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.

At least 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Dimensionally Reduced Model for Rapid and Accurate Prediction of Gas Saturation, Pressure, and Brine Production in a CO 2 Storage Application: Case Study Using the SACROC Field as Part of SMART Task 5

This technical report presents work conducted by the sub surface analysis team of the Strategic Systems Analysis & Engineering group at NETL for Task 5 of SMART Phase 1. This study involved the development of deep learning models for CO 2 geologic storage that are capable of accurate prediction of spatio-temporal outputs of CO 2 saturation, pressure, and brine production in three dimensional space over a storage operation's injection and post-injection timeframes. The model framework involves ensembling multi-layer encoder networks that provide dimesionality reduction of geologic inputs with fully connected long short-term memory (LSTM) neural networks that generate time-series prediction This approach offers a means to maximize training time efficiency, reduce computational memory burden, and minimize prediction turnaround.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Disentangling Rotational Dynamics and Ordering Transitions in a System of Self-Organizing Protein Nanorods via Rotationally Invariant Latent Representations

The dynamics of complex ordering systems with active rotational degrees of freedom exemplified by protein self-assembly is explored using a machine learning workflow that combines deep learning-based semantic segmentation and rotationally invariant variational autoencoder-based analysis of orientation and shape evolution. The latter allows for disentanglement of the particle orientation from other degrees of freedom and compensates for lateral shifts. The disentangled representations in the latent space encode the rich spectrum of local transitions that can now be visualized and explored via continuous variables. The time dependence of ensemble averages allows insight into the time dynamics of the system and, in particular, illustrates the presence of the potential ordering transition. Finally, analysis of the latent variables along the single-particle trajectory allows tracing these parameters on a single-particle level. The proposed approach is expected to be universally applicable for the description of the imaging data in optical, scanning probe, and electron microscopy seeking to understand the dynamics of complex systems where rotations are a significant part of the process.

representation learning↗
DOE OSTI2021

Modeling laser-driven ion acceleration with deep learning

Developments in machine learning promise to ameliorate some of the challenges of modeling complex physical systems through neural-network-based surrogate models. High-intensity, short-pulse lasers can be used to accelerate ions to mega-electronvolt energies, but to model such interactions requires computationally expensive techniques such as particle-in-cell simulations. Multilayer neural networks allow one to take a relatively sparse ensemble of simulations and generate a surrogate model that can be used to rapidly search the parameter space of interest. In this study, we created an ensemble of over 1,000 simulations modeling laser-driven ion acceleration and developed a surrogate to study the resulting parameter space. A neural-network-based approach allows for rapid feature discovery not possible for traditional parameter scans given the computational cost. A notable observation made during this study was the dependence of ion energy on the pre-plasma gradient length scale. While this methodology harbors great promise for ion acceleration, it has ready application to all topics in which large-scale parameter scans are restricted by significant computational cost or relatively large, but sparse, domains.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Application of Dimensionality Reduction in Machine Learning Modeling of CO2 Storage

In this study, we developed deep learning models that are capable of predicting spatio-temporal outputs of CO2 saturation, pressure, and brine production in a 3D saline storage reservoir over 30 years of continuous CO2 injection and a 50-year post-injection timeframe. To improve computational efficiency and maintain performance accuracy, the model framework involves ensembling multi-layer autoencoder networks that provide dimensionality reduction of geologic inputs with fully connected long short-term memory (LSTM) neural networks that generate time-series prediction. This study was presented as poster at the 2022 Carbon Management Project Review Meeting held in Pittsburgh, PA (August 15 – 19, 2022).

Bello, Kolawole↗
DOE OSTI2023

Effect of image resolution on automated classification of chest X-rays

Deep learning (DL) models have received much attention lately for their ability to achieve expert-level performance on the accurate automated analysis of chest X-rays (CXRs). Recently available public CXR datasets include high resolution images, but state-of-the-art models are trained on reduced size images due to limitations on graphics processing unit memory and training time. As computing hardware continues to advance, it has become feasible to train deep convolutional neural networks on high-resolution images without sacrificing detail by downscaling. This study examines the effect of increased resolution on CXR classification performance. We used the publicly available MIMIC-CXR-JPG dataset, comprising 377,110 high resolution CXR images for this study. We applied image downscaling from native resolution to 2048 × 2048 pixels, 1024 × 1024 pixels, 512 × 512 pixels, and 256 × 256 pixels and then we used the DenseNet121 and EfficientNet-B4 DL models to evaluate clinical task performance using these four downscaled image resolutions. We find that while some clinical findings are more reliably labeled using high resolutions, many other findings are actually labeled better using downscaled inputs. We qualitatively verify that tasks requiring a large receptive field are better suited to downscaled low resolution input images, by inspecting effective receptive fields and class activation maps of trained models. Lastly, we show that stacking an ensemble across resolutions outperforms each individual learner at all input resolutions while providing interpretable scale weights, indicating that diverse information is extracted across resolutions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Iterative sampling of expensive simulations for faster deep surrogate training

Deep neural network (DNN) surrogates of expensive physics simulations are enabling a rapid change in the way that common experimental design and analysis tasks are approached. Surrogate models allow simulations to be performed in parallel and separately from downstream tasks, thereby enabling analyses that would be impossible with the simulation in-the-loop; surrogates based on DNNs can effectively emulate diverse non-scalar data of the types collected in fusion and laboratory-astrophysics experiments. The challenge is in training the surrogate model, for which large ensembles of physics simulations must be run, preferably without wasting computational effort on uninteresting simulations. Here, in this paper, we present an iterative sampling scheme that can preferentially propose simulations in interesting regions of parameter space without neglecting unexplored regions, allowing high-quality and wide-ranging surrogate models to be trained using 2–3 times fewer simulations compare to space-filling designs. Our approach uses an explicit importance function defined on the simulation output space, balanced against a measure of simulation density which serves as a proxy for surrogate accuracy. It is easy to implement and can be tuned to find interesting simulations early in the study, allowing surrogates to be trained quickly and refined as new simulations become available; this represents an important step towards the routine generation of deep surrogate models quickly enough to be truly relevant to experimental work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Forced Patterns of Sea Level Rise in the Community Earth System Model Large Ensemble From 1920 to 2100

To provide context for observed sea level rise, the forced response (FR) in dynamic sea level (DSL) during the 20th and 21st centuries is examined in the Community Earth System Model Large Ensemble (LE). After accounting for simulation drift, which in the LE is sizable, the DSL FR is found to be complex, both in space and time. Its evolving character is suggested to arise from both the diversity and transient evolution of climate forcing agents and the slow adjustment timescales of the intermediate and deep oceans. Nonetheless, various intervals of spatially coherent change simulated for the recent past and near future are identified, and their characteristics and associated driving mechanisms are identified and discussed. The mid- to late-20th century DSL FR is characterized by an hemispherically asymmetric pattern of change, with depressed rates of rise in the northern oceans. There is also a dipole of change in the Southern Ocean caused by changes in near-surface zonal winds. Through the late 20th and early 21st centuries, a different pattern of rise emerges with elevated rates in the tropics and depressed rates at high latitudes. Zonal and interbasin variations characterize both intervals and involve the pattern and depth of anomalous ocean heat content storage and spatial contrasts in the expansion coefficient tied mainly to base state temperature, with greater rates of rise in warm regions per unit warming. Finally, the relative roles of surface flux and ocean convergence anomalies are examined.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Tree-based algorithms for weakly supervised anomaly detection

Weakly supervised methods have emerged as a powerful tool for model-agnostic anomaly detection at the Large Hadron Collider (LHC). While these methods have shown remarkable performance on specific signatures such as dijet resonances, their application in a more model-agnostic manner requires dealing with a larger number of potentially noisy input features. In this paper, we show that using boosted decision trees as classifiers in weakly supervised anomaly detection gives superior performance compared to deep neural networks. Boosted decision trees are well known for their effectiveness in tabular data analysis. Our results show that they not only offer significantly faster training and evaluation times, but they are also robust to a large number of noisy input features. By using advanced gradient boosted decision trees in combination with ensembling techniques and an extended set of features, we significantly improve the performance of weakly supervised methods for anomaly detection at the LHC. This advance is a crucial step toward a more model-agnostic search for new physics. Published by the American Physical Society 2024

Astronomy & Astrophysics↗
DOE OSTI2021

Soil Water Potentials (1990-2018) from a calibrated ELM-FATES, and rooting depth analyses scripts, PA-BCI, Panama

This dataset has ELM-FATES simulation outputs and scripts that accompany and reproduce the manuscript, Chitra-Tarak et al. (2021) Hydraulically-vulnerable trees survive on deep-water access during droughts in a tropical forest. New Phytologist. https: //doi.org/10.1111/nph.17464”. This dataset is organized into four parts: (1) source code for the model, Energy Exascale Earth System Land Model-Functionally Assembled Advanced Terrestrial simulator (ELM-FATES) (2) R scripts associated with ELM-FATES simulations: to prepare files for parameter ensemble simulation runs, calibrate the model with observed hydrological fluxes observed at BCI, re-run the model with tuned parameters and obtain long-term soil matric potentials by depth (3) ELM-FATES hydrological simulation outputs at PA-BCI, Panama (1990-2018, daily), and (4) R scripts for inverse rooting depth modeling and post-processing: prepare datasets and inversely model tree rooting depths at BCI, test hypotheses about the relationship of rooting depths with plant hydraulic traits and drought-induced mortality, and reproduce the manuscript itself. n.b. 1. Data needed to run R scripts in (2) and (4) and thus to reproduce the manuscript are sourced from various public datasets. Refer to the data availability section of the accompanying manuscript. 2. This dataset version (prepared on May 12, 2021) matches the revised and published version of the accompanying manuscript (published May 16, 2021) replacing a previous version. In the publication, this dataset is cited as follows: Chitra-Tarak R, Xu C, Aguilar S, Anderson-Teixeira K, Chambers J, Detto M, Faybishenko B, Fisher R, Knox R, Koven C et al. 2020. Soil water potentials (1990–2018) from a calibrated ELM-FATES, and rooting depth analyses scripts, PA-BCI, Panama. 2.0. NGEE Tropics Data Collection. doi: 10.15486/ngt/1696806

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Supernova pointing capabilities of DUNE

The determination of the direction of a stellar core collapse via its neutrino emission is crucial for the identification of the progenitor for a multimessenger follow-up. A highly effective method of reconstructing supernova directions within the Deep Underground Neutrino Experiment (DUNE) is introduced. The supernova neutrino pointing resolution is studied by simulating and reconstructing electron-neutrino charged-current absorption on 40 Ar and elastic scattering of neutrinos on electrons. Procedures to reconstruct individual interactions, including a newly developed technique called “brems flipping,” as well as the burst direction from an ensemble of interactions are described. Performance of the burst direction reconstruction is evaluated for supernovae happening at a distance of 10 kpc for a specific supernova burst flux model. The pointing resolution is found to be 3.4 degrees at 68% coverage for a perfect interaction-channel classification and a fiducial mass of 40 kton, and 6.6 degrees for a 10 kton fiducial mass respectively. Assuming a 4% rate of charged-current interactions being misidentified as elastic scattering, DUNE’s burst pointing resolution is found to be 4.3 degrees (8.7 degrees) at 68% coverage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Supernova pointing capabilities of DUNE

The determination of the direction of a stellar core collapse via its neutrino emission is crucial for the identification of the progenitor for a multimessenger follow-up. A highly effective method of reconstructing supernova directions within the Deep Underground Neutrino Experiment (DUNE) is introduced. The supernova neutrino pointing resolution is studied by simulating and reconstructing electron-neutrino charged-current absorption on Ar 40 and elastic scattering of neutrinos on electrons. Procedures to reconstruct individual interactions, including a newly developed technique called “brems flipping,” as well as the burst direction from an ensemble of interactions are described. Performance of the burst direction reconstruction is evaluated for supernovae happening at a distance of 10 kpc for a specific supernova burst flux model. The pointing resolution is found to be 3.4 degrees at 68% coverage for a perfect interaction-channel classification and a fiducial mass of 40 kton, and 6.6 degrees for a 10 kton fiducial mass respectively. Assuming a 4% rate of charged-current interactions being misidentified as elastic scattering, DUNE’s burst pointing resolution is found to be 4.3 degrees (8.7 degrees) at 68% coverage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Comparing quantile regression forest and mixture density long short-term memory models for probabilistic post-processing of satellite precipitation-driven streamflow simulations

Abstract. Deep learning (DL) and machine learning (ML) are widely used in hydrological modelling, which plays a critical role in improving the accuracy of hydrological predictions. However, the trade-off between model performance and computational cost has always been a challenge for hydrologists when selecting a suitable model, particularly for probabilistic post-processing with large ensemble members. This study aims to systematically compare the quantile regression forest (QRF) model and countable mixtures of asymmetric Laplacians long short-term memory (CMAL-LSTM) model as hydrological probabilistic post-processors. Specifically, we evaluate their ability in dealing with biased streamflow simulations driven by three satellite precipitation products across 522 nested sub-basins of the Yalong River basin in China. Model performance is comprehensively assessed using a series of scoring metrics from both probabilistic and deterministic perspectives. Our results show that the QRF model and the CMAL-LSTM model are comparable in terms of probabilistic prediction, and their performances are closely related to the flow accumulation area (FAA) of the sub-basin. The QRF model outperforms the CMAL-LSTM model in most sub-basins with smaller FAA, while the CMAL-LSTM model has an undebatable advantage in sub-basins with FAA larger than 60 000 km2 in the Yalong River basin. In terms of deterministic predictions, the CMAL-LSTM model is preferred, especially when the raw streamflow is poorly simulated and used as input. However, setting aside the differences in model performance, the QRF model with 100-member quantiles demonstrates a noteworthy advantage by exhibiting a 50 % reduction in computation time compared to the CMAL-LSTM model with the same ensemble members in all experiments. As a result, this study provides insights into model selection in hydrological post-processing and the trade-offs between model performance and computational efficiency. The findings highlight the importance of considering the specific application scenario, such as the catchment size and the required accuracy level, when selecting a suitable model for hydrological post-processing.

Geology↗
DOE OSTI2024

Identifying Robust Decarbonization Pathways for the Western U.S. Electric Power System Under Deep Climate Uncertainty

Climate change threatens the resource adequacy of future power systems. Existing research and practice lack frameworks for identifying decarbonization pathways that are robust to climate-related uncertainty. We create such an analytical framework, then use it to assess the robustness of alternative pathways to achieving 60% emissions reductions from 2022 levels by 2040 for the Western U.S. power system. Our framework integrates power system planning and resource adequacy models with 100 climate realizations from a large climate ensemble. Climate realizations drive electricity demand; thermal plant availability; and wind, solar, and hydropower generation. Among five initial decarbonization pathways, all exhibit modest to significant resource adequacy failures under climate realizations in 2040, but certain pathways experience significantly less resource adequacy failures at little additional cost relative to other pathways. By identifying and planning for an extreme climate realization that drives the largest resource adequacy failures across our pathways, we produce a new decarbonization pathway that has no resource adequacy failures under any climate realizations. This new pathway is roughly 5% more expensive than other pathways due to greater capacity investment, and shifts investment from wind to solar and natural gas generators. Our analysis suggests modest increases in investment costs can add significant robustness against climate change in decarbonizing power systems. Our framework can help power system planners adapt to climate change by stress testing future plans to potential climate realizations, and offers a unique bridge between energy system and climate modeling.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

MARS: Malleable Actor-Critic Reinforcement Learning Scheduler

In this paper, we introduce MARS, a new scheduling system for HPC-cloud infrastructures based on a cost-aware, flexible reinforcement learning approach, which serves as an intermediate layer for next generation HPC-cloud resource manager. MARS ensembles the pre-trained models from heuristic workloads and decides on the most cost-effective strategy for optimization. A whole workflow application would be split into several optimizable dependent sub-tasks, then based on the pre- defined resource management plan, a reward will be generated after executing a scheduled task. Lastly, MARS updates the Deep Neural Network (DNN) model based on the reward. MARS is designed to optimize the existing models through reinforcement mechanisms. MARS adapts to the dynamics of workflow applications, selects the most cost-effective scheduling solution among pre-built scheduling strategies (backfilling, SJF, etc.) and self- learning deep neural network model at run-time. We evaluate MARS with different real-world workflow traces. MARS can achieve 5%-60% increased performance compare to state-of-the- art approaches.

Baheri, Betis↗
DOE OSTI2023

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of ‹ instrument, verb, target › combination delivers more comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. Here, the challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and the assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. Here, a total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms from the competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Inverse Mapping of the Collision Kernel and Wall Flux Scaling in a Tall Convection‐Cloud Chamber Using Local Sensors and Knowledge‐Informed Deep Learning

Droplet collision–coalescence is a crucial process in cloud physics, but accurately representing this process under different dynamical conditions remains challenging. A proposed future convective‐cloud chamber aims to investigate this key process, but the method for observing it remains unclear, even though it is theoretically established that collision‐coalescence will occur. This study serves as a proof‐of‐concept demonstration of how knowledge‐informed deep learning, combined with measurement data from local sensors in the chamber, can be used to estimate the collision kernels, which determine how the droplet size distribution evolves during collision‐coalescence. In addition to estimating the collision kernel, we also address wall fluxes, another uncertain but important process that acts as a source of heat and moisture in the chamber. Ensemble runs of large‐eddy simulations are conducted by scaling the wall fluxes and the collision kernel, while the measured flow and cloud properties are used as inputs for a neural network. Results indicate that this approach successfully maps the scaling of wall fluxes and the collision kernel with biases of approximately 1% or less relative to the range of the target data. This proof‐of‐concept lays the groundwork for future applications; when the real measurements are available, real sensor data combined with the trained model presented in this work will enable estimation of the actual wall fluxes and collision kernel.

cloud chamber↗
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 OSTI2021

Z-Sequence: photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours

ABSTRACT We introduce Z-Sequence, a novel empirical model that utilizes photometric measurements of observed galaxies within a specified search radius to estimate the photometric redshift of galaxy clusters. Z-Sequence itself is composed of a machine learning ensemble based on the k-nearest neighbours algorithm. We implement an automated feature selection strategy that iteratively determines appropriate combinations of filters and colours to minimize photometric redshift prediction error. We intend for Z-Sequence to be a standalone technique but it can be combined with cluster finders that do not intrinsically predict redshift, such as our own DEEP-CEE. In this proof-of-concept study, we train, fine-tune, and test Z-Sequence on publicly available cluster catalogues derived from the Sloan Digital Sky Survey. We determine the photometric redshift prediction error of Z-Sequence via the median value of |Δ$z$|/(1 + $z$) (across a photometric redshift range of 0.05 ≤ $z$ ≤ 0.6) to be ∼0.01 when applying a small search radius. The photometric redshift prediction error for test samples increases by 30–50 per cent when the search radius is enlarged, likely due to line-of-sight interloping galaxies. Eventually, we aim to apply Z-Sequence to upcoming imaging surveys such as the Legacy Survey of Space and Time to provide photometric redshift estimates for large samples of as yet undiscovered and distant clusters.

Chan, Matthew C.↗