NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
DELTA: An Open-Source Framework to Simplify Deep Learning with Satellite ImageryDELTA (Deep Earth Learning, Tools, and Analysis) is an open-source framework developed at NASA for deep learning on satellite imagery based on tensorflow. It helps simplify data engineering and preprocessing steps and reduces the need for a lot of the boilerplate code that needs written to make datasets palatable for machine learning. This lets data scientists focus on model development while DELTA handles the grunt work. This presentation will demonstrate DELTA’s functionality and share some examples from an active project using it for flood mapping.
Document ID
20210018788
Acquisition Source
Ames Research Center
Document Type
Presentation
Authors
Michael von Pohle
(Universities Space Research Association Columbia, Maryland, United States)
Brian Coltin
(Stinger Ghaffarian Technologies (United States) Greenbelt, Maryland, United States)
Scott Mcmichael
(KBR (United States) Houston, Texas, United States)
Padraig Furlong
(Wyle (United States) El Segundo, California, United States)
Date Acquired
July 16, 2021
Subject Category
Earth Resources And Remote Sensing
Meeting Information
Meeting: LaRC Data Science Expo
Location: Hampton, VA
Country: US
Start Date: July 13, 2021
End Date: July 15, 2021
Sponsors: Langley Research Center
Funding Number(s)
CONTRACT_GRANT: NNA16BD14C
CONTRACT_GRANT: 80ARC020D0010
Distribution Limits
Public
Copyright
Portions of document may include copyright protected material.
Technical Review
Single Expert