Search NASA⌕ Search

Engineering topics

Jennifer Wei

Publications and source records attributed to Jennifer Wei.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2024

Analyzing EOSDIS Dataset Research Outputs using Knowledge Graphs and Large Language Models

Datasets, unlike publications, can be updated over time, with each new version receiving a DOI but not always being linked to previous ones. This complicates tracking citations across a dataset’s lifecycle. We address this by integrating dataset versions and citations into a knowledge graph (KG), which helps trace dataset citations and analyze dataset usage in applied research. To categorize publications from various journals, we fine-tuned NASA IMPACT INDUS Large Language Model (LLM) on a labeled publication set, assigning publications to one of twenty applied research areas. By linking datasets to these research areas, we improved dataset searchability and discovery through these domains.

open-source↗
NASA NTRS2020

Assessing the Impacts of Two Averaging Methods on AIRS Level 3 Monthly Products and Multi-Year Monthly Means

The Atmospheric Infrared Sounder (AIRS) onboard NASA’s Aqua satellite provides more than 16 years of data. Its monthly gridded (Level 3) product has been widely used for climate research and applications. Since counts of successful soundings in a grid cell are used to derive monthly averages, this “Averaged By Observations (ABO)” approach effectively gives equal importance to all participating soundings within a month. It is conceivable, then, that days with more observations due to day-to-day orbit shift and regimes with better retrieval skills, will contribute disproportionately to the monthly average within a cell. Alternatively, the AIRS Level 3 monthly product can be produced through an "Averaged By Days (ABD)” approach, where the monthly mean in a grid cell is a simple average of the daily means. The effects of these averaging methods on the AIRS version 6 monthly product are assessed quantitatively using temperature and water vapor at surface and 500hPa. The ABO method results in a warmer (slightly colder) global mean temperature at surface (500hPa) and a drier global mean water vapor than ABD method. The AIRS multi-year monthly mean temperature and water vapor from both methods are also compared with the Modern-Era Retrospective analysis for Research and Applications – 2 (MERRA-2) product and evaluated with a simulation experiment, indicating the ABD method has less error and is more closely correlated with MERRA-2. In summary, the ABD method is recommended for future versions of the AIRS Level 3 monthly product and more data services supporting Level 3 aggregation are needed.

AIRS↗
NASA NTRSDate not supplied

Enhancing NASA Earth Science Data Discovery from Scientific Publications

Earth observations from space borne instruments have evolved explosively in the past decades. Following closely are reanalysis systems assimilating model and observational data, yielding even longer records and larger number of variables. Thanks to advances in internet technology, it is now easier than ever to visualize and analyze these data using web interfaces. On the other hand, it also becomes an increasingly daunting task to build upon the existing knowledge published in various peer reviewed sources, and navigate toward the most relevant data, analysis, and visualization. We present an analysis of a subset of publications that utilized a popular visualization web interface at the NASA Goddard Earth Science Data and Information Services Center. Known as "Giovanni", it allows researchers from wide backgrounds to work with hundreds of variables from space observations and assimilation systems. Since coming online more than a decade ago, Giovanni has been credited in more than 100 papers per year, and the total count now is estimated to be nearly 1,500. Many of these papers contain valuable information about when, where and how Giovanni has been used, and hence forge an opportunity to learn and share the knowledge of which variables were used for what research projects. The purpose of our work is to retrieve the information from the papers and organize it as a knowledge repository which links together datasets, variables, places, dates and phenomena all of which reflect the essence of the published research. Since the publications are unstructured texts, we use natural language processing along with machine learning methods in the retrieval process. One of the challenges is deciphering the dataset names, because in many cases researchers refer to variables, rather than the datasets containing them. To constrain the number of terms, we deploy Earth Science ontologies as dictionaries for the term extraction. We demonstrate that storing these terms and underlying ontologies, along with datasets, variables and papers in the knowledge graph database, enables various linkages between all these entities facilitating the data discovery. Thus, we are setting a qualitatively new stage in improvements of web data interfaces, where machine learning techniques are used to establish and optimize usage-based discovery of data.

Irina V Gerasimov↗
NASA NTRSDate not supplied

Atmospheric Infrared Sounder Version 7 Near-Real-Time Product and Imagery Released by NASA GES DISC

The NASA Goddard Earth Sciences Data and Information Services Center (GES DISC) has been the home of data processing, archive, and distribution services for data from the Atmospheric Infrared Sounder (AIRS) mission since its launch in 2002. The GES DISC provides service to both AIRS routine and Near Real-Time (NRT) products. The AIRS NRT products are an important element in the Land, Atmosphere Near real-time Capability for EOS (LANCE). In collaboration with AIRS Project, the GES DISC has just released products from the Version 7 algorithm. The new version algorithm provides significant improvements over the previous version. The most substantial advances are: improved consistency between day and night water vapor; improved total column ozone and temperature; improved infrared-only (IR-only) retrievals, especially in high latitude regions; an improved Stochastic Cloud Clearing Neural Network used as a first guess at the initial value in the iterative retrieval process; and removal of ambiguity in surface classification in the IR-only retrieval algorithm. In addition, the GES DISC produces AIRS NRT imagery. The AIRS NRT imagery are generated by mosaicking and mapping the available AIRS 6-minute retrieval granules to a global projection. The images are constantly refreshed when new granules are produced. The AIRS NRT Viewer and LANCE Worldview provide visualization services to online users for AIRS NRT imagery. The data products used to generate this imagery include atmospheric temperature, humidity, precipitation, cloud, Dust Score, CO, and SO2. In this presentation, we will demonstrate visualization of the AIRS NRT imagery from the new Version 7, and demonstrate some improvements over the previous version. Progress on improving the AIRS NRT imagery, a collaboration project with the AIRS Applications Development Team at NASA Jet Propulsion Laboratory (JPL), will also be presented.

Feng Ding↗
NASA NTRSDate not supplied

Application of ML/AI for Identifying Earth Science Datasets in Research Publications

NASA Data Active Archive Centers, or DAACs, ingest, store and distribute data acquired from satellites, ground systems as well as modelling data. These data are organized by the datasets, each presenting collection of files usually associated with the certain mission, instrument, processing level, parameter(s), algorithm and/or model. The number of datasets offered by a single DAAC to the public varies. GES DISC, for example, currently offers for public use approximately ~1,300 datasets. While each publicly offered dataset comes with supporting documentation, it is challenging for novice and even experienced scientists to navigate among the datasets that offer similar parameters to find the datasets for their particular research application. Supplying dataset documentation with the scientific paper citations that refer to that dataset provides means for the dataset users to educate themselves with the application research that dataset is being used in. Collecting citations of the papers that use the datasets for their research yield valuable insights into application areas of those datasets, information about usage of the dataset groups for specific applications and those application topics. It also gives insights into the “deep metrics” of the dataset usage, as opposed to the common metrics of the dataset usage such as number of users who downloaded the dataset files and volumes of downloaded data. Association of a certain scientific paper with the dataset(s) presents a challenge because most of the paper authors do not properly cite the datasets, datasets usually have cryptic names and Digital Object Identifiers (DOIs) that are used for dataset identification were assigned to the datasets only few years ago. Simple Google or online library search do not provide even meaningful fraction of the results when performed by the dataset name or DOI, however they provide too many results when the search is done by more broader terms such as mission and instrument names. Attempts to create an AI system capable to identify dataset in the scientific papers have already been made using neural networks classifiers on the basis of the dataset mission, instrument and variable name. This method was applied to NASA SEDAC, which has 41 datasets in total. In GES DISC there can be as many as ~100 datasets per mission/instrument with some of the datasets consisting of multiple variables so there is a need for more differentiating parameters for dataset identification in the paper. The approach we are currently investigating is creating AI classifiers that are based on multiple dataset features, or keywords, extracted from the NASA Earthdata Common Dataset Repository (CMR). The features are weighted based on how precisely they can identify a dataset. The classifier uses preprocessed paper text as input and searches for the CMR datasets whose feature sets are the closest to the feature sets contained in the paper. The challenges of dataset identification include variety of ways the paper authors describe the datasets in their papers and incomplete tagging of the CMR dataset description (DIFs).

Irina Gerasimov↗
NASA NTRSDate not supplied

Search Enhancements using Natural Language Processing Techniques

NASA Goddard Earth Sciences Data and Information Services Center (GESDISC) is one of the 12 NASA Science Mission Directorate Data Centers. The main goal of GESDISC is to provide earth science data, information, and services to the earth science data community. Consequently, data discovery is at the center of our mission and our search engine is the primary tool for our users to interact, find, and access our data. Existing search approaches are largely focused on hard-matching of keywords in the search query with dataset metadata. Here we propose to expand the search by introducing a complementary natural language processing (NLP) search. At the heart of our proposed NLP search, we trained a joint embedding using scientific text corpus and a curated set of dataset metadata. The embedding learns the association between words in our dataset metadata and those of the scientific text corpus. This enables us to go beyond simple hard-matching of a query and data set metadata and have a notion of “similarity” between the search query and the datasets. We further integrated our NLP search into the Elastic Search (ES) framework leveraging similarity search capabilities offered through the “dense_vector” field type. Our preliminary evaluations show that our proposed NLP search has the potential to be utilized to complement the existing search engine and serve as a base for a dataset recommendation system.

Armin Mehrabian↗
NASA NTRSDate not supplied

Australian Bushfire in 2020: Accessing MERRA-2 Data in GES DISC Remotely through OPeNDAP & Calculating Statistics with Python3

The evolution and transport of thick haze from the 2020 Australian bushfire is tracked using the NASA Modern-Era Retrospective analysis for Research and Applications version 2 (MERRA-2) data archived at the NASA GES DISC data center. The MERRA-2 provides global data at 0.5 x 0.625 spatial resolution since the year 1980. In this use case, with xarray, a python3 library, we remotely accessed the hourly aerosol optical depth (AOD) and PM2.5 data through the OpeNDAP service provided by GES DISC. We also derived weekly data from hourly ones.

Xiaohua Pan↗
NASA NTRSDate not supplied

Creating a knowledge graph to connect scientific publications and datasets for improving discovery of GES DISC’s data and services

The NASA Goddard Earth Sciences Data and Information Services Center (GES DISC) archives and distributes to the public hundreds of Earth Science data collections. These collections are used in research, resulting in thousands of scientific papers published each year. As new users come to GES DISC for the data, it is important for them to understand how these data were used in the prior research. For this we are creating the Knowledge Graph that connects research paper citation and the data collection metadata. The relationships created in the graph have potential for the Web applications that utilize this information to directly connect the paper research to the GES DISC datasets and services. We will demonstrate these relationships using the Web application prototype.

Nathaniel Ross Crosby↗
NASA NTRSDate not supplied

Improving Earth Science Dataset Search with Publication

The NASA Goddard Earth Sciences Data and Information Services Center (GESDISC) archives a large number of Earth observational datasets. Thousands of the publications are created each year based on these datasets. The content of these publications can be used for discovery of the datasets based on the characteristics of applicational research. We leverage the content of these publications to retrieve the information about phenomena and domains where measurements from the datasets were utilized through linking these publications and dataset in Knowledge Graph. We retrieve phenomena and domain information using SWEET ontology and produce the set of keywords that are linked to the datasets. Further, we evaluate this link strength according to the frequency of dataset usage in the papers mentioning these keywords. We demonstrate how this linkage can improve dataset search by comparing the search results obtained from Common Metadata Repository (CMR) search and the publications based data.

Kristina Stoyanova↗
NASA NTRSDate not supplied

Automated classification of scientific publications linked to GES DISC datasets

The data collections archived and distributedby the GES DISC NASA data center arewidely utilized for various Earth Science studies.As these collections are created, many researchworks are published regarding the collections, algorithms,validations and applications. SinceGES DISC collects these publications and providestheir citations for the users, it is helpful tocategorize them based on how they relate to the datasetsthey are associated with. Specifically,whether the publication that is linked to GES DISCdataset is using it for applicational research,or if it describes the algorithm for dataset creation,or the validation of the dataset, or providesthe general overview of the data collection. Currently,this process requires simple manuallabelling, and as such, may be possible to solve viaautomation. To approach this problem, wedeveloped machine learning classifiers to predictthe category a publication belongs to. We usedmanually labeled publications as training data forsupervised machine learning algorithms:Random Forest and Naive Bayes. We achieved classificationaccuracy that is substantially betterthan the baseline accuracy, thus greatly improvingthe efficiency of the publication internalanalysis.

Rohan Dayal↗
NASA NTRSDate not supplied

An Automated Approach to Labelling Datasets in Earth Science Publications

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

Edward Jahoda↗
NASA NTRSDate not supplied

Supervised Machine Learning Approach for Classifying Earth Science Publications

The data collections archived and distributed by the GES DISC NASA data center are widely utilized for various Earth Science studies. As these collections are created, many research works are published regarding these collections' algorithms, their validation, and their applications. As NASA data centers collect these publications for public use, it is helpful to categorize them based on how they relate to their associated datasets. Specifically, whether the publication linked to the GES DISC dataset is using it for applicational research, describing the algorithm used for the dataset creation, validating the dataset, or providing a general overview of the data collection. Currently, this process requires simple manual labeling, and as such, it may be possible to solve via automation. To approach this problem, machine learning classifiers were developed to predict a publication's category. Manually labeled publications were used as the training data for the supervised machine learning algorithms, specifically Random Forest and Multinomial Naïve Bayes. After balancing the dataset and implementing the Multinomial Naïve Bayes algorithm, the classification accuracy achieved was substantially higher than the baseline accuracy, thus significantly improving the efficiency of publication labeling.

Rohan Dayal↗
NASA NTRSDate not supplied

Development of a Knowledge Graph for Dataset Discovery and Identification at a NASA Data Center

The NASA Goddard Earth Sciences Data and Information Services Center (GES DISC) archives and distributes hundreds of Earth Science data collections to the public. These collections are used in research, resulting in the publication of thousands of scientific papers each year. As new users come to GES DISC for data, it is important for them to understand how prior research used the data. To help researchers, a knowledge graph (KG) was designed and implemented to connect publication citations with dataset metadata. The relationships created in the graph have the potential to allow the Web applications that utilize this information to directly connect the publication to the GES DISC datasets and services. These relationships are demonstrated using a web application prototype. In addition, the graph can also make connections between publications, datasets, and measurements based on the mentions of datasets and their attributes in the publications. To demonstrate this capability, a web application was created that takes the excerpt from the publication and returns a most likely dataset and measurement pairing, ranking the results based on how often these datasets and measurements were used in prior publications.

Nathaniel Crosby↗
NASA NTRSDate not supplied

Towards Automated Analytics of Research Publications

For readers of scientific publications it remains a big challenge to unambiguously relate the published research with the data used. To a substantial degree it is attributed to authors, journals, editors, and reviewers not prioritizing correct data citation, which impacts traceability, repeatability, and giving credits to published authors and their funding sources. Furthermore, uniform classification of the content of the published research is hampered by journals using journal specific topics and letting authors to assign free text keywords to their papers. We demonstrate automated analytics methods for extracting and relating datasets used and the research application areas by processing 1,300 research papers that referenced the NASA Giovanni service (but probably not the datasets in particular) as supporting their publication process. This presentation was given during the 2022 ESIP January meeting held virtually in January 2022.

Irina Gerasimov↗
NASA NTRSDate not supplied

Application of a Dataset-Publication Knowledge Graph for Improving Earth Science Data Search

Finding a dataset at a NASA data center that is the best fit for the researcher’s application presents a challenge, not only for a novice user but for an experienced one, due to the data complexity and a multitude of choices of the existing data. Users often search for the data based on the application they are interested in, their research domain, phenomena, research topic, etc. As existing dataset metadata may not cover these search terms, the user may not obtain the most relevant results for their purpose. This problem was addressed by leveraging the content of the titles and abstracts of the research papers that utilize NASA datasets. For this, features from the paper titles and abstracts were extracted, and then a knowledge graph (KG) was used to link these features to the datasets used in that paper. The search for the datasets was tested by querying this knowledge graph through various terms extracted from Earth Science ontologies such as Semantic Web for Earth and Environment Technology (SWEET), and it was shown that this KG search outperforms the existing search that exclusively queries the dataset metadata.

Kristina Stoyanova↗
NASA NTRSDate not supplied

A Newly Developing Community-Oriented Data System from NASA GES DISC

Data services are essential to facilitate data access and to aid efficiency of conducting research and application activities. With emerging technologies such as cloud computing and AI/ML (Artificial Intelligence/Machine Learning) leading the pace of the data world, the NASA Goddard Earth Sciences Data and Information Services Center (GES DISC), home to the permanent archive for multidisciplinary Earth Observation (EO) geospatial data to study atmospheric composition, weather and climate variability, and water and energy cycles is no exception.Interfacing directly with users as part of data center work, we understand the challenges for the required time and effort to discover, visualize, and analyze large varieties and quantities of Earth Observation information for research, monitoring, and decision-making, largely due to the existing data and information systems aim to support experienced users, but has been proved difficult for non-earth scientists and new users that are unfamiliar with the variety of formats and structures in which data, metadata, and information are stored, as well as the required methods to use them. To address these challenges, I will update our latest activities with regard to water-and energy-related products and community-oriented and user-friendly services at the GES DISC, including our plans for the emerging technologies.

Jennifer Wei↗