Engineering Papers⌕ Search

SEARCH · Engineering Papers

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

Machine Learning and Economic Models to Enable Risk-Informed Condition Based Maintenance of a Nuclear Plant Asset

The primary objective of this research is to address challenges in the implementation of risk-informed, condition-based predictive maintenance (PdM), which reduces operating costs while still maintaining the safety and reliability of commercial nuclear power plants (NPPs). To achieve the objective, risk models are being developed by taking advantage of advancements in data analytics, deep learning, machine learning (ML), and artificial intelligence (AI). The notable outcomes presented in the report include ? Development of a ML models using heterogeneous plant process and vibration data collected at different spatial and temporal resolutions from the Salem?s CWS to diagnose a circulating water pump (CWP) failure based on salient fault signatures. The developed diagnostic models are extendable to other faults associated with CWPs and CWP motors given associated fault signatures. ? Development of a natural language processing (NLP) technique to automatically classify the WO data into different categories. The developed NLP technique was validated on independent WO data. This automates the tedious and time-consuming activity of mining and classifying WOs by subject matter experts. ? Estimation of mean time between downtime (i.e., time duration between time instances when 1 or more CWPs are not available) and developed an approach to establish reliability of CWS components using unstructured WO data along with CWS plant process data. ? Formulation of economic model based on Markov chain models. The parameters of associated with the transition rate between different states of Markov chain models were estimated using WO data. The economic model formulation and discussion captures both time-independent and time-dependent parameter variation, leading to risk-informed decision-making.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Mapping wall-to-wall fractional cover of Arctic tundra plant functional types in Alaska using 20-m spatial resolution satellite imagery and harmonized plot observations

Estimates of fractional cover (fCover) across given land surfaces are used to assess, and often model, vegetation composition and diversity, which are crucial for understanding the health and functioning of terrestrial ecosystems. Remote sensing provides a useful means for scaling local, plot-measured fCover estimates to regional scales. Leveraging a recently synthesized and harmonized plot database, this study generated wall-to-wall maps of fCover for six Alaskan-Arctic plant functional types (PFT), including non-vascular plants, forbs, graminoids, and deciduous and evergreen shrubs, using 20-m satellite data (Sentinel-1, Sentinel-2, ArcticDEM) using a machine learning regression approach, specifically the random forest (RF) algorithm, which is well-suited for handling nonlinear relationships and high-dimensional satellite datasets. This study additionally addressed the spatio-temporal inconsistencies e.g., sampling scale, plot size, and collection year in plot measured fCover by adopting a multivariate outlier detection approach—Cook’s distance—to identify high-quality plots for model training and validation. Our approach achieves high accuracy (R 2 = 0.59–0.93, root mean squared errors = 0.02–0.10 for all PFTs) between plot-observed and satellite-derived fCover when using high-quality plot samples. The mapped fCover characterizes the spatial patterns of different PFTs across the tundra biome at a 20-m resolution, providing key information needed for improved representation of Arctic tundra vegetation in terrestrial biosphere models to better understand climate-vegetation feedback across the Arctic tundra.

Arctic tundra↗

What can be Learned from X-Ray Spectroscopy Concerning Hot Gas in the Local Bubble and Charge Exchange Processes

Solar wind charge exchange produces diffuse X-ray emission with a variable surface brightness comparable to that of the cosmic background. While the temporal variation of the charge exchange emission allows some separation of the components, there remains a great deal of uncertainty as to the zero level of both. Because the production mechanisms of the two components are considerably different, their spectra would provide critical diagnostics to the understanding of both. However, current X-ray observatories are very limited in both spectral resolution and sensitivity in the critical soft X-ray (less than 1.0 keV) energy range. Non-dispersive high-resolution spectrometers, such as the calorimeter proposed for the Spectrum Roentgen Gamma mission, will be extremely useful in distinguishing the cascade emission of charge exchange from the spectra of thermal bremsstrahlung cosmic plasmas.

Snowden, Steven L.↗

Optimal Proactive Vehicle Relocation for On-Demand Mobility Service with Deep Convolution-LSTM Network

This study develops an innovative model for inferring optimal proactive relocation strategy for empty vehicles of on-demand mobility service (OMS) directly from past observations of passenger demand. The output of our model is a row stochastic relocation matrix which gives the probability that an empty vehicle should be relocated from location i to location j at any given time. The matrix itself is high-dimensional and therefore challenging to obtain accurate estimation with traditional machine learning approach. Our model proposes the low-rank approximation of the relocation matrix, and introduces the deep convolution-LSTM network which extracts low-level spatial and temporal features from past demand observations for best restoration of the actual low rank approximation vector. The model is trained by deriving the optimal matching strategies from one year of real-world trip data. The results show that our model is able to predict the low-rank approximation of the relocation matrix with 4% of mean absolute error, may reduce the relocation cost by 20%-45% as compared to the real-world observations and is 50% optimal as compared to the global optimal matching with perfect information.

Lei, Zengxiang↗

Recent increases in annual, seasonal, and extreme methane fluxes driven by changes in climate and vegetation in boreal and temperate wetland ecosystems

Climate warming is expected to increase global methane (CH 4 ) emissions from wetland ecosystems. Although in situ eddy covariance (EC) measurements at ecosystem scales can potentially detect CH 4 flux changes, most EC systems have only a few years of data collected, so temporal trends in CH 4 remain uncertain. Here, we use established drivers to hindcast changes in CH 4 fluxes (FCH 4 ) since the early 1980s. We trained a machine learning (ML) model on CH 4 flux measurements from 22 [methane-producing sites] in wetland, upland, and lake sites of the FLUXNET-CH 4 database with at least two full years of measurements across temperate and boreal biomes. The gradient boosting decision tree ML model then hindcasted daily FCH 4 over 1981-2018 using meteorological reanalysis data. We found that, mainly driven by rising temperature, half of the sites (n = 11) showed significant increases in annual, seasonal, and extreme FCH 4 , with increases in FCH 4 of ca. 10% or higher found in the fall from 1981–1989 to 2010–2018. The annual trends were driven by increases during summer and fall, particularly at high-CH 4 -emitting fen sites dominated by aerenchymatous plants. We also found that the distribution of days of extremely high FCH 4 (defined according to the 95th percentile of the daily FCH 4 values over a reference period) have become more frequent during the last four decades and currently account for 10–40% of the total seasonal fluxes. The share of extreme FCH 4 days in the total seasonal fluxes was greatest in winter for boreal/taiga sites and in spring for temperate sites, which highlights the increasing importance of the non-growing seasons in annual budgets. Our results shed light on the effects of climate warming on wetlands, which appears to be extending the CH 4 emission seasons and boosting extreme emissions.

54 ENVIRONMENTAL SCIENCES↗

Using AI to build a hydrobiogeochemical soil model

Soil water content is a function of inputs from precipitation and outputs via evaporation, transpiration, lateral flow, and vertical percolation, and is sensitive to biogeochemical processes. As such, soils serve as an ideal integrator of atmospheric, hydrological, and biogeochemical processes affecting the water cycle. In addition, soil water retention capacity, infiltration rates, and hydraulic conductivity can buffer or exacerbate the effects of extreme precipitation events (e.g., flooding, runoff, subsurface transport, erosion, greenhouse gas emissions) and mitigate the impact of droughts and heat waves on land systems (e.g., fire, crop failure). However, integrating water cycle measurements spanning different land atmosphere compartments across scales is a fundamental barrier for numerical model predictability. A significant challenge is that each domain (soil, hydrology, biology, and atmosphere) typically collects different sets of data at different temporal and spatial frequencies/scales, and even different dimensionalities (2D vs 3D). To implement soil as an integrator of the water cycle in land models, we suggest that novel machine learning (ML) tools can be developed to effectively simulate complex landscapes across various domains and scales, extended to regions with sparse or no data. The ultimate goals are to improve predictive understanding of land-atmosphere interactions and to extend the predictability of current Earth System Models (ESMs) through better integration of hydrological and biogeochemical data. We envision a framework in which: (1) ML-aided data reconstructions enable the merger of data sources into a unified geospatial product; (2) automated detection techniques are used to improve the knowledge of complex soil processes and interactions; and (3) this knowledge is leveraged and incorporated into models through AI-based emulators to distinctly connect the land and atmospheric compartments of the water cycle in models.

54 ENVIRONMENTAL SCIENCES↗

Fracture Network Prediction Using Physics-based Machine Learning Algorithms

In recent years, systematic CO2 injection into geological reservoirs across the U.S. has gained traction as a strategy to mitigate greenhouse gas emissions. This approach necessitates precise monitoring to ensure secure containment, minimize risks, and optimize storage management. Our study leverages machine learning (ML) techniques to advance the understanding of CO2 injection processes, focusing on the Illinois Basin. Over a three-year injection period, we analyzed microseismic data, identifying 19 temporal intervals with significant bottom-hole pressure changes. By partitioning microseismic events into these intervals and estimating b-values, we revealed over 100 clusters of events related to fracture initiation or reactivation. Advanced spatial analysis highlighted horizontally-oriented fractures along the NNW-SSE axis. This quantification of fracture networks informs dynamic injection scheduling, work-over strategies, and risk assessments, enhancing carbon capture, utilization, and storage (CCUS) operations. Additionally, our methodology offers valuable insights for oil and gas operations and geothermal development, supporting fracture-based monitoring and risk mitigation.

Kumar, Abhash↗

A global DSCOVR/EPIC-based hourly/daily shortwave radiation/PAR dataset

Accurate characterization of the global downward shortwave (SW) and photosynthetically active radiation (PAR) is fundamental for Earth system modeling and global change research. Combined with a machine-learning method, we used the Earth Polychromatic Imaging Camera (EPIC) data onboard the Deep Space Climate Observatory (DSCOVR) to generate the global SW/PAR dataset at both hourly and daily temporal scales and 0.1degree×0.1degree spatial resolution. Covering a period from June, 2015 to June (about 4 years), 2019, the dataset consists of total SW/PAR and their direct and diffuse components. Our dataset will be valuable for understanding the diurnal cycles and seasonal patterns of ecosystem processes, as well as the solar energy utilizations

14 SOLAR ENERGY↗

A globally sampled high-resolution hand-labeled validation dataset for evaluating surface water extent maps

Effective monitoring of global water resources is increasingly critical due to climate change and population growth. Advancements in remote sensing technology, specifically in spatial, spectral, and temporal resolutions, are revolutionizing water resource monitoring, leading to more frequent and high-quality surface water extent maps using various techniques such as traditional image processing and machine learning algorithms. However, satellite imagery datasets contain trade-offs that result in inconsistencies in performance, such as disparities in measurement principles between optical (e.g., Sentinel-2) and radar (e.g., Sentinel-1) sensors and differences in spatial and spectral resolutions among optical sensors. Therefore, developing accurate and robust surface water mapping solutions requires independent validations from multiple datasets to identify potential biases within the imagery and algorithms. However, high-quality validation datasets are expensive to build, and few contain information on water resources. For this purpose, we introduce a globally sampled, high-spatial-resolution dataset labeled using 3 m PlanetScope imagery. Our surface water extent dataset comprises 100 images, each with a size of 1024×1024 pixels, which were sampled using a stratified random sampling strategy covering all 14 biomes. We highlighted urban and rural regions, lakes, and rivers, including braided rivers and coastal regions. We evaluated two surface water extent mapping methods using our dataset – Dynamic World, based on Sentinel-2, and the NASA IMPACT model, based on Sentinel-1. Dynamic World achieved a mean intersection over union (IoU) of 72.16 % and F1 score of 79.70 %, while the NASA IMPACT model had a mean IoU of 57.61 % and F1 score of 65.79 %. Performance varied substantially across biomes, highlighting the importance of evaluating models on diverse landscapes to assess their generalizability and robustness. Our dataset can be used to analyze satellite products and methods, providing insights into their advantages and drawbacks. Our dataset offers a unique tool for analyzing satellite products, aiding the development of more accurate and robust surface water monitoring solutions. The dataset can be accessed via https://doi.org/10.25739/03nt-4f29.

54 ENVIRONMENTAL SCIENCES↗

Human Performance in Simulated Reduced Gravity Environments

NASA is currently designing a new space suit capable of working in deep space and on Mars. Designing a suit is very difficult and often requires trade‐offs between performance, cost, mass, and system complexity. Our current understanding of human performance in reduced gravity in a planetary environment (the moon or Mars) is limited to lunar observations, studies from the Apollo program, and recent suit tests conducted at JSC using reduced gravity simulators. This study will look at our most recent reduced gravity simulations performed on the new Active Response Gravity Offload System (ARGOS) compared to the C‐9 reduced gravity plane. Methods: Subjects ambulated in reduced gravity analogs to obtain a baseline for human performance. Subjects were tested in lunar gravity (1.6 m/sq s) and Earth gravity (9.8 m/sq s) in shirt‐sleeves. Subjects ambulated over ground at prescribed speeds on the ARGOS, but ambulated at a self‐selected speed on the C‐9 due to time limitations. Subjects on the ARGOS were given over 3 minutes to acclimate to the different conditions before data was collected. Nine healthy subjects were tested in the ARGOS (6 males, 3 females, 79.5 +/- 15.7 kg), while six subjects were tested on the C‐9 (6 males, 78.8 +/- 11.2 kg). Data was collected with an optical motion capture system (Vicon, Oxford, UK) and was analyzed using customized analysis scripts in BodyBuilder (Vicon, Oxford, UK) and MATLAB (MathWorks, Natick, MA, USA). Results: In all offloaded conditions, variation between subjects increased compared to 1‐g. Kinematics in the ARGOS at lunar gravity resembled earth gravity ambulation more closely than the C‐9 ambulation. Toe‐off occurred 10% earlier in both reduced gravity environments compared to earth gravity, shortening the stance phase. Likewise, ankle, knee, and hip angles remained consistently flexed and had reduced peaks compared to earth gravity. Ground reaction forces in lunar gravity (normalized to Earth body weight) were 0.4 +/- 0.2 on the ARGOS, but only 0.2 +/- 0.1 on the C‐9. Discussion: Gait analysis showed differences in joint kinematics and temporal‐spatial parameters between the reduced gravity simulators and with respect to earth gravity. Although most of the subjects chose a somewhat unique ambulation style as a result of learning to ambulate in a new environment, all but two were consistent with keeping an Earth‐like gait. Learning how reduced gravity affects ambulation will help NASA to determine optimal suit designs, influence mission planning, help train crew, and may shed light on the underlying methods the body uses to optimize gait for energetic efficiency. Conclusion: Kinematic and kinetic analysis demonstrated noteworthy differences between an offloaded environment and 1‐g, as would be expected. The analysis showed a trend to change the ambulation style in an offloaded environment to a rolling‐loping walk (resembling crosscountry skiing) with increased swing time. This ambulation modification, particularly in the ARGOS, indicated that the relative kinetic energy of the subject was increased, on average, per the static body weight compared to the 1‐g condition. How much of this was influenced by the active offloading of the ARGOS system is unknown.

Cowley, Matthew↗

Patterns of bird and bat migration along Lake Michigan and Lake Huron coastal areas

Wind energy is becoming a more important and common source of renewable energy. Coastal areas produce high winds and as a result more wind farms are being established along coastlines. These same coastal areas are also potentially migration corridors, as birds and bats avoid the risks of crossing open water (e.g. encountering inclement weather or predators without adequate cover in close proximity). Bats and birds that migrate along shorelines developed with wind turbines are at risk for turbine collisions and related fatalities (i.e., barotrauma). We examined the fall migration of bats and night flying birds at 5 sites along the Great Lakes shorelines. After standardizing habitat types, we specifically compared species use at 5 shoreline plots versus 5 plots 3 miles inland. We used an acoustic-radar sampling system between sunset and sunrise to capture species flight patterns, bird calls, and echolocative activity of bats. The radar sampling unit covered a 2-km radius, whereas the volume recorded by the acoustic unit varied by the frequency of the call. Our results showed that the flight activity of both bats and birds was highest at inland sites consistently across all sites. Acoustic activity of both bats and birds decreased over the fall migration period. Our data did not support the alternative hypothesis that the shoreline provides more intensely used fall migration corridors than inland areas for bats and night migrant birds. Our data suggest that shoreline areas may be less important as a travel corridor to bats and night-flying birds than more inland areas. Further studies should be conducted to determine if this pattern is consistent among temporal and spatial variables and consistent for further offshore. Future conservation efforts may need to critically consider inland areas in efforts to reduce risk from wind turbine fatalities. By learning the migratory habits of bats and birds, specifically whether they are using the coastline, inland pathways, or offshore routes, wind energy developers can significantly reduce negative impacts to bats and birds by siting wind turbines in non-migratory areas.

17 WIND ENERGY↗

Towards Surrogate Modeling of Subgrid Turbulent Transport for 3D Radiative Hydrodynamic Simulations of the Quiet Sun

In this work, we investigate the use of deep learn-ing techniques as surrogate models, to enhance the estimationof effects of subgrid turbulent transport for 3D radiatuve hy-drodynamic simulations of the quiet Sun. We develop two dis-tinct 3D Convolutional Neural Networks (3DCNNs) to capturespatio-temporal dependencies in 3D velocity fields, leveragingdifferent activation functions and architectural designs. Thesemodels integrate both averaged velocity vector components andscalar features such as plasma density to enhance predictionaccuracy. Additionally, a Multilayer Perceptron (MLP) modelis employed to approximate complex nonlinear relationships,offering a comparison in performance between convolutionaland fully connected architectures. Logarithmic transformationis applied to the targets to handle heavily skewed data, im-proving model performance. All models are compared againsta physics-based Gradient Model. Results show that the 3DCNNmodels excel at approximating Reynolds stress tensors, makingthem a candidate for assisting in producing reduced resolutionsimulations, and thereby reducing computational overheadwhile maintaining higher accuracy than the baseline. Thesefindings demonstrate the potential of deep learning, particu-larly CNNs, to advance scalable and accurate simulations ofsolar dynamics, offering a promising alternative to traditionalturbulence models.

Heliophysics↗

Reconceptualizing public participation in environmental assessment as EA civics

Notwithstanding the considerable attention placed on creating meaningful opportunities for public participation in environmental assessment (EA), many participants and those who have reviewed participation processes often find practice sorely wanting. This reality stands in stark juxtaposition to future environmental governance needs, which will require increased openness, deliberation and transdisciplinary knowledge in order to deal with environmental change that is ever more uncertain, complex and conflictual. In this paper, our purpose was to consider how to meet those needs through reconceptualizing public participation as EA civics, founded on an active citizen base, deliberative in nature and orientated toward learning. We do this through developing a new conceptual model of next generation participation processes that is relevant at multiple spatial scales and institutional levels, is applicable to the entire assessment cycle and spans temporal scales through feedback loops. Our EA civics model builds on the “civics approach” to environmental governance and “action civics” by extending their core ideas to participation in EA. We did this by conducting an integrative literature review (including numerous papers we have contributed over the years) and reflecting on our own experiences as EA participants. We apply current thinking on public participation design to our EA civics conceptualization and highlight important design features that have received scant attention. We conclude that EA civics holds promise for fairer and more robust participation processes if all aspects of the model are considered and the actions related to each are implemented. - Highlights: • Consideration of the ‘civics approach’ and ‘action civics’ in an EA context • Conceptualization of public participation as EA civics • Reflection on the EA civics as a model of participation suitable for next generation assessment.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗

Distributed renewable energy resource trust metrics and secure routing

To ensure reliable and predictable service in the electrical grid between distributed renewable distributed energy resources (DERs) it is important to gauge the level of trust present within critical components and DER aggregators (DERAs). Although trust throughout a smart grid is temporal and dynamically varies according to measured states, it is possible to accurately formulate communications and service level strategies based on such trust measurements. Utilizing an effective set of machine learning and statistical methods, it is shown that establishment of trust levels between DERAs using behavioral pattern analysis is possible. Further, it is also shown that the establishment of such trust can facilitate simple secure communications routing between DERAs. Providing secure routing between DERAs enables a grid operator to maintain service level agreements to its customers, reduce the attack surface and increase operational resiliency.

97 MATHEMATICS AND COMPUTING↗

Power generation forecasting for solar plants based on Dynamic Bayesian networks by fusing multi-source information

A Dynamic Bayesian network (DBN) model for solar power generation forecasting in solar plants is proposed in this paper. The key idea is to fuse sensor data, operational indicators, meteorological data, lagged output power information, and model errors for more accurate short-term (e.g., hours) and mid-term (e.g., days to weeks) power generation forecasting. The proposed DBN augments automated data-driven structure learning with expert knowledge encoding using continuous and categorical data given constraints to represent causal relationships within a solar inverter system. Additionally, an error compensation mechanism is proposed to capture temporal fluctuation. The effectiveness of the DBN on solar power generation forecasting was evaluated by rolling window analysis with one-year testing data collected from a local solar plant. The proposed DBN is compared with four state-of-art methods including support-vector regression (SVR), k-nearest neighbors (kNN), artificial neural network (ANN), and long short-term memory (LSTM) models. The result show that the proposed DBN achieves better accuracy in general, and it is not as data-hungry as some neural network-based models. The proposed DBN is also shown to have robust and consistent forecasting power with different forecasting horizons. The accuracy is 92% - 95% from one hour to one week ahead forecasting.

14 SOLAR ENERGY↗

Field Calibration Techniques used to Characterize the Radiometric Stability of the GEO-CAPE Airborne Simulator (GCAS)

The GEOstationary Coastal and Air Pollution Events (GEO-CAPE) Airborne Simulator (GCAS) was developed at NASA’s Goddard Space Flight Center (GSFC) and has flown in multiple field campaigns to perform mapping of the regional-scale EPA criteria pollutants nitrogen dioxide, ozone, and formaldehyde. GCAS will also participate invalidation campaigns for NASA’s Tropospheric Emissions: Monitoring POllution (TEMPO) mission and the Korean Geostationary Environment Monitoring Spectrometer (GEMS) mission, both scheduled to launch in the early 2020s. GCAS houses two commercial Offner-type grating spectrometers that measure backscattered solar spectral radiance from the near-ultraviolet to near-infrared at high spatial resolution (typically 250 meters at 8.5 kilometer altitude). These radiances are used to retrieve spatial and temporal distributions of trace gases relevant to the boundary layer and free tropospheric atmospheric chemistry cycles. In this paper, we describe the field calibration techniques employed to characterize the spectral and temporal radiometric stability of the system during its most recent deployment in the 2018 Long Island Sound Trace Ozone Study (LISTOS) field campaign. Overall measurement uncertainty, retrieval impacts, and lessons learned for future deployments will also be described.

NASA’s Tropospheric Emissions: Monitoring POllutio↗