Artificial intelligence (AI) refers to the simulation of human decision-making abilities within a machine. Machine learning (ML) is a subfield of AI that uses statistics and mathematical models to detect patterns in data. Applying it to big data collections such as NASA Earth Observation Data, AI and ML can be used to quickly and efficiently sift through years of data and images to find relationships that humans cannot detect (or take too long) to detect. NASA's Earth Science Data Systems (ESDS) program is committed to using AI and recognizes the potential to significantly advance existing data system capabilities, improve operations, and maximize the use of NASA Earth Observation data.
The related concept is deep learning. It uses a huge neural network with many layers of processing units to harness computing power and improved training technology advances to learn complex patterns with a large amount of data.
ESDS AI/ML research is primarily carried out through NASA's interagency implementation and the Advanced Concepts Team (Impact). Located at NASA's Marshall Space Flight Center in Huntsville, Alabama, Impact works to promote the ESDS goal of maximizing scientific returns for NASA's mission and experiments for scientists, decision makers and society. The Impact ML team consists of machine learning experts, computer scientists and geoscience data experts and works to build tools and pipelines for applying ML algorithms to NASA Earth Science data sets to improve data discovery.
In addition to working with AI/ML via Impact, the NASA Distributed Active Archives Center (DAACS) team applies AI and ML to archive and distribute data. One example is ongoing work at NASA's Goddard Earth Sciences Data and Information Services Center (GES DISC), implementing a machine learning framework using natural language processing (NLP) to help GES disk data users find the right data set.
ESDS also promotes AI/ML research through progressive collaboration connections for NASA's Earth System Science (Access) program. This competitive program develops and implements technologies to effectively manage, discover, and utilize NASA Earth Observation Archives for Scientific Research and Applications to support NASA Earth Sciences research goals. The Access 2019 solicitation specifically called for ML technology development related to NASA Earth Science Data Systems (including new training data sets for ML).
Another NASA supports to promote AI/ML research is the Frontier Development Lab (FDL). FDL is an applied research accelerator created as an initiative through NASA's Chief Technologist Office and is based at NASA's Ames Research Center in Silicon Valley, California. Through collaborations within NASA and collaborations with academia and Silicon Valley companies, FDL is working on further NASA AI efforts.
