Search NASA⌕ Search

SEARCH · Search NASA

Results for “temporal learning”

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 505 records · Page 28
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

An interpretable machine learning model for advancing terrestrial ecosystem predictions

We apply an interpretable Long Short-Term Memory (iLSTM) network for land-atmosphere carbon flux predictions based on time series observations of seven environmental variables. iLSTM enables interpretability of variable importance and variable-wise temporal importance to the prediction of targets by exploring internal network structures. The application results indicate that iLSTM not only improves prediction performance by capturing different dynamics of individual variables, but also reasonably interprets the different contribution of each variable to the target and its different temporal relevance to the target. This variable and temporal importance interpretation of iLSTM advances terrestrial ecosystem model development as well as our predictive understanding of the system.

Lu, Dan↗
DOE OSTI2019

Machine Learning-Based Investigation of the Associations between Residential Power Consumption and Weather Conditions

Machine learning feature selection analyses were conducted to understand the impact of various weather attributes on power electricity demand and its components in the northwest United States. Load profiles data were obtained from the Northwest Energy Efficiency Alliance (NEEA) and processed to yield hourly load profiles with the same temporal resolution as the weather conditions data obtained from the National Oceanic and Atmospheric Administration (NOAA) for representative weather stations. The data were divided into five seasons; for each season, for each load component, the influences of weather factors were evaluated and quantified using cross-correlation, principal component analysis, and mutual information evaluation; then predictive models were developed based on the ranked/screened factors using the regression tree (RT) approach. After multi-fold cross-validation, the optimal complexity/depth of the regress tree models is found to vary for different load components, and the prediction accuracy using RT and weather data can be higher than 80% for heating and refrigeration, or lower than 30% for vent and cooking. The study provides guidance on improvement of load profile generation, or even serves as a standalone predictive tool for approximating load profiles in balance authorities or climate zones where load profile data is absent.

load composite, load profiling, NEEA, mutual infor↗
DOE OSTI2022

Inferring protein expression changes from mRNA in Alzheimer’s dementia using deep neural networks

Identifying the molecular systems and proteins that modify the progression of Alzheimer’s disease and related dementias (ADRD) is central to drug target selection. However, discordance between mRNA and protein abundance, and the scarcity of proteomic data, has limited our ability to advance candidate targets that are mainly based on gene expression. Therefore, by using a deep neural network that predicts protein abundance from mRNA expression, here we attempt to track the early protein drivers of ADRD. Specifically, by applying the clei2block deep learning model to 1192 brain RNA-seq samples, we identify protein modules and disease-associated expression changes that were not directly observed at the mRNA level. Moreover, pseudo-temporal trajectory inference based on the predicted proteome became more closely correlated with cognitive decline and hippocampal atrophy compared to RNA-based trajectories. This suggests that the predicted changes in protein expression could provide a better molecular representation of ADRD progression. Furthermore, overlaying clinical traits on protein pseudotime trajectory identifies protein modules altered before cognitive impairment. These results demonstrate how our method can be used to identify potential early protein drivers and possible drug targets for treating and/or preventing ADRD.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Adaptive Graph Learning with Transformer for Multi-Reservoir Inflow Prediction

Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for multi-reservoir inflow forecasting. AdaTrip constructs dynamic graphs where reservoirs are nodes with directed edges reflecting hydrological connections, employing attention mechanisms to automatically identify crucial spatial and temporal dependencies. Evaluation on thirty reservoirs in the Upper Colorado River Basin demonstrates superiority over existing baselines, with improved performance for reservoirs with limited records through parameter sharing. Additionally, AdaTrip provides interpretable attention maps at edge and time-step levels, offering insights into hydrological controls to support operational decision-making. Our code is available at https://github.com/humphreyhuu/AdaTrip.

Hu, Pengfei [ORNL] (ORCID:0009000367130950)↗
DOE OSTI2026

A Data-driven Phytotechnology Framework for Identification and Remediation of Leached-Metals-Contaminated Soil Near Coal Ash Impoundments

This project developed and evaluated advanced remote sensing and machine learning approaches to identify, monitor, and address environmental contamination associated with coal combustion residual (CCR) impoundments and landfills at coal-fired power plants. In Phase I, historical and multi-temporal Sentinel-2 satellite imagery, groundwater monitoring data, and environmental variables were integrated to detect vegetation stress potentially caused by toxic metal leaching from coal ash disposal sites. Multiple vegetation and biophysical indices were analyzed to determine their effectiveness in identifying abnormal vegetation growth patterns linked to contamination. Results from case studies conducted at coal ash–impacted power plant sites in North Carolina and Virginia demonstrated that satellite-based vegetation monitoring can serve as an effective early indicator of environmental stress associated with metals such as arsenic, cadmium, cobalt, lead, lithium, radium, and thallium.

01 COAL, LIGNITE, AND PEAT↗
NASA NTRS2011

Doppler Radar Profiler for Launch Winds at the Kennedy Space Center (Phase 1a)

The NASA Engineering and Safety Center (NESC) received a request from the, NASA Technical Fellow for Flight Mechanics at Langley Research Center (LaRC), to develop a database from multiple Doppler radar wind profiler (DRWP) sources and develop data processing algorithms to construct high temporal resolution DRWP wind profiles for day-of-launch (DOL) vehicle assessment. This document contains the outcome of Phase 1a of the assessment including Findings, Observations, NESC Recommendations, and Lessons Learned.

Murri, Daniel G.↗
NASA NTRSDate not supplied

Remote Sensing of Lineage Functional Types for Modeling and Monitoring Biodiversity

Hyperspectral remote sensing has the potential to continuously scale plant function and plant diversity information from landscape to global extents. Numerous studies have indicated that VSWIR (400-2500 nm) reflectance properties of vegetation capture evolutionarily conserved biochemical, structural, and other functional attributes of plant species. Spectral properties conserved in plants provide the opportunity to both 1) aggregate species into lineages with improved classification accuracy and 2) link those lineages directly to plant traits. Full realization of this goal will enable parameterization of Land Surface Models (LSMs) with remotely sensed information, e.g., canopy nitrogen, and better representations of biodiversity and functional diversity in biogeographic studies. In this study, we use hyperspectral AVIRIS data from the 2013 HyspIRI campaign over the Southern Sierra Nevada, California flight box to investigate the potential for incorporating evolutionary thinking into landcover classification. We link the airborne hyperspectral data with vegetation plot data from roughly 1372 surveys and a phylogeny representing 1361 species. We aggregate species into lineages ranging from species level groups down to similar number of Plant Functional Types as often used in LSMs. We assessed the ability of Random Forest and Partial Least Squares Discriminant Analysis to discriminate across these different phylogenetic scales and determine the optimal number of lineages to classify. Although there are some temporal and spatial differences in our training data, our best approaches achieved moderate classification accuracy (Kappa > 0.65). Given an optimal number of lineages, we explored approaches to improve classifications including machine learning and unmixing approaches. This work suggests that lineage-based methods may be a promising way to leverage the huge amounts of data that will come from high resolution and high return interval hyperspectral data planned for the Surface Biology and Geology mission with sparsely sampled existing ground-based ecological data.

Hyperspectral↗
DOE OSTI2024

Rapid detection of rare events from in situ X-ray diffraction data using machine learning

High-energy X-ray diffraction methods can non-destructively map the 3D microstructure and associated attributes of metallic polycrystalline engineering materials in their bulk form. These methods are often combined with external stimuli such as thermo-mechanical loading to take snapshots of the evolving microstructure and attributes over time. However, the extreme data volumes and the high costs of traditional data acquisition and reduction approaches pose a barrier to quickly extracting actionable insights and improving the temporal resolution of these snapshots. This article presents a fully automated technique capable of rapidly detecting the onset of plasticity in high-energy X-ray microscopy data. The technique is computationally faster by at least 50 times than the traditional approaches and works for data sets that are up to nine times sparser than a full data set. This new technique leverages self-supervised image representation learning and clustering to transform massive data sets into compact, semantic-rich representations of visually salient characteristics ( e.g. peak shapes). These characteristics can rapidly indicate anomalous events, such as changes in diffraction peak shapes. It is anticipated that this technique will provide just-in-time actionable information to drive smarter experiments that effectively deploy multi-modal X-ray diffraction methods spanning many decades of length scales.

Zheng, Weijian↗
DOE OSTI2020

Acoustic Energy Release During the Laboratory Seismic Cycle: Insights on Laboratory Earthquake Precursors and Prediction

Abstract Machine learning can predict the timing and magnitude of laboratory earthquakes using statistics of acoustic emissions. The evolution of acoustic energy is critical for lab earthquake prediction; however, the connections between acoustic energy and fault zone processes leading to failure are poorly understood. Here, we document in detail the temporal evolution of acoustic energy during the laboratory seismic cycle. We report on friction experiments for a range of shearing velocities, normal stresses, and granular particle sizes. Acoustic emission data are recorded continuously throughout shear using broadband piezo‐ceramic sensors. The coseismic acoustic energy release scales directly with stress drop and is consistent with concepts of frictional contact mechanics and time‐dependent fault healing. Experiments conducted with larger grains (10.5 μm) show that the temporal evolution of acoustic energy scales directly with fault slip rate. In particular, the acoustic energy is low when the fault is locked and increases to a maximum during coseismic failure. Data from traditional slide‐hold‐slide friction tests confirm that acoustic energy release is closely linked to fault slip rate. Furthermore, variations in the true contact area of fault zone particles play a key role in the generation of acoustic energy. Our data show that acoustic radiation is related primarily to breaking/sliding of frictional contact junctions, which suggests that machine learning‐based laboratory earthquake prediction derives from frictional weakening processes that begin very early in the seismic cycle and well before macroscopic failure.

58 GEOSCIENCES↗
NASA NTRS2026

PERSIANN-Unet: A Global Deep Learning Framework for Near-Real-Time Precipitation Estimation Using Infrared Data

Access to high-quality, high-resolution, near-real-time precipitation data is essential for hydrological and meteorological research and disaster mitigation. Traditional tools such as rain gauges and radar networks, though effective, have limitations, including sparse coverage in remote areas and high operational costs. Satellite data, with its global coverage and high spatial and temporal resolutions, mitigates limitations in coverage. Satellite precipitation products like Hydro Estimator (HE), Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (IMERG), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) utilize both geosynchronous thermal infrared (IR) and passive microwave (PMW) data in their operation. PMW sensors offer detailed atmospheric profiles but suffer from higher latency, whereas IR sensors provide lower latency but only capture cloud-top information. Despite this constraint, IR data remains attractive for low-latency precipitation estimation. Recent advances in deep learning, particularly convolutional neural networks (CNNs), have further improved satellite precipitation retrievals. This study introduces PERSIANN-Unet (PUnet or PERSIANN V3), a quasi-global algorithm covering 60°N–60°S that combines IR data, monthly climatology, and the UNet architecture to produce half-hourly precipitation estimates at 0.04° resolution. The product is evaluated against HE, IMERG, and PDIR-Now for 2022–2023. Results show that PUnet closely matches its training target, IMERG V07 Final, at the global scale, and performance is further evaluated against Stage IV as a reference over CONUS. Training PUnet on IMERG (2016–2021) leverages a high-quality, integrated PMW IR-gauge precipitation product while developing an IR-based framework not reliant on PMW availability. By operating on a single global image, PUnet avoids tile partitioning and blending steps, reducing edge discontinuities, and produces more spatially consistent precipitation fields across hemispheres.

Phu Nguyen↗
DOE OSTI2026

High-Resolution South American Wind Resource Data Downscaled with Generative Machine Learning Conditioned on Near-Surface Observations

High-resolution historical wind data was developed for the entirety of South America using the innovative Super-Resolution for Renewable Resource Data (sup3r) machine learning framework. The publicly available Sup3rWind South America dataset represents a significant advancement in wind resource data generation, leveraging generative machine learning conditioned on near-surface observations from the Meteorological Assimilation Data Ingest System (MADIS) to efficiently and accurately downscale coarse reanalysis data from the European Centre for Medium-Range Weather Forecasts (ERA5). This approach produces fine-scale, spatially and temporally coherent wind and meteorological fields hundreds of times more computationally efficient than traditional numerical weather modeling methods, enabling access to high-fidelity wind information across both continental and offshore regions. Sup3rWind South America builds on the earlier Sup3rWind Ukraine dataset through improvements in model architecture and outputs conditioned on near-surface observation inputs. As with the Ukraine data release, this dataset includes wind speed, wind direction, temperature, relative humidity, and pressure at a horizontal resolution of ~2 km, representing a 15x spatial enhancement relative to the 31 km ERA5 grid. Wind speed and direction are provided at 5-minute resolution, a 12x temporal refinement compared to the hourly ERA5 data, while temperature, relative humidity, and pressure remain at hourly resolution. The data covers all years from 2005 to 2024. Before downscaling, ERA5 inputs were bias-corrected using long-term monthly means and a limited number of quality-controlled observations to align large-scale statistics with regional conditions. The resulting dataset is the first publicly available high-resolution timeseries wind record that provides full spatial coverage of South America. Model validation demonstrates strong agreement with observations across several statistical metrics, consistent with other state-of-the-art high-resolution wind resource datasets. The potential applications of Sup3rWind South America span renewable energy resource assessment, energy system modeling, and grid resilience analysis. The 20-year record and high spatial and temporal resolution support accurate estimation of long-term energy yield and the economic feasibility of potential wind development sites. Continuous coverage across both continental and offshore regions enables comprehensive site prospecting within exclusive economic zones. The 2 km, 5-minute resolution data provide the spatial and temporal variability required for power system simulation, operational planning, and regional risk assessments.

17 WIND ENERGY↗
DOE OSTI2021

Adaptive Protection of Scientific Backbone Networks Using Machine Learning

In this article, we propose a new protection scheme for backbone networks to guarantee high service availability. The presented scheme does not require any reconfiguration immediately after the failure (i.e., it is proactive). At the same time, it does not require any reserved backup network resources either. To achieve these seemingly contradictory goals, we utilize the recent advancements in Machine Learning (ML) to implement a network intelligence that periodically re-allocates the unused capacity as protection bandwidth to meet the service availability requirements of each connection. Our goal is achieved by two components (1) predicting the traffic for the next period on each link, and (2) intelligently selecting the best fit dedicated protection scheme for the next period depending on the estimated unused (spare) bandwidth and the previous service availability violations. Note that re-allocating protection bandwidth affects neither the operational connections nor the current best practice of operators to over-provision network bandwidth to support elephant flows. Finally, we provide a case study on the real traffic from Energy Sciences Network (ESnet), a high-speed, international scientific backbone network. The key benefit of our framework is that adaptively utilizing the over-provisioned bandwidth for spare capacity is sufficient to improve the availability from three-nines to five-nines (in ESnet for the 30 examined connections). The drawback is negligible bandwidth limitations; the user perceives a minor and very temporal bandwidth limitation in less than 0.1% of the time.

42 ENGINEERING↗
DOE OSTI2025

Predicting Pulsed-Laser Deposition SrTiO 3 Homoepitaxy Growth Dynamics Using High-Speed Reflection High-Energy Electron Diffraction

Pulsed-laser deposition (PLD) is a powerful technique for growing complex oxides with controlled stoichiometry. To understand growth dynamics therein, it is common to leverage in situ spectroscopies, such as reflection high-energy electron diffraction (RHEED), to monitor surface crystallinity. Most commercial systems rely on video-rate cameras operating at 60-120 Hz that lack sufficient temporal resolution to capture growth dynamics at practical deposition frequencies. Here, a high-speed platform to record in situ dynamics via RHEED at >500 Hz is implemented. An open-source analysis package is designed to fit diffraction spots to 2D Gaussians, allowing single-pulse surface reconstruction kinetics extraction. Using homoepitaxially deposited (001)-oriented SrTiO 3 as a model system, we demonstrate how high-speed RHEED can provide real-time insight into growth processes obscured by slower acquisition systems. By fitting the single-pulse intensity to a set of exponential functions, we observe changes in the characteristic decay time and mechanism correlated to the substrate step width and surface termination. We observe distinct surface effects, with diffraction intensity decaying on lower-energy TiO 2 -terminated surfaces and stabilizing on SrO- or mixed-terminated surfaces. Similarly, using an exponential model, the extracted characteristic time of adatom deposition decreases with increased density of bonding sites associated with mixed termination and narrower step widths. Ultimately, this work shows how increasing RHEED temporal resolution can uncover new insights into growth processes, with practical implications for the design and control of PLD processes. This experimental platform provides new capabilities to enable data-driven machine learning analysis and autonomous control systems to enhance the complexity and fecundity of PLD.

(SrO)↗
DOE OSTI2024

High-Resolution Meteorology with Climate Change Impacts from Global Climate Model Data Using Generative Machine Learning

As renewable energy generation increases, the impacts of weather and climate on energy generation and demand become critical to the reliability of the energy system. However, these impacts are often overlooked. Global climate models (GCMs) can be used to understand possible changes to our climate, but their coarse resolution makes them difficult to use in energy system modelling. Here we present open-source generative machine learning methods that produce meteorological data at a nominal spatial resolution of 4 km at an hourly frequency based on inputs from 100 km daily-average GCM data. These methods run 40 times faster than traditional downscaling methods and produce data that have high-resolution spatial and temporal attributes similar to historical datasets. We demonstrate that these methods can be used to downscale projected changes in wind, solar and temperature variables across multiple GCMs including projections for more frequent low-wind and high-temperature events in the Eastern United States.

climate change↗
DOE OSTI2024

MetaPoL: Immersive VR based Indoor Patterns of Life (PoL) and Anomalies Data Generation for Insider Threat Modeling in Nuclear Security

Insider threats are perhaps the most serious challenges that nuclear and radiological security systems face. Insiders pose such a great threat due to their access, authority, and knowledge, granting them opportunities to bypass dedicated nuclear and radiological security elements. For example, in one of the latest major insider threat incidents to nuclear security, the Doel-4 nuclear powerplant in Belgium suffered a shutdown, the threat of nuclear materials diversion, and long-term loss of tens of millions of dollars. Seven years of investigation concluded that it was an inside job and attempted sabotage. In this regard, there is an immediate need for R&D and technology integration in the domain of modeling indoor Patterns-of-Life (PoL) and anomaly detection. This can be achieved by using datasets of facility users’ mobility and activity, which can support the design of algorithms for insider threat modeling and detection. However, due to classification, privacy, sensitivity, and safety protocols, such datasets from real physical nuclear reactor facilities are not only hard to share, but also not always feasible to deploy and collect. Aiming to find an alternate solution, our proposed demonstration work - MetaPoL, is the first-ever (for the application space) immersive VR (virtual reality) environment of a real-world secure facility and allows users to move-and-stay through the designed indoor physical layout and also encounter NPCs (non-player characters) that emulate other facility users. In the MetaPoL an interactive user performs realistic spatio-temporal movement, dwelling and activities using a Meta Quest Pro VR headset, and that generates high-frequency (in time) high-resolution (in space) indoor spatial-temporal datasets that are valuable for PoL modeling and anomaly detection research specifically for insider threat modeling and detection mission. Such generated realistic, rich in context, and mission specific datasets can boost AI/Machine Learning based research for modeling and detecting insider threats in nuclear security and nonproliferation.

Gunaratne, Chathika↗
DOE OSTI2023

Evaluation of Multi-Fidelity Soil Moisture Products Across the Continental United States

We have aggregated the most recent soil moisture datasets from a diverse range of sources, encompassing the Continental United States (CONUS). These sources encompass gridded data from remote sensing products, reanalysis products, machine learning-based projects, and land surface modeling products. Additionally, we have obtained and processed in-situ soil moisture observations from the International Soil Moisture Network. The collected datasets exhibit variations in both temporal and spatial resolutions. Among the 20 datasets, six are available at a spatial resolution of 0.25 degrees, while three are at a coarser spatial resolution of 25 km. To minimize spatial interpolation, we conducted data uncertainty evaluations at the 0.25-degree spatial resolution. For our data evaluations, we maintained a monthly temporal resolution, which effectively captures soil moisture seasonality and interannual variability. Our data processing strategy preserves the raw data and interpolated data at their original temporal resolutions. Datasets with higher temporal resolutions, including daily, three-hourly, and hourly datasets, are set aside for subsequent analyses. These analyses will delve into topics such as soil moisture changes and recovery during extreme weather events. Furthermore, we have processed auxiliary data to enhance our evaluation, leveraging tools such as Google Earth Engine. This includes incorporating topography data, land use land cover data, Köppen-Geiger climate classification, and more to provide a comprehensive assessment from multiple sources.

Li, Lingcheng↗
NASA NTRSDate not supplied

Data Science and the Knowledge Discovery Adventure

This talk will cover the important steps involved in the data science and knowledge discovery process: • Initial fact gathering (interview domain experts, review reports, articles, state-of-the-art) • Identify the problem (prediction, classification, statistical analysis, etc.) • Survey supporting data sources • Understand the data (numerical, categorical, text, sampling rate, data quality issues, etc.) • Selecting relevant features and sources • Acquire the data (set up agreements with the data stewards, APIs to download, etc.) • Merge data sources (temporal, spatial, common key, other ontologies...) • Feature Engineering (non linear domain knowledge or physics-based relationships) • Build data processing pipeline (may need to tap into data stream, develop parallel processing algorithm, federated learning etc.) • Build model and test (tune hyper-parameters, cross validation.) • Analyze/Validate results (do the results make sense. Does it answer the original question). • Deploy/Publish (Monitor and assess benefits)

Data science↗