Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep data”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

OPER: Optimality-Guided Embedding Table Parallelization for Large-scale Recommendation Model

With the sharp increasing volume of user data, Deep Learning Recommendation Model (DLRM) becomes an indispensable infrastructure in large technology companies. However, large-scale DLRM on the multi-GPU platform is still inefficient due to unbalanced workload partitioning and intensive inter-GPU communication. To this end, we propose OPER, an OPtimality guided Embedding table placement for large-scale Recommendation model training and inference. OPER explores the potential of mitigating remote memory access latency in DLRM through fine-grained embedding table placement. Specifically, OPER proposes a theoretical modeling that builds up the relationship between EMT placement and the embedding communication latency in both training and inference. OPER proves the NP hardness of finding the optimal embedding table placement and proposes a heuristic algorithm that yields near optimal placement. OPER implements a SHMEM-based embedding table training system and a unified embedding index mapping to support fine-grained embedding table sharding and placement. Comprehensive experiments reveal that OPER achieves on average 3.4× and 5.1× speedup on training and inference respectively over state-of-the-art DLRM frameworks.

Wang, Zheng↗
DOE OSTI2020

Multimodal Data Representation with Deep Learning for Extracting Cancer Characteristics from Clinical Text

This paper presents a multimodal data representation to improve the performance of deep learning models for extracting cancer key characteristics from unstructured text in pathology reports. Specifically, in addition to using the text as the input to deep learning models, we use concept unique identifiers (CUIs) as another source of information to the models. We analyze the performance of different text and CUI data representations, including word embeddings and bag of embeddings (BOE), with a convolutional neural network (CNN) and a fully connected multilayer perceptron neural network (MLP-NN). The high level document embeddings from text and CUI inputs are combined by concatenating them and then applying a classifier. The model is used for extracting cancer subsite and histology from pathology reports. These two classification tasks have a large number of labels, i.e. 317 for subsite and 556 for histology, with extreme class imbalance. We compare the performance of the developed DL models across the two tasks based on micro- and macro-F1 scores. The evaluation shows that a multi-channel DL model that utilizes text represented by word embeddings and CUIs represented by BOE outperforms other DL models. Also, this approach significantly improves the model performance on low prevalence classes.

Alawad, Mohammed↗
DOE OSTI2014

White dwarfs in the UKIRT infrared deep sky survey data release

We have identified 8 to 10 new cool white dwarfs from the Large Area Survey (LAS) Data Release 9 of the United Kingdom InfraRed Telescope (UKIRT) Infrared Deep Sky Survey (UKIDSS). The data set was paired with the Sloan Digital Sky Survey to obtain proper motions and a broad ugrizYJHK wavelength coverage. Optical spectroscopic observations were secured at Gemini Observatory and confirm the degenerate status for eight of our targets. The final sample includes two additional white dwarf candidates with no spectroscopic observations. We rely on improved one-dimensional model atmospheres and new multi-dimensional simulations with CO5BOLD to review the stellar parameters of the published LAS white dwarf sample along with our additional discoveries. Most of the new objects possess very cool atmospheres with effective temperatures below 5000 K, including two pure-hydrogen remnants with a cooling age between 8.5 and 9.0 Gyr, and tangential velocities in the range 40 km s{sup –1} ≤v {sub tan} ≤ 60 km s{sup –1}. They are likely thick disk 10-11 Gyr old objects. In addition, we find a resolved double degenerate system with v {sub tan} ∼ 155 km s{sup –1} and a cooling age between 3.0 and 5.0 Gyr. These white dwarfs could be disk remnants with a very high velocity or former halo G stars. We also compare the LAS sample with earlier studies of very cool degenerates and observe a similar deficit of helium-dominated atmospheres in the range 5000 < T {sub eff} (K) < 6000. We review the possible explanations for the spectral evolution from helium-dominated toward hydrogen-rich atmospheres at low temperatures.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

The Morphology and Structure of Stellar Populations in the Fornax Dwarf Spheroidal Galaxy from Dark Energy Survey Data

Using deep wide-field photometry 3 yr data (Y3) from the Dark Energy Survey (DES), we introduce a panoramic study of the Fornax dwarf spheroidal galaxy. The data discussed here—a small subset of the full survey—uniformly cover a region of 25 deg 2 centered on the galaxy to a depth of g ~ 23.5. We use these data to study the structural properties of Fornax, overall stellar population, and its member stars in different evolutionary phases. We also search for possible signs of tidal disturbance. Fornax is found to be significantly more spatially extended than what early studies suggested. No statistically significant distortions or signs of tidal disturbances were found down to a surface brightness limit of ~32.1 mag arcsec -2 . Yet, there are hints of shell-like features located ~20'–40' from the center of Fornax that may be stellar debris from past merger events. We also find that intermediate-age and young main-sequence populations show different orientation at the galaxy center and have many substructures. The deep DES Y3 data allow us to characterize the age of those young stellar substructures with great accuracy, both those previously known and those newly identified as possible overdensities in this work, on the basis of their color–magnitude diagram morphology. We find that the youngest overdensities are all found on the eastern side of Fornax, where the Fornax field population itself is slightly younger than in the west. In summary, the high-quality DES Y3 data reveal that Fornax has many rich structures and provide insights into its complex formation history.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

DeepClone: Lightweight State Replication of Deep Learning Models for Data Parallel Training

Training modern deep neural network (DNN) models involves complex workflows triggered by model exploration, sensitivity analysis, explainability, etc. A key primitive in this context is the ability to clone a model training instance, i.e. “fork” the training process in a potentially different direction, which enables comparisons of different evolution paths using variations of training data and model parameters. However, in a quest improve the training throughput, a mix of data parallel, model parallel, pipeline parallel and layer-wise parallel approaches are making the problem of cloning highly complex. In this paper, we explore the problem of efficient cloning under such circumstances. To this end, we leverage several properties of data-parallel training and layer-wise parallelism to design DeepClone, a cloning approach based on augmenting the execution graph to gain direct access to tensors, which are then sharded and reconstructed asynchronously in order to minimize runtime overhead, standby duration, readiness duration. Compared with state-of-art approaches, DeepClone shows orders of magnitude improvement for several classes of DNN models.

data-parallel training↗
DOE OSTI2022

Unpolarized transverse momentum distributions from a global fit of Drell-Yan and semi-inclusive deep-inelastic scattering data

We present an extraction of unpolarized transverse-momentum-dependent parton distribution and fragmentation functions based on more than two thousand data points from several experiments for two different processes: semi-inclusive deep-inelastic scattering and Drell-Yan production. The baseline analysis is performed using the Monte Carlo replica method and resumming large logarithms at N 3 LL accuracy. The resulting description of the data is very good (χ 2 /N dat = 1.06). For semi-inclusive deep-inelastic scattering, predictions for multiplicities are normalized by factors that cure the discrepancy with data introduced by higher-order perturbative corrections.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2019

Troubleshooting deep-learner training data problems using an evolutionary algorithm on Summit

Architectural and hyper-parameter design choices can influence deep-learner (DL) model fidelity but can also be affected by malformed training and validation data. However, practitioners may spend significant time refining layers and hyper-parameters before discovering that distorted training data was impeding training progress. We found that an evolutionary algorithm (EA) can be used to diagnose this kind of DL problem. An EA evaluated thousands of DL configurations on Summit that yielded no overall improvement in DL performance, which suggested problems with the training and validation data. We suspected that Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement that was applied to previously generated digital surface models (DSMs), for which we were training DLs to find errors, had damaged the training data. Subsequent runs with an alternative global normalization yielded significantly improved DL performance. However, the DL Intersection Over Union (IOU) still exhibited consistent sub-par performance, which suggested further problems with the training data and DL approach. Nonetheless, we were able to diagnose this problem within a 12-hour span via Summit runs, which prevented several weeks of unproductive trial-and-error DL configuration refinement, and allowed for a more timely convergence on an ultimately viable solution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques

Using multiple geophysical methods has become a prevailing approach in numerous geophysical applications to investigate subsurface structures and parameters. These multimethod-based exploration strategies have the potential to greatly diminish uncertainties and ambiguities encountered during geophysical data analysis and interpretation. One of the applications is the cooperative inversion of airborne magnetic and gravity gradient data for the interpretation of data obtained in mineral, oil and gas, and geothermal explorations. In this paper, a unified cooperative inversion framework is designed by combining the standard separate inversions with a deep neural network (DNN), which serves as the link between different types of data. A well-trained DNN takes the separately inverted susceptibility and density models as the inputs and provides improved models that will be used as the initial models of deterministic inversions. A two-round iteration strategy is adopted to guarantee the reasonability of the recovered models and overall efficiency of the inversion. In addition, this deep-learning (DL)-based framework demonstrates excellent generalization abilities when tested on models that are entirely distinct from the training data sets. The framework can easily incorporate multiphysics without necessitating any structural changes to the network. Synthetic experiments validate that our DL-based method outperforms conventional separate inversions and cross-gradient-based joint inversion in view of the accuracy of the recovered models and inversion efficiency. Successful application to field data further verifies the effectiveness of our DL-based method.

Geochemistry & Geophysics↗
DOE OSTI2023

Improving Protein–Ligand Interaction Modeling with cryo-EM Data, Templates, and Deep Learning in 2021 Ligand Model Challenge

Elucidating protein–ligand interaction is crucial for studying the function of proteins and compounds in an organism and critical for drug discovery and design. The problem of protein–ligand interaction is traditionally tackled by molecular docking and simulation, which is based on physical forces and statistical potentials and cannot effectively leverage cryo-EM data and existing protein structural information in the protein–ligand modeling process. In this work, we developed a deep learning bioinformatics pipeline (DeepProLigand) to predict protein–ligand interactions from cryo-EM density maps of proteins and ligands. DeepProLigand first uses a deep learning method to predict the structure of proteins from cryo-EM maps, which is averaged with a reference (template) structure of the proteins to produce a combined structure to add ligands. The ligands are then identified and added into the structure to generate a protein–ligand complex structure, which is further refined. The method based on the deep learning prediction and template-based modeling was blindly tested in the 2021 EMDataResource Ligand Challenge and was ranked first in fitting ligands to cryo-EM density maps. These results demonstrate that the deep learning bioinformatics approach is a promising direction for modeling protein–ligand interactions on cryo-EM data using prior structural information.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Accelerating the discovery of battery electrode materials through data mining and deep learning models

The availability of crystalline materials databases allows for building accurate machine learning (ML) models that can accelerate the exploration of materials chemical space for energy storage applications. In this work, we screen all inorganic materials included in the Materials Project and AFLOW databases as potential metal-ion battery electrodes. We develop an efficient protocol to mine and screen raw data in current databases and provide a new database of electrode materials by considering pairs of charged and discharged electrodes. This effort leads to a new database with over 190,000 instances, in contrast to the original battery database which contains about 5000. The expanded battery data set is then used to build regression-based deep neural network models for predicting average voltages and percentage volume changes upon charging and discharging, which present improvements of at least 28% for target properties with respect to previous models, and are now able to predict anode electrodes (low voltage region) as well as electrodes that will not work in electrochemical cells (negative voltages), overcoming the challenges identified in previous ML models for battery electrodes. Additionally, a further screening of the expanded database itself allowed us to identify 35 novel electrode candidates with excellent battery performance metrics.

25 ENERGY STORAGE↗
DOE OSTI2024

A Transfer Learning Strategy for Improving the Data Efficiency of Deep Reinforcement Learning Control in Smart Buildings

Reinforcement learning (RL) is a powerful tool that has shown promising results in many domains such as robotics and game-playing. Because RL algorithms learn optimal control policies by continuously interacting with their environments, these algorithms require a lot of data to learn, which limits their application to a wide range of domains. For this reason, there is an immense need for improving the training and data efficiency of RL. Towards addressing this research gap, this paper proposes a transfer learning (TL) approach to improve the efficiency of the RL algorithms by reducing data need and, thus, reducing training time. To demonstrate the proposed approach, a knowledge transfer from a set of buildings to another building was conducted. The results show that the proposed TL approach is a promising method that can efficiently harness the information from similar RL tasks and reduce the data needs of RL algorithms.

Amasyali, Kadir↗
DOE OSTI2024

Machine-learned closure of URANS for stably stratified turbulence: connecting physical timescales & data hyperparameters of deep time-series models

Stably stratified turbulence (SST), a model that is representative of the turbulence found in the oceans and atmosphere, is strongly affected by fine balances between forces and becomes more anisotropic in time for decaying scenarios. Moreover, there is a limited understanding of the physical phenomena described by some of the terms in the Unsteady Reynolds-Averaged Navier–Stokes (URANS) equations—used to numerically simulate approximate solutions for such turbulent flows. Rather than attempting to model each term in URANS separately, it is attractive to explore the capability of machine learning (ML) to model groups of terms, i.e. to directly model the force balances. We develop deep time-series ML for closure modeling of the URANS equations applied to SST. We consider decaying SST which are homogeneous and stably stratified by a uniform density gradient, enabling dimensionality reduction. We consider two time-series ML models: long short-term memory and neural ordinary differential equation. Both models perform accurately and are numerically stable in a posteriori (online) tests. Furthermore, we explore the data requirements of the time-series ML models by extracting physically relevant timescales of the complex system. We find that the ratio of the timescales of the minimum information required by the ML models to accurately capture the dynamics of the SST corresponds to the Reynolds number of the flow. The current framework provides the backbone to explore the capability of such models to capture the dynamics of high-dimensional complex dynamical system like SST flows.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Towards automated and real-time multi-object detection of anguilliform fishes from sonar data using YOLOv8 deep learning algorithm

Eels (Anguilla spp.), including American eels (Anguilla rostrata), European eels (Anguilla anguilla), and Japanese eels (Anguilla japonica), are species of critical management and regulatory concern due to their vulnerability to various stressors during downstream migrations. Accurate and efficient detection of migrating eels can improve our understanding of fish behaviors and fish-hydraulic structure interactions, thereby facilitating the design, operation, and optimization of more effective downstream passage facilities from both biological and economic perspectives. However, a real-time, automated framework for detecting migrating eels in real-world applications is currently lacking. Leveraging imaging sonar as a reliable technology for fish passage monitoring, field data are acquired using imaging sonar and then converted to single sonar frames/images for subsequent analysis. In this study, a framework based on the You Only Look Once Version 8 (YOLOv8)-based convolutional neural network is proposed for multi-object detection of eels and non-eel fish using the sonar images after image subtraction and additional wavelet denoising. The results from both training and testing phases demonstrate that the framework's ability can successfully detect both eels and non-eel fish in preprocessed sonar images, achieving F1-scores and mAP@0.50 exceeding 0.84. Additionally, the incorporation of wavelet denoising during preprocessing slightly improve detection performance. Furthermore, the transferability of this framework from eel to lamprey detection is demonstrated to be feasible given the similar morphological characteristics of these two species. Overall, the proposed framework achieves accurate and efficient detection of migrating eels, providing reliable and real-time information that can help conserve vulnerable eel and eel-like populations.

Deep learning↗
DOE OSTI2019

Predicting plug loads with occupant count data through a deep learning approach

Predictive control has gained increasing attention for its ability to reduce energy consumption and improve occupant comfort in buildings. The plug loads prediction is a key component for the predictive building controls, as plug loads is a major source of internal heat gains in buildings. This study proposed a novel method to apply the Long-Short-Term-Memory (LSTM) Network, a special form of Recurrent Neural Network, to predict plug loads. The occupant count and the time have been confirmed to drive the plug load profile and thus selected as the features for the plug load prediction. The LSTM network was trained and tested with ground truth occupant count data collected from a real office building in Berkeley, California. Results from the LSTM network markedly improve the prediction accuracy compared with traditional linear regression methods and the classical Artificial Neural Network. 95% of 1-hour predictions from LSTM network are within ±1 kW of the actual plug loads, given the average plug loads during the office hour is 8.6 kW. The CV(RMSE) of the predicted plug load is 11% for the next hour, and 20% for the next eight hours. Lastly, we compared four prediction approaches with the office building we monitored: LSTM vs. ARIMA, with occupant counts vs. without occupant counts. It was found, the prediction error of the LSTM approach is around 4% less than the ARIMA approach. Using occupant counts as an exogenous input could further reduce the prediction error by 5%-6%. The findings of this paper could shed light on the plug load prediction for building control optimizations such as model-predictive control.

Occupant count↗