SEARCH · Search NASA
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.
This document describes the Arrival Runway Model (ARM) Machine Learning (ML) service developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
This document describes the Departure Runway Model (DRM) Machine Learning (ML) service developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
This document describes the Estimated ON Model (EON) Machine Learning (ML) services developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
This document describes the Airport Configuration Prediction Model (ACPM) Machine Learning (ML) service developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
This document describes the Impeded (ITIM) and Unimpeded Taxi In Time Prediction Model (UTIM) Machine Learning (ML) services developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
This document describes the Impeded (ITOM) and Unimpeded Taxi Out Time Prediction Model (UTOM) Machine Learning (ML) services developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
Future needs of the National Airspace System require decision support tools to adopt a service-oriented architecture in alignment with the FAA’s vision for an Info-Centric NAS. To achieve this, many existing systems will need to undergo a digital transformation from a monolithic decision support tool to a service-oriented architecture where individual services are exposed through well defined Application Programming Interfaces (APIs). To enable this transformation, NASA has developed the Digital Information Platform as a cloud based foundation for development of aviation services with a special focus towards Artificial Intelligence and Machine Learning (ML) services. This paper describes the work required for the transformation of NASA’s legacy surface management system to a real-time ML based decision support system deployed in the cloud. Details of the Machine Learning Operations (MLOps) infrastructure and best practices are described which enabled the end-toend lifecycle management of ML within an integrated software system. Validation results are provided from an operational field evaluation where performance was benchmarked against the legacy approach.
This paper describes a study on the estimation of the unimpeded taxi out time using Machine Learning (ML) tools and proposes an implementation that can be used to make real-time predictions at any airport in the National Airspace System. Kedro, an open-source pipeline framework, is used to develop the model definition and training. Models are stored in scikit-learn containers on a MLFlow server where they can be retrieved and served to make predictions in the live system. These open source frameworks provide common structures between ML services, allow for easier maintenance and updates, and overall deliver an easier CI/CD (Continuous Integration/Continuous Deployment) process. The current models were trained on data acquired at KCLT and KDFW from June 1st to December 31st, 2019 and compute taxi time in the ramp, airport movement area (AMA) and total (from gates to runways). The current versions of the models achieve relatively low uncertainties of about 10 to 15% for the total and AMA taxi times and about 20% for the ramp taxi time at both KCLT and KDFW. Initial tests on offline data from 2020 and 2021 show a small degradation (10 to 15%) in accuracy performance indicating the model’s resilience to operational changes over time.
This presentation describes a study on the estimation of the unimpeded taxi out time using Machine Learning (ML) tools and proposes an implementation that can be used to make real-time predictions at any airport in the National Airspace System. Kedro, an open-source pipeline framework, is used to develop the model definition and training. Models are stored in scikit-learn containers on a MLFlow server where they can be retrieved and served to make predictions in the live system. These open source frameworks provide common structures between ML services, allow for easier maintenance and updates, and overall deliver an easier CI/CD (Continuous Integration/Continuous Deployment) process. The current models were trained on data acquired at KCLT and KDFW from June 1st to December 31st, 2019 and compute taxi time in the ramp, airport movement area (AMA) and total (from gates to runways). The current versions of the models achieve relatively low uncertainties of about 10 to 15% for the total and AMA taxi times and about 20% for the ramp taxi time at both KCLT and KDFW. Initial tests on offline data from 2020 and 2021 show a small degradation (10 to 15%) in accuracy performance indicating the model’s resilience to operational changes over time.
The path to NAS-wide implementation for ATD-2 multi-airport IADS is as a digital service for flight operators that builds on and supplements FAA TBO investments. This session will focus on a suite of Machine Learning (ML) services the ATD-2 team developed to model airport surface operations. The approach used to leverage SWIM data sets will be described and a preliminary analysis of ML model accuracy will be presented. NASA’s plans to build on this work under the ATM-X Digital Information Platform (DIP) sub-project will be discussed.
Explore the source record for details and available documents.
Usage of Machine Learning (ML) algorithms within NASA’s Science Mission Directorates have been increasing over theyears. This can be quantitatively observed in the upward trends of ML usage found by analyzing the publications andpresentations (in affiliation with NASA) available through NASA Technical Reports Server (NTRS) and PubMed Central(PMC). Identifying the problem types and class of ML algorithms used to tackle them across the divisions can presentopportunities for collaborations, interdisciplinary projects and knowledge transfer for sustainable partnerships. In thispresentation, we will present the trend analysis of ML algorithms used in different SMD divisions based on the publicationsand presentations publicly available. We identify these trends by leveraging ML algorithms which are able to search throughthe publication texts semantically; which are also highly scalable. We will also present an analysis on the available opensource tools and services in NASA leveraging AI/ML algorithms. This work will provide ample avenues for collaborativeefforts across different disciplines based on the surfaced trends.
Usage of Machine Learning (ML) algorithms within NASA’s Science Mission Directorates have been increasing over the years. This can be quantitatively observed in the upward trends of ML usage found by analyzing the publications and presentations (in affiliation with NASA) available through NASA Technical Reports Server (NTRS) and PubMed Central(PMC). Identifying the problem types and class of ML algorithms used to tackle them across the divisions can present opportunities for collaborations, interdisciplinary projects and knowledge transfer for sustainable partnerships. In this presentation, we will present the trend analysis of ML algorithms used in different SMD divisions based on the publications and presentations publicly available. We identify these trends by leveraging ML algorithms which are able to search through the publication texts semantically; which are also highly scalable. We will also present an analysis on the available opensource tools and services in NASA leveraging AI/ML algorithms. This work will provide ample avenues for collaborative efforts across different disciplines based on the surfaced trends.
An emerging use-case of machine learning (ML) is to train a model on a high-performance system and deploy the trained model on energy-constrained embedded systems. Neuromorphic hardware platforms, which operate on principles of the biological brain, can significantly lower the energy overhead of a machine learning inference task, making these platforms an attractive solution for embedded ML systems. In this paper, we present a design-technology tradeoff analysis to implement such inference tasks on the processing elements (PEs) of a Non-Volatile Memory (NVM)-based neuromorphic hardware. Through detailed circuit-level simulations at scaled process technology nodes, we show the negative impact of technology scaling on the information-processing latency, which impacts the quality-of-service (QoS) of an embedded ML system. At a finer granularity, the latency inside a PE depends on 1) the delay introduced by parasitic components on its current paths, and 2) the varying delay to sense different resistance states of its NVM cells. Based on these two observations, we make the following three contributions. First, on the technology front, we propose an optimization scheme where the NVM resistance state that takes the longest time to sense is set on current paths having the least delay, and vice versa, reducing the average PE latency, which improves the QoS. Second, on the architecture front, we introduce isolation transistors within each PE to partition it into regions that can be individually power-gated, reducing both latency and energy. Finally, on the system-software front, we propose a mechanism to leverage the proposed technological and architectural enhancements when implementing a machine-learning inference task on neuromorphic PEs of the hardware. Evaluations with a recent neuromorphic hardware architecture show that our proposed design-technology co-optimization approach improves both performance and energy efficiency of machine-learning inference tasks without incurring high cost-per-bit.
Transitioning from an onsite Maintenance & Diagnostics Center to cloud-based services offers many new opportunities with computing power and storage, but also new challenges in terms of networking and security. This report will cover everything required for that transition including data processing and uploading to cloud services, feature selection, model creation, and result visualization for decision making. Although there are several other cloud-based services (e.g. Amazon Web Services and Google Cloud), this report explores Microsoft Azure to simplify nomenclature and maintain a consistent focus. Many of the services offered by Microsoft Azure are also available in the other cloud-based services, and their differences have been recorded in other literature. The Azure services most important to a nuclear power plant including networking & security, storage & databases, and Artificial Intelligence (AI) are reviewed here. Networking covers all aspects related to communication to Azure resources including security, privacy, and redundancy. Storage & databases includes data storage, upgrading, patching, backups, and monitoring. The AI services allows the user access to the machine learning (ML) techniques developed with Azure including automated ML, anomaly detection, computer vision, and natural language processing. This report summaries the features, capabilities, and challenges when using cloud-based services in a user-friendly manner.
Machine Learning (ML) has become one of the important tools for High Energy Physics analysis. As the size of the dataset increases at the Large Hadron Collider (LHC), and at the same time the search spaces become bigger and bigger in order to exploit the physics potentials, more and more computing resources are required for processing these ML tasks. In addition, complex advanced ML workflows are developed in which one task may depend on the results of previous tasks. How to make use of vast distributed CPUs/GPUs in WLCG for these big complex ML tasks has become a popular research area. In this paper, we present our efforts enabling the execution of distributed ML workflows on the Production and Distributed Analysis (PanDA) system and intelligent Data Delivery Service (iDDS). First, we describe how PanDA and iDDS deal with large-scale ML workflows, including the implementation to process workloads on diverse and geographically distributed computing resources. Next, we report real-world use cases, such as HyperParameter Optimization, Monte Carlo Toy confidence limits calculation, and Active Learning. Finally, we conclude with future plans.
Recent years have seen a substantial increase in the application of machine learning (ML) for automated analysis of nondestructive examination (NDE) data. One of the applications of interest is the use of ML for the analysis of data from in-service inspection of welds in nuclear power and other industries. These types of inspections are performed in accordance with criteria described in the ASME Boiler and Pressure Vessel Code and require the use of reliable NDE techniques. The rapid growth in ML methods and the diversity of possible approaches indicate a need to assess the current capabilities of ML and automated data analysis for NDE and identify any gaps or shortcomings in current ML technologies as applied to the automated analysis of NDE data. In particular, there is a need to determine the impact of ML on the NDE reliability. This paper discusses the findings from a literature survey on the current state of ML for the automated analysis of data from ultrasonic NDE of weld flaws. It discusses an overview of ultrasonic NDE as used for weld inspections in nuclear power and other industries. Herein, data sets and ML models used in the literature are summarized, along with a generally applicable workflow for ML. Findings on the capabilities, limitations and potential gaps in feature selection, data selection, and ML model optimization are discussed. The paper identified several needs for quantifying and validating the performance of ML methods for ultrasonic NDE, including the need for common data sets.
Brief updates of Digital Information Platform (DIP) plans for platform-enabled sustainable aviation services. DIP will provide the capability to integrate key flight information from multiple sources and make it easier to access data critical to developing services using advanced techniques such as machine learning. NASA will share ML-based microservices on the platform for industry to use as reference implementations. The platform will support an ecosystem to share reusable services and promote innovation for digital information.