SEARCH · Engineering Papers

Results for “training data quality”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

All sources NASA NTRS DOE OSTI

NASA NTRS2023

A Global Land Cover Training Dataset From 1984 to 2020

State-of-the-art cloud computing platforms such as Google Earth Engine (GEE) enable regional-to-global land cover and land cover change mapping with machine learning algorithms. However, collection of high-quality training data, which is necessary for accurate land cover mapping, remains costly and labor-intensive. To address this need, we created a global database of nearly 2 million training units spanning the period from 1984 to 2020 for seven primary and nine secondary land cover classes. Our training data collection approach leveraged GEE and machine learning algorithms to ensure data quality and biogeographic representation. We sampled the spectral-temporal feature space from Landsat imagery to efficiently allocate training data across global ecoregions and incorporated publicly available and collaborator-provided datasets to our database. To reflect the underlying regional class distribution and post-disturbance landscapes, we strategically augmented the database. We used a machine learning-based cross-validation procedure to remove potentially mis-labeled training units. Our training database is relevant for a wide array of studies such as land cover change, agriculture, forestry, hydrology, urban development, among many others.

Radost Stanimirova↗

NASA NTRSDate not supplied

Machine Learning Based Crater Detection for Terrain Relative Navigation

As Lunar exploration continues to become more commonplace, reliable methods of precise Terrain Relative Navigation (TRN) are needed. While there are many TRN techniques available, one that has received increased interest in the past few years is that of crater based navigation. Crater based navigation has numerous benefits, including being a human recognizable feature (important for crewed missions), as well as the fact that craters are often possible hazards that need to be detected and avoided. The use of crater based navigation has been limited however. This has been due to the difficulty of running such algorithms on board a spacecraft, as well as the difficulty in procuring large amounts of the required training data. This paper presents a new rendering tool for generating large amounts of high quality training data. It then looks at two recently developed machine learning techniques for crater detection and crater identification in real-time on near-future space hardware.

computer vision↗

NASA NTRS2011

Integrating Machine Learning into a Crowdsourced Model for Earthquake-Induced Damage Assessment

On January 12th, 2010, a catastrophic 7.0M earthquake devastated the country of Haiti. In the aftermath of an earthquake, it is important to rapidly assess damaged areas in order to mobilize the appropriate resources. The Haiti damage assessment effort introduced a promising model that uses crowdsourcing to map damaged areas in freely available remotely-sensed data. This paper proposes the application of machine learning methods to improve this model. Specifically, we apply work on learning from multiple, imperfect experts to the assessment of volunteer reliability, and propose the use of image segmentation to automate the detection of damaged areas. We wrap both tasks in an active learning framework in order to shift volunteer effort from mapping a full catalog of images to the generation of high-quality training data. We hypothesize that the integration of machine learning into this model improves its reliability, maintains the speed of damage assessment, and allows the model to scale to higher data volumes.

crowdsourcing↗

NASA NTRS2009

Developing Dual Polarization Applications For 45th Weather Squadron's (45 WS) New Weather Radar: A Cooperative Project With The National Space Science and Technology Center (NSSTC)

A new weather radar is being acquired for use in support of America s space program at Cape Canaveral Air Force Station, NASA Kennedy Space Center, and Patrick AFB on the east coast of central Florida. This new radar includes dual polarization capability, which has not been available to 45 WS previously. The 45 WS has teamed with NSSTC with funding from NASA Marshall Spaceflight Flight Center to improve their use of this new dual polarization capability when it is implemented operationally. The project goals include developing a temperature profile adaptive scan strategy, developing training materials, and developing forecast techniques and tools using dual polarization products. The temperature profile adaptive scan strategy will provide the scan angles that provide the optimal compromise between volume scan rate, vertical resolution, phenomena detection, data quality, and reduced cone-of-silence for the 45 WS mission. The mission requirements include outstanding detection of low level boundaries for thunderstorm prediction, excellent vertical resolution in the atmosphere electrification layer between 0 C and -20 C for lightning forecasting and Lightning Launch Commit Criteria evaluation, good detection of anvil clouds for Lightning Launch Commit Criteria evaluation, reduced cone-of-silence, fast volume scans, and many samples per pulse for good data quality. The training materials will emphasize the appropriate applications most important to the 45 WS mission. These include forecasting the onset and cessation of lightning, forecasting convective winds, and hopefully the inference of electrical fields in clouds. The training materials will focus on annotated radar imagery based on products available to the 45 WS. Other examples will include time sequenced radar products without annotation to simulate radar operations. This will reinforce the forecast concepts and also allow testing of the forecasters. The new dual polarization techniques and tools will focus on the appropriate applications for the 45 WS mission. These include forecasting the onset of lightning, the cessation of lightning, convective winds, and hopefully the inference of electrical fields in clouds. This presentation will report on the results achieved so far in the project.

Roeder, W.P.↗

NASA NTRSDate not supplied

Curating AI-Ready Datasets for Equity and Environmental Justice: A Data-Centric AI Case Study

An equitable and environmentally just community is essentialin order to avoid disproportionate burden borne by vulnerablecommunities. This need becomes pressing in the aftermathof an extreme event such as disaster or hazard when it is diffi-cult for the governing bodies to implement resource allocationas per the need. Artificial Intelligence (AI) algorithms canhelp surface Equity and Environmental Justice (EEJ) issueswhen trained on EEJ datasets. However, curating AI-readyEEJ training datasets is challenging due to differences in fac-tors such as heterogeneity, resolution, modality, and level ofexpertise in labeling. Additionally, EEJ issues involve sensi-tive information where uncertainties and errors could degradethe performance of AI algorithms. For eg. Error in seasonalcrop yield information can highly affect the prediction of an-nual crop yield. To address these challenges, Data-centricAI (DCAI) methods are employed, which enhance AI algo-rithm performance even with limited training samples. DCAIprioritizes data quality, thereby reducing the adverse effectsof uncertainties and errors during the model training process.This research proposes a novel dataset and benchmark for an-alyzing the effect of the Maui Wildfire of 2023 for Equityand Environmental Justice (EEJ) issues. The proposed datasetaligns with the concepts of DCAI such as annotation quality,data preprocessing, privacy, feature engineering, governanceand provenance. We firmly believe that the proposed datasetwould lay a foundation to implement robust and reliable mod-ern AI algorithms for addressing EEJ issues.

Paridhi Parajuli↗

NASA NTRSDate not supplied

FloodPlanet: High-Resolution Commercial Imagery for Training and Validation of Deep Learning-Based Models of Inundation Extent

Flooding events are becoming increasingly frequent worldwide and are known to cause extensive damage. Public optical and radar satellite imagery can be used to detect large areas of inundation in rural areas, however, long revisit times and coarse spatial resolution limit applications for short-lived events and urban areas. Commercial constellations such as those operated by Planet offer increased spatial and temporal resolution and can supplement mapping efforts to provide more information to disaster response, relief, and mitigation efforts. Deep learning requires high quality labeled data for training across coincident sensors. The FloodPlanet dataset presented here contains labeled surface water for 18 events across the world based on Planetscope imagery with coincident Harmonized Landsat Sentinel-2 ( HLS) or Sentinel-1 and builds upon the previously existing Sen1Floods11, xBD, and NASA Sentinel-1 datasets. Sen1Floods11 includes 4,831 512x512 pixel overlapping tiles of coincident Sentinel-1 and Sentinel-2 data observing 11 flood events across the world from 2017-2019. The dataset contains a combination of automated and hand-labeled surface water for use in training and validation of inundation modeling efforts. The xBD dataset identifies flood-damaged buildings and indicates the scale of damage to each (none, minor, moderate, and major) from four flood events which occurred in the United States, India, Nepal, and Bangladesh from the same time period. The NASA dataset contains hand-labeled water bodies observed in Sentinel-1 imagery during five flood events within the 2017-2019 period. The effort presented here utilizes observations from these previously investigated flood events to generate labels of surface water at the 3-5m spatial resolution provided by Planetscope and facilitate the comparison between public and commercial data. A data pipeline was built which uses clustering algorithms to pick the most suitable overlapping chips between the public data and PlanetScope data for manual labeling. Labels were created manually using NASA’s ImageLabeler tool and include areas of high- and low-confidence water. The high confidence designation is reserved for areas of open, unobstructed water while low confidence is used for areas of suspected water beneath vegetation, clouds, or cloud shadows. Expected to be released in late 2022, the FloodPlanet dataset will include tiled imagery with a unique ID for each 1024x1024 pixel tile, 7 bands of HLS data, and high- and low-confidence flood labels in both shapefile and tiff formats. The authors will follow Spatial Temporal Access Catalog (STAC) guidelines to release FloodPlanet on the Radiant Earth ML hub, which hosts public datasets for machine learning.

Alexander Melancon↗

NASA NTRS1980

Evaluation of SLAR and thematic mapper MSS data for forest cover mapping using computer-aided analysis techniques

Several possibilities were considered for defining the data set in which the same test areas could be used for each of the four different spatial resolutions being evaluated. The LARSYS CLUSTER was used to sort the vectors into spectral classes to reduce the within-spectral class variability in an effort to develop training statistics. A data quality test was written to determine the basic signal to noise characteristics within the data set being used. Because preliminary analysis of the LANDSAT MSS data revealed the presence of high cirrus clouds, other data sets are being sought.

Hoffer, R. M.↗

NASA NTRS2012

Generating Ground Reference Data for a Global Impervious Surface Survey

We are engaged in a project to produce a 30m impervious cover data set of the entire Earth for the years 2000 and 2010 based on the Landsat Global Land Survey (GLS) data set. The GLS data from Landsat provide an unprecedented opportunity to map global urbanization at this resolution for the first time, with unprecedented detail and accuracy. Moreover, the spatial resolution of Landsat is absolutely essential to accurately resolve urban targets such as buildings, roads and parking lots. Finally, with GLS data available for the 1975, 1990, 2000, and 2005 time periods, and soon for the 2010 period, the land cover/use changes due to urbanization can now be quantified at this spatial scale as well. Our approach works across spatial scales using very high spatial resolution commercial satellite data to both produce and evaluate continental scale products at the 30m spatial resolution of Landsat data. We are developing continental scale training data at 1m or so resolution and aggregating these to 30m for training a regression tree algorithm. Because the quality of the input training data are critical, we have developed an interactive software tool, called HSegLearn, to facilitate the photo-interpretation of high resolution imagery data, such as Quickbird or Ikonos data, into an impervious versus non-impervious map. Previous work has shown that photo-interpretation of high resolution data at 1 meter resolution will generate an accurate 30m resolution ground reference when coarsened to that resolution. Since this process can be very time consuming when using standard clustering classification algorithms, we are looking at image segmentation as a potential avenue to not only improve the training process but also provide a semi-automated approach for generating the ground reference data. HSegLearn takes as its input a hierarchical set of image segmentations produced by the HSeg image segmentation program [1, 2]. HSegLearn lets an analyst specify pixel locations as being either positive or negative examples, and displays a classification of the study area based on these examples. For our study, the positive examples are examples of impervious surfaces and negative examples are examples of non-impervious surfaces. HSegLearn searches the hierarchical segmentation from HSeg for the coarsest level of segmentation at which selected positive example locations do not conflict with negative example locations and labels the image accordingly. The negative example regions are always defined at the finest level of segmentation detail. The resulting classification map can be then further edited at a region object level using the previously developed HSegViewer tool [3]. After providing an overview of the HSeg image segmentation program, we provide a detailed description of the HSegLearn software tool. We then give examples of using HSegLearn to generate ground reference data and conclude with comments on the effectiveness of the HSegLearn tool.

Tilton, James C.↗

NASA NTRS2018

Agricultural Burning and Air Quality over Northern India: A Synergistic Analysis Using NASA's A-Train Satellite Data and Ground Measurements

In the recent years, New Delhi, the capital city of India, has ranked among the most polluted cities in the world regarding its air quality related to the submicron Particulate Matter (PM(sub 2.5)). Using NASA's A-train satellite data (MODIS, OMI, and CALIOP), ground-level PM2.5 measured in New Delhi (2013-2016), and back-trajectory calculations, we show that the PM(sub 2.5). over New Delhi is strongly affected by the agricultural fires in the northwestern Indian states of Punjab and Haryana during the post-monsoon season (October and November). The mass concentration of PM2.5 escalates from ~50 μg m(exp -3) measured prior to the onset of residue burning in early October to as high as 300 μg m(exp -3) (24-hour averaged, 7- day running mean) during the peak burning period in early November. A linear regression analysis reveals that the variations in PM(sub 2.5) over New Delhi can be attributed to the concurrent changes in the satellite retrievals of fire counts and aerosols over the crop burning area. The back-trajectory analysis shows that most clusters (> 80%) of the northwesterly flow near the ground intercepted the crop burning region before arriving at the receptor location in New Delhi; this further corroborates the transport patterns inferred from the satellite data. A 15-year long satellite record (2002-2016) reveals an increasing trend in agricultural fires (~617 per year) and aerosol loading (0.031 and 0.04 per year in aerosol optical depth and UV aerosol index) in November. Increasing levels of crop residue burning and resulting particulate matter pollution at an alarming rate over northern India is a pressing concern demanding corrective measures to substantially reduce or completely diminish the crop burning through an effective residue management system.

Crop Residue Fires↗

NASA NTRSDate not supplied

Machine-Learned Committor Functions for Reactive Molecular Dynamics

Reactive molecular dynamics (MD) is a powerful tool for atomistic-scale modeling of a diverse range of chemical processes. However, scaling these simulations to large systems and long times scales remains a challenge because of the complexity of the potential energy function required. The authors previously developed a heuristic approach, called REACTER, that incorporates reactivity in MD simulations in a less general but much more computationally efficient manner. REACTER uses standard, fixed valence force fields as the underlying potentialenergy surface for describing all interatomic interactions but adds a procedure for enforcing user-defined reactions that occur when certain geometric constraints on relative atomic positions are satisfied. Further, these bonding changes can be accepted or rejected with a probability related tothe local thermal energy. This work seeks to generalize this approach by replacing the set of user defined geometric constraints and energetic criteria with a committor function that specifies the probability of a reaction occurring on the basis of the local atomic configuration. The committor function is a useful mathematical tool for modeling rare events but, unfortunately, is very difficult to compute for realistic systems in a general way. This work describes a method for approximating the committor function using a machine learning approach, specifically a deep neural network trained with data from reactive MD and DFT-based dynamics simulations. This network is coupled to the existing REACTER protocol, as implemented in the LAMMPS MD package, and used to make on-the-fly predictions of reaction probabilities without the more extensive user input previously required. The new method is demonstrated using the polymerization of polystyrene as a case study. Although very dependent on the quality and quantity of training data, machine-learned committor functions show promise as a method for incorporating reaction probability from higher level calculations into highly scalable MD simulations.

polymer simulations↗

NASA NTRS1976

NASA/ESA CT-990 Spacelab simulation. Appendix A: The experiment operator

A joint NASA/ESA endeavor was established to conduct an extensive spacelab simulation using the NASA CV-990 airborne laboratory. The scientific payload was selected to perform studies in upper atmospheric physics and infrared astronomy with principal investigators from France, the Netherlands, England, and several groups from the United States. Two experiment operators from Europe and two from the U.S. were selected to live aboard the aircraft along with a mission manager for a six-day period and operate the experiments in behalf of the principal scientists. This appendix discusses the experiment operators and their relationship to the joint mission under the following general headings: selection criteria, training programs, and performance. The performance of the proxy operators was assessed in terms of adequacy of training, amount of scientific data obtained, quality of data obtained, and reactions to problems that arose in experiment operation.

Reller, J. O., Jr.↗

NASA NTRSDate not supplied

Development of TEMPO Products and Tools to Support Air Quality Management Decisions

The TEMPO mission has been observing air pollutants every hour during the daytime across its Field of Regard (FoR) covering greater North America since First Light on August 2, 2023. The highly anticipated public release of TEMPO data occurred on May 20, 2024, consisting of level 2 and level 3 trace gas data products of nitrogen dioxide, formaldehyde, and ozone. Our project at the NASA SPoRT Center is developing value-added products and tools to support the TEMPO mission and Early Adopters program with special attention on the air quality management community. The initial focus of this project is evaluating the TEMPO products over stakeholder target areas using Pandora and surface monitor observations. Methods for oversampling TEMPO data to 1 km resolution are being applied over the target areas to resolve fine-scale emission sources and pollutant gradients. Machine learning techniques using TEMPO, surface monitor, and model data to estimate surface-level nitrogen dioxide concentrations are being developed over the target areas. Our SPoRT viewer has been updated to include visualizations of the TEMPO products and an ArcGIS dashboard is being designed for enabling air quality management stakeholders to efficiently analyze TEMPO data. Training materials including user guides are being developed to ensure the effective and sustained use of TEMPO data in air quality management applications. The major outcome of this project is to support the inclusion of TEMPO data in exceptional event demonstrations by active engagement with stakeholders and ultimately enable more informed air quality management decisions in the future. This talk will provide an update on our project activities and showcase use cases of TEMPO data for monitoring different emission sources including wildland fire smoke.

air quality↗

NASA NTRSDate not supplied

Machine Learning Pipeline for Earth Science Using Sagemaker

Machine learning (ML) is gaining popularity in the Earth science domain. Higher the amount of quality data, the better the model. CPU training of such ML models is slow; GPU is used for training. Maintaining GPU servers is an additional responsibility. Multiple iterations of experiments needed before a better performing model is trained. Dataset creation, versioning of datasets, models, and experiments is hard.

Iksha Gurung↗

NASA NTRS2019

Citizen Science Data Quality: The GLOBE Program

The Global Learning and Observations to Benefit the Environment (GLOBE) Program is an international program that provides a way for students and the public to contribute Earth system observations. Currently 122 countries, more than 40,000 schools, and 200,000 citizen scientists are participating in GLOBE. Since 1995, participants have contributed 195 million observations. Modes of data collection and data entry have evolved with technology over the lifetime of the program, including the launch of the GLOBE Observer mobile app in 2016 to broaden access and public participation in data collection. GLOBE must meet the data needs of a diverse range of stakeholders, from elementary school classrooms to scientists across the globe, including NASA scientists. Operational quality assurance measures include participant training, adherence to standardized data collection protocols, range and logic checks, and an approval process for photos submitted with an observation. In this presentation, we will discuss the current state of operational data QA/QC, as well as additional QA/QC processes recently explored and future directions.

Amos, Helen↗

NASA NTRSDate not supplied

Developing Open-Source Training Materials for AI/ML and Space Biological Sciences Using NASA Cloud-Based Data

Artificial Intelligence (AI) and Machine Learning (ML) has gained significant traction in the biological and biomedical research fields, in part due to a culture of open data sharing and reuse. AI/ML methodology is well-suited to recognize and predict biological patterns from high-dimensional next-generation sequencing data (e.g. whole genome sequencing, transcriptomic sequencing), as well as from biological or medical imaging data (e.g. microscopy, computed tomography, ultrasound, magnetic resonance imaging, radiography). These methodologies hold particular promise for space biosciences research and automated space health monitoring systems. However, there are key considerations for properly training, validating, and testing a machine learning model in biological research or clinical application. Inexperienced researchers can produce models that perform poorly outside of the training dataset. Open Science principles such as data sharing and open-source code must go hand-in-hand with publicly available, high-quality training curricula in best practices, with modules centered on real-life scientific use cases and data so future AI/ML practitioners gain experience on real problems. Here we present the development of open-source training materials for AI/ML and space biosciences, as part of the NASA Transform to Open Science Training (TOPST) initiative. We develop 4 independent training programs, focused on the following topics: 1) Fundamentals of Machine Learning and Space Biosciences Domain, 2) Open Science, Artificial Intelligence, and Ethical Best Practices for Data Sharing and Analysis, 3) Using AI/ML Classification to Identify Gene Networks Affected By Space Exposure in Mouse Liver, and 4) Using Neural Networks to Find DNA Damage Patterns in Immune Cells after Radiation. All programs leverage cloud-based NASA biological datasets. The curriculum we present will enable worldwide access to training in AI/ML and scientific analysis.

James Casaletto↗

NASA NTRSDate not supplied

Developing Open-Source Training Materials for AI/ML and Space Biological Sciences Using NASA Cloud-Based Data

Artificial Intelligence (AI) and Machine Learning (ML) has gained significant traction in the biological and biomedical research fields in the last two decades, in part thanks to an increasing culture of open data sharing and reuse. Due to its capability for identifying complex relationships and patterns, AI/ML methodology is particularly well suited to recognize and predict biological patterns from high-dimensional next-generation sequencing data (e.g. whole genome sequencing, transcriptomic sequencing), as well as from biological or medical imaging data (e.g. microscopy, computed tomography, ultrasound, magnetic resonance imaging, radiography). These methodologies hold particular promise for space biosciences research and automated space health monitoring systems. However, there are many key considerations for properly training, validating, and testing a machine learning model in biological research or clinical application. Even with the positive culture of Open Science and data sharing, inexperienced researchers working quickly without proper checks can produce models that perform poorly outside of the immediate training dataset. Lessons learned from biological AI/ML research indicate that Open Science principles such as data sharing and open-source code must go hand-in-hand with publicly available, high-quality training curricula in best practices, with modules centered on real-life scientific use cases and data so future AI/ML practitioners gain experience on real problems. Here we present the development of open-source training materials for AI/ML and space biosciences, as part of the NASA Transform to Open Science Training (TOPST) initiative. We develop 4 independent training programs, focused on the following topics: 1) Fundamentals of Machine Learning and Space Biosciences Domain, 2) Open Science, Artificial Intelligence, and Ethical Best Practices for Data Sharing and Analysis, 3) Using AI/ML Classification to Identify Gene Networks Affected By Space Exposure in Mouse Liver, and 4) Using Neural Networks to Find DNA Damage Patterns in Immune Cells after Radiation. All programs leverage cloud-based NASA biological datasets. The curriculum we present will enable worldwide access to training in AI/ML and scientific analysis.

James Andrew Casaletto↗

NASA NTRSDate not supplied

High School Citizen Scientists Use AI/ML to Predict Intra-Ocular Pressure From Gene Expression Data for Spaceflown Mice

Artificial Intelligence (AI) and Machine Learning (ML) have increasingly become pivotal in biological and biomedical research, largely due to the culture of open data sharing and its associated benefits. The methodologies inherent in AI/ML are particularly adept at identifying and forecasting biological phenotypes from the vast amounts of data generated by next-generation sequencing technologies. These techniques offer substantial promise for advancing research in space biosciences and for the development of automated systems for monitoring space health. Nevertheless, there are crucial aspects to consider when training, validating, and testing machine learning models in both biological research and clinical contexts. It is essential that Open Science principles, including data sharing and the availability of open-source code, are complemented by high-quality, publicly accessible training resources. These resources should focus on best practices and include modules based on real-world scientific cases and data to ensure that future AI/ML practitioners gain practical experience with genuine problems. Addressing this knowledge gap, we have designed, developed, and delivered both interactive and self-paced training programs for citizen scientists worldwide, enabling them to utilize AI/ML for space biology research. This initiative was made possible through generous funding from a Transformation to Open Science Training grant. The interactive training sessions, conducted this summer, utilized AI/ML techniques to analyze data from the Open Science Data Repository, specifically targeting the effects of spaceflight on ocular structure and function. The dataset OSD-583, from the Rodent Research 9 mission, provides experimental data detailing the ocular responses of mice subjected to a 35-day spaceflight, compared with ground control counterparts. Using OSD-583 as observational data, our summer training participants applied AI/ML methods to predict intraocular pressure from RNA-seq data and identify the genes most predictive of the observed responses. Further analysis through pathway enrichment and gene set enrichment revealed that these genes are involved in molecular and cellular processes contributing to retinal degeneration.

James Casaletto↗

NASA NTRS1979

Design information for solar-heating systems

Report contains preliminary design information for two solar-heating and hot water systems presently under development. Information includes quality control data, special tooling specifications, hazard analysis, and preliminary training program for installation contractors.

Source record↗