Search NASA⌕ Search

SEARCH · Search NASA

Results for “predictive distribution”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Knowledge-guided graph machine learning for spatially distributed prediction of daily discharge and nitrogen export dynamics

Spatially distributed prediction of streamflow and nitrogen export dynamics is essential for precision management of agricultural watersheds. While temporal deep learning models such as Long Short-Term Memory (LSTM) have shown strong performance at basin scales, their ability to generalize spatially is limited by insufficient representation of spatial dependencies and flow paths, particularly under data-scarce conditions. To address this gap, we propose HydroGraphNet, a knowledge-guided graph machine learning framework that integrates process-based knowledge and explicit spatial learning into temporal modeling. This framework incorporates directed graph topology to encode watershed connectivity and upstream inflows, with mass balance constraints to improve physical consistency. To enhance generalization in sparsely monitored regions, HydroGraphNet is pretrained on synthetic data generated by the SWAT+ (Soil and Water Assessment Tool Plus) model. We evaluated HydroGraphNet in the Upper Sangamon River Basin (44 HUC-12 subwatersheds, 2001–2020) against two LSTM baselines: a lumped basin-level model and a distributed variant. When benchmarked on SWAT+ simulations in pretraining, HydroGraphNet improved test NSEs by 8.9% (discharge) and 13.7% (NO₃–N load) in temporal extrapolation, and by 27.1% and 34.7% in spatial extrapolation, relative to the Lumped LSTM baseline. After fine-tuning with USGS monitoring data, the model achieved mean test NSE (KGE) scores of 0.768 (0.861) for discharge and 0.626 (0.664) for NO₃–N load, substantially outperforming baselines. Attribution analysis further highlighted the importance of upstream inflow representation and graph-based spatial learning in capturing cross-subwatershed dependencies. The model also reproduced seasonal hydrological and biogeochemical patterns consistent with known processes, demonstrating its robustness and process fidelity for spatially distributed prediction. Altogether, HydroGraphNet advances the integration of physical knowledge and spatially explicit learning in hydrological modeling, offering a generalizable framework for distributed modeling to support spatially targeted water quality management in data-scarce watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

A two-step short-term probabilistic wind forecasting methodology based on predictive distribution optimization

With increasing wind penetrations into electric power systems, probabilistic wind forecasting becomes more critical to power system operations because of its capability of quantifying wind uncertainties. In this paper, a two-step probabilistic wind forecasting approach based on pinball loss optimization is developed. First, a multimodel machine learning-based ensemble deterministic forecasting framework is adopted to generate deterministic forecasts. The deterministic forecast is assumed to be the mean value of the predictive distribution at each forecasting time stamp. Then, the optimal unknown parameter (i.e., standard deviation) of the predictive distribution is estimated by a support vector regression surrogate model based on the deterministic forecasts. Lastly, probabilistic forecasts are generated from the predictive distribution. Numerical results of case studies at eight locations show that the developed two-step probabilistic forecasting methodology has improved the pinball loss metric score by up to 35% compared to a baseline quantile regression forecasting model.

17 WIND ENERGY↗
DOE OSTI2021

Dark energy survey internal consistency tests of the joint cosmological probes analysis with posterior predictive distributions

Beyond ΛCDM, physics or systematic errors may cause subsets of a cosmological data set to appear inconsistent when analysed assuming ΛCDM. Here, we present an application of internal consistency tests to measurements from the Dark Energy Survey Year 1 (DES Y1) joint probes analysis. Our analysis relies on computing the posterior predictive distribution (PPD) for these data under the assumption of ΛCDM. We find that the DES Y1 data have an acceptable goodness of fit to ΛCDM, with a probability of finding a worse fit by random chance of p = 0.046. Using numerical PPD tests, supplemented by graphical checks, we show that most of the data vector appears completely consistent with expectations, although we observe a small tension between large- and small-scale measurements. A small part (roughly 1.5 per cent) of the data vector shows an unusually large departure from expectations; excluding this part of the data has negligible impact on cosmological constraints, but does significantly improve the p-value to 0.10. The methodology developed here will be applied to test the consistency of DES Year 3 joint probes data sets.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Predicting distribution of malaria vector larval habitats in Ethiopia by integrating distributed hydrologic modeling with remotely sensed data

Abstract Larval source management has gained renewed interest as a malaria control strategy in Africa but the widespread and transient nature of larval breeding sites poses a challenge to its implementation. To address this problem, we propose combining an integrated high resolution (50 m) distributed hydrological model and remotely sensed data to simulate potential malaria vector aquatic habitats. The novelty of our approach lies in its consideration of irrigation practices and its ability to resolve complex ponding processes that contribute to potential larval habitats. The simulation was performed for the year of 2018 using ParFlow-Common Land Model (CLM) in a sugarcane plantation in the Oromia region, Ethiopia to examine the effects of rainfall and irrigation. The model was calibrated using field observations of larval habitats to successfully predict ponding at all surveyed locations from the validation dataset. Results show that without irrigation, at least half of the area inside the farms had a 40% probability of potential larval habitat occurrence. With irrigation, the probability increased to 56%. Irrigation dampened the seasonality of the potential larval habitats such that the peak larval habitat occurrence window during the rainy season was extended into the dry season. Furthermore, the stability of the habitats was prolonged, with a significant shift from semi-permanent to permanent habitats. Our study provides a hydrological perspective on the impact of environmental modification on malaria vector ecology, which can potentially inform malaria control strategies through better water management.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2015

Novel Radiobiological Gamma Index for Evaluation of 3-Dimensional Predicted Dose Distribution

Purpose: To propose a gamma index-based dose evaluation index that integrates the radiobiological parameters of tumor control (TCP) and normal tissue complication probabilities (NTCP). Methods and Materials: Fifteen prostate and head and neck (H&N) cancer patients received intensity modulated radiation therapy. Before treatment, patient-specific quality assurance was conducted via beam-by-beam analysis, and beam-specific dose error distributions were generated. The predicted 3-dimensional (3D) dose distribution was calculated by back-projection of relative dose error distribution per beam. A 3D gamma analysis of different organs (prostate: clinical [CTV] and planned target volumes [PTV], rectum, bladder, femoral heads; H&N: gross tumor volume [GTV], CTV, spinal cord, brain stem, both parotids) was performed using predicted and planned dose distributions under 2%/2 mm tolerance and physical gamma passing rate was calculated. TCP and NTCP values were calculated for voxels with physical gamma indices (PGI) >1. We propose a new radiobiological gamma index (RGI) to quantify the radiobiological effects of TCP and NTCP and calculate radiobiological gamma passing rates. Results: The mean RGI gamma passing rates for prostate cases were significantly different compared with those of PGI (P<.03–.001). The mean RGI gamma passing rates for H&N cases (except for GTV) were significantly different compared with those of PGI (P<.001). Differences in gamma passing rates between PGI and RGI were due to dose differences between the planned and predicted dose distributions. Radiobiological gamma distribution was visualized to identify areas where the dose was radiobiologically important. Conclusions: RGI was proposed to integrate radiobiological effects into PGI. This index would assist physicians and medical physicists not only in physical evaluations of treatment delivery accuracy, but also in clinical evaluations of predicted dose distribution.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2025

Uncertainty quantification for neural network potential foundation models

Abstract For neural network potentials (NNPs) to gain widespread use, researchers must be able to trust model outputs. However, the blackbox nature of neural networks and their inherent stochasticity are often deterrents, especially for foundation models trained over broad swaths of chemical space. Uncertainty information provided at the time of prediction can help reduce aversion to NNPs. In this work, we detail two uncertainty quantification (UQ) methods. Readout ensembling, by finetuning the readout layers of an ensemble of foundation models, provides information about model uncertainty, while quantile regression, by replacing point predictions with distributional predictions, provides information about uncertainty within the underlying training data. We demonstrate our approach with the MACE-MP-0 model, applying UQ to the foundation model and a series of finetuned models. The uncertainties produced by the readout ensemble and quantile methods are demonstrated to be distinct measures by which the quality of the NNP output can be judged.

36 MATERIALS SCIENCE↗
DOE OSTI2025

pnnl/SNAP

In this work, we detail two uncertainty quantification (UQ) methods that provide complementary information. Readout ensembling, by finetuning only the readout layers of an ensemble of foundation models, provides information about model uncertainty. Amending the final readout layer to predict upper and lower quantiles replaces point predictions with distributional predictions, which provide information about uncertainty within the underlying training data. We demonstrate our approach with the MACE-MP-0 model, applying UQ to both the foundation model and a series of finetuned models. The uncertainties produced by the ensemble and quantile methods are demonstrated to be distinct measures by which the quality of the NNP output can be judged.

Pope, Jenna (Bilbrey) [Pacific Northwest National ↗
DOE OSTI2022

Challenges in Markov Chain Monte Carlo for Bayesian Neural Networks

Markov chain Monte Carlo (MCMC) methods have not been broadly adopted in Bayesian neural networks (BNNs). This paper initially reviews the main challenges in sampling from the parameter posterior of a neural network via MCMC. Such challenges culminate to lack of convergence to the parameter posterior. Nevertheless, this paper shows that a nonconverged Markov chain, generated via MCMC sampling from the parameter space of a neural network, can yield via Bayesian marginalization a valuable posterior predictive distribution of the output of the neural network. Further, classification examples based on multilayer perceptrons showcase highly accurate posterior predictive distributions. The postulate of limited scope for MCMC developments in BNNs is partially valid; an asymptotically exact parameter posterior seems less plausible, yet an accurate posterior predictive distribution is a tenable research avenue.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Models, data, and scripts associated with “Prediction of Distributed River Sediment Respiration Rates using Community-Generated Data and Machine Learning”

This data package is associated with the publication “Prediction of Distributed River Sediment Respiration Rates using Community-Generated Data and Machine Learning’’ submitted to the Journal of Geophysical Research: Machine Learning and Computation (Scheibe et al. 2024). River sediment respiration observations are expensive and labor intensive to obtain and there is no physical model for predicting this quantity. The Worldwide Hydrobiogeochemisty Observation Network for Dynamic River Systems (WHONDRS) observational data set (Goldman et al.; 2020) is used to train machine learning (ML) models to predict respiration rates at unsampled sites. This repository archives training data, ML models, predictions, and model evaluation results for the purposes of reproducibility of the results in the associated manuscript and community reuse of the ML models trained in this project. One of the key challenges in this work was to find an optimum configuration for machine learning models to work with this feature-rich (i.e. 100+ possible input variables) data set. Here, we used a two-tiered approach to managing the analysis of this complex data set: 1) a stacked ensemble of ML models that can automatically optimize hyperparameters to accelerate the process of model selection and tuning and 2) feature permutation importance to iteratively select the most important features (i.e. inputs) to the ML models. The major elements of this ML workflow are modular, portable, open, and cloud-based, thus making this implementation a potential template for other applications. This data package is associated with the GitHub repository found at Please see the file level metadata (flmd; “sl-archive-whondrs_flmd.csv”) for a list of all files contained in this data package and descriptions for each. Please see the data dictionary (dd; “sl-archive-whondrs_dd.csv”) for a list of all column headers contained within comma separated value (csv) files in this data package and descriptions for each. The GitHub repository is organized into five top-level directories: (1) “input_data” holds the training data for the ML models; (2) “ml_models” holds machine learning models trained on the data in “input_data”; (3) “scripts” contains data preprocessing and postprocessing scripts and intermediate results specific to this data set that bookend the ML workflow; (4) “examples” contains the visualization of the results in this repository including plotting scripts for the manuscript (e.g., model evaluation, FPI results) and scripts for running predictions with the ML models (i.e., reusing the trained ML models); (5) “output_data” holds the overall results of the ML model on that branch. Each trained ML model resides on its own branch in the repository; this means that inputs and outputs can be different branch-to-branch. Furthermore, depending on the number of features used to train the ML models, the preprocessing and postprocessing scripts, and their intermediate results, can also be different branch-to-branch. The “main-*” branches are meant to be starting points (i.e. trunks) for each model branch (i.e. sprouts). Please see the Branch Navigation section in the top-level README.md in the GitHub repository for more details. There is also one hidden directory “.github/workflows”. This hidden directory contains information for how to run the ML workflow as an end-to-end automated GitHub Action but it is not needed for reusing the ML models archived here. Please the top-level README.md in the GitHub repository for more details on the automation.

13C↗
DOE OSTI2022

Distributed model predictive control for coordinated, grid-interactive buildings

Continued focus on reducing carbon emissions and improving energy efficiency requires buildings to become grid-interactive and not just behave as static consumers. A distributed model predictive control (DMPC) algorithm known as Limited-Communication (LC) DMPC is modified to enable grid-interactive buildings. A grid-aggregator subsystem is added that allows for a bulk grid power reference signal to be followed while the individual building subsystems also achieve their local comfort objectives. The LC-DMPC algorithm is applied for the first time to systems with multiple buildings. Adequate power tracking is shown for different simulation scenarios involving heterogeneous buildings, and next steps are discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2018

Active Power Control for Wind Farms Using Distributed Model Predictive Control and Nearest Neighbor Communication: Preprint

Wind plant control strategies, including axial induction and wake steering control, aim to improve the performance of wind farms, including increasing energy production and decreasing turbine loads. This paper presents a linear model of wake characteristics for use with a distributed model predictive control method for the purpose of optimizing axial induction and yaw misalignment setpoints. In particular, we use an iterative, distributed control method with nearest neighbor communication to coordinate turbine control actions that account for wake interactions between turbines. Simulations of the model and controller are performed on a 2x3 array of turbines using a modified version of the FLOw Redirection and Induction in Steady-state (FLORIS) model to dynamically track the relevant wake parameters. Preliminary results show the controller's ability to follow an arbitrary wind farm power reference signal for the purpose of providing active power control (APC) ancillary services for power grid stability. This efficient distributed control strategy can enable real-time wind farm optimization and control, even for very large scale farms.

17 WIND ENERGY↗
DOE OSTI2021

Streamflow simulation in data-scarce basins using Bayesian and physics-informed machine learning models

Hydrologic predictions at rural watersheds are important but also challenging due to data shortage. Long short-term memory (LSTM) networks are a promising machine learning approach and have demonstrated good performance in streamflow predictions. However, due to its data-hungry nature, most LSTM applications focus on well-monitored catchments with abundant and high-quality observations. In this work, we investigate predictive capabilities of LSTM in poorly monitored watersheds with short observation records. To address three main challenges of LSTM applications in data-scarce locations, i.e., overfitting, uncertainty quantification (UQ), and out-of-distribution prediction, we evaluate different regularization techniques to prevent overfitting, apply a Bayesian LSTM for UQ, and introduce a physics-informed hybrid LSTM to enhance out-of-distribution prediction. Through case studies in two diverse sets of catchments with and without snow influence, we demonstrate that 1) when hydrologic variability in the prediction period is similar to the calibration period, LSTM models can reasonably predict daily streamflow with Nash–Sutcliffe efficiency above 0.8, even with only 2 years of calibration data; 2) when the hydrologic variability in the prediction and calibration periods is dramatically different, LSTM alone does not predict well, but the hybrid model can improve the out-of-distribution prediction with acceptable generalization accuracy; 3) L2 norm penalty and dropout can mitigate overfitting, and Bayesian and hybrid LSTM have no overfitting; and 4) Bayesian LSTM provides useful uncertainty information to improve prediction understanding and credibility. In conclusion, these insights have vital implications for streamflow simulation in watersheds where data quality and availability are a critical issue.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Machine Learning-Based Prediction of Distribution Network Voltage and Sensors Allocation: Preprint

Increasing penetration of fast-varying energy resources may negatively affect power systems' operation. At the same time, sensor deployment throughout distribution networks improves system awareness and enables the development of new and advanced voltage control solutions. Such control techniques rely on accurate prediction in anticipation to voltage violation scenarios. This paper analyzes various approaches for voltage prediction in a distribution system; it is shown that combining multiple techniques into a single regressor improves its predictive power. Moreover, a two-step regressor is proposed, where initial predictions based on a global regressor are refined by local regressors; in this case, prediction errors decrease significantly. Additionally, a clustering approach is employed for performing sensor allocation, so that only the most influential buses are selected for monitoring without diminishing prediction accuracy.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Machine Learning-Based Prediction of Distribution Network Voltage and Sensor Allocation

Increasing penetration of fast-varying energy resources may negatively affect power systems' operation. At the same time, sensor deployment throughout distribution networks improves system awareness and enables the development of new and advanced voltage control solutions. Such control techniques rely on accurate prediction in anticipation to voltage violation scenarios. This paper analyzes various approaches for voltage prediction in a distribution system; it is shown that combining multiple techniques into a single regressor improves its predictive power. Moreover, a two-step regressor is proposed, where initial predictions based on a global regressor are refined by local regressors; in this case, prediction errors decrease significantly. Additionally, a clustering approach is employed for performing sensor allocation, so that only the most influential buses are selected for monitoring without diminishing prediction accuracy.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2020

Machine Learning-Based Prediction of Distribution Network Voltage and Sensor Allocation

Increasing penetration levels of fast-varying energy resources might negatively affect power system operation. At the same time, sensor deployment throughout distribution networks improves system awareness and enables the development of new and advanced voltage control solutions. Such control techniques rely on accurate prediction in anticipation of voltage violation scenarios. This paper analyzes various approaches to voltage prediction in a distribution system, and it is shown that combining multiple techniques into a single regressor improves its predictive power. Moreover, a two-step regressor is proposed in which initial predictions based on a global regressor are refined by local regressors; in this case, prediction errors decrease significantly. Additionally, a clustering approach is employed to perform sensor allocation so that only the most influential buses are selected for monitoring without diminishing prediction accuracy.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2015

SU-E-T-798: Verification of 3DVH Dose Distribution Before Clinical Implementation for Patient-Specific IMRT QA

Purpose: In recent years patient-specific IMRT QA has transitioned from film and chamber measurements to beam-by-beam 2D array measurements. 3DVH takes this transition a step further by estimating the 3D dose distribution delivered using 2D per beam diode array measurements. In this study, the 3D dose distribution generated by 3DVH is compared to film and chamber measurements. In addition, the accuracy ROI volume and error detection is investigated. Methods: Composite film and ion chamber measurements in a solid water phantom were performed for 9 IMRT PINNACLE patient plans for 4 treatment sites. The film and chamber measurements were compared to the dose distribution predicted by 3DVH using MAPCHECK2 per beam measurements. The absolute point dose measurement (CAX) was extracted from the predicted 3DVH and PINNACLE dose distribution and was compared by taking the ratio of measured to predicted doses. The dose distribution measured with film was compared to the distribution in the corresponding plane (AX, SAG, COR) extracted from predicted dose distribution by 3DVH and PINNACLE using a 2D gamma analysis. Gamma analysis was performed with 2% dose, 2 mm DTA, 20% threshold, and global normalization. In addition, the percent difference between 3DVH and PINNACLE ROI volumes was calculated. Results: The average ratio of the measured point dose vs the 3DVH predicted dose was 1.017 (σ=0.011). The average gamma passing rate for measured vs 3DVH dose distributions was 95.1% (σ=2.53%). The average percent difference of 3DVH vs PINNACLE ROI volume was 2.29% (σ=2.5%). Conclusion: The dose distributions predicted by 3DVH using MAPCHECK2 measurements are the same as the distributions that would have been obtained using film and chamber. The ROI volumes used in 3DVH are not an exact match to those in PINNACLE; the effect requires more investigation. The accuracy of error detection by 3DVH is currently being investigated.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

MO-G-201-04: Knowledge-Based Planning for Single-Isocenter Stereotactic Radiosurgery to Multiple Brain Metastases

Purpose: Single-isocenter, linac-based SRS for multiple brain metastases (multi-mets) can deliver highly conformal radiation doses and reduce overall patient treatment time compared to other therapy techniques. This study aims to quantify the dosimetric benefits of knowledge-based planning (KBP) for multi-met treatments. Methods: Using a previously-published KBP methodology (an artificial neural network (ANN) trained on single-target linac-based SRS plans), 3D dose distribution predictions for multi-met patients were obtained by treating each brain lesion as a solitary target and subsequently combining individual predictions into a single distribution using a dose-weighted geometric averaging to obtain the best results in the inter-target space. 17 previously-treated multi-met plans, with target numbers ranging from N=2–5, were used to validate the ANN predictions and subsequent KBP auto-planning routine. The fully-deliverable KBP plans were developed by converting dose distribution predictions into patient-specific optimization objectives while maintaining identical target normalizations (typically PTV V100%=D98%). Plan quality improvements were quantified by the difference between SRS quality metrics (QMs): δdQM=QM(clinical)-QM(KBP). QMs of interest were: gradient measure (GM), conformity index (CI), brain V10 and V5, brainstem D0.1cc and heterogeneity index (HI). Finally, overall plan quality was judged via blinded plan comparison by SRS-specializing physicians. Results: Two clinical plans were found to be significant outliers wherein plan quality was dramatically worse than KBP. Despite indicating KBP superiority, these were removed from the QM analysis to prevent skewing the results. In the remaining cases, clinical and KBP QMs were nearly identical with modest improvements in the KBP sample: δGM=0.12±0.56mm, δCI=−0.01±0.04, Brain δV10=0.8±2.6cc, brain δV5=6.3 ±10.7cc, brainstem δD0.1cc=0.06±1.19Gy and δHI= −0.04±0.05. Ultimately, 13/17 KBP plans were deemed superior to the manual plans in blinded physician review. Conclusion: The results demonstrate that KBP-driven automated planning in linac-based single-isocenter treatments for multiple brain metastases is indistinguishable from, or even better than, traditional manual planning. J. Hattangadi: Research Grant; Varian Medical Systems; K.L. Moore: Research Grant: Varian Medical Systems.

60 APPLIED LIFE SCIENCES↗