IN14A:
Achieving Deep Learning by Systemizing Machine Learning with Big Data Engines II

Submit an Abstract to this Session Please know the abstract submission deadline has passed. There are no exceptions to this deadline and no new abstracts can be submitted.
You can still search the program to see your colleague�s abstract submissions as well as the sessions submitted for the 2016 Fall Meeting. The final program will be released in early October.


Session ID#: 16826

Session Description:
Big Data has created a mature class of disruptive technologies that have been adopted by a number of large-scale geoscience data infrastructures. While developments in Big Data are proceeding at pace, advanced, machine-automated methods are being introduced to extract information and knowledge from large volumes and varieties of data. However, it is reported that data preparation still takes the majority of the time spent on data mining and/or machine learning exercises. When scalability is realized for both volume and variety, Big Data systems are apt to make such exercises more effortless. They thus serve as ideal platforms to systemize machine learning and to achieve deep learning with much better value. In this session we seek presentations demonstrating the vision of Big Data for geosciences, reports of current machine/deep learning efforts, the challenges such efforts faced and/or are facing, and potentials and solutions in Big Data to address these challenges.
Primary Convener:  Kwo-Sen Kuo, University of Maryland, College Park, United States; Bayesics, LLC, Bowie, MD, United States
Conveners:  Michael J Friedel, GNS Science, Lower Hutt, New Zealand, Michael M Little, NASA, Earth Science Technology Office, Greenbelt, MD, United States and Jens F Klump, CSIRO, Mineral Resources, Perth, Australia
Chairs:  Michael M Little, NASA, Earth Science Technology Office, Greenbelt, MD, United States, Jens F Klump, CSIRO, Mineral Resources, Perth, Australia, Kwo-Sen Kuo, University of Maryland, College Park, United States; Bayesics, LLC, Bowie, MD, United States and Michael J Friedel, GNS Science, Lower Hutt, New Zealand
OSPA Liaison:  Kwo-Sen Kuo, University of Maryland, College Park, United States; Bayesics, LLC, Bowie, MD, United States
Index Terms:

1908 Cyberinfrastructure [INFORMATICS]
1914 Data mining [INFORMATICS]
1932 High-performance computing [INFORMATICS]
1942 Machine learning [INFORMATICS]

Abstracts Submitted to this Session:

Classification and Localization of Extreme Weather Patterns with Deep Learning (Invited) (167092)
Mr Prabhat1, Yunjie Liu2, Evan Racah2, Kenneth Kunkel3, David A Lavers4, Michael F Wehner2 and William Drew Collins5, (1)University of California Berkeley, Earth and Planetary Sciences, Berkeley, CA, United States, (2)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (3)CICS-NC/NCDC, Asheville, NC, United States, (4)Scripps Institution of Oceanography, La Jolla, CA, United States, (5)Lawrence Berkeley National Laboratory, Earth and Environmental Science, Berkeley, CA, United States
A Knowledge Discovery framework for Planetary Defense (183560)
Yongyao Jiang1, Chaowei Phil Yang2, Yun Li1, Manzhu Yu3, Myra Bambacus4, Bernie Seery4 and Brent Barbee4, (1)George Mason University Fairfax, Fairfax, VA, United States, (2)George Mason University Fairfax, Geography and Geoinformation Science, Fairfax, VA, United States, (3)Penn State University, State College, United States, (4)NASA Goddard Space Flight Center, Greenbelt, MD, United States
Exploring the Earth Using Deep Learning Techniques (Invited) (124461)
Pablo Rozas Larraondo, Benjamin James Kingston Evans and Joseph Antony, Australian National University, Canberra, ACT, Australia

Unsupervised Change Detection for Geological and Ecological Monitoring via Remote Sensing: Application on a Volcanic Area (188240)

Nicola Falco1, Gro B. M. Pedersen2, Olga Kolbrún Vilmunandardóttir3, Joaquin Maria Munoz Cobo Belart2, Fridthór Sófus Sigurmundsson3 and Jón Atli Benediktsson4, (1)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (2)University of Iceland, Institute of Earth Sciences, Reykjavik, Iceland, (3)University of Iceland, Institute of Life and Environmental Sciences, Reykjavik, Iceland, (4)University of Iceland, Faculty of Electrical and Computer Engineering, Reykjavik, Iceland
Evaluating data-driven causal inference techniques in noisy physical and ecological systems (135106)
Christopher Tennant1,2 and Laurel Larsen2, (1)Idaho State University, Geoghraphy, Pocatello, ID, United States, (2)University of California Berkeley, Geography, Berkeley, CA, United States
Riding the Hype Wave: Evaluating new AI Techniques for their Applicability in Earth Science (Invited) (125041)
Rahul Ramachandran, NASA Marshall Space Flight Center, Huntsville, AL, United States, Jia Zhang, Carnegie Mellon University Silicon Valley, Moffett Field, CA, United States, Manil Maskey, NASA, Office of Data Science and Informatics (ODSI), Huntsville, United States and Tsengdar J Lee, NASA Headquarters, Washington, United States
DeepSAT: A Deep Learning Approach to Tree-cover Delineation in 1-m NAIP Imagery for the Continental United States (193792)
Sangram Ganguly1, Saikat Basu2, Ramakrishna R Nemani1, Supratik Mukhopadhyay2, Andrew Michaelis3 and Petr Votava3, (1)NASA Ames Research Center, Moffett Field, CA, United States, (2)Louisiana State University, Computer Science, Baton Rouge, LA, United States, (3)California State University Monterey Bay, Seaside, CA, United States
Building Knowledge Graphs for NASA’s Earth Science Enterprise (176642)
Tsengdar J Lee1, Jia Zhang2, Rahul Ramachandran3, Runyu Shi2, Qihao Bao2, Patrick N Gatlin4, Amanda Markert5, Manil Maskey6 and Jeffrey Miller7, (1)NASA Headquarters, Washington, United States, (2)Carnegie Mellon University Silicon Valley, Moffett Field, CA, United States, (3)NASA Marshall Space Flight Center, Huntsville, United States, (4)NASA Marshall Space Flight Center, Huntsville, AL, United States, (5)University of Alabama in Huntsville, Earth System Science Center, Huntsville, AL, United States, (6)NASA, Office of Data Science and Informatics (ODSI), Huntsville, United States, (7)University of Alabama in Huntsville, Huntsville, AL, United States

See more of: Earth and Space Science Informatics