Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep ensemble”

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.

100 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Model Scripts for "Old-Aged Groundwater Contributes to Mountain Hillslope Hydrologic Dynamics"

The partitioning of water inputs between deep and shallow groundwater flow paths is a fundamental processes, yet is challenging to observe. Numerical models provide a valuable tool to further develop insights on these groundwater mixing processes. This repository contains scripts to run the ParFlow-CLM and EcoSLIM integrated hydrologic models along the Pumphouse Hillslope in the East River Watershed and associated python scripts to process model outputs. Files includes input decks for the associated models, python scripts, and text and css files to support the model runs and processing. The 2-D hillslope model simulates from 2000 to 2021 using transient forcing conditions from the publicly available NLDAS-2 dataset. We develop an ensemble of models with variable hydrogeologic and soil parameters. Model outputs from the ensemble of runs are compared to to water level observations at the PLM1 and PLM6 wells published at (https://data.ess-dive.lbl.gov/view/doi:10.15485/1866836) and groundwater mean ages published at (https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1960042. The model results are used to evaluate hillslope water mass-balance transience and mixing dynamics between groundwater flow paths with young (<10 year) and old (>10 year) ages.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Discriminative versus generative approaches to simulation-based inference

Most of the fundamental, emergent, and phenomenological parameters of particle and nuclear physics are determined through parametric template fits. Simulations are used to populate histograms which are then matched to data. This approach is inherently lossy, since histograms are binned and low-dimensional. Deep learning has enabled unbinned and high-dimensional parameter estimation through neural likelihood(-ratio) estimation. We compare two approaches for neural simulation-based inference (NSBI): one based on discriminative learning (classification) and one based on generative modeling. These two approaches are directly evaluated on the same datasets, with a similar level of hyperparameter optimization in both cases. In addition to a Gaussian dataset, we study NSBI using a Higgs boson dataset from the FAIR Universe Challenge. We find that both the direct likelihood and likelihood ratio estimation are able to effectively extract parameters with reasonable uncertainties. For the numerical examples and within the set of hyperparameters studied, we found that the likelihood ratio method is more accurate and/or precise. Both methods have a significant spread from the network training and would require ensembling or other mitigation strategies in practice.

high energy physics↗
DOE OSTI2024

Estimating irrigation water use from remotely sensed evapotranspiration data: Accuracy and uncertainties at field, water right, and regional scales

Irrigated agriculture is the dominant user of water globally, but most water withdrawals are not monitored or reported. As a result, it is largely unknown when, where, and how much water is used for irrigation. Here, we evaluated the ability of remotely sensed evapotranspiration (ET) data, integrated with other datasets, to calculate irrigation water withdrawals and applications in an intensively irrigated portion of the United States. We compared irrigation calculations based on an ensemble of satellite-driven ET models from OpenET with reported groundwater withdrawals from hundreds of farmer irrigation application records and a statewide flowmeter database at three spatial scales (field, water right group, and management area). At the field scale, we found that ET-based calculations of irrigation agreed best with reported irrigation when the OpenET ensemble mean was aggregated to the growing season timescale (bias = 1.6–4.9%, R 2 = 0.53–0.74), and agreement between calculated and reported irrigation was better for multi-year averages than for individual years. At the water right group scale, linking pumping wells to specific irrigated fields was the primary source of uncertainty. At the management area scale, calculated irrigation exhibited similar temporal patterns as flowmeter data but tended to be positively biased with more interannual variability. Disagreement between calculated and reported irrigation was strongly correlated with annual precipitation, and calculated and reported irrigation agreed more closely after statistically adjusting for annual precipitation. The selection of an ET model was also an important consideration, as variability across ET models was larger than the potential impacts of conservation measures employed in the region. From these results, we suggest key practices for working with ET-based irrigation data that include accurately accounting for changes in soil moisture, deep percolation, and runoff; careful verification of irrigated area and well-field linkages; and conducting application-specific evaluations of uncertainty.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Improving Trustworthiness of Data-Driven Power Grid Contingency Analysis With Bayesian Residual Graph Neural Networks

The evolving energy landscape requires novel tools to efficiently perform contingency analysis and reliability assessment of power grids, potentially in real-time. The high computational cost of traditional power flow solvers limits their applicability in practice. Machine learning (ML) surrogates such as deep neural networks (NNs) accelerate power flow solvers computations, enabling high-order contingency analysis and real-time decision-making by learning highly nonlinear functions and integrating grid topology via graph architectures. However, (graph) NNs lack predictive power away from training data and do not provide predictive confidence estimates. Here, we present a Bayesian residual graph NN that integrates knowledge from low-fidelity data via residual training and embeds granular quantification of uncertainties, improving trustworthiness critical for high-consequence decision-making. Applying Bayesian concepts to NNs is challenging due to the high-dimensionality of both the parameter space, complicating derivation of a meaningful prior, and the output space in large grid systems, requiring enhanced techniques to assess the predicted high-dimensional uncertainties. Our contributions include: (1) Deriving a prior for fully connected and graph NNs that leverages low-fidelity data to guide mean predictions and appropriately control prior predictive uncertainty. (2) Integrating this prior within an ensembling with anchoring scheme for efficient approximate posterior inference. (3) Deriving enhanced metrics to assess accuracy of both the mean and uncertainty predictions in high dimensions, appropriately accounting for correlations propagated through graph layers. The resulting Bayesian residual graph NN is tested on a contingency analysis task for 14-bus and 118-bus grids.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

The Interaction Between Climate Forcing and Feedbacks

A Perturbed Parameter Ensemble (PPE) with the Community Atmosphere Model version 6 (CAM6) is used to better understand the sensitivity of aerosol forcing and cloud feedbacks to changes in model processes. Aerosol forcing through aerosol-cloud interactions is mostly negative (a cooling) due to shortwave radiation, while feedbacks are positive or negative in different regions due to contrasting longwave and shortwave effects. Both forcing and feedbacks are related to the mean climate state. Higher magnitude cloud radiative effects generally mean larger magnitude net negative forcing and larger magnitude net positive feedback. Aerosol forcing is broadly related to the susceptibility of clouds to drop number. Feedbacks also related to susceptibility, but to a lesser extent and in different regions to aerosol forcing. Aerosol forcing and cloud feedbacks are anti-correlated in the CAM6 PPE such that stronger negative forcing is associated with stronger positive feedbacks. Even the processes governing forcing and feedback sensitivity in the PPE are similar. These include the warm rain formation process, ice loss processes and deep convective intensity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration, and Development of Hidden Geothermal Resources

The primary goals of this project are identifying hidden geothermal resources in the USA and designing profitable enhanced geothermal systems (EGS). Many non-obvious processes and parameters could characterize geothermal resources and could control the ultimate energy potential of geothermal fields. Diverse datasets (e.g., geology, geochemistry, geophysics, satellite, airborne geophysics) are available to help characterize geothermal resources, but this data is sparse and multi-scale. This has hindered attempts to leverage the datasets for geothermal exploration and profitable EGS design. Recent advancements in machine learning (ML) give promise to overcome these issues. Modern ML methods and tools can (1) analyze large datasets, (2) assimilate model ensembles that include a multitude of inputs and outputs, (3) process sparse datasets, (4) perform transfer learning between sites with different data quality, (5) extract hidden geothermal signatures from field and simulation data, (6) label geothermal resources and processes, (7) identify high-value data acquisition targets, and (8) guide geothermal exploration and production by selecting optimal exploration, production, and drilling strategies. In this work, we implement ML-based geothermal exploration and an enhanced geothermal systems (EGS) design tool to achieve the above goals. Our exploration tool is GeoThermalCloud (GTC) EGS design tool is GeoDT-ML. GTC (github.com/SmartTensors/GeoThermalCloud.jl) utilizes a LANL unsupervised ML platform called SmartTensors (https://tensors.lanl.gov/) to automate data analyses and interpretations by extracting hidden signatures to identify geothermal prospects. It enables the identification of critical measurements needed to identify geothermal resource signatures. GeoDT-ML (github.com/SmartTensors/GeoThermalCloud.jl/tree/master/) adds coupling to GeoDT (https://github.com/GeoDesignTool/GeoDT.git) for stochastic EGS design optimization and performance prediction. GeoDT-ML leverages recent advances in deep learning and high-performance computing. Contributors to this effort include LANL, PNNL, Google, Stanford, and Julia Computing.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Evaluating Sea Breezes and Associated Convective Cloud Evolution in the Model Gray Zone

We characterize convective clouds associated with sea‐breeze circulations (SBC) using multi‐agency observations and multi‐case ensemble model simulations. The focus is on assessing convective cloud lifecycle properties and their merging behavior, as well as the environmental conditions they are embedded in, particularly SBC features. In total, 46 SBC days over the Houston‐Galveston region are selected and simulated using the Weather Research and Forecasting (WRF) model at a gray zone scale with a forecast‐like parameterization setup. Advanced techniques, including change‐point detection, a Lagrangian cloud tracking method, and a newly developed cell merging and splitting detection algorithm, are applied and/or developed for this study. Our findings indicate that the WRF model at 1 km grid spacing well represents the thermodynamic conditions over the region, as well as SBC timing and intensity. However, for the associated convective cells, WRF overestimates the 30‐dBZ echo top height, cell area, and maximum radar reflectivity compared to radar observations. This overestimation is potentially due to under‐resolved entrainment processes, an overestimated merging frequency, and the overestimation of updraft intensity. Furthermore, the model exhibits a deficiency in simulating congestus clouds, showing a more rapid transition from shallow to deep convection compared to observed behavior. Moreover, observations indicate stronger, deeper, and wider clouds when merging happens. Conversely, in simulations, the merging process does not necessarily lead to higher or longer‐lived cells, as many cases experience rapid and frequent merging and splitting which may result in more variance in convective updraft velocity during the convection lifetime.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Daily evapotranspiration changes during heatwaves at 32 NEON sites, 2019-2021

This dataset provides partitioned evapotranspiration (ET, the combined loss of water from soil and plant surfaces) anomalies during heatwave events—soil evaporation (E) and transpiration (T)—for 268 heatwave events across 32 National Ecological Observatory Network (NEON) flux sites in the contiguous United States from 2019–2021. Using an ensemble of four high-frequency turbulence methods (Flux-variance Similarity, Conditional Eddy Covariance [CEC], CEC with Water-Use Efficiency, and Conditional Eddy Accumulation; see Zahn and Bou-Zeid 2024), half-hourly transpiration-to-evapotranspiration (T/ET) ratios were derived from 20 hertz (Hz, cycles per second) eddy covariance measurements of carbon dioxide (CO₂) and water vapor (H₂O) concentrations. The dataset spans six vegetation types including evergreen and deciduous forests, grasslands, cultivated crops, shrublands, and emergent herbaceous wetlands. Data Package Contents: The dataset includes a single CSV (comma-separated values) file containing daily anomalies (deviations from baseline conditions) for transpiration (Delta_T), evaporation (Delta_E), total evapotranspiration (Delta_ET), and T/ET ratio (Delta_T_ET) during each day of identified heatwave events. The file also includes site codes, dates, heatwave event identifiers, and day-of-heatwave indicators. The CSV file can be opened with spreadsheet software (Microsoft Excel, Google Sheets) or programming environments (Python, R, MATLAB). This resource enables researchers to investigate ecosystem-specific responses to thermal extremes, validate land surface model partitioning of ET fluxes, and examine feedbacks between water cycling and surface energy balance during heatwaves. The dataset is particularly valuable for studies linking vegetation hydraulic strategies to climate resilience, as it captures the divergent responses of shallow-rooted versus deep-rooted ecosystems. Potential applications include improving drought early warning systems, informing irrigation management strategies, and advancing our mechanistic understanding of land-atmosphere interactions under extreme heat conditions.

Day of Heatwave↗
DOE OSTI2025

GenAI4UQ: A software for forward and inverse uncertainty quantification using conditional generative AI

We introduce GenAI4UQ, a software package for forward and inverse uncertainty quantification in model calibration, parameter estimation, and ensemble forecasting. GenAI4UQ leverages a generative AI-based conditional modeling framework to address limitations of traditional inverse modeling techniques, such as Markov Chain Monte Carlo (MCMC) methods. By replacing computationally intensive iterative processes with a direct, learned mapping, GenAI4UQ enables efficient calibration of input parameters and generation of predictions directly from observations. The software supports rapid ensemble forecasting with robust uncertainty quantification while maintaining computational and storage efficiency. Built-in auto-tuning of hyperparameters simplifies model training, ensuring accessibility for users with varying expertise. Its versatile conditional generative framework is applicable across diverse scientific domains. While GenAI4UQ offers significant advantages in flexibility and efficiency, users should interpret its uncertainty estimates with caution in data-sparse scenarios, as the model may overestimate uncertainty—an effect common to all surrogate-based approaches including MCMC with surrogate models. Despite this, GenAI4UQ transforms inverse modeling by providing a fast, reliable, and user-friendly solution. It empowers researchers and practitioners to quickly estimate parameter distributions and generate model predictions for new observations, facilitating efficient decision-making and advancing the state of uncertainty quantification in computational modeling.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

GrainGNN: A dynamic graph neural network for predicting 3D grain microstructure

We propose GrainGNN, a surrogate model for the evolution of polycrystalline grain structure under rapid solidification conditions in metal additive manufacturing. High fidelity simulations of solidification microstructures are typically performed using multicomponent partial differential equations (PDEs) with moving interfaces. The inherent randomness of the PDE initial conditions (grain seeds) necessitates ensemble simulations to predict microstructure statistics, e.g., grain size, aspect ratio, and crystallographic orientation. Here, currently such ensemble simulations are prohibitively expensive and surrogates are necessary.In GrainGNN, we use a dynamic graph to represent interface motion and topological changes due to grain coarsening. We use a reduced representation of the microstructure using hand-crafted features; we combine pattern finding and altering graph algorithms with two neural networks, a classifier (for topological changes) and a regressor (for interface motion). Both networks have an encoder-decoder architecture; the encoder has a multi-layer transformer long-short-term-memory architecture; the decoder is a single layer perceptron.We evaluate GrainGNN by comparing it to high-fidelity phase field simulations for in-distribution and out-of-distribution grain configurations for solidification under laser power bed fusion conditions. GrainGNN results in 80%–90% pointwise accuracy; and nearly identical distributions of scalar quantities of interest (QoI) between phase field and GrainGNN simulations compared using Kolmogorov-Smirnov test. GrainGNN's inference speedup (PyTorch on single x86 CPU) over a high-fidelity phase field simulation (CUDA on a single NVIDIA A100 GPU) is 150×–2000× for 100-initial grain problem. Further, using GrainGNN, we model the formation of 11,600 grains in 220 seconds on a single CPU core.

36 MATERIALS SCIENCE↗