Search NASA⌕ Search

SEARCH · Search NASA

Results for “Machine Learning Models”

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 739 records · Page 41

A generalizable machine learning approach to predict land surface temperature

Monitoring of land surface and atmospheric states is highly reliant on satellite data. Traditionally, data products are generated using carefully tuned and validated algorithms for low-earth orbit (LEO) sensors. However, the emerging constellation of geostationary (GEO) sensors contributes global, high temporal resolution observations which can better capture the diurnal variability of key observables like land surface temperature (LST). Using high performance computing and datasets from the NASA Earth Exchange, we exploit co-located, co-temporal observations from LEO and GEO satellites to develop a deep learning-based method for sensor-to-sensor algorithm emulation. Our model is trained on GOES-16 thermal bands to predict MODIS Terra LST and achieves a validation error <2K. Further, application of the model to unseen times of day and a second GEO sensor observing an unseen spatial domain demonstrate the generalization of the deep learning model across space, time and spectra. We anticipate that the synergies between a variety of active orbit configurations can be used to accelerate application of existing algorithms to new datasets.

Kate Marie Duffy↗

Finite-difference simulation and visualization of elastodynamics in time-evolving generalized curvilinear coordinates

Modeling and simulation of free and forced structural vibrations is essential to an overall structural health monitoring capability. In the various embodiments, a first principles finite-difference approach is adopted in modeling a structural subsystem such as a mechanical gear by solving elastodynamic equations in generalized curvilinear coordinates. Such a capability to generate a dynamic structural response is widely applicable in a variety of structural health monitoring systems. This capability (1) will lead to an understanding of the dynamic behavior of a structural system and hence its improved design, (2) will generate a sufficiently large space of normal and damage solutions that can be used by machine learning algorithms to detect anomalous system behavior and achieve a system design optimization and (3) will lead to an optimal sensor placement strategy, based on the identification of local stress maxima all over the domain.

Kaul, Upender K.↗

An Automated Approach to Labelling Datasets in Earth Science Publications

NASA Data Active Archive Centers, orDAACs, ingest, store, and distribute dataacquired from satellites, ground systems as well asreanalysis models. Many authors use this datain their research. However, most of the datasets usedin Earth Science Publications are not citedcorrectly or not cited at all. Thus, there is no directlink between the datasets used and thescientific publications which reference them. Thisleads to issues with reproducibility of theresults, attribution of the research results, anddiscovery of new datasets. This project began byexploring various methods of automatically labellingGoddard Earth Sciences Data andInformation Services Center (GES DISC) datasets usingSupervised Machine Learning and EarthData Search Common Metadata Repository (CMR) queries.The ultimate goal was to create alibrary of citations that utilized automated citationlabeling to directly link the researchpublications to the data they use. Supervised MachineLearning approaches struggled due to thelimited amount of labelled training data to learnfrom. Increasing the volume of training data isdifficult as it requires subject matter experts todevote time to manually reviewing journalarticles and determining the datasets used. The CMRqueries were inconsistent because theunderlying metadata is continuously being updated.Thus, it is hard to generalize theeffectiveness of the CMR results as they are dependenton the internal state of CMR. Theseapproaches helped inform the decision to transitionthe project into using a Knowledge Graph.Another key aspect of this project focused on theautomated extraction of features (platform,instrument, variables, etc) and explicit citationsfrom within Earth Science Publications. Theseautomated extractions were used to classify researchpapers based on their platform/instrumentcouples. This information was input into the CitationManagement System for GES DISC. Theseplatform/instrument couples also provide an additionalfacet that can be searched on the GESDISC website.

Edward Jahoda↗

Machine learning for Deep Space Network antenna motions detection

Highly stable frequency and timing standards are essential for deep-space missions and radio science. At the NASA Deep Space Network (DSN), these standards are distributed through a network of underground fiber cables to support several Goldstone antennas. Independently developed frequency-measuring instruments generate tremendous quantities of data to monitor and validate the antennas’ stringent frequency requirements. In this paper, we propose a lightweight processing tool capable of detecting disturbances on the frequency signal caused by DSN antenna motions. Our training data is sampled from the movement log of the antenna of interest and the generated data from the fiber optic metrology instrument linked to the antenna. We demonstrate that a convolutional neural network (CNN) model can achieve high accuracies on classifying instances of antenna movements and is an effective predictor when used iteratively on longer, variable stretches of metrology data. The simplicity, low training cost, and high accuracies of our model strongly suggest its efficacy in identifying and troubleshooting frequency disturbances caused by the antenna.

Yi, Lin↗

Flight Trajectory Prediction Based on Hybrid-Recurrent Networks

The development of future technologies for the National Airspace System (NAS) will be reliant on a new communications infrastructure capable of managing the limited available spectrum for communications among aircraft and ground systems. Emerging approaches to autonomous allocation of aviation spectrum mostlyrely on machine learning techniques, where 4D (longitude, latitude, altitude, time) trajectory prediction is an important data input to enable real-time resource allocation. This study explores and evaluates effective data sources and deep recurrent neural network techniques when determining flight trajectories. Specifically, data are collected and evaluated in a 100-day and 14-day period. Sources of data include NASA Sherlock Data Warehouse, MIT Lincoln Labs Corridor Integrated Weather Service (CIWS), and assorted NOAA weather datasets. Deep learning models for 4D predictions all utilize a hybrid-recurrent technique. A baseline model is considered via the convolutional-LSTM design from the existing literature. The modified design considers Gated Recurrent Units (GRU), Independently Recurrent Neural Networks (IndRNN), and stand-alone self-attention layers. Results indicatethe effectiveness of LSTM and GRUcells for state-of-the-art data processing (interpolation). Additionally, GRUs may be quickly trained with limited data, allowing for exacting improvements with optimizer selection. Attention mechanisms provide notable performance improvements to convolutional layers and may extend dimensional capabilities of a learning model. Finally, NOAA measurements provide only a supplemental value, requiring support from tailored measurements for Air Traffic Management.

Nathan Schimpf↗

Advancing Open Source Science Initiatives Through Public-Private Partnerships

Collaboration is fundamental to advancing open science within the science community. With the recent developments in technology and research, the establishment of formal partnerships between the private sector and government agencies are needed to bridge the knowledge gaps and expedite the time to actionable science. NASA’s Interagency Implementation and Advanced Concepts Team (IMPACT) seeks to address this challenge by establishing non-reimbursable Space Act Agreements with industry leaders in cloud computing, artificial intelligence (AI) and machine learning. The purpose of these agreements is to advance open source science initiatives in the areas of data discovery, access and use of high value NASA science data sets on the cloud. As well as, jointly work on common research problems to accelerate the development and adoption of new AI technologies. Current success stories include co-locating NASA datasets from multiple science disciplines on one platform using Amazon Web Services Open Data Registry, developing AI Foundation Models for Science with IBM and co-hosting training workshops and tutorials for the science community aimed at providing hands-on experience with using NASA data and AI models on the cloud. In summary, we will present an overview of our partnerships supporting open source science initiatives, describe current activities and lessons learned that may be useful to others considering similar partnerships with the private sector.

Elizabeth Fancher↗

Natural Language Processing (NLP) Analysis of NOTAMs for Air Traffic Management Optimization

With new emerging technologies in the field of NLP, we explore their applications to digitize and analyze heritage Air Traffic Management (ATM) documents for planning and optimizing airspace operations. Specifically, this research focuses on harvesting semi-structured or un-structured information contained in Notices to Airmen (NOTAMs). Using NLP and other advanced data analytics, we will construct a data-driven framework which facilitates finding language patterns and the use of pretrained language models for classification and extraction of useful airspace constraints and restrictions. These may lead to tools that assist airspace users in understanding the constraints more efficiently, contributing to better route planning and safer execution. This paper explores three workflows entailing different NLP tasks. First, unsupervised techniques like word embedding and topic modeling are used for pattern finding and document classification. Second, a dataset is created by extracting information from the semi-structured NOTAM format as metadata for categorizing, visualizing, and extracting key entities driving NOTAM content. Third, modern pre-built deep learning based transformer models such as BERT, RoBERTa, and XLNet are evaluated on the question answering task, an even more robust approach to information extraction, as well as their respective fine-tuning tasks. In this work we include various performance metrics for the trained models to evaluate both accuracy and precision and we show that the models can be generalized for their respective tasks. The research work developed shows promise in uncovering trends in digital NOTAMs in the NAS and also offers a new framework for digitizing and inferring insights from free-form legacy NOTAMs, that are yet to be digitized. Video is an mp4 download, with a play time of 9 min 35 secs.

Natural Language Processing↗

Novel Hourly-Resolved Global Cloud Property Composite from Operational Satellites Imagers

Numerous applications in satellite remote sensing of surface properties, atmospheric state, composition, and radiation require accurate knowledge of the location and characteristics of clouds. Operational satellite imager radiances are valuable for cloud detection and for deriving many different physical parameters that can be used for a variety of weather, aviation, and energy applications. The NASA Satellite ClOud and Radiation Property retrieval System (SatCORPS) applies a suite of algorithms to meteorological satellite data to provide cloud properties, radiative fluxes and other parameters on a global scale. This paper describes a new global high-resolution dataset of cloud properties made available for community use that is constructed from analyses of a constellation of meteorological satellite imagers. Data taken from Meteosat-8/9 and -11, Himawari-8/9, GOES-16, and -17/-18, Aqua, Terra, Suomi-NPP and NOAA-20 are processed and composited on a 3-km grid to provide hourly global coverage. A historical multi-year dataset is available to serve various needs including modeling challenges related to cloud evaluations and parameterizations. Near real-time data products are also currently available between 60N and 60S. Efforts are underway to operationalize polar orbiting satellite cloud detection methods for low-latency applications over polar regions. The cloud detection and retrieval algorithms have been developed over many years to support NASA weather and climate programs such as the Clouds and Earth’s Radiant Energy System (CERES). To improve the utility of the data products, machine learning and other innovative methods are applied in various ways to help minimize data product uncertainties under the most challenging conditions and to improve their consistency at all times of day. A brief description of the methods highlighting the unique aspects of the SatCORPS data products will be presented along with information on their status and availability.

SatCORPS↗

Enhancing Metal Additive Manufacturing Training with the Advanced Vision Language Model: A Pathway to Immersive Augmented Reality Training for Non-Experts

This paper introduces an innovative training system for the Renishaw AM400 metal printer, leveraging the synergy of the advanced Vision Language Model (VLM) with Augmented Reality (AR) within the Digital Twins (DT) framework. Aimed at overcoming the limitations of conventional training methods in metal additive manufacturing (AM), our system integrates AR to provide an immersive learning environment, enhancing the real-world experience with interactive digital overlays. The core of the system lies in its use of VLM, which, pre-trained on diverse datasets, excels in processing multi-modal data, thereby offering nuanced and contextually relevant guidance for trainees. Key experiments demonstrate the system’s effectiveness, particularly highlighting the usage of VLM as an Artificial Intelligence (AI) agent to integrate external tools like YOLO-v7 for valve state classification and CRAFT for control panel text recognition. This approach significantly improves recognition accuracy, operational understanding, and human–machine interaction, especially for non-expert users, making complex metal AM operations more accessible. The research not only showcases the potential of AR and VLM in industrial training but also sets a new standard for smart manufacturing practices, indicating broader applications in various industrial domains.

Metal additive manufacturing↗

Future Model-Based Systems Engineering Vision and Strategy Bridge for NASA

A vision for the future of model-based systems engineering (MBSE) at NASA in 2029 and a strategy bridge towards that future are presented. Strategic thinking and leading change concepts were used to analyze reports and presentations on global trends and visionary thinking about the future of systems and digital engineering. The context, strategic time horizon, stakeholders, strategic challenges, strategic advantages, driving forces, and opportunities were considered. The analysis resulted in a future vision of MBSE that shows what NASA systems engineers and digital machines will do to perform rapid, extraordinary, and unprecedented missions. The NASA systems engineer, in this future vision, works with a global project team in a virtual and collaborative environment, engineers the system, and uses digital approaches as the routine and default way of working. The digital machines provide data-driven and automated mission designs; have a backbone of program and project management, systems engineering, and product life-cycle management; and are a knowledge-sharing infrastructure. The NASA systems engineer and the systems engineering team are envisioned to use digital machines to plan and perform rapid exploration missions, develop a digital twin that lasts across the life cycle, and develop enduring and adaptable systems. NASA has an engineering enterprise and a life-cycle management framework that endure, adapt, and respond. A strategy bridge based on the Baldrige Criteria for Performance Excellence Framework and lessons learned from a recent MBSE initiative illuminates a way forward from today to this desired future. The bridge lays out a strategy for leaders and recommends investments of today for immediate benefits and for benefits in 2029.

model-based systems engineering, digital engineeri↗

Modeling a Miniaturized Scanning Electron Microscope Focusing Column - Lessons Learned in Electron Optics Simulation

This presentation discusses work done to assess the design of a focusing column in a miniaturized Scanning Electron Microscope (SEM) developed at the NASA Marshall Space Flight Center (MSFC) for use in-situ on the Moon-in particular for mineralogical analysis. The MSFC beam column design uses purely electrostatic fields for focusing, because of the severe constraints on mass and electrical power consumption imposed by the goals of lunar exploration and of spaceflight in general. The resolution of an SEM ultimately depends on the size of the focused spot of the scanning beam probe, for which the stated goal here is a diameter of 10 nanometers. Optical aberrations are the main challenge to this performance goal, because they blur the ideal geometrical optical image of the electron source, effectively widening the ideal spot size of the beam probe. In the present work the optical aberrations of the mini SEM focusing column were assessed using direct tracing of non-paraxial rays, as opposed to mathematical estimates of aberrations based on paraxial ray-traces. The geometrical ray-tracing employed here is completely analogous to ray-tracing as conventionally understood in the realm of photon optics, with the major difference being that in electron optics the lens is simply a smoothly varying electric field in vacuum, formed by precisely machined electrodes. Ray-tracing in this context, therefore, relies upon a model of the electrostatic field inside the focusing column to provide the mathematical description of the "lens" being traced. This work relied fundamentally on the boundary element method (BEM) for this electric field model. In carrying out this research the authors discovered that higher accuracy in the field model was essential if aberrations were to be reliably assessed using direct ray-tracing. This led to some work in testing alternative techniques for modeling the electrostatic field. Ultimately, the necessary accuracy was attained using a BEM/Fourier series hybrid approach. The presentation will give background remarks about the MSFC mini Lunar SEM concept and electron optics modeling, followed by a description of the alternate field modeling techniques that were tried, along with their incorporation into a ray-trace simulation. Next, the validation of this simulation against commercially available software will be discussed using an example lens as a test case. Then, the efficacy of aberration assessment using direct ray-tracing will be demonstrated, using this same validation case. The discussion will include practical error checks of the field solution. Finally, the ray-trace assessment of the MSFC mini Lunar SEM concept will be shown and discussed. The authors believe this presentation will be of general interest to practitioners of modeling and simulation, as well as those with a general optics background. Because electron optics and photon optics share many basic concepts (e.g., lenses, images, aberrations, etc.), the appeal of this presentation need not be restricted to just those interested in charged particle optics.

Modeling Miniaturizing Scanning↗

Formal Validation of Fault Management Design Solutions

The work presented in this paper describes an approach used to develop SysML modeling patterns to express the behavior of fault protection, test the model's logic by performing fault injection simulations, and verify the fault protection system's logical design via model checking. A representative example, using a subset of the fault protection design for the Soil Moisture Active-Passive (SMAP) system, was modeled with SysML State Machines and JavaScript as Action Language. The SysML model captures interactions between relevant system components and system behavior abstractions (mode managers, error monitors, fault protection engine, and devices/switches). Development of a method to implement verifiable and lightweight executable fault protection models enables future missions to have access to larger fault test domains and verifiable design patterns. A tool-chain to transform the SysML model to jpf-Statechart compliant Java code and then verify the generated code via model checking was established. Conclusions and lessons learned from this work are also described, as well as potential avenues for further research and development.

Statechart↗

Serious Gaming for Building a Basis of Certification via Trust and Trustworthiness of Autonomous Systems

Autonomous systems governed by a variety of adaptive and nondeterministic algorithms are being planned for inclusion into safety-critical environments, such as unmanned aircraft and space systems in both civilian and military applications. However, until autonomous systems are proven and perceived to be capable and resilient in the face of unanticipated conditions, humans will be reluctant or unable to delegate authority, remaining in control aided by machine-based information and decision support. Proving capability, or trustworthiness, is a necessary component of certification. Perceived capability is a component of trust. Trustworthiness is an attribute of a cyber-physical system that requires context-driven metrics to prove and certify. Trust is an attribute of the agents participating in the system and is gained over time and multiple interactions through trustworthy behavior and transparency. Historically, artificial intelligence and machine learning systems provide answers without explanation - without a rationale or insight into the machine “thinking”. In order to function as trusted teammates, machines must be able to explain their decisions and actions. This transparency is a product of both content and communication. NASA’s Autonomy Teaming & TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project seeks to build a basis for certification of autonomous systems via establishing metrics for trustworthiness and trust in multi-agent team interactions, using AI (Artificial Intelligence) explainability and persistent modeling and simulation, in the context of mission planning and execution, with analyzable trajectories. Inspired by Massively Multiplayer Online Role Playing Games (MMORPG) and Serious Gaming, the proposed ATTRACTOR modeling and simulation environment is similar to online gaming environments in which player (aka agent) participants interact with each other, affect their environment, and expect the simulation to persist and change regardless of any individual agent’s active participation. This persistent simulation environment will accommodate individual agents, groups of self-organizing agents, and large-scale infrastructure behavior. The effects of the emerging adaptation and coevolution can be observed and measured to building a basis of measurable trustworthiness and trust, toward certification of safety-critical autonomous systems.

Allen, B. Danette↗

Harmonized Sentinel-1 SAR Global River Geometry and Inundation Database

Satellite-based observations on river geometries are sporadic in time, space, or both. Most satellite-based surface water maps, river widths, water surface elevations (WSE), slopes, and bathymetry are asynchronized in time and space. The current configuration of satellites such as Sentinel-6 measured the WSE but is missing the river width, slopes, and depths. To advance hydrological sciences research, there is a need to produce a harmonized time series of river geometry data of non-SWOT satellites in partnership with the upcoming SWOT mission. The SWOT satellite will measure river width, height, and slope but missing river depth measurements in space and time. Further, none of these current satellites measure the WSE, river width, and slopes synchronously. In this work, we use the Sentinel-1 SAR satellite data archive from 2015 to the present to create a global river width and surface water database at the reach scale. A modified version of the Sentinel SAR surface water classification algorithm from ASF is used to quantify the surface water extent on the stream approximately every six days (at the equator) at 10m spatial resolution globally. This 10m water mask is fed into a workflow to quantify the river widths, surface water inundations, slopes, and synthetic bathymetry in SWORD (SWOT River Database) stream networks. A Satellite HAND is used to address the cloud obscured surface water observations using a trained machine learning algorithm. We use WSE derived from the Global Water Monitor from NASA GSFC, Hydroweb from LEGOS, and ICESat-2 to harmonize the WSE observation. And Landsat-8/9 and Sentinel-2 water observations to fill the gaps in the Sentinel-1 SAR database. We use Congo River Basin as a test case where we have more than 500 radar altimetry-based WSE, continuous series of Sentinel-1, ICESat-2, Landsat-8/9, and Sentinel-2 observations. A Congo River hydrologic model is used to generate the streamflow discharge. The satellite observed river reaches are assimilated with the stream flows computed by the routing models. And the downstream reaches in the river network without satellite observations get optimized for discharge/river geometry at each observation cycle. Our final product is a harmonized river geometry dataset (reach's water extent, WSE, slope, synthetic bathymetry) for Congo Basin's SWORD reaches.

Chandana Gangodagamage↗

Vegetation Greening Mitigates the Impacts of Increasing Extreme Rainfall on Runoff Events

Future flood risk assessment has primarily focused on heavy rainfall as the main driver, with the assumption that projected increases in extreme rain events will lead to subsequent flooding. However, the presence of and changes in vegetation have long been known to influence the relationship between rainfall and runoff. Here, we extract historical (1850–1880) and projected (2070–2100) daily extreme rainfall events, the corresponding runoff, and antecedent conditions simulated in a prominent large Earth system model ensemble to examine the shifting extreme rainfall and runoff relationship. Even with widespread projected increases in the magnitude (78% of the land surface) and number (72%) of extreme rainfall events, we find projected declines in event-based runoff ratio (runoff/rainfall) for a majority (57%) of the Earth surface. Runoff ratio declines are linked with decreases in antecedent soil water driven by greater transpiration and canopy evaporation (both linked to vegetation greening) compared to areas with runoff ratio increases. Using a machine learning regression tree approach, we find that changes in canopy evaporation is the most important variable related to changes in antecedent soil water content in areas of decreased runoff ratios (with minimal changes in antecedent rainfall) while antecedent ground evaporation is the most important variable in areas of increased runoff ratios. Our results suggest that simulated interactions between vegetation greening, increasing evaporative demand, and antecedent soil drying are projected to diminish runoff associated with extreme rainfall events, with important implications for society.

soil moisture↗

Communicating Metrics of Land Surface Temperature Variability Using Multi-sensor Machine Learning

Land surface temperature (LST) is a key climate observable used to detect changes in the Earth’s surface energy budget that influence carbon and water cycles. Land surface temperature exhibits strong diurnal variability, which geostationary satellites can observe at scale thanks to their temporal resolution. Due to anthropogenic climate and land use changes, the surface energy balance has been considerably modified and may be described by changes in diurnal temperature range and extremes. Using high performance computing and datasets from the NASA Earth Exchange, we exploit co-located, co-temporal observations from low-earth orbit (LEO) and geostationary (GEO) sensors to develop a deep learning-based method for LEO-to-GEO algorithm emulation. Our model is trained to predict MODIS Terra LST from GOES-16 thermal bands and achieves validation error <2K. Application of the model to unseen times of day (observed by MODIS Aqua) and a new GEO sensor (Himawari-8) observing an unseen spatial domain, demonstrate the generalization of the deep learning model across space, time and spectra. Further, time series clustering approaches are examined with the objective of identifying key indicators of change in diurnal cycling and extremes on a continental scale. Communicating LST variability observed by geostationary satellites can have impacts in multiple disciplines, from understanding of snow, vegetation and soil dynamics, to recognizing trends in heat events relevant to human health.

Kate Duffy↗

Initial Analysis of and Predictive Model Development for Weather Reroute Advisory Use

In response to severe weather conditions, traffic management coordinators specify reroutes to route air traffic around affected regions of airspace. Providing analysis and recommendations of available reroute options would assist the traffic management coordinators in making more efficient rerouting decisions. These recommendations can be developed by examining historical data to determine which previous reroute options were used in similar weather and traffic conditions. Essentially, using previous information to inform future decisions. This paper describes the initial steps and methodology used towards this goal. A method to extract relevant features from the large volume of weather data to quantify the convective weather scenario during a particular time range is presented. Similar routes are clustered. A description of the algorithm to identify which cluster of reroute advisories were actually followed by pilots is described. Models built for fifteen of the top twenty most frequently used reroute clusters correctly predict the use of the cluster for over 60 of the test examples. Results are preliminary but indicate that the methodology is worth pursuing with modifications based on insight gained from this analysis.

machine learning↗

Statistical learning framework for safety and failure analysis of a DNN-based autonomous aircraft system

Deep Neural Networks (DNNs) and Machine Learning technology is increasingly used for safety-critical applications in the Aerospace domain. To ensure safe operations, the DNN and the system must undergo rigorous verification and validation, including advanced statistical analyses. Performance and safety of the DNN and system behavior must not only be analyzed for the nominal case, but under numerous off-nominal and failure cases. In this paper we will describe how our statistical learning framework SYSAI can efficiently perform such analyses using the tool’s unique combination of advanced learning modeling and statistical analysis techniques. SYSAI can effectively explore the high-dimensional state and failure space of the system under test; geometrical shape detection of safety regions and boundaries support explainability of the results to the designer. In this paper, we report experiments and results obtained with a vision-based DNN control system (ACT) that is capable of autonomously steering an aircraft down a runway.

Yuning He↗