Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning efficiency”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

Improving performance through concept formation and conceptual clustering

Research from June 1989 through October 1992 focussed on concept formation, clustering, and supervised learning for purposes of improving the efficiency of problem-solving, planning, and diagnosis. These projects resulted in two dissertations on clustering, explanation-based learning, and means-ends planning, and publications in conferences and workshops, several book chapters, and journals; a complete Bibliography of NASA Ames supported publications is included. The following topics are studied: clustering of explanations and problem-solving experiences; clustering and means-end planning; and diagnosis of space shuttle and space station operating modes.

Fisher, Douglas H.↗
NASA NTRS2019

Understanding Machine Learning in Earth Science: A Natural Language Processing Approach

Machine learning (ML) is being increasingly utilized in Earth science research. Benefits of ML include efficiency, reduction of human error, and ability to extract hidden patterns within data. However, the mutual lack of each other’s domain knowledge by ML and Earth science stands as a barrier to timely and effective implementation. Earth science, in particular, faces challenges in generating sample data, compared to those of traditional ML problems such as face recognition or stock predictions, where data is abundant and not lacking in ground truth, which is necessary for labeling. Earth science data are more varying in formats, such as HDF5 and image resolutions, and are not standardized across instruments, even within a given Earth science discipline. Previous studies have been done to outline the specific challenges that Earth science faces with ML, while others have focused on using existing publications to mine information efficiently. Other resources such as Scikit-Learn have developed decision trees for choosing appropriate machine learning algorithms, but application within Earth science subjects becomes much more complex. For the current study, we propose a methodology and tool that aids in implementation of ML in Earth science using natural language processing (NLP). Our work comprises three main parts: (1) analyzing existing publications related to ML and Earth science, using natural language processing: (2) extracting from the publications information on ML models subjects in Earth Science: and (3) visualizing the extracted relationships as a network graph. The resulting network graph should aid the Earth science communities in applying optimal ML algorithms and guiding data preparation through visualization of similar studies. The network graph and analysis of document similarity will be the basis of our next step, which is to develop a decision tree for selecting optimal machine learning methodologies for specified Earth science applications.

Zheng, Laura↗
NASA NTRS2015

NASA Lessons Learned on Reusable and Expendable Launch Vehicle Operations and Their Application Towards DARPA's Experimental Spaceplane (XS-1) Program

Outline: Selected Historic Shuttle Operations Data; Shuttle Lessons Learned Recommendations for Lower Cost, Operationally Efficient Launch Vehicle Systems; Selected Expendable launch vehicle experiences; Past NASA Launch Vehicle Development Programs, Studies (1985 to present); Discussion: Suggested applications of NASA Lessons Learned to already-baselined contractor XS-1 Phase I concepts.

Reusable launch vehicle↗
NASA NTRS2004

Perceptual learning through optimization of attentional weighting: human versus optimal Bayesian learner

Human performance in visual detection, discrimination, identification, and search tasks typically improves with practice. Psychophysical studies suggest that perceptual learning is mediated by an enhancement in the coding of the signal, and physiological studies suggest that it might be related to the plasticity in the weighting or selection of sensory units coding task relevant information (learning through attention optimization). We propose an experimental paradigm (optimal perceptual learning paradigm) to systematically study the dynamics of perceptual learning in humans by allowing comparisons to that of an optimal Bayesian algorithm and a number of suboptimal learning models. We measured improvement in human localization (eight-alternative forced-choice with feedback) performance of a target randomly sampled from four elongated Gaussian targets with different orientations and polarities and kept as a target for a block of four trials. The results suggest that the human perceptual learning can occur within a lapse of four trials (<1 min) but that human learning is slower and incomplete with respect to the optimal algorithm (23.3% reduction in human efficiency from the 1st-to-4th learning trials). The greatest improvement in human performance, occurring from the 1st-to-2nd learning trial, was also present in the optimal observer, and, thus reflects a property inherent to the visual task and not a property particular to the human perceptual learning mechanism. One notable source of human inefficiency is that, unlike the ideal observer, human learning relies more heavily on previous decisions than on the provided feedback, resulting in no human learning on trials following a previous incorrect localization decision. Finally, the proposed theory and paradigm provide a flexible framework for future studies to evaluate the optimality of human learning of other visual cues and/or sensory modalities.

Non-NASA Center↗
NASA NTRS2011

Standards and Specifications for Ground Processing of Space Vehicles: From an Aviation-Based Shuttle Project to Global Application

Proprietary or unique designs and operations are expected early in any industry's development, and often provide a competitive early market advantage. However, there comes a time when a product or industry requires standardization for the whole industry to advance...or survive. For the space industry, that time has come. Here, we will focus on standardization of ground processing for space vehicles and their ground systems. With the retirement of the Space Shuttle, and emergence of a new global space race, affordability and sustainability are more important now than ever. The growing commercialization of the space industry and current global economic environment are driving greater need for efficiencies to save time and money. More RLV's (Reusable Launch Vehicles) are being developed for the gains of reusability not achievable with traditional ELV's (Expendable Launch Vehicles). More crew/passenger vehicles are also being developed. All of this calls for more attention needed for ground processing-repeatedly before launch and after landing/recovery. RLV's should provide more efficiencies than ELV's, as long as MRO (Maintenance, Repair, and Overhaul) is well-planned-even for the unplanned problems. NASA's Space Shuttle is a primary example of an RLV which was supposed to thrive on reusability savings with efficient ground operations, but lessons learned show that costs were (and still are) much greater than expected. International standards and specifications can provide the commonality needed to simplify design and manufacturing as well as to improve safety, quality, maintenance, and operability. There are standards organizations engaged in the space industry, but ground processing is one of the areas least addressed. Challenges are encountered due to various factors often not considered during development. Multiple vehicle elements, sites, customers, and contractors pose various functional and integration difficulties. Resulting technical publication structures and methods are incongruent. Some processing products are still done on paper, some electronic, and many being converted in between. Business systems then are not fully compatible, and paper as well as electronic conversions are time-consuming and costly. NASA and its Shuttle contractors setup rules and systems to handle what has produced over 130 RLV launches, but they have had many challenges. Attempts have been made to apply aviation industry specifications to make the Shuttle more efficient with its ground processing. One efficiency project example was to make a Shuttle Maintenance Manual (SMM) based on the commercial ATA (Air Transport Association of America) Spec 100 for technical publications. This industry standard, along with others, has been a foundation for efficient global MRO of commercial airlines for years. A modified version was also made for some military aircraft. The SMM project found many similarities in Spec 100 which apply to the Shuttle, and room for expansion for space systems/structures not in aircraft. The SMM project team met with the ATA and representatives from NASA's X-33 and X-34 programs to discuss collaboration on a national space standard based on Spec 100. A pilot project was enabled for a subset of Shuttle systems. Full implementation was not yet achieved, X-33 and X-34 were cancelled, and the Shuttles were then designated for retirement. Nonetheless, we can learn from this project how to expand this concept to all space vehicle products. Since then, ATA has joined with ASD (AeroSpace and Defence Industries Association of Europe) and AIA (Aerospace Industries Association) to form a much-enhanced and expanded international specification: Sl000D, International Specification for Technical Publications. It includes air, land, and sea vehicles, missiles, support equipment, ordnance, and communications. It is used by a growing number of countries for commercial and government products. Its modular design is supported by a Common Source Dabase (CSDB), and COTS (commercial off-the-shelf) software is available for production of IETP's (Interactive Electronic Technical Publications). A few space industry products in Europe have begun to apply Sl000D already. Also, there are other related standards/specifications which have global implications. We have an opportunity to adapt Sl000D and possibly other standards for use with space vehicles and ground systems. Sl000D has plenty of flexibility to apply to any product needed. To successfully grow the viability of the space industry, all members, commercial and government, will need to engage cooperatively in developing and applying standards to move toward interoperability. If we leverage and combine the best existing space standards and specifications, develop new ones to address known gaps, and adapt the best applicable features from other industries, we can establish an infrastructure to not only accelerate current development, but also build longevity for a more cohesive international space community.

Ingalls, John↗
NASA NTRS1991

Adjoint-operators and non-adiabatic learning algorithms in neural networks

Adjoint sensitivity equations are presented, which can be solved simultaneously (i.e., forward in time) with the dynamics of a nonlinear neural network. These equations provide the foundations for a new methodology which enables the implementation of temporal learning algorithms in a highly efficient manner.

Toomarian, N.↗
NASA NTRS1990

Planning and scheduling research at NASA Ames Research Center

Planning and scheduling is the area of artificial intelligence research that focuses on the determination of a series of operations to achieve some set of (possibly) interacting goals and the placement of those operations in a timeline that allows them to be accomplished given available resources. Work in this area at the NASA Ames Research Center ranging from basic research in constrain-based reasoning and machine learning, to the development of efficient scheduling tools, to the application of such tools to complex agency problems is described.

Friedland, Peter↗
NASA NTRS1994

Software Process Assessment (SPA)

NASA's environment mirrors the changes taking place in the nation at large, i.e. workers are being asked to do more work with fewer resources. For software developers at NASA's Goddard Space Flight Center (GSFC), the effects of this change are that we must continue to produce quality code that is maintainable and reusable, but we must learn to produce it more efficiently and less expensively. To accomplish this goal, the Data Systems Technology Division (DSTD) at GSFC is trying a variety of both proven and state-of-the-art techniques for software development (e.g., object-oriented design, prototyping, designing for reuse, etc.). In order to evaluate the effectiveness of these techniques, the Software Process Assessment (SPA) program was initiated. SPA was begun under the assumption that the effects of different software development processes, techniques, and tools, on the resulting product must be evaluated in an objective manner in order to assess any benefits that may have accrued. SPA involves the collection and analysis of software product and process data. These data include metrics such as effort, code changes, size, complexity, and code readability. This paper describes the SPA data collection and analysis methodology and presents examples of benefits realized thus far by DSTD's software developers and managers.

Rosenberg, Linda H.↗
NASA NTRS2007

Integration and Testing Challenges of Small Satellite Missions: Experiences from the Space Technology 5 Project

The Space Technology 5(ST5) payload was successfully carried into orbit on an OSC Pegasus XL launch vehicle, which was carried aloft and dropped from the OSC Lockheed L-1011 from Vandenberg Air Force Base March 22,2006, at 9:03 am Eastern time, 6:03 am Pacific time. In order to reach the completion of the development and successful launch of ST 5, the systems integration and test(I&T) team determined that a different approach was required to meet the project requirements rather than the standard I&T approach used for single, room-sized satellites. The ST5 payload, part of NASA's New Millennium Program headquartered at JPL, consisted of three micro satellites (approximately 30 kg each) and the Pegasus Support Structure (PSS), the system that connected the spacecrafts to the launch vehicle and deployed the spacecrafts into orbit from the Pegasus XL launch vehicle. ST5 was a technology demonstration payload, intended to test six (6) new technologies for potential use for future space flights along with demonstrating the ability of small satellites to perform quality science. The main technology was a science grade magnetometer designed to take measurements of the earth's magnetic field. The three spacecraft were designed, integrated, and tested at NASA Goddard Space Flight Center with integration and environmental testing occurring in the Bldg. 7-1 0-15-29. The three spacecraft were integrated and tested by the same I&T team. The I&T Manager determined that there was insufficient time in the schedule to perform the three I&T spacecraft activities in series used standard approaches. The solution was for spacecraft #1 to undergo integration and test first, followed by spacecraft #2 and #3 simultaneously. This simultaneous integration was successful for several reasons. Each spacecraft had a Lead Test Conductor who planned and coordinated their spacecraft through its integration and test activities. One team of engineers and technicians executed the integration of all three spacecraft, learning and gaining knowledge and efficiency as spacecraft #1 integration and testing progressed. They became acutely familiar with the hardware, operation and processes for I&T, thus each team member had the experience and knowledge to safely execute I&T for spacecraft #2 and #3 together. The integration team was very versatile and each member could perform many different activities or work any spacecraft, when needed. Daily meetings between the three Lead TCs and technician team allowed the team to plan and implement activities efficiently. The three (3) spacecraft and PSS were successfully integrated and tested, shipped to the launch site, and ready for launch per the I&T schedule that was planned three years previously.

Sauerwein, Timothy A.↗
NASA NTRS2008

Integration and Testing Challenges of Small, Multiple Satellite Missions: Experiences from the Space Technology 5 Project

The ST5 technology demonstration mission led by GSFC of NASA's New Millennium Program managed by JPL consisted of three micro satellites (approximately 30 kg each) deployed into orbit from the Pegasus XL launch vehicle. In order to meet the launch date schedule of ST5, a different approach was required rather than the standard I&T approach used for single, room-sized satellites. The three spacecraft were designed, integrated, and tested at NASA Goddard Space Flight Center. It was determined that there was insufficient time in the schedule to perform three spacecraft I&T activities in series using standard approaches. The solution was for spacecraft #1 to undergo integration and test first, followed by spacecraft #2 and #3 simultaneously. This simultaneous integration was successful for several reasons. Each spacecraft had a Lead Test Conductor who planned and coordinated their spacecraft through its integration and test activities. One team of engineers and technicians executed the integration of all three spacecraft, learning and gaining knowledge and efficiency as spacecraft #1 integration and testing progressed. They became acutely familiar with the hardware, operation and processes for I&T, thus had the experience and knowledge to safely execute I&T for spacecraft #2 and #3. The integration team was extremely versatile; each member could perform many different activities or work any spacecraft, when needed. ST5 was successfully integrated, tested and shipped to the launch site per the I&T schedule that was planned three years previously. The I&T campaign was completed with ST5's successful launch on March 22, 2006.

Sauerwein, Timothy A.↗
NASA NTRS2016

Flat H Frangible Joint Evolution

Space vehicle staging and separation events require pyrotechnic devices. They are single-use mechanisms that cannot be tested, nor can failure-tolerant performance be demonstrated in actual flight articles prior to flight use. This necessitates the implementation of a robust design and test approach coupled with a fully redundant, failure-tolerant explosive mechanism to ensure that the system functions even in the event of a single failure. Historically, NASA has followed the single failure-tolerant (SFT) design philosophy for all human-rated spacecraft, including the Space Shuttle Program. Following the end of this program, aerospace companies proposed building the next generation human-rated vehicles with off-the-shelf, non-redundant, zero-failure-tolerant (ZFT) separation systems. Currently, spacecraft and launch vehicle providers for both the Orion and Commercial Crew Programs (CCPs) plan to deviate from the heritage safety approach and NASA's SFT human rating requirements. Both programs' partners have base-lined ZFT frangible joints for vehicle staging and fairing separation. These joints are commercially available from pyrotechnic vendors. Non-human-rated missions have flown them numerous times. The joints are relatively easy to integrate structurally within the spacecraft. In addition, the separation event is debris free, and the resultant pyro shock is lower than that of other design solutions. It is, however, a serious deficiency to lack failure tolerance. When used for critical applications on human-rated vehicles, a single failure could potentially lead to loss of crew (LOC) or loss of mission (LOM)). The Engineering and Safety & Mission Assurance directorates within the NASA Johnson Space Center took action to address this safety issue by initiating a project to develop a fully redundant, SFT frangible joint design, known as the Flat H. Critical to the ability to retrofit on launch vehicles being developed, the SFT mechanisms must fit within the same three-dimensional envelope as current designs as well as meet structural loads requirements. There is increased mass associated with the redundant design, and the goal is to minimize the weight impact as much as possible. These requirements presented significant challenges, both technically and financially; these challenges will be explored in this paper. Perhaps greater than the technical issues confronted during this design process, were the financial considerations. These were a significant part of the story of this design and development plan. Insufficient financial and labor resources were formidable barriers to completing this project. Nevertheless, JSC personnel successfully conducted several test series at JSC with very useful results. The many lessons learned drove design improvements, performance efficiency, and increased functional reliability. This paper examines the significant technical and financial challenges that these requirements posed to the project team. It discusses the evolution of the SFT frangible joint design, including optimization, testing, and successful partnering of the Johnson Space Center (JSC) engineering and JSC safety organizations, to enhance the flight safety margin for America's next generation of human-rated space vehicles.

Diegelman, Thomas E.↗
NASA NTRS2020

Automated Cardiovascular Pathology Assessment using Semantic Segmentation and Ensemble Learning

Cardiac magnetic resonance imaging provides high spatial resolution, enabling improved extraction of important functional and morphological features for cardiovascular disease staging. Segmentation of ventricular cavities and myocardium in cardiac cine sequencing provides a basis to quantify cardiac measures such as ejection fraction. A method is presented that curtails the expense and observer bias of manual cardiac evaluation by combining semantic segmentation and disease classification into a fully automatic processing pipeline. The initial processing element consists of a robust dilated convolutional neural network architecture for voxel-wise segmentation of the myocardium and ventricular cavities. The resulting comprehensive volumetric feature matrix captures diagnostic clinical procedure data and is utilized by the final processing element to model a cardiac pathology classifier. Our approach evaluated anonymized cardiac images from a training data set of 100 patients (4 pathology groups, 1 healthy group, 20 patients per group) examined at the University Hospital of Dijon. The top average Dice index scores achieved were 0.940, 0.886, 0.849 for structure segmentation of the left ventricle (LV), myocardium and right ventricle (RV) respectively. A 5-ary pathology classification accuracy of 90% was recorded on an independent test set using the trained model. Performance results demonstrate potential for advanced machine learning methods to deliver accurate, efficient and reproducible cardiac pathological assessment.

Semantic Segmentation↗
NASA NTRSDate not supplied

Variance Decomposition of MEDLI2 Reconstructed Heating Using Neural Networks

The Mars Entry, Descent, and Landing Instrumentation (MEDLI2) sensor suite collected data during entry of the Mars 2020 Perseverance rover into Mars’ atmosphere. An inverse estimation of the backshell and heatshield surface aeroheating was performed, using the data from the MEDLI2 Instrumented Sensor Plugs, a network of thermocouples embedded within the thermal protection system across the aeroshell. Monte Carlo analysis was conducted to assess the sensitivity of the surface heat rate, temperature, and heat load to uncertainties in thermocouple depth and material properties. In this paper, a variance decomposition method using Sobol indices was employed to understand the relative contributions of each uncertainty parameter. Performing this analysis using results from the inverse analysis tool FIAT_Opt was found to require incredibly high computation time, and thus machine learning models were trained and evaluated as a surrogate model for FIAT_Opt. This paper demonstrates that machine learning models can be an efficient, accurate alternative to state-of-the-art inverse analysis tools like FIAT_Opt, especially for computationally-expensive processes. Using these models, the sensitivity analysis showed that uncertainties in heat capacity and thermal conductivity were the main drivers for the overall uncertainty in peak reconstructed heating and heat load.

H S Alpert↗
NASA NTRS2004

Computing and combustion

Coming into the Combustion Branch of the Turbomachinery and Propulsion Systems Division, there was not any set project planned out for me to work on. This was understandable, considering I am only at my sophmore year in college. Also, my mentor was a division chief and it was expected that I would be passed down the line. It took about a week for me to be placed with somebody who could use me. My first project was to write a macro for TecPlot. Commonly, a person would have a 3D contour volume modeling something such as a combustion engine. This 3D volume needed to have slices extracted from it and made into 2D scientific plots with all of the appropriate axis and titles. This was very tedious to do by hand. My macro needed to automate the process. There was some education I needed before I could start, however. First, TecPlot ran on Unix and Linux, like a growing majority of scientific applications. I knew a little about Linux, but I would need to know more to use the software at hand. I took two classes at the Learning Center on Unix and am now comfortable with Linux and Unix. I already had taken Computer Science I and II, and had undergone the transformation from Computer Programmer to Procedural Epistemologist. I knew how to design efficient algorithms, I just needed to learn the macro language. After a little less than a week, I had learned the basics of the language. Like most languages, the best way to learn more of it was by using it. It was decided that it was best that I do the macro in layers, starting simple and adding features as I went. The macro started out slicing with respect to only one axis, and did not make 2D plots out of the slices. Instead, it lined them up inside the solid. Next, I allowed for more than one axis and placed each slice in a separate frame. After this, I added code that transformed each individual slice-frame into a scientific plot. I also made frames for composite volumes, which showed all of the slices in the same XYZ space. I then designed an addition companion macro that exported each frame into its own image file. I then distributed the macros to a test group, and am awaiting feedback. In the meantime, a am researching the possible applications of distributed computing on the National Combustor Code. Many of our Linux boxes were idle for most of the day. The department thinks that it would be wonderful if we could get all of these idle processors to work on a problem under the NCC code. The client software would have to be easily distributed, such as in screensaver format or as a program that only ran when the computer was not in use. This project proves to be an interesting challenge.

Thompson, Daniel↗
NASA NTRS2019

Machine Learning Prototype App For Recognition of Fruits

As the incidence of obesity and associated negative health consequences is rising, it becomes crucial to monitor the dietary choices of individuals. Unfortunately, traditional methods to collect this information involve collecting food frequency questionnaires from individuals using paper. Electronic food trackers have been developed to collect food data, but they require participants to manually label and describe the content of their meals, and which may be difficult for researchers to interpret in a standardized fashion. Machine learning, however, provides an easy and efficient method for both participants and researchers to label food items with standardized descriptions. This project aims to create a prototype phone application that can identify and label photos of apples. This is done by making a machine learning model through Turicreate, a python module, which is then implemented into an iOS app through Xcode and Swift. The modules used in Swift include CoreML and AVFoundation. This machine learning application will be incorporated with a MealLogger phone app that is also under development. The MealLogger app will be used to keep track of participants' calorie intake and other personal details throughout the sleep study. The machine learning model will present several potential identities of the foods found in the photo, and the user will only need to select the correct option. This will be a user-friendly method for participants to easily log their food consumption without the hard work of manually inputting each and every description. Some limitations to this project include the wide variety of food, including those within different cultures. To deal with this, the model will include the most generic food categories, which the participant may select, and produce a drop-down menu of more specific dishes under that specified category, with the option of self-input. Additional questionnaires may be implemented according to the food type selected This will allow the process to be quick and easy, but also specific for the purpose of analysis. The release of the application will require a much longer process, but the machine learning prototype presents a first step toward an application that may change data analysis for researchers interested in collecting food intake from individuals living in the real world.

Food tracker↗
NASA NTRS1992

There is No Free Lunch: Tradeoffs in the Utility of Learned Knowledge

With the recent introduction of learning in integrated systems, there is a need to measure the utility of learned knowledge for these more complex systems. A difficulty arrises when there are multiple, possibly conflicting, utility metrics to be measured. In this paper, we present schemes which trade off conflicting utility metrics in order to achieve some global performance objectives. In particular, we present a case study of a multi-strategy machine learning system, mutual theory refinement, which refines world models for an integrated reactive system, the Entropy Reduction Engine. We provide experimental results on the utility of learned knowledge in two conflicting metrics - improved accuracy and degraded efficiency. We then demonstrate two ways to trade off these metrics. In each, some learned knowledge is either approximated or dynamically 'forgotten' so as to improve efficiency while degrading accuracy only slightly.

Kedar, Smadar T.↗
NASA NTRS2010

Multi-Stage System for Automatic Target Recognition

A multi-stage automated target recognition (ATR) system has been designed to perform computer vision tasks with adequate proficiency in mimicking human vision. The system is able to detect, identify, and track targets of interest. Potential regions of interest (ROIs) are first identified by the detection stage using an Optimum Trade-off Maximum Average Correlation Height (OT-MACH) filter combined with a wavelet transform. False positives are then eliminated by the verification stage using feature extraction methods in conjunction with neural networks. Feature extraction transforms the ROIs using filtering and binning algorithms to create feature vectors. A feedforward back-propagation neural network (NN) is then trained to classify each feature vector and to remove false positives. The system parameter optimizations process has been developed to adapt to various targets and datasets. The objective was to design an efficient computer vision system that can learn to detect multiple targets in large images with unknown backgrounds. Because the target size is small relative to the image size in this problem, there are many regions of the image that could potentially contain the target. A cursory analysis of every region can be computationally efficient, but may yield too many false positives. On the other hand, a detailed analysis of every region can yield better results, but may be computationally inefficient. The multi-stage ATR system was designed to achieve an optimal balance between accuracy and computational efficiency by incorporating both models. The detection stage first identifies potential ROIs where the target may be present by performing a fast Fourier domain OT-MACH filter-based correlation. Because threshold for this stage is chosen with the goal of detecting all true positives, a number of false positives are also detected as ROIs. The verification stage then transforms the regions of interest into feature space, and eliminates false positives using an artificial neural network classifier. The multi-stage system allows tuning the detection sensitivity and the identification specificity individually in each stage. It is easier to achieve optimized ATR operation based on its specific goal. The test results show that the system was successful in substantially reducing the false positive rate when tested on a sonar and video image datasets.

Chao, Tien-Hsin↗
NASA NTRSDate not supplied

Dense Feature Tracking of Atmospheric Winds with Deep Optical Flow

Atmospheric winds are a key physical phenomenon impacting natural hazards, energy transport, ocean currents, large-scale circulation, and ecosystem fluxes. Observing winds is a complex process and presents a large gap in NASA’s Earth Observation System. Atmospheric motion vectors (AMVs) aim to fill this gap by making numerical estimates of cloud movement between sequences of multi-spectral satellite images, tracking clouds and water vapor. Recent imaging hardware and software advancements have enabled the use of numerical optical flow techniques to produce accurate and dense vector fields outperforming traditional methods. This work presents WindFlow as the first machine learning based system for feature tracking atmospheric motion using optical flow. Due to the lack of large-scale satellite-based observations, we leverage high-resolution numerical simulations from NASA's GEOS-5 Nature Run to perform supervised learning and transfer to satellite images. We demonstrate that our approach using deep learning based optical flow scales to ultra-high-resolution images of size 2881x5760 with less than 1 m/s bias and 2.5 m/s average error. Four network and learning architectures are compared and it is found that recurrent all-pairs field transforms (RAFT) produces the lowest errors on all metrics for wind speed and direction. Results on held out numerical outputs shows RAFT's good performance in each of the spatial, temporal, and physical dimensions. A comparison between WindFlow and an operational AMV product against rawinsonde observations show that RAFT transfers across simulations and thermal infrared satellite observations. This work shows that machine learning based optical flow is an efficient approach to generating robust feature tracking for AMVs consistently over large regions.

Atmospheric winds↗