SEARCH · Engineering Papers

Results for “ensemble prediction”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov–Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in modeling complex functions. Building on this, we introduce Conformalized-KANs, which integrate conformal prediction, a distribution-free UQ technique, with KAN ensembles to generate calibrated prediction intervals with guaranteed coverage.} Extensive numerical experiments are conducted to evaluate the effectiveness of these methods, focusing particularly on the robustness and accuracy of the prediction intervals under various hyperparameter settings. We show that the conformal KAN predictions can be applied to recent extensions of KANs, including Finite Basis KANs (FBKANs) and multifideilty KANs (MFKANs). The results demonstrate the potential of our approaches to significantly improve the reliability and applicability of KANs in scientific machine learning.

• Artificial intelligence (AI) / machine learning ↗

DOE OSTI2024

Prediction of laser beam spatial profiles in a high-energy laser facility by use of deep learning

We adapt the significant advances achieved recently in the field of generative artificial intelligence/machine-learning to laser performance modeling in multipass, high-energy laser systems with application to high-shot-rate facilities relevant to inertial fusion energy. Advantages of neural-network architectures include rapid prediction capability, data-driven processing, and the possibility to implement such architectures within future low-latency, low-power consumption photonic networks. Four models were investigated that differed in their generator loss functions and utilized the U-Net encoder/decoder architecture with either a reconstruction loss alone or combined with an adversarial network loss. We achieved inference times of 1.3 ms for a 256 × 256 pixel near-field beam with errors in predicted energy of the order of 1% over most of the energy range. It is shown that prediction errors are significantly reduced by ensemble averaging the models with different weight initializations. These results suggest that including the temporal dimension in such models may provide accurate, real-time spatiotemporal predictions of laser performance in high-shot-rate laser systems.

47 OTHER INSTRUMENTATION↗

DOE OSTI2022

PyTREES

PyTREES (Python tool for Training/Testing Robust Explainable Ensembles on Spectra) is software that implements a data-driven approach to predicting the amount of specific oxides present in materials samples of laser-induced breakdown spectroscopy (LIBS); such as from the ChemCam instrument suite onboard the NASA Curiosity rover. PyTREES is designed to input LIBS data in the format provided by the ChemCam team [1]. PyTREES then applies appropriate pre-processing to this data [2], and implements several regression methods for predicting oxides from spectra. The regression methods include: ensemble methods (random forest, extra trees, and gradient boosting regression) and blended submodels using the “double blending” technique. PyTREES additionally implements methods for quantifying the importance of features in regression model: (1) mean decrease in impurity (MDI) and (2) permutation importance to investigate the wavelengths used by the regression methods. [1] Gasda et al. (2021). Spectrochim Acta B, 181, 106223. [2] Clegg et al. (2017). Spectrochim Acta B , 129, 64–85.

Oyen, Diane↗

DOE OSTI2025

Meeting Global Health Needs via Infectious Disease Forecasting: Development of a Reliable Data-Driven Framework

Infectious diseases (IDs) have a significant detrimental impact on global health. Timely and accurate ID forecasting can result in more informed implementation of control measures and prevention policies. To meet the operational decision-making needs of real-world circumstances, we aimed to build a standardized, reliable, and trustworthy ID forecasting pipeline and visualization dashboard that is generalizable across a wide range of modeling techniques, IDs, and global locations. We forecasted 6 diverse, zoonotic diseases (brucellosis, campylobacteriosis, Middle East respiratory syndrome, Q fever, tick-borne encephalitis, and tularemia) across 4 continents and 8 countries. We included a wide range of statistical, machine learning, and deep learning models (n=9) and trained them on a multitude of features (average n=2326) within the One Health landscape, including demography, landscape, climate, and socioeconomic factors. The pipeline and dashboard were created in consideration of crucial operational metrics—prediction accuracy, computational efficiency, spatiotemporal generalizability, uncertainty quantification, and interpretability—which are essential to strategic data-driven decisions. While no single best model was suitable for all disease, region, and country combinations, our ensemble technique selects the best-performing model for each given scenario to achieve the closest prediction. For new or emerging diseases in a region, the ensemble model can predict how the disease may behave in the new region using a pretrained model from a similar region with a history of that disease. The data visualization dashboard provides a clean interface of important analytical metrics, such as ID temporal patterns, forecasts, prediction uncertainties, and model feature importance across all geographic locations and disease combinations. As the need for real-time, operational ID forecasting capabilities increases, this standardized and automated platform for data collection, analysis, and reporting is a major step forward in enabling evidence-based public health decisions and policies for the prevention and mitigation of future ID outbreaks.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2020

Filament-Free Bulk Resistive Memory Enables Deterministic Analogue Switching

Digital computing is nearing its physical limits as computing needs and energy consumption rapidly increase. Analogue-memory-based neuromorphic computing can be orders of magnitude more energy efficient at data-intensive tasks like deep neural networks, but has been limited by the inaccurate and unpredictable switching of analogue resistive memory. Filamentary resistive random access memory (RRAM) suffers from stochastic switching due to the random kinetic motion of discrete defects in the nanometer-sized filament. Here, this stochasticity is overcome by incorporating a solid electrolyte interlayer, in this case, yttria-stabilized zirconia (YSZ), toward eliminating filaments. Filament-free, bulk-RRAM cells instead store analogue states using the bulk point defect concentration, yielding predictable switching because the statistical ensemble behavior of oxygen vacancy defects is deterministic even when individual defects are stochastic. Both experiments and modeling show bulk-RRAM devices using TiO2-X switching layers and YSZ electrolytes yield deterministic and linear analogue switching for efficient inference and training. Bulk-RRAM solves many outstanding issues with memristor unpredictability that have inhibited commercialization, and can, therefore, enable unprecedented new applications for energy-efficient neuromorphic computing. Beyond RRAM, this work shows how harnessing bulk point defects in ionic materials can be used to engineer deterministic nanoelectronic materials and devices.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Characterizing uncertainty in Community Land Model version 5 hydrological applications in the United States

Abstract Land surface models such as the Community Land Model Version 5 (CLM5) are essential tools for simulating the behavior of the terrestrial system. Despite the extensive application of CLM5, limited attention has been paid to the underlying uncertainties associated with its hydrological parameters and how these uncertainties affect water resource applications. To address this long-standing issue, we use five meteorological datasets to conduct a comprehensive hydrological parameter uncertainty characterization of CLM5 over the hydroclimatic gradients of the conterminous United States. Key datasets produced from the uncertainty characterization experiment include: a benchmark dataset of CLM5 default hydrological performance, parameter sensitivities for 28 hydrological metrics, and large-ensemble outputs for CLM5 hydrological predictions. The presented datasets will assist CLM5 calibration and support broad applications, such as evaluating drought and flood vulnerabilities. The datasets can be used to identify the hydroclimatological conditions under which parametric uncertainties demonstrate substantial effects on hydrological predictions and clarify where further investigations are needed to understand how hydrological prediction uncertainties interact with other Earth system processes.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Monte carlo simulations and experiments of all-silica zeolite LTA assembly combining structure directing agents that match cage sizes

In this work, we investigated the influence of organic structure-directing agents (OSDAs) on the formation rates of all-silica zeolite LTA using both simulations and experiments, to shed light on the crystallization process. We compared syntheses using one OSDA with a diameter close to the size of the large cavity in LTA, and two OSDAs of diameters matching the sizes of both the small and large LTA cavities. Reaction-ensemble Monte Carlo (RxMC) simulations predict a speed up of LTA formation using two OSDAs matching the LTA pore sizes; this qualitative result is confirmed by experimental studies of crystallization kinetics, which find a speedup in all-silica LTA crystallization of a factor of 3. Analyses of simulated rings and their Si–O–Si angular energies during RxMC crystallizations show that all ring sizes in the faster crystallization exhibit lower angular energies, on average, than in the slower crystallization, explaining the origin of the speedup through packing effects.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Role of morphology in defect formation and photo-induced carrier instabilities in amorphous indium oxide

Ab initio molecular dynamics liquid-quench simulations and hybrid density functional calculations are performed to model the effects of room-temperature atomic fluctuations and photo-illumination on the structural and electronic properties of amorphous sub-stoichiometric In 2 O 2.96 . A large configurational ensemble is employed to reliably predict the distribution of localized defects as well as their response to the thermal and light activation. The results reveal that the illumination effects on the carrier concentration are greater in amorphous configurations with shorter In–O bond length and reduced polyhedral sharing as compared to the structures with a more uniform morphology. Further, the obtained correlation between the photo-induced carrier density and the reduction in the number of fully coordinated In-atoms implies that metal oxides with a significant fraction of crystalline/amorphous interfaces would show a more pronounced response to illumination. Photo-excitation also produces In–O 2 –In defects that have not been previously found in sub-stoichiometric amorphous oxides; these defects are responsible for carrier instabilities due to overdoping.

74 ATOMIC AND MOLECULAR PHYSICS↗

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

Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing *

Abstract Monitoring impurity gases in spent nuclear fuel (SNF) canisters is a novel structural health monitoring approach for SNF in dry storage. The SNF canisters are sealed containers that do not facilitate visual access to the inside. Acoustic sensing can be deployed by taking advantage of the pathways unobstructed by internal hardware. Although the ultrasonic time-of-flight measurement can provide valuable information, it is limited in its ability to discern the concentration of only one impurity gas. As such, deep learning algorithms, particularly convolutional neural networks (CNNs), offer a promising solution. In this study, CNN-based probabilistic deep learning models were implemented to detect and quantify multiple impurity gases in helium. An experimental platform was established to simulate canister conditions, and ultrasonic test data were collected. The presence of argon and air in helium at concentrations ranging from 0% to 1.2% at increments of 0.05% was considered. The multi-layer perceptron, decision tree, and logistic regression classifiers achieved high accuracies when distinguishing pure helium from helium with impurities. CNN with dropout layers and CNN using maximum likelihood estimation showed a similar performance, indicating their ability to capture uncertainties. The ensemble CNN model exhibited improved predictions and the ability to balance individual gas concentration by integrating 1D- and 2D-CNN models. These findings contribute probabilistic deep learning solutions for impurity gas detection and analysis within SNF canisters, thus ensuring safe storage and management of SNFs.

47 OTHER INSTRUMENTATION↗

DOE OSTI2023

Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification

It is critical that machine learning (ML) model predictions be trustworthy for high-throughput catalyst discovery approaches. Uncertainty quantification (UQ) methods allow estimation of the trustworthiness of an ML model, but these methods have not been well explored in the field of heterogeneous catalysis. Herein, we investigate different UQ methods applied to a crystal graph convolutional neural network to predict adsorption energies of molecules on alloys from the Open Catalyst 2020 dataset, the largest existing heterogeneous catalyst dataset. We apply three UQ methods to the adsorption energy predictions, namely k-fold ensembling, Monte Carlo dropout, and evidential regression. The effectiveness of each UQ method is assessed based on accuracy, sharpness, dispersion, calibration, and tightness. Evidential regression is demonstrated to be a powerful approach for rapidly obtaining tunable, competitively trustworthy UQ estimates for heterogeneous catalysis applications when using neural networks. Recalibration of model uncertainties is shown to be essential in practical screening applications of catalysts using uncertainties.

36 MATERIALS SCIENCE↗

DOE OSTI2024

A multi-algorithm approach for modeling coastal wetland eco-geomorphology

Coastal wetlands play an important role in the global water and biogeochemical cycles. Climate change makes it more difficult for these ecosystems to adapt to the fluctuation in sea levels and other environmental changes. Given the importance of eco-geomorphological processes for coastal wetland resilience, many eco-geomorphology models differing in complexity and numerical schemes have been developed in recent decades. However, their divergent estimates of the response of coastal wetlands to climate change indicate that substantial structural uncertainties exist in these models. To investigate the structural uncertainty of coastal wetland eco-geomorphology models, we developed a multi-algorithm model framework of eco-geomorphological processes, such as mineral accretion and organic matter accretion, within a single hydrodynamics model. The framework is designed to explore possible ways to represent coastal wetland eco-geomorphology in Earth system models and reduce the related uncertainties in global applications. We tested this model framework at three representative coastal wetland sites: two saltmarsh wetlands (Venice Lagoon and Plum Island Estuary) and a mangrove wetland (Hunter Estuary). Through the model–data comparison, we showed the importance of using a multi-algorithm ensemble approach for more robust predictions of the evolution of coastal wetlands. We also found that more observations of mineral and organic matter accretion at different elevations of coastal wetlands and evaluation of the coastal wetland models at different sites in diverse environments can help reduce the model uncertainty.

58 GEOSCIENCES↗

DOE OSTI2024

An overview of the Western United States Dynamically Downscaled Dataset (WUS-D3)

Abstract. Predicting future climate change over a region of complex terrain, such as the western United States (US), remains challenging due to the low resolution of global climate models (GCMs). Yet the climate extremes of recent years in this region, such as floods, wildfires, and drought, are likely to intensify further as climate warms, underscoring the need for high-quality and high-resolution predictions. Here, we present an ensemble of dynamically downscaled simulations over the western US from 1980–2100 at 9 km grid spacing, driven by 16 latest-generation GCMs. This dataset is titled the Western US Dynamically Downscaled Dataset (WUS-D3). We describe the challenges of producing WUS-D3, including GCM selection and technical issues, and we evaluate the simulations' realism by comparing historical results to temperature and precipitation observations. The future downscaled climate change signals are shaped in physically credible ways by the regional model's more realistic coastlines and topography. (1) The mean warming signals are heavily influenced by more realistic snowpack. (2) Mean precipitation changes are often consistent with wetting on the windward side of mountain complexes, as warmer, moister air masses are uplifted orographically during precipitation events. (3) There are large fractional precipitation increases on the lee side of mountain complexes, leading to potentially significant changes in water resources and ecology in these arid landscapes. (4) Increases in precipitation extremes are generally larger than in the GCMs, driven by locally intensified atmospheric updrafts tied to sharper, more realistic gradients in topography. (5) Changes in temperature extremes are different from what is expected by a shift in mean temperature and are shaped by local atmospheric dynamics and land surface feedbacks. Because of its high resolution, comprehensiveness, and representation of relevant physical processes, this dataset presents a unique opportunity to evaluate societally relevant future changes in western US climate.

Rahimi, Stefan (ORCID:0000000331884462)↗

DOE OSTI2022

Evaluation of WRF-Solar Cloud Forecast Using the NSRDB: Preprint

Cloud forecast is a crucial component in predicting solar irradiance from numerical weather prediction (NWP) models. Assessing cloud properties from the NWP models requires significant work due to the need for high-quality data, spatial analysis covering model extent, and detailed analysis of model performance for different types of clouds. This study presents an evaluation of the WRF-Solar cloud forecast using the National Solar Radiation Database (NSRDB). We propose an evaluation framework applied to a single model prediction as well as ensemble-based forecasts. Various cloud detection metrics are calculated when comparing with the satellite-derived dataset. The mismatched clouds from the WRF-Solar model are quantified using nine cloud types classified by cloud top height and cloud optical depth. The results based on the WRF-Solar forecasts covering the entire U.S. for the full year of 2018 shows mismatched cloud frequency in the range of 8% - 46% for thick and high-level (deep convective) to thin and low-level (cumulus) clouds.

cloud mask forecast↗

DOE OSTI2024

OT Operational Anomaly Detection (OAD) T&D + DER

The growth of utility-scale renewable energy resources, distributed energy resources (DER), and transportation electrification has increased uncertainty and cybersecurity risks in power grids. The Purdue Enterprise Reference Architecture model which is widely adopted by the utility industry is now insufficient to protect the power grid against cyber-attacks. There is a need to identify what cybersecurity model is effective on Energy Management System (EMS), Advanced Distribution Management System (ADMS), and DER Management System (DERMS) to address the fundamental cybersecurity challenges in the age of increasing renewable energy and DER share as well as consumer participation in the electric energy industry. The next generation of cybersecurity model for OT network should be able to detect inside attackers, mitigate the cybersecurity risks arising from the new grid participants including DER aggregators, electric vehicle owners, and behind-the-meter consumers outside the utility company, and develop the strategy to trust consumer measurement data. This panel will discuss the challenges and pathways for the development of an ensemble cybersecurity model based on predictive state estimation to detect cybersecurity anomalies in OT network including EMS, ADMS, and DERMS.

cybersecurity↗

NASA NTRS2013

Modeling Weather Impact on Airport Arrival Miles-in-Trail Restrictions

When the demand for either a region of airspace or an airport approaches or exceeds the available capacity, miles-in-trail (MIT) restrictions are the most frequently issued traffic management initiatives (TMIs) that are used to mitigate these imbalances. Miles-intrail operations require aircraft in a traffic stream to meet a specific inter-aircraft separation in exchange for maintaining a safe and orderly flow within the stream. This stream of aircraft can be departing an airport, over a common fix, through a sector, on a specific route or arriving at an airport. This study begins by providing a high-level overview of the distribution and causes of arrival MIT restrictions for the top ten airports in the United States. This is followed by an in-depth analysis of the frequency, duration and cause of MIT restrictions impacting the Hartsfield-Jackson Atlanta International Airport (ATL) from 2009 through 2011. Then, machine-learning methods for predicting (1) situations in which MIT restrictions for ATL arrivals are implemented under low demand scenarios, and (2) days in which a large number of MIT restrictions are required to properly manage and control ATL arrivals are presented. More specifically, these predictions were accomplished by using an ensemble of decision trees with Bootstrap aggregation (BDT) and supervised machine learning was used to train the BDT binary classification models. The models were subsequently validated using data cross validation methods. When predicting the occurrence of arrival MIT restrictions under low demand situations, the model was able to achieve over all accuracy rates ranging from 84% to 90%, with false alarm ratios ranging from 10% to 15%. In the second set of studies designed to predict days on which a high number of MIT restrictions were required, overall accuracy rates of 80% were achieved with false alarm ratios of 20%. Overall, the predictions proposed by the model give better MIT usage information than what has been currently provided under current day operations. Traffic flow managers can use these predictions to identify potential MIT restrictions to eliminate (e.g., those occurring during low arrival demand periods), and to determine the days in which a significant number of restrictions may be required

Operation↗

NASA NTRS2021

A Phenomenon-Based Decomposition of Model-Based Estimates of Boreal Winter ENSO Variability

Climate models are now routinely being used to simulate and predict climate variability on time scales ranging from sub-seasonal to seasonal and longer. As such, there are now long histories of such simulations and predictions spanning multiple decades and multiple ensemble members, both of which are crucial for separating climate signal from climate noise. A key focus of such runs has been the El Niño-Southern Oscillation (ENSO), spurred by recent improvements in our ability to predict such events, though questions remain as to how well climate models do beyond simply always predicting the “canonical” atmospheric response to an ENSO event—something simple statistical models already do reasonably well. This is a critical issue that needs addressing, given the importance of event-to-event differences for predicting regional impacts of ENSO teleconnections, and the need to justify the expense of running sophisticated climate models. Unfortunately, current diagnostic tools are not well suited for quantifying the different sources of variability associated with specific phenomena such as ENSO. More generally, while much effort has focused on addressing model bias, less has been done to address errors in second moment statistics—an issue whose importance is gaining increased attention particularly as we build climate prediction systems capable of taking advantage of forecasts of opportunity—a capability that requires reliable estimates of forecast uncertainty. In this report, we outline a phenomenon-based statistical decomposition of climate variance(in essence a detailed variance budget)that is specifically tailored to address the above questions by separating the variability (both the signal and noise) into that tied to the long-term average impact of a particular phenomenon(the composite mean) and the event-to-event(E2E) variability about the composite mean. In addition, we provide related decompositions of the correlations that allow us to quantify how much of the agreement with observations (the skill) comes from the composite mean as opposed to from the E2Evariability. As an example, we present the results of such a decomposition for ENSO based on simulations with the GEOS atmospheric general circulation model (AGCM), with a focus on the monthly mean impacts over North America during boreal winter(December –March). Here we take advantage of existing GEOS AGCM simulations that were produced as companion simulations to MERRA-2for the period 1980-2016. Comparisons are made throughout with MERRA-2.

ENSO↗

DOE OSTI2025

Data-Driven Kinetic Reaction Networks for Separation Chemistry

Understanding complex, multistep chemical reactions at the molecular level is a major challenge whose solution would greatly benefit the design and optimization of numerous chemical processes. The separation of rare-earth (4f) and actinide (5f) elements is an example where improving our chemical understanding is important for designing and optimizing new chemistries, even with a limited number of observations. Here, in this work, we leverage data-driven artificial intelligence and machine-learning approaches to develop kinetic reaction networks that describe the liquid–liquid extraction mechanism of uranium using N,N-di-2-ethylhexyl-isobutyramide (DEHiBA). Specifically, we compare and contrast the properties of two classes of models: (1) purely data-driven models that are regularized using chemistry-agnostic, L1 regression and (2) chemistry-informed models that are regularized using relative reaction energies provided by quantum mechanical calculations. We observe that purely data-driven models are unbiased, simple, and accurate in their predictions of experimental measurements when provided with sufficient data but are difficult to fully constrain and interpret. In contrast, chemistry-informed models exhibit significantly improved chemical interpretability and consistency, providing a detailed description of the separation process while achieving high accuracy through ensemble averaging. Overall, the dominant species predicted to be extracted into the organic phase is UO 2 (NO 3 ) 2 (DEHiBA) 2 , agreeing with experimental slope analysis, thermodynamic modeling, EXAFS, and crystal structures. This work demonstrates that leveraging the fundamental structure of the problem can lead to efficient learning schemes that provide both accurate predictions and chemical insights at a low computational cost.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗