NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
earth science deep learning: applications and lessons learnedDeep Learning: A subfield of machine learning; Algorithms inspired by function of the brain; Scales with amount of training data; Powerful tool without the need for feature engineering; Suitable for Earth Science applications. Deep Learning for Earth science at MSFC (Marshall Space Flight Center): Phenomena identification; Hurricane intensity (wind speed) estimation; Severe storm (hailstorm) detection; Transverse bands detection; Entity extraction for knowledge graph creation; Ephemeral water detection.
Document ID
20190025806
Document Type
Presentation
Authors
Maskey, Manil
(NASA Marshall Space Flight Center Huntsville, AL, United States)
Ramachandran, Rahul
(NASA Marshall Space Flight Center Huntsville, AL, United States)
Miller, J. J.
(Alabama Univ. Huntsville, AL, United States)
Zhang, Jia
(Carnegie Mellon Univ. Pittsburgh, PA, United States)
Gurung, Iksha
(Alabama Univ. Huntsville, AL, United States)
Date Acquired
June 9, 2019
Publication Date
July 24, 2018
Subject Category
Earth Resources and Remote Sensing
Report/Patent Number
MSFC-E-DAA-TN56304
Meeting Information
IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2018)(Valencia)
Funding Number(s)
WBS: 656052
CONTRACT_GRANT: NNM11AA01A
Distribution Limits
Public
Copyright
Portions of document may include copyright protected material.
Keywords
Labeled Data
Training
Deep Learning
Events

Available Downloads

NameType 20190025806.pdf STI

Related Records

IDRelationTitle20180008578See AlsoEarth Science Deep Learning: Applications and Lessons Learned