leads to improved models that outperform the original pre-trained models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

New RES and DIS Uncertainties for NOvA Cross-Section Model

NOvA is a long-baseline neutrino experiment at Fermilab that studies neutrino oscillations via electron neutrino appearance and muon neutrino disappearance. The oscillation measurements compare the Far Detector data to an oscillated prediction informed by the Near Detector (ND) data. This ND-informed prediction is produced from the neutrino generator GENIE, which provides NOvA with a set of interaction uncertainties. However, this coverage does not account for all interaction uncertainties relevant for NOvA, in particular for resonance production (RES) and deep inelastic scattering (DIS) processes, which comprise a substantial portion of NOvA's interactions. Here we introduce six new cross section uncertainties that affect RES and DIS interactions, which represent degrees of freedom not available in the previous NOvA model. After careful studying of their impact, we incorporate them to the NOvA cross-section model. We show the impact of these new uncertainties on various reconstructed quantities.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Assessing and benchmarking the fidelity of posterior inference methods for astrophysics data analysis

In this era of large and complex astronomical survey data, interpreting, validating, and comparing inference techniques becomes increasingly difficult. This is particularly critical for emerging inference methods like Simulation-Based Inference (SBI), which offer significant speedup potential and posterior modeling flexibility, especially when deep learning is incorporated. We present a study to assess and compare the performance and uncertainty prediction capability of Bayesian inference algorithms – from traditional MCMC sampling of analytic functions to deep learning-enabled SBI. We focus on testing the capacity of hierarchical inference modeling in those scenarios. Before we extend this study to cosmology, we first use astrophysical simulation data to ensure interpretability. We demonstrate a probabilistic programming implementation of hierarchical and non-hierarchical Bayesian inference using simulations derived from the DeepBench software library, a benchmarking tool developed by our group that generates simple and controllable astrophysical objects from first principles. This study will enable astronomers and physicists to harness the inference potential of these methods with confidence.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Coarse-Grained Density Functional Theory Predictions via Deep Kernel Learning

Scalable electronic predictions are critical for soft materials design. Recently, the Electronic Coarse-Graining (ECG) method was introduced to renormalize all-atom quantum chemical (QC) predictions to coarse-grained (CG) resolutions using deep neural networks (DNNs). While DNNs can learn complex representations that prove challenging for kernel-based methods, they are susceptible to overfitting and the overconfidence of uncertainty estimations. Here, we develop ECG within a GPU-accelerated Deep Kernel Learning (DKL) framework to enable CG QC predictions using range-separated hybrid density functional theory (DFT), obtaining a 107 speedup relative to naive all-atom QC. By treating the predicted electronic properties as random Gaussian Processes, DKL incorporates CG mapping degeneracy by learning the distribution of electronic energies as a function of CG configuration. DKL-ECG accurately reproduces molecular orbital energies from range-separated DFT while facilitating efficient training via active learning using the uncertainties provided by DKL. Further, we show that while active learning algorithms enable efficient sampling of a more diverse configurational space relative to random sampling, all explored query methods exhibit comparable performance for the examined system. We attribute this result to the significant overlap of the feature space and output property distributions across multiple temperatures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Incorporating geological structure into sensitivity analysis of subsurface contaminant transport

Simulating subsurface contaminant transport at the kilometer-scale often entails modeling reactive flow and transport within and through complex geologic structures. These structures are typically meshed by hand and as a result geologic structure is usually represented by one or a few deterministically generated geological models for uncertainty studies of flow and transport in the subsurface. Uncertainty in geologic structure can have a significant impact on contaminant transport. In this study, the impact of geologic structure on contaminant tracer transport in a shale formation is investigated for a simplified generic deep geologic repository for permanent disposal of spent nuclear fuel. An open-source modeling framework is used to perform a sensitivity analysis study on transport of two tracers from a generic spent nuclear fuel repository with uncertain location of the interfaces between the stratum of the geologic structure. The automated workflow uses sampled realizations of the geological structural model in addition to uncertain flow parameters in a nested sensitivity analysis. Concentration of the tracers at observation points within, in line with, and downstream of the repository are used as the quantities of interest for determining model sensitivity to input parameters and geological realization. Finally, the results of the study indicate that the location of strata interfaces in the geological structure has a first-order impact on tracer transport in the example shale formation, and that this impact may be greater than that of the uncertain flow parameters.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2022

Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency control to maintain system reliability and security. Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years. However, existing DRL-based solutions have two main limitations: 1) they cannot handle well with a wide range of grid operation conditions, system parameters, and contingencies; 2) they generally lack the ability to fast adapt to new grid operation conditions, system parameters, and contingencies, limiting their applicability for real-world applications. Here, in this paper, we mitigate these limitations by developing a novel deep meta-reinforcement learning (DMRL) algorithm. The DMRL combines the meta strategy optimization together with DRL, and trains policies modulated by a latent space that can quickly adapt to new scenarios. We test the developed DMRL algorithm on the IEEE 300-bus system. We demonstrate fast adaptation of the meta-trained DRL polices with latent variables to new operating conditions and scenarios using the proposed method, which achieves superior performance compared to the state-of-the-art DRL and model predictive control (MPC) methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

HAMscope: a snapshot Hyperspectral Autofluorescence Miniscope for real-time molecular imaging

We introduce HAMscope, a compact, snapshot hyperspectral autofluorescence miniscope that enables real-time, label-free molecular imaging in a wide range of biological systems. By integrating a thin polymer diffuser into a widefield miniscope, HAMscope spectrally encodes each frame and employs a probabilistic deep learning framework to reconstruct 30-channel hyperspectral stacks (452-703 nm) or directly infer molecular composition maps from single images. A scalable multi-pass U-Net architecture with transformer-based attention and per pixel uncertainty estimation enables high spatio-spectral fidelity (mean absolute error ∼0.0048) at video rates. While initially demonstrated in plant systems, including lignin, chlorophyll, and suberin imaging in intact poplar and cork tissues, the platform is readily adaptable to other applications such as neural activity mapping, metabolic profiling, and histopathology. We show that the system generalizes to out-of-distribution tissue types and supports direct molecular mapping without the need for spectral unmixing. HAMscope establishes a general framework for compact, uncertainty-aware spectral imaging that combines minimal optics with advanced deep learning, offering broad utility for real-time biochemical imaging across neuroscience, environmental monitoring, and biomedicine.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

DetSuM: Detector Surrogate Model for LArTPC

In large neutrino experiments such as the Deep Underground Neutrino Experiment (DUNE), estimating detector response uncertainties typically requires simulation samples that consume substantial computing resources and time. To mitigate this challenge, we present DetSuM, an uncertainty-aware surrogate model designed to capture the detector response variations with reduced computing load compared to full simulations. This poster describes the construction and evaluation of DetSuM using simulation and reconstruction datasets in a rare-event search at DUNE. We assess DetSuM's ability to predict key detector-response variations and their associated uncertainties, discuss current limitations, and outline improvements to extend its validity in systematics studies of DUNE physics.

Li, Aobo [UC, San Diego]↗
NASA NTRS2012

Reliability Impacts in Life Support Architecture and Technology Selection

Quantitative assessments of system reliability and equivalent system mass (ESM) were made for different life support architectures based primarily on International Space Station technologies. The analysis was applied to a one-year deep-space mission. System reliability was increased by adding redundancy and spares, which added to the ESM. Results were thus obtained allowing a comparison of the ESM for each architecture at equivalent levels of reliability. Although the analysis contains numerous simplifications and uncertainties, the results suggest that achieving necessary reliabilities for deep-space missions will add substantially to the life support ESM and could influence the optimal degree of life support closure. Approaches for reducing reliability impacts were investigated and are discussed.

Lange Kevin E.↗
DOE OSTI2022

Warming Response of Deep Soil Carbon (LDRD Final Report)

The overarching objective of this LDRD project was to determine the vulnerability of deep soil organic carbon (SOC) to warming in the Sierra Nevada region. Deep soils (>30 cm) store more than 70% of global SOC, and increased SOC decomposition and CO 2 emissions caused by warming are potentially large climate change feedbacks. According to the Intergovernmental Panel on Climate Change, temperatures are expected to increase by 4°C by the year 2100, warming the land and underlying soil, and making understanding of how warming will influence deep SOC storage and persistence critical to projecting the land carbon sink. However, uncertainty remains in our process-level understanding and ability to quantify how projected warming will impact the stability of carbon in deep soils. We investigated warming effects on deep (up to 16 m) SOC stability across climate, vegetation, and soil mineralogy gradients in California. We sampled soils from the surface to bedrock (down to 16 meters) at four sites representing vastly different ecosystems across the Northern and Southern Sierra Nevada mountains. This study quantified the response of SOC concentration, distribution, and vulnerability to warming using a soil incubation experiment to warm the whole soil profile and radiocarbon and stable isotopes to assess which pools are vulnerable to loss under warming. Our results refine our understanding of the terrestrial carbon cycle by revealing the vulnerability of deep SOC to future changes in climate and how minerology may influence that vulnerability.

58 GEOSCIENCES↗