Earth observations are a key component which facilitates scientific progress. NASA's Interagency Implementation and Advanced Concepts Team (IMPACT) prototypes the latest technologies to support new science and applications from Earth observation data.
IMPACT Focus Areas
IMPACT expands the use of Earth observation data through innovation, partnerships, and technology.
Fostering Innovation
IMPACT works to improve existing processes and develop best practices that maximize the effectiveness and efficiency of Earth science data management and stewardship.
Building Strategic Connections
IMPACT helps to bring NASA Earth observations and data products to other agencies via services and software. Its efforts broaden data use, allowing scientists outside of NASA to better use NASA data.
Enabling Technology Adoption
IMPACT rapidly prototypes and tests the latest technical and management concepts using machine learning/artificial intelligence techniques. New capabilities are developed, proven, and infused across NASA’s Earth Science Data System program.
IMPACT is not just for developers—you don't need to be an expert developer to harness IMPACT's user-friendly and flexible tools and solutions. Our tools and solutions incorporate the latest in design and data management best practices, and come with straightforward, accessible documentation covering the aspects of implementation and use.
IMPACT Successes
IMPACT offers a diverse set of machine learning and data informatics tools to advance the use and management of Earth observation data.
APT
The Algorithm Publication Tool (APT) enables open, reproducible science by helping scientists write standardized, high-quality Algorithm Theoretical Basis Documents (ATBDs) collaboratively via a single end-to-end authoring tool. The APT establishes and implements a standardized ATBD governance process and provides a free and open portal to ensure all ATBDs are discoverable and accessible to users.
Hurricane Intensity Estimator
The Deep Learning-based Hurricane Intensity Estimator is an online platform that demonstrates the use of a machine learning model for estimating the wind speed of hurricanes.
pyQuARC
pyQuARC reads and evaluates metadata records with a focus on the consistency and robustness of the metadata, and flags opportunities to improve or add to contextual metadata information in order to help connect users to relevant data products.
Phenomena Detection Portal
The Phenomena Detection Portal is an online platform for visualizing the detection of multiple phenomena by machine learning models.
CASEI
The Catalog of Archived Suborbital Earth Science Investigations (CASEI) is an inventory of NASA’s airborne and field campaigns for Earth science. View the CASEI user interface demo.
ImageLabeler
ImageLabeler is a web-based tool used to facilitate the labeling of Earth science images for use in training machine learning models.
HDCRS Summer School
In collaboration with the IEEE GRSS Earth Science Informatics Technical Committee, IMPACT held a High Performance and Disruptive Computing in Remote Sensing (HDCRS) machine learning summer school session for 26 global and diverse students.
IMPACT's projects improve existing processes and develop best practices that maximize the effectiveness and efficiency of Earth science data management and stewardship. New capabilities are developed, proven, and infused across the Earth Science Data System program.
ADMG
The Airborne Data Management Group (ADMG), which leads the Airborne and Field Data Resource Center (AFDRC), develops systematic approaches to airborne data management and stewardship. The ADMG develops best practices for airborne data management and provides a knowledge base for airborne campaigns, data centers, managers, scientists and users.
ARC
Analysis and Review of CMR (ARC) focuses on improving the discoverability, accessibility, and usability of NASA’s Earth science data holdings by ensuring all NASA collection and granule level metadata records in NASA’s Common Metadata Repository (CMR) meet a minimum standard of quality. The ARC team reviews the metadata for these collections, identifies opportunities for improvement in the records, works with the data providers, develops methods to automate the quality evaluation checks, and develops processes to minimize issues in the future.
DCD
Data Curation for Discovery (DCD) designs and implements a systematic plan to assist other agencies in incorporating NASA Earth observation data into their workflows. The DCD team improves the discoverability of NASA Earth science data and other curated Earth observation data in trusted catalogs and platforms.
HLS
In the Harmonized Landsat and Sentinel-2 (HLS) project, data from the NASA/USGS Landsat 8 and Landsat 9 and the ESA (European Space Agency) Sentinel-2A and Sentinel-2B platforms generate a harmonized, analysis-ready surface reflectance data product. The resulting HLS global land surface reflectance data is generated every 2 to 3 days at 30 meter resolution.
Machine Learning Project
The Machine Learning Project team improves data discovery by building tools and pipelines that apply machine learning algorithms to NASA Earth science datasets.
SNWG
Satellite Needs Working Group (SNWG) is comprised of a team which serves as the data liaison between the U.S. Group on Earth Observations SNWG and ESDIS. Using the biennial surveys of participating agencies conducted by SNWG to assess their needs for U.S. government Earth observing satellite applications, the team creates a profile of agency needs and develops mappings to data that meet those needs.
IMPACT hosts periodic TechTalks to connect subject matter experts with the ESDS community. This webinar series focuses on mitigating misinformation in and about science.
Previous TechTalks
“Mitigating Misinformation in and About Science”
Dr. Jevin West
February 15, 2023
“TOPS and Oracle for Research"
Dr. Vivien Raymond
November 14, 2022
"Training Foundation Models Anywhere with Hybrid Cloud"
Dr. Marquita Ellis and Dr. Davis Wertheimer
August 30, 2022
"Five Geo-Computational Challenges for Rapid Assessment of Post-Disaster Areas Using Earth Observation (EO) Data"
Dr. Surya Durbha
June 15, 2022
"Developing a Smarter Way to Search: Parsing the Online ‘Forest’ To Find Data for Your Research Needs Using a Scalable Integrated Data Discovery System"
Dr. Kelly Rose and Vic Baker
December 6, 2021
"Advancing Global Food Security and SDGs with Machine Learning and Earth Observations"
Dr. Hannah Kerner
August 12, 2021
"Watson NLP Library"
Sukriti Sharma
April 20, 2021
"Building a Tiny Knowledge Graph with BERT and Graph Convolutions"
Dr. Dennis Gannon
March 11, 2021
"From Pixels to Products: An Overview of Satellite Remote Sensing"
Dr. Sundar Christopher
January 29, 2021
Check out the annual IMPACT newsletter for project highlights, successes, and details about in-progress work.
To receive a copy of our newsletter in your inbox, please email us.