IMPACT is an interdisciplinary team that works to further ESDS’s goal of overseeing the lifecycle of Earth science data to maximize the scientific return of NASA's missions and experiments for research and applied scientists, decision makers, and the society at large. IMPACT’s three focus areas are interagency collaboration, assessment and evaluation, and advanced concepts.

  • Manage Interagency Implementation: IMPACT connects ESDS with other agencies to improve knowledge and use of Earth science data.
  • Provide Assessment and Evaluation Expertise: IMPACT provides the informatics, data systems and domain science expertise needed to assess specific elements of NASA's Earth Science Data and Information System (ESDIS) Project and its existing processes.
  • Develop Advanced Concepts: IMPACT provides strategic, technical, and management expertise for rapid prototyping, development, and testing of advanced ideas in data and information systems for Earth observations.

IMPACT's Goals

  • IMPACT builds partnerships with other Federal agencies, the applications community, decision makers, NGOs, and other organizations to encourage the adoption of NASA’s Earth observation data into their workflows and operational models.
  • IMPACT enhances NASA’s existing data infrastructure, tools and services to encourage broader use of NASA’s data for all users.
  • IMPACT enables technology and innovation in order to lower the barriers to using complex Earth observation data.

IMPACT’s Projects

IMPACT supports the ESDS Program mission with multiple projects in three focus areas. Some of the projects are:


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.

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.


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.

Airborne Data Management Group (ADMG) 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.


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.

Public-Private Open Data Partnership (OpenData)
The goal of this effort is to:

  1. demonstrate the potential of cloud computing in applying algorithms to the data to enable processing and analytics at scale;
  2. improve over the existing methods of data search and minimize reliance on internal search tools; and
  3. explore partnerships in the field of artificial intelligence and machine learning in order to utilize these techniques in novel applications to address existing data discovery, access and use challenges.

IMPACT's AI and ML Research

The increase in Earth science observation instruments and platforms throughout the world has resulted in an exponential rate of data growth. This presents the Earth science community with a rich and ever expanding archive of useful data. The application of artificial intelligence (AI) and machine learning (ML) offer the potential for innovative new data analysis and the generation of valuable insights from this massive archive of Earth observation data.

The ML team within IMPACT works to build tools and pipelines that apply AI and ML techniques to improve discovery of NASA science data. For data systems and programs, AI and foundation models (FMs) have the potential to transform the three main aspects of open science: increasing accessibility to the scientific process and knowledge, making research and knowledge sharing more efficient, and understanding scientific impact.

Along with IBM Research, we are exploring AI technology, specifically FMs, to provide an easier way for researchers to analyze and draw insights from large NASA datasets. Contrary to conventional task-specific ML models that serve singular purposes, FMs are designed and fine tuned for a wide range of applications such as natural language processing or image recognition.

Our goals include the following:

•    Incorporate AI/ML into different stages of the data lifecycle to improve functionality and operations
•    Create forward-looking tools, services, and processes by envisioning new ways to lower barriers to data and information
•    Harness technology advances in data and information systems to expand community impact
•    Engage with commercial, academic, and international partners to collaborate on challenging problems and explore new innovations

By investing in targeted low risk, high reward technology, we aim to accelerate the adoption of new technologies for the broader use.

Recent successes include ImageLabeler, a user-friendly labeling interface that facilitates labeling multiple images at a time; the Harmonized Landsat and Sentinel-2 (HLS) Geospatial FM, the first geospatial FM specifically trained with NASA’s Earth observation satellite imagery; and the Phenomena Detection Portal, which uses machine learning for real-time detection of Earth science phenomena.


Last Updated