IN21D:
Deep Learning for Geoscience Posters


Submit an Abstract to this Session


Session ID#: 49601

Session Description:
Recent advances in computer science and data analytics have brought machine learning techniques to the forefront of geoscience research. As a result, old questions are being addressed in new ways as techniques are being developed to exploit large volume and complex data sets. Among the many machine learning techniques, the deep learning approach has proven to be particularly successful for a variety of scientific and industrial applications. In computer science domain, scientists have recently developed various novel deep learning algorithms for diverse applications. The collection of new algorithms includes convolutional neural networks, generative adversarial networks, and recurrent neural networks, to name a few. Simultaneously, there have been many exciting demonstrations of successful machine learning applications applying deep, active, reinforced, supervised and unsupervised techniques in the geoscience.  The goal of this session is to introduce those recent results and new directions to our geo-community of researchers, educators, and students.
Primary Convener:  Youzuo Lin, Los Alamos National Laboratory, Los Alamos, United States
Conveners:  Emily S Schultz-Fellenz, Los Alamos National Laboratory, EES-14, Los Alamos, NM, United States and David D Coblentz, Los Alamos National Laboratory, Los Alamos, United States
Primary Liaison:  Youzuo Lin, Los Alamos National Laboratory, Los Alamos, United States
Chairs:  Youzuo Lin, Los Alamos National Laboratory, Los Alamos, United States, Emily S Schultz-Fellenz, Los Alamos National Laboratory, EES-14, Los Alamos, NM, United States and David D Coblentz, University of Arizona, Tucson, United States
OSPA Liaison:  Youzuo Lin, Los Alamos National Laboratory, Los Alamos, United States
Index Terms:

0520 Data analysis: algorithms and implementation [COMPUTATIONAL GEOPHYSICS]
0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
1906 Computational models, algorithms [INFORMATICS]
1914 Data mining [INFORMATICS]

Abstracts Submitted to this Session:

Climate Science, Deep Learning, and Pattern Discovery: The Madden-Julian Oscillation as a Test Case (414589)
Benjamin A Toms1,2, Karthik Kashinath3, Mr Prabhat2, Mayur Mudigonda4 and Da Yang5,6, (1)Colorado State University, Fort Collins, CO, United States, (2)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (3)NVIDIA Corporation, Santa Clara, CA, United States, (4)University of California Berkeley, Berkeley, CA, United States, (5)University of California, Davis, Land, Air and Water Resources, Davis, United States, (6)Lawrence Berkeley National Laboratory, Berkeley, United States
Eikonal tomography constrained by local sparse and low-rank matrix factorization (423857)
Peter Gerstoft, University of California San Diego, Scripps Institution of Oceanography, La Jolla, United States, Michael Joseph Bianco, University of California San Diego, La Jolla, CA, United States, Ruixian Liu, University of California San Diego, Electrical and Computer Engineering, La Jolla, CA, United States and Hao Zhang, University of California San Diego,, Electrical Computer Engineering, San Diego, CA, United States
Detecting the hidden seismicity of Mars (448103)
Carene S Larmat, Los Alamos National Laboratory, Los Alamos, NM, United States and Xiaomeng Li, University of New Mexico Main Campus, Albuquerque, United States
Deep Learning to Represent Sub-grid Processes in Climate Models (348761)
Stephan Rasp, Ludwig Maximilians University of Munich, Munich, Germany, Mike S Pritchard, University California Irvine, Earth System Science, Irvine, United States and Pierre Gentine, Columbia University, Department of Earth and Environmental Engineering, New York, United States
Self-Supervised Feature Learning with CRF Embedding for Hyperspectral Image Classication (355297)
Yuebin Wang1, Jie Mei2 and Liqiang Zhang2, (1)China University of Geosciences Beijing, School of Land Science and Technology, Beijing, China, (2)Beijing Normal University, Beijing, China
Farm Land Assessment Using Deep Fully Convolutional Neural Networks (358195)
Junxiao Wang, Nanjing University of Finance & Economics, School of Public Administration, Nanjing, China, Xingong Li, University of Kansas, Department of Geography and Atmospheric Science, Lawrence, United States and Shenglu Zhou, Nanjing University, Nanjing, China
Can we rely on machine learning to reveal short term precursors of volcanic activity on Mt. Etna? (362661)
Flavio Cannavo, National Institute of Geophysics and Volcanology, Rome, Italy and Andrea Cannata, National Institute of Geophysics and Volcanology, Osservatorio Etneo, Rome, Italy; University of Perugia, Dipartimento di Fisica e Geologia, Perugia, Italy
Deep Learning for Transverse Cirrus Band Detection and Analysis (373469)
Jeffrey Miller1, Udaysankar S Nair2, Rahul Ramachandran3 and Manil Maskey3, (1)University of Alabama in Huntsville, Huntsville, AL, United States, (2)University of Alabama in Huntsville Earth System Science Center, Huntsville, AL, United States, (3)NASA Marshall Space Flight Center, Huntsville, United States
A Deep Learning Architecture for Long-Range Forecasting of Sea Surface Temperature Anomalies (395103)
Xi Liu1, Pang-Ning Tan2, Tyler Wilson3, Pouyan Hatami1 and Lifeng Luo4, (1)Michigan State University, East Lansing, MI, United States, (2)Michigan State University, Department of Computer Science and Engineering, East Lansing, United States, (3)Michigan State University, Computer Science and Engineering, East Lansing, MI, United States, (4)Michigan State University, Department of Geography, Environment, and Spatial Sciences, East Lansing, MI, United States
A Deep Neural Network Model for Improving Hourly Precipitation Estimates from Numerical Models (402701)
Baoxiang Pan1, Kuo-lin Hsu2, Amir AghaKouchak2 and Soroosh Sorooshian2, (1)University of California Irvine, Irvine, CA, United States, (2)University of California, Irvine, Department of Civil and Environmental Engineering, Irvine, United States
Deep learning based global Arctic sea ice concentration retrieval algorithm (403165)
Junhwa Chi1, Hyun Cheol Kim2 and Sung Jae Lee2, (1)Pukyong National University, Major of Big Data Convergence, Division of Data and Information Sciences, College of Information Technology and Convergence, Busan, South Korea, (2)Korea Polar Research Institute, Incheon, South Korea
Deep Graph Convolution for Weather Prediction (414017)
Tyler Wilson1, Xi Liu2,3, Pang-Ning Tan4, Pouyan Hatami3 and Lifeng Luo5, (1)Michigan State University, Computer Science and Engineering, East Lansing, MI, United States, (2)Milwaukee, WI, United States, (3)Michigan State University, East Lansing, MI, United States, (4)Michigan State University, Department of Computer Science and Engineering, East Lansing, United States, (5)Michigan State University, Department of Geography, Environment, and Spatial Sciences, East Lansing, MI, United States
Deep Cloud Classification Method based on Multi-Channel Satellite Images (429980)
Xinyue Su, Tsinghua University, Beijing, China and Tiejian Li, Tsinghua University, State Key Laboratory of Hydroscience and Engineering, Department of Hydraulic Engineering, Beijing, China
A Deep Learning Parameterization for Ozone Dry Deposition Velocities (438270)
Sam James Silva, Massachusetts Institute of Technology, Civil and Environmental Engineering, Cambridge, MA, United States, Colette L Heald, Massachusetts Institute of Technology, Civil and Environmental Engineering, Cambridge, United States and Sai Ravela, Massachusetts Institute of Technology, Department of Earth, Atmospheric and Planetary Sciences (EAPS), Cambridge, United States
Cloud characterization with deep learning (439373)
Ricardo Barros Lourenco, University of Chicago, Center for Robust Decision Making on Climate and Energy Policy(RDCEP), Chicago, IL, United States, Casper Neo, University of Chicago, Center for Robust Decision Making on Climate and Energy Policy (RDCEP), Chicago, IL, United States, Elisabeth J Moyer, University of Chicago, Department of the Geophysical Sciences, Chicago, United States and Ian T Foster, Argonne National Laboratory / University of Chicago, Chicago, IL, United States
Estimating Douglas Fir volume proportion from Remote Sensing images using Deep Learning (458289)
Snehal More, Virginia Tech, Blacksburg, United States and L. M. Moskal, University of Washington Seattle Campus, School of Environmental and Forest Sciences, Seattle, United States
Hierarchical Scale Dependence and Co-existence of Chaotic and Non-Chaotic Processes within a Generalized Lorenz Model: A Study using Kernel PCA and SVM Methods (462110)
Jialin Cui and Bo-Wen Shen, San Diego State University, San Diego, CA, United States
Bathymetry estimation using deep learning techniques (468849)
Hojat Ghorbanidehno1, Jonghyun Harry Lee2, Matthew Farthing3, Tyler Hesser3, Peter K Kitanidis4 and Eric F Darve1, (1)Stanford University, Mechanical Engineering, Stanford, CA, United States, (2)University of Hawai‘i at Mānoa, Civil, Environmental and Construction Engineering/ Water Resources Research Center, Honolulu, United States, (3)U.S. Army Engineer Research and Development Center, Coastal and Hydraulics Laboratory, Vicksburg, United States, (4)Stanford University, Department of Civil and Environmental Engineering, Stanford, CA, United States

See more of: Earth and Space Science Informatics