Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “machine learning tools”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS2016

Time Series Explorer: Bayesian Blocks with Generalized Profiles and in Higher Dimensions

The Time Series Explorer (TSE) is a project aimed at provided new and advanced time series analysis algorithms in two forms: a tool kit and an automated pipeline applying selected tools in machine learning settings. I will present a sketch of TSE with emphasis on time-domain modeling in general and recent improvements of the Bayesian Block (BB) algorithm in particular. This includes generalizing the shape of the elementary blocks from the current constant-rate model to general shapes, such as two-sided exponentials. Related topics will include extension of BB to higher dimensions and a novel way to detect and characterize short time-scale bursts in time-tagged event data. The Fermi Gamma Ray Space Telescope light curve for the Crab Nebula will be used as an example for all of the algorithms discussed. This work is in collaboration with Tom Loredo.

Bayesian Block (BB) algorithm↗
NASA NTRS2019

Lunar Development Lab (LDL) Concept Leading to the First Human Lunar Outpost

The Lunar Development Lab (LDL) is a new concept to bring together academia, industry, non-profit organizations and NASA in an accelerator environment to generate new design solutions, technologies and architectures that will lead to the first human lunar outpost. By leveraging key partnerships in lunar science, mining, construction, chemical engineering and other key fields as well as making available rapid design, economic analysis, artificial intelligence (AI) and machine learning (ML) tools, significant progress can be made in a short amount of time. Therefore, the goal of LDL is to accelerate development and focus on economic solutions that can lead to sustainable and economical human lunar outpost.

Zuniga, Allison↗
NASA NTRS2021

Topic Modeling Tool for PeTaL (Periodic Table of Life)

A topic modeling tool is constructed for the purpose of providing insights from biology to the engineer within the framework of PeTaL (Periodic Table of Life). The machine learning text mining tools–latent Dirichlet allocation (LDA) and nonnegative matrix factorization (NMF) with Kullback-Leibler (KL) divergence—are used to provide topic clusters to the user. Topic clusters are the underlying themes of a paper. For the text modeling problem, NMF-KL is the equivalent of probabilistic latent semantic analysis. Both LDA and NMF-KL are top-performing modeling tools. These tools are used to identify biological specimens relevant to the user. Various organisms solve a particular survival problem in nature differently. The topic clusters allow people without domain expertise to find these cross-topic themes in the body of documents and then branch out and examine papers whose target organisms solve the engineer’s problem. Abstracts from the Journal of Experimental Biology were used as input for the clustering tool in addition to a curated set of articles for validation. The tool is able to accept alternate input sources.

Machine learning↗
NASA NTRS1987

Intelligent fault-tolerant controllers

A system with fault tolerant controls is one that can detect, isolate, and estimate failures and perform necessary control reconfiguration based on this new information. Artificial intelligence (AI) is concerned with semantic processing, and it has evolved to include the topics of expert systems and machine learning. This research represents an attempt to apply AI to fault tolerant controls, hence, the name intelligent fault tolerant control (IFTC). A generic solution to the problem is sought, providing a system based on logic in addition to analytical tools, and offering machine learning capabilities. The advantages are that redundant system specific algorithms are no longer needed, that reasonableness is used to quickly choose the correct control strategy, and that the system can adapt to new situations by learning about its effects on system dynamics.

Huang, Chien Y.↗
NASA NTRS2017

Application of Machine Learning to Rotorcraft Health Monitoring

Machine learning is a powerful tool for data exploration and model building with large data sets. This project aimed to use machine learning techniques to explore the inherent structure of data from rotorcraft gear tests, relationships between features and damage states, and to build a system for predicting gear health for future rotorcraft transmission applications. Classical machine learning techniques are difficult, if not irresponsible to apply to time series data because many make the assumption of independence between samples. To overcome this, Hidden Markov Models were used to create a binary classifier for identifying scuffing transitions and Recurrent Neural Networks were used to leverage long distance relationships in predicting discrete damage states. When combined in a workflow, where the binary classifier acted as a filter for the fatigue monitor, the system was able to demonstrate accuracy in damage state prediction and scuffing identification. The time dependent nature of the data restricted data exploration to collecting and analyzing data from the model selection process. The limited amount of available data was unable to give useful information, and the division of training and testing sets tended to heavily influence the scores of the models across combinations of features and hyper-parameters. This work built a framework for tracking scuffing and fatigue on streaming data and demonstrates that machine learning has much to offer rotorcraft health monitoring by using Bayesian learning and deep learning methods to capture the time dependent nature of the data. Suggested future work is to implement the framework developed in this project using a larger variety of data sets to test the generalization capabilities of the models and allow for data exploration.

machine learning↗
NASA NTRSDate not supplied

Improving Access to the GEOS Composition Forecast Model with API Development and Ingestion into Google Earth Engine

The GEOS Composition Forecast (GEOS-CF) model produces forecast and historical estimates of atmospheric composition and meteorology fields, which provide useful insight into air quality issues and events. In a year for which Canadian wildfires created adverse air quality conditions in the eastern United States, access to model fields such as PM2.5 are in high demand. The GEOS-CF team at the NASA Global Modeling and Assimilation Office (GMAO) first developed in-house solutions to improve data access via the CF API, and recently partnered with Google to ingest a collated set of model diagnostics into the Google Earth Engine (GEE) data repository. GEOS-CF model output is also being ingested into AWS storage. Creating these various open access points to GEOS-CF model diagnostics provides the public with an opportunity to easily interact with air quality information. Users are able to use a temporally consistent global grid of air quality fields in machine learning applications, mapping tools, and data informatics. Hosting GEOS-CF forecasts and the historical timeseries of these chemistry and meteorology fields in GEE allows users to create dynamic JavaScript-based air quality applications in the GEE code editor. GEOS-CF users can also access the model output via the GEE Python application programming interface (API), making it easy to perform various analyses with Python. This presentation will show two examples of accessing the GEOS-CF model through GEE. The first is an example application made in the GEE code editor which allows users to view time series plots and downscaled maps of surface level NO2. The second example exhibits using the GEE Python API to create a machine learning model to temporally gap-fill between air quality observations. These examples are an introduction to the many possible benefits of having open access to the GEOS-CF model through multiple platforms.

Callum Wayman↗
NASA NTRSDate not supplied

Improving Access to the GEOS Composition Forecast Model with API Development and Ingestion into Google Earth Engine

The GEOS Composition Forecast (GEOS-CF) model produces forecast and historical estimates of atmospheric composition and meteorology fields, which provide useful insight into air quality issues and events. In a year for which Canadian wildfires created adverse air quality conditions in the eastern United States, access to model fields such as PM2.5 are in high demand. The GEOS-CF team at the NASA Global Modeling and Assimilation Office (GMAO) first developed in-house solutions to improve data access via the CF API, and recently partnered with Google to ingest a collated set of model diagnostics into the Google Earth Engine (GEE) data repository. GEOS-CF model output is also being ingested into AWS storage. Creating these various open access points to GEOS-CF model diagnostics provides the public with an opportunity to easily interact with air quality information. Users are able to use a temporally consistent global grid of air quality fields in machine learning applications, mapping tools, and data informatics. Hosting GEOS-CF forecasts and the historical timeseries of these chemistry and meteorology fields in GEE allows users to create dynamic JavaScript-based air quality applications in the GEE code editor. GEOS-CF users can also access the model output via the GEE Python application programming interface (API), making it easy to perform various analyses with Python. This presentation will show two examples of accessing the GEOS-CF model through GEE. The first is an example application made in the GEE code editor which allows users to view time series plots and downscaled maps of surface level NO 2 . The second example exhibits using the GEE Python API to create a machine learning model to temporally gap-fill between air quality observations. These examples are an introduction to the many possible benefits of having open access to the GEOS-CF model through multiple platforms.

Callum Wayman↗
NASA NTRSDate not supplied

DELTA: An Open-Source Framework to Simplify Machine Learning with Satellite Imagery

DELTA (Deep Earth Learning, Tools, and Analysis) is an open-source framework developed at NASA to simplify running and training machine learning (ML) models on satellite imagery. Users new to machine learning can run existing ML models on satellite imagery with minimal setup and configuration. For experienced ML users, DELTA helps simplify data engineering, preprocessing steps, and reduces the need for boilerplate code that needs written to make satellite imagery datasets palatable for machine learning. This lets data scientists focus on model development while DELTA handles the imagery manipulation. This presentation will demonstrate DELTA’s functionality and share some examples from an active project using it for flood mapping using imagery from multiple satellite sources

Michael von Pohle↗
NASA NTRSDate not supplied

DELTA: An Open-Source Framework to Simplify Machine Learning with Satellite Imagery

DELTA (Deep Earth Learning, Tools, and Analysis) is an open-source framework developed at NASA to simplify running and training machine learning (ML) models on satellite imagery. Users new to machine learning can run existing ML models on satellite imagery with minimal setup and configuration. For experienced ML users, DELTA helps simplify data engineering, preprocessing steps, and reduces the need for boilerplate code that needs written to make satellite imagery datasets palatable for machine learning. This lets data scientists focus on model development while DELTA handles the imagery manipulation. This presentation will demonstrate DELTA’s functionality and share some examples from an active project using it for flood mapping using imagery from multiple satellite sources.

deep learning↗
NASA NTRS2021

PIXLISE-C: Exploring The Data Analysis Needs of NASA Scientists for Mineral Identification

NASA JPL scientists working on the micro x-ray fluorescence (microXRF) spectroscopy data collected from Mars surface perform data analysis to look for signs of past microbial life on Mars. Their data analysis workflow mainly involves identifying mineral com- pounds through the element abundance in spatially distributed data points. Working with the NASA JPL team, we identified pain points and needs to further develop their existing data visualization and analysis tool. Specifically, the team desired improvements for the process of creating and interpreting mineral composition groups. To address this problem, we developed an interactive tool that enables scientists to (1) cluster the data using either manual lasso-tool selection or through various machine learning clustering algorithms, and (2) compare the clusters and individual data points to make informed decisions about mineral compositions. Our preliminary tool supports a hybrid data analysis workflow where the user can manually refine the machine-generated clusters.

Davidoff, Scott↗
NASA NTRS2019

Atmospheric Chemistry Modeling and Air Quality Forecasting Using Machine Learning

Atmospheric chemistry models are a central tool to study the impact of chemical constituents on the environment, vegetation and human health. These models split the atmosphere in a large number of grid-boxes and consider the emission of compounds into these boxes and their subsequent transport, deposition, and chemical processing. The chemistry is represented through a series of simultaneous ordinary differential equations, one for each compound. Given the difference in life-times between the chemical compounds (milli-seconds for O1D to years for CH4) these equations are numerically stiff and solving them consists of a significant fraction of the computational burden of a chemistry model.We have investigated a machine learning approach to emulate the chemistry instead of solving the differential equations numerically. From a one-month simulation of the GEOS-Chem model we have produced a training dataset consisting of the concentration of compounds before and after the differential equations are solved, together with some key physical parameters for every grid-box and time-step. From this dataset we have trained a machine learning algorithm (regression forest) to be able to predict the concentration of the compounds after the integration step based on the concentrations and physical state at the beginning of the time step. We have then included this algorithm back into the GEOS-Chem model, bypassing the need to integrate the chemistry.This machine learning approach shows many of the characteristics of the full simulation and has the potential to be substantially faster. There are a wide range of application for such an approach - generating boundary conditions, for use in air quality forecasts, chemical data assimilation systems, etc. We discuss speed and accuracy of our approach, and highlight some potential future directions for improving it.

Keller, Christoph A.↗
NASA NTRS2019

Atmospheric Chemistry Modeling Using Machine Learning

Atmospheric chemistry models are a central tool to study the impact of chemical constituents on the environment, vegetation and human health. These models split the atmosphere in a large number of grid-boxes and consider the emission of compounds into these boxes and their subsequent transport, deposition, and chemical processing. The chemistry is represented through a series of simultaneous ordinary differential equations, one for each compound. Given the difference in life-times between the chemical compounds (milli-seconds for O1D to years for CH4) these equations are numerically stiff and solving them consists of a significant fraction of the computational burden of a chemistry model. We have investigated a machine learning approach to emulate the chemistry instead of solving the differential equations numerically. From a one-month simulation of the GEOS-Chem model we have produced a training dataset consisting of the concentration of compounds before and after the differential equations are solved, together with some key physical parameters for every grid-box and time-step. From this dataset we have trained a machine learning algorithm (regression forest) to be able to predict the concentration of the compounds after the integration step based on the concentrations and physical state at the beginning of the time step. We have then included this algorithm back into the GEOS-Chem model, bypassing the need to integrate the chemistry. This machine learning approach shows many of the characteristics of the full simulation and has the potential to be substantially faster. There are a wide range of application for such an approach - generating boundary conditions, for use in air quality forecasts, chemical data assimilation systems, etc. We discuss speed and accuracy of our approach, and highlight some potential future directions for improving it.

Keller, Christoph A.↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗
NASA NTRSDate not supplied

NASA GeneLab Multi-study Visualization Portal

NASA GeneLab has helped advance the field of Space Biology by providing a public repository where researchers can store, share, analyze and visualize the results of space flight related omics experiments. The GeneLab data visualization portal allows any user, regardless of bioinformatics knowledge or access to computational resources, to interact with the experimental data, draw their own conclusions, and gain insights about the effects of space on living systems. These tools help democratize scientific research and foster the NASA Open Science initiative. The new multi-study feature of the GeneLab visualization platform allows users to mine study metadata from RNA sequencing (RNA-seq) experiments to identify samples of interest by filtering datasets based on organism, tissue, assay technology type, and/or factor. Once samples are selected from multiple datasets, users can combine and normalize the sample data, then utilize the visualization displays, including Principal Component Analysis (PCA) plots, to assess sample distributions. Finally, users can perform differential gene expression analysis on the combined data and visualize the results through PCA plots, Volcano plots, Pair plots, Heatmap, Ideogram and Gene Set Enrichment Analysis. All user-generated results and visualizations will be available for download. Here, we present a biological study using samples from multiple GeneLab RNA-seq datasets and analyzed using the multi-study visualization platform to demonstrate inter- and intra-study variability, as well as commonly differentially expressed genes between spaceflight and ground control conditions across datasets. This new feature opens a wide range of possibilities and opportunities for further development including combining other assay technology types and integration with batch effect correction techniques and machine learning applications. Overall, this tool allows users to increase the statistical power of individual experiments, validate hypothesis, identify patterns, and opens the door to new and exciting research.

space biology↗
NASA NTRS2014

Review and Analysis of Algorithmic Approaches Developed for Prognostics on CMAPSS Dataset

Benchmarking of prognostic algorithms has been challenging due to limited availability of common datasets suitable for prognostics. In an attempt to alleviate this problem several benchmarking datasets have been collected by NASA's prognostic center of excellence and made available to the Prognostics and Health Management (PHM) community to allow evaluation and comparison of prognostics algorithms. Among those datasets are five C-MAPSS datasets that have been extremely popular due to their unique characteristics making them suitable for prognostics. The C-MAPSS datasets pose several challenges that have been tackled by different methods in the PHM literature. In particular, management of high variability due to sensor noise, effects of operating conditions, and presence of multiple simultaneous fault modes are some factors that have great impact on the generalization capabilities of prognostics algorithms. More than 70 publications have used the C-MAPSS datasets for developing data-driven prognostic algorithms. The C-MAPSS datasets are also shown to be well-suited for development of new machine learning and pattern recognition tools for several key preprocessing steps such as feature extraction and selection, failure mode assessment, operating conditions assessment, health status estimation, uncertainty management, and prognostics performance evaluation. This paper summarizes a comprehensive literature review of publications using C-MAPSS datasets and provides guidelines and references to further usage of these datasets in a manner that allows clear and consistent comparison between different approaches.

Uncertainty↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗