Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “prediction 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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Regional-scale soil carbon predictions can be enhanced by transferring global-scale soil–environment relationships

Accurate modelling and mapping soil organic carbon are crucial for supporting soil health restoration and climate change mitigation at both regional and global scales. However, regional soil predictions often suffer from data scarcity and high prediction uncertainty. Utilizing a pre-trained global-to-regional soil carbon predictive model can be a potential solution to address this challenge. Despite its promise, how to construct and apply the global-scale model to enhance regional-scale soil carbon mapping remains largely unexplored. Here, we propose the Global Soil Carbon Pre-trained Model (GSoilCPM), a deep-learning-based domain adaptative model, to enhance regional-scale soil carbon predictions. Based on large amount of environmental covariate data and 106,167 soil samples across the globe, we verify our hypothesis of the effectiveness of this 'global-to-regional' modelling strategy. The pre-trained model can be then transferred and fine-tuned to bridge the regional- and global-scale soil–environment relationships. We applied and validated this modelling strategy in four regional-scale study areas, three in the Northern Hemisphere and one in the Southern Hemisphere, each with distinct environmental background. Compared to traditional modelling approaches as a baseline, four case studies all demonstrated significant improvement in prediction accuracy across diverse environments and varying data availabilities. The average percentage improvement across all regions is 10.93% (absolute values decreased by 1.20 g kg−1 averagely) in MAE and 29.04% (absolute values increased by 0.10 averagely) in CCC. The applicability and future horizons of using GSoilCPM were further discussed. We further reveal that regions with fewer soil samples or lower baseline accuracy benefit more from the pre-trained global model. Our findings highlight the advantages of leveraging the generalized knowledge from global models to enhance specifically localized soil modelling, positioning a potential paradigm shift in digital soil mapping, and far-reaching implications for soil monitoring and land management.

Deep learning↗
DOE OSTI2025

mphys-surrogate-model

This repository contains python scripts for building and studying reduced-order-modeling representations of droplet coalescence for eventual use in atmospheric models. The included data are generated from high-fidelity superdroplet methods and are utilized by machine learning pipelines to build data-driven models of droplet size distributions that evolve under coalescence. This repository further includes scripts to determine prediction (uncertainty) intervals on the data-driven model products based on conformal prediction.

Katona, JonasE [Lawrence Livermore National Labora↗
DOE OSTI2025

Assessment of ESM Readiness Level for Exascale HPC

Advancement of Earth System Models (ESMs) is becoming increasingly challenging due to a confluence of factors including increasing model complexity – to more fully represent the earth system, increasing spatial resolution - to achieve higher accuracy by resolving fine-scale dynamical to physical, biological, and chemical processes and their interaction, increasing ensemble size - to more accurately represent predictive uncertainty, and increased computing requirements – to enable more accurate and timely weather predictions and climate projections for societal benefit. The belief by many that computing will take care of itself is no longer valid given the disruptive changes in HPC that are driving up the cost of computing, increasing the difficulty of using emerging HPC effectively, and exposing limits in parallelism, portability and scalability of the ESM applications themselves.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

A Bayesian Deep Learning Approach to Near-Term Climate Prediction

Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate prediction. The example problem setting we consider consists of predicting natural variability of the North Atlantic sea surface temperature on the interannual timescale in the pre-industrial control simulation of the Community Earth System Model. While previous works have considered the use of recurrent networks such as convolutional LSTMs and reservoir computing networks in this and other similar problem settings, we currently focus on the use of feedforward convolutional networks. In particular, we find that a feedforward convolutional network with a Densenet architecture is able to outperform a convolutional LSTM in terms of predictive skill. Next, we go on to consider a probabilistic formulation of the same network based on Stein variational gradient descent and find that in addition to providing useful measures of predictive uncertainty, the probabilistic (Bayesian) version improves on its deterministic counterpart in terms of predictive skill. Finally, we characterize the reliability of the ensemble of machine learning models obtained in the probabilistic setting by using analysis tools developed in the context of ensemble numerical weather prediction.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Probabilistic and maximum entropy modeling of chemical reaction systems: Characteristics and comparisons to mass action kinetic models

We demonstrate and characterize a first-principles approach to modeling the mass action dynamics of metabolism. Starting from a basic definition of entropy expressed as a multinomial probability density using Boltzmann probabilities with standard chemical potentials, we derive and compare the free energy dissipation and the entropy production rates. We express the relation between entropy production and the chemical master equation for modeling metabolism, which unifies chemical kinetics and chemical thermodynamics. Because prediction uncertainty with respect to parameter variability is frequently a concern with mass action models utilizing rate constants, we compare and contrast the maximum entropy model, which has its own set of rate parameters, to a population of standard mass action models in which the rate constants are randomly chosen. We show that a maximum entropy model is characterized by a high probability of free energy dissipation rate and likewise entropy production rate, relative to other models. We then characterize the variability of the maximum entropy model predictions with respect to uncertainties in parameters (standard free energies of formation) and with respect to ionic strengths typically found in a cell.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

REV-INR: Regularized Evidential Implicit Neural Representation for Uncertainty-Aware Volume Visualization

Applications of Implicit Neural Representations (INRs) have emerged as a promising deep learning approach for compactly representing large volumetric datasets. These models can act as surrogates for volume data, enabling efficient storage and on-demand reconstruction via model predictions. However, conventional deterministic INRs only provide value predictions without insights into the model’s prediction uncertainty or the impact of inherent noisiness in the data. This limitation can lead to unreliable data interpretation and visualization due to prediction inaccuracies in the reconstructed volume. Identifying erroneous results extracted from model-predicted data may be infeasible, as raw data may be unavailable due to its large size. To address this challenge, we introduce REV-INR, Regularized Evidential Implicit Neural Representation, which learns to predict data values accurately along with the associated coordinate-level data uncertainty and model uncertainty using only a single forward pass of the trained REV-INR during inference. By comprehensively comparing and contrasting REV-INR with existing well-established deep uncertainty estimation methods, we show that REV-INR achieves the best volume reconstruction quality with robust data (aleatoric) and model (epistemic) uncertainty estimates using the fastest inference time. Consequently, we demonstrate that REV-INR facilitates assessment of the reliability and trustworthiness of the extracted isosurfaces and volume visualization results, enabling analyses to be solely driven by model-predicted data.

Saklani, Shanu [Indian Institute of Technology, Ka↗
DOE OSTI2021

Defining Computational Emissivity Uncertainty Over Large Temperature Scales Due to Surface Evolution

There is a dearth in the literature on how to capture the uncertainty generated by material surface evolution in thermal modeling. This leads to inadequate or highly variable uncertainty representations for material properties, specifically emissivity when minimal information is available. Inaccurate understandings of prediction uncertainties may lead decision makers to incorrect conclusions, so best engineering practices should be developed for this domain. In order to mitigate the aforementioned issues, this study explores different strategies to better capture the thermal uncertainty response of engineered systems exposed to fire environments via defensible emissivity uncertainty characterizations that can be easily adapted to a variety of use cases. Here, two unique formulations (one physics-informed and one mathematically based) are presented. The formulations and methodologies presented herein are not exhaustive but more so are a starting point and give the reader a basis for how to customize their uncertainty definitions for differing fire scenarios and materials. Lastly, the impact of using this approach versus other commonly used strategies and the usefulness of adding rigor to material surface evolution uncertainty is demonstrated.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

High-resolution modeling of indoor radon exposure with uncertainty quantification in Utah

Indoor radon accounts for 37% of population-level exposure to ionizing radiation in the United States. However, radon metrics are typically reported at coarse spatial scales, potentially obscuring meaningful local variation. We developed a high-resolution modeling framework to estimate indoor radon concentrations across Utah while explicitly quantifying predictive uncertainty. A total of 19,497 residential radon measurements collected between 2006 and 2017 were combined with environmental and housing characteristics and analyzed using a geospatial neural network that accommodates spatial dependence and nonlinear associations. Predictions were generated on a uniform hexagonal grid at 0.73 km2 resolution (H3 level 8). Out-of-sample predictions aggregated to the H3 level 8 grid showed good agreement with observed concentrations (Pearson r=0.64), while household-level predictions exhibited more moderate agreement (r=0.45). The model produced well-calibrated uncertainty estimates, with 24.1% of held-out observations exceeding the predicted 75th-percentile threshold. Maps of predicted radon concentrations and the probability of exceeding the U.S. EPA action level of 148 Bq/m3 (4 pCi/L) revealed substantial fine-scale spatial heterogeneity that was not apparent in conventional coarse-resolution summaries, with greater local variability observed in densely monitored urban counties than in sparsely sampled regions. High-resolution radon models that explicitly quantify uncertainty provide a useful framework for characterizing the spatial distribution of indoor radon and identifying areas of elevated exceedance risk. These findings highlight the value of fine-scale monitoring data and uncertainty-aware modeling approaches for radon exposure assessment, environmental risk characterization, and radon-related health research.

Wu, Yunhan [ORNL] (ORCID:0000000178842994)↗
DOE OSTI2023

Comparing emulation methods for a high‐resolution storm surge model

Abstract Realistic simulations of complex systems are fundamental for climate and environmental studies. Large computer systems are often not sufficient to run sophisticated computational models for large numbers of different input settings. Statistical surrogate models, or emulators, are key tools enabling fast exploration of the simulator input space. Gaussian processes have become standard for computer simulator emulation. However, they require careful implementation to scale appropriately, motivating alternative methods more recently introduced. We present a comparison study of surrogates of the Sea, Lake, and Overland Surges from Hurricanes (SLOSH) simulator—the simulator of choice for government agencies—using four emulation approaches: BASS; BART; SEPIA; and RobustGaSP. SEPIA and RobustGaSP use Gaussian processes, BASS implements adaptive splines, and BART is based on ensembles of regression trees. We describe the four models and compare them in terms of computation time and predictive metrics. These surrogates use proven and distinct methodologies, are available through accessible software, and quantify prediction uncertainty. Our data cover millions of response values. We find that SEPIA and RobustGaSP provide exceptional predictive power, but cannot scale to emulate experiments as large as the one considered in this paper as effectively as BASS and BART.

Hutchings, Grant↗
NASA NTRS2015

Evaluating Coastal Landscape Response to Sea-Level Rise in the Northeastern United States - Approach and Methods

The U.S. Geological Survey is examining effects of future sea-level rise on the coastal landscape from Maine to Virginia by producing spatially explicit, probabilistic predictions using sea-level projections, vertical land movement rates (due to isostacy), elevation data, and land-cover data. Sea-level-rise scenarios used as model inputs are generated by using multiple sources of information, including Coupled Model Intercomparison Project Phase 5 models following representative concentration pathways 4.5 and 8.5 in the Intergovernmental Panel on Climate Change Fifth Assessment Report. A Bayesian network is used to develop a predictive coastal response model that integrates the sea-level, elevation, and land-cover data with assigned probabilities that account for interactions with coastal geomorphology as well as the corresponding ecological and societal systems it supports. The effects of sea-level rise are presented as (1) level of landscape submergence and (2) coastal response type characterized as either static (that is, inundation) or dynamic (that is, landform or landscape change). Results are produced at a spatial scale of 30 meters for four decades (the 2020s, 2030s, 2050s, and 2080s). The probabilistic predictions can be applied to landscape management decisions based on sea-level-rise effects as well as on assessments of the prediction uncertainty and need for improved data or fundamental understanding. This report describes the methods used to produce predictions, including information on input datasets; the modeling approach; model outputs; data-quality-control procedures; and information on how to access the data and metadata online.

terrain↗
DOE OSTI2019

Spatial Predictions and Associated Uncertainty of Annual Soil Respiration at the Global Scale

Abstract Soil respiration (Rs), the soil‐to‐atmosphere CO 2 flux produced by microbes and plant roots, is a critical but uncertain component of the global carbon cycle. Our current understanding of the variability and dynamics is limited by the coarse spatial resolution of existing estimates. We predicted annual Rs and associated uncertainty across the world at 1‐km resolution using a quantile regression forest algorithm trained with observations from the global Soil Respiration Database spanning from 1961 to 2011. This model yielded a global annual Rs estimate of 87.9 Pg C/year with an associated global uncertainty of 18.6 (mean absolute error) and 40.4 (root mean square error) Pg C/year. The estimated annual heterotrophic respiration (Rh), derived from empirical relationships with Rs, was 49.7 Pg C/year over the same period. Predicted Rs rates and associated uncertainty varied widely across vegetation types, with the greatest predicted rates of Rs in evergreen broadleaf forests (accounting for 20.9% of global Rs). The greatest prediction uncertainties were in northern latitudes and arid to semiarid ecosystems, suggesting that these areas should be targeted in future measurement campaigns. This study provides predictions of Rs (and associated prediction uncertainty) at unprecedentedly high spatial resolution across the globe that could help constrain local‐to‐global process‐based models. Furthermore, it provides insights into the large variability of Rs and Rh across vegetation classes and identifies regions and vegetation types with poor model performance that should be prioritized for future data collection.

Warner, D. L.↗
DOE OSTI2022

Developing a Consistent Travel-Time Framework for Comparing Three-Dimensional Velocity Models for Seismic Location Accuracy

Abstract Location algorithms have historically relied on simple, one-dimensional (1D) velocity models for fast seismic event locations. 1D models are generally used as travel-time lookup tables, one for each seismic phase, with travel-times pre-calculated for event distance and depth. These travel-time lookup tables are extremely fast to use and this fast computational speed makes them the preferred type of velocity model for operational needs. Higher-dimensional (i.e., three-dimensional—3D) seismic velocity models are becoming readily available and provide more accurate event locations over 1D models. The computational requirements of these 3D models tend to make their operational use prohibitive. Additionally, comparing location accuracy for 3D seismic velocity models tends to be problematic, as each model is determined using different ray-tracing algorithms. Attempting to use a different algorithm than the one used to develop a model usually results in poor travel-time prediction. We demonstrate and test a framework to create first-P and first-S 3D travel-time correction surfaces using an open-source framework ( PCalc + GeoTess , https://www.sandia.gov/salsa3d/software/geotess ) that easily stores 3D travel-time and uncertainty data. This framework produces fast travel-time and uncertainty predictions and overcomes the ray-tracing algorithm hurdle because the lookup tables can be generated using the exact ray-tracing algorithm that is preferred for a model.

3D velocity models↗
DOE OSTI2025

Spatiotemporal Downscaling Model for Solar Irradiance Forecast Using Nearest-Neighbor Random Forest and Gaussian Process

Accurate solar photovoltaic (PV) capacity estimation requires high-resolution, site-specific solar irradiance data to account for localized variability. However, global datasets, such as the National Solar Radiation Database (NSRDB), provide regional averages that fail to capture the fine-scale fluctuations critical for large-scale grid integration. This limitation is particularly relevant in the context of increasing distributed energy resources (DERs) penetration, such as rooftop PV. Additionally, it is critical to the implementation of the U.S. Federal Energy Regulatory Commission (FERC) Order 2222, which facilitates DER participation in U.S. bulk power markets. To address this challenge, this study evaluates Nearest-Neighbor Random Forest (NNRF) and Nearest-Neighbor Gaussian Process (NNGP) models for spatiotemporal downscaling of global solar irradiance data. By leveraging historical irradiance and meteorological data, these models incorporate spatial, temporal, and feature-based correlations to enhance local irradiance predictions. The NNRF model, a machine-learning approach, prioritizes computational efficiency and predictive accuracy, while the NNGP model offers a level of interpretability and prediction uncertainty by numerically quantifying correlations and dependencies in the data. Model validation was conducted using day-ahead predictions. The results showed that the average Goodness of Fit (GoF) of the NNRF model of 90.61% across all eight sites outperformed the GoF of the NNGP of 85.88%. Additionally, the computational speed of NNRF was 2.5 times faster than the NNGP. Finally, the NNGP displayed polynomial scaling while the NNRF scaled linearly with increasing number of nearest neighbors. Additional validation of the model on five sites in Puerto Rico further confirmed the superiority of the NNRF model over the NNGP model. These findings highlight the robustness and computational efficiency of NNRF for large-scale solar irradiance downscaling, making it a strong candidate for improving PV capacity estimation and real-time electricity market integration for DERs.

Asiedu, Shadrack (ORCID:0009000646004826)↗
DOE OSTI2023

Deep neural network uncertainty quantification for LArTPC reconstruction

We evaluate uncertainty quantification (UQ) methods for deep learning applied to liquid argon time projection chamber (LArTPC) physics analysis tasks. As deep learning applications enter widespread usage among physics data analysis, neural networks with reliable estimates of prediction uncertainty and robust performance against overconfidence and out-of-distribution (OOD) samples are critical for their full deployment in analyzing experimental data. While numerous UQ methods have been tested on simple datasets, performance evaluations for more complex tasks and datasets are scarce. Here we assess the application of selected deep learning UQ methods on the task of particle classification using the PiLArNet monte carlo 3D LArTPC point cloud dataset. We observe that UQ methods not only allow for better rejection of prediction mistakes and OOD detection, but also generally achieve higher overall accuracy across different task settings. We assess the precision of uncertainty quantification using different evaluation metrics, such as distributional separation of prediction entropy across correctly and incorrectly identified samples, receiver operating characteristic curves (ROCs), and expected calibration error from observed empirical accuracy. We conclude that ensembling methods can obtain well calibrated classification probabilities and generally perform better than other existing methods in deep learning UQ literature.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Grassmannian diffusion maps based surrogate modeling via geometric harmonics

Abstract A novel surrogate model based on the Grassmannian diffusion maps (GDMaps) and utilizing geometric harmonics (GH) is developed for predicting the response of complex physical phenomena. The method utilizes GDMaps to obtain a low‐dimensional representation of the underlying behavior of physical/mathematical systems with respect to uncertain input parameters. Using this representation, GH, an out‐of‐sample extension technique, is employed to create a global map from the input parameter space to a Grassmannian diffusion manifold. GH is further employed to locally map points on the diffusion manifold onto the tangent space of a Grassmann manifold. The exponential map is then used to project the points in the tangent space onto the Grassmann manifold, where reconstruction of the full solution is performed. The performance of the proposed surrogate model is verified with three examples. The first problem is a toy example used to illustrate the technique. In the second example, errors associated with the various mappings are assessed by studying response predictions of the electric potential of a dielectric cylinder in a homogeneous electric field. The last example applies the method for uncertainty prediction in the strain field evolution in a model amorphous material using the shear transformation zone theory of plasticity.

42 ENGINEERING↗
DOE OSTI2024

Adaptive Framework for Maintenance Scheduling Based on Dynamic Preventive Intervals and Remaining Useful Life Estimation

Data-based prognostic methods exploit sensor data to forecast the remaining useful life (RUL) of industrial settings to optimize the scheduling of maintenance actions. However, implementing sensors may not be cost-effective or practical for all components. Traditional preventive approaches are not based on sensor data; however, they schedule maintenance at equally spaced intervals, which is not a cost-effective approach since the distribution of the time between failures changes with the degradation state of other parts or changes in working conditions. This study introduces a novel framework comprising two maintenance scheduling strategies. In the absence of sensor data, we propose a novel dynamic preventive policy that adjusts intervention intervals based on the most recent failure data. When sensor data are available, a method for RUL prediction, designated k-LSTM-GFT, is enhanced to dynamically account for RUL prediction uncertainty. The results demonstrate that dynamic preventive maintenance can yield cost reductions of up to 51.8% compared to conventional approaches. The predictive approach optimizes the exploitation of RUL, achieving costs that are only 3–5% higher than the minimum cost achievable while ensuring the safety of critical systems since all of the failures are avoided.

Nunes, Pedro (ORCID:0000000180012172)↗
DOE OSTI2021

Cookoff of Powdered and Pressed Explosives using a Micromechanics Pressurization Model

Cookoff experiments of powdered and pressed TATB-based plastic bonded explosives (PBXs) have been modeled using a pressure-dependent universal cookoff model (UCM) in combination with a micromechanics pressurization (MMP) model described in a companion paper. The MMP model is based on the accumulation of decomposition gases at nucleation sites that load the surrounding TATB crystals and binder. This is the first cookoff model to use an analytical mechanics solution for compressibility and thermal expansion to describe internal pressurization caused by both temperature and decomposition occurring within closed-pore explosives. This approach produces more accurate predictions of ignition time and pressurization within high-density explosives than simple equation-of-state models. The current paper gives details of the reaction chemistry, model parameters, predicted uncertainty, and validation using experiments from multiple laboratories with errors less than 6 %. The UCM/MMP model framework gives more accurate thermal ignition predictions for high density explosives that are initially impermeable to decomposition gases.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2022

An adaptive knowledge-based data-driven approach for turbulence modeling using ensemble learning technique under complex flow configuration: 3D PWR sub-channel with DNS data

This work describes a new approach to increase the accuracy of Reynolds-averaged Navier–Stokes (RANS) in modeling turbulence flow leveraging the machine learning technique. Traditionally, different turbulence models for Reynolds stress are developed for different flow patterns based on human knowledge. Each turbulence model has a certain application domain and prediction uncertainty. In recent years, with the rapid improvements of machine learning techniques, researchers start to develop an approach to compensate for the prediction discrepancy of traditional turbulence models with statistical models and data. However, the approach has deficiencies in several aspects. For example, the amount of human knowledge introduced to the statistical model couldn’t be controlled, which makes the statistical model learn from a very naïve stage and limits its application. In this work, a new approach is developed to address those deficiencies. Here, the new approach uses the “ensemble learning” technique to control the amount of human knowledge introduced into the statistical model. Therefore, the new approach could be adaptive to the multiple application domains. In conclusion, according to the results of case study, the new approach shows higher accuracy than both traditional turbulence models and the previous machine learning approach.

42 ENGINEERING↗