EP027
Machine Learning Applications in Earth Surface Processes Research

Session ID#: 75302

Session Description:
A rapidly-increasing amount of data is available to researchers studying earth surface processes. Complementary to these new data are the development of highly accessible machine learning tools that allow users to gain insight and make predictions with a range of techniques for regression and classification, Bayesian inference, and deep learning. Machine learning techniques can provide new and exciting ways to interpret, understand, and predict earth surface processes from small to large scales — from sediment transport and hydrodynamics to large-scale morphological behavior, ecogeomorphology, climate- and storm- driven processes, human couplings and decision support tools. We are soliciting contributions to this session that highlight the use of machine learning techniques to address issues relevant for geomorphology, earth surface processes, hydrology, and coastal processes research.
Index Terms:

1824 Geomorphology: general [HYDROLOGY]
1910 Data assimilation, integration and fusion [INFORMATICS]
1942 Machine learning [INFORMATICS]
4217 Coastal processes [OCEANOGRAPHY: GENERAL]

Primary Convener:  Kristen Splinter, University of New South Wales, Sydney, NSW, Australia
Conveners:  Margaret L Palmsten, Naval Research Laboratory, Stennis Space Center, MS, United States and Evan B Goldstein, University of North Carolina at Greensboro, Geography, Environment, and Sustainability, Greensboro, NC, United States
Primary Liaison:  Kristen Splinter, University of New South Wales, Sydney, NSW, Australia
 
Simulation to the dynamics of soil organic carbon stock in alpine regions with machine learning technique (486702)
Meng Zhu1, Wei Liu Dr.1, Qi Feng2 and Chengqi Zhang Dr.1, (1)Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, China, (2)Key Laboratory of Ecohydrology of Inland River Basin, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, China
 
Automated channel water extraction in complex areas using machine learning algorithms applied to airborne LiDAR data: the case of the Mont Saint Michel bay (490725)
Laurent Froideval, Xavier Pellerin LE BAS, Nathan Fillâtre, Christophe Conessa, Olivier Monfort and Laurent Benoit, Normandie Univ, UNICAEN, UNIROUEN, CNRS, M2C, Laboratoire de Morphodynamique Continentale et Côtière (M2C), Caen, France
 
DEEP LEARNING AS A TOOL FOR RAPIDLY ASSESSING PORE-WATER PRESSURE CONDITIONS IN HILLSLOPES (493161)
Elijah David Orland, University of Oregon, Earth Sciences, Eugene, OR, United States, Josh J Roering, University of Oregon, Eugene, OR, United States, Benjamin B Mirus, USGS Geologic Hazards Science Center, Golden, CO, United States, Matthew A. Thomas, USGS, Geologic Hazards Science Center, Golden, CO, United States and Brian D Collins, USGS Landslide Hazards Program, Menlo Park, CA, United States
 
Machine learning predictions of submarine slope instability across multiple spatial and temporal scales (Invited) (499483)
Jeffrey Obelcz1, Warren T Wood2, Benjamin J Phrampus3 and Taylor Runyan Lee3, (1)NRC Postdoctoral Investigator, US Naval Research Laboratory, Stennis, MS, United States, (2)US Naval Research Laboratory, Geology and Geophysics, Washington, DC, United States, (3)US Naval Research Laboratory, Geology and Geophysics, Stennis Space Center, MS, United States
 
Developing a CNN for automated detection of Carolina bays from publicly available LiDAR data (503330)
Mark Lundine, University of Delaware, Oceanography, Lewes, DE, United States and Arthur C Trembanis, University of Delaware, School of Marine Science and Policy, Newark, DE, United States
 
An Assessment of Transfer Learning Methods for Coastal Change Detection Using Convolutional Neural Networks (Invited) (513418)
Mara Morgenstern Orescanin, Naval Postgraduate School, Oceanography, Monterey, CA, United States, Marko Orescanin, California State University Monterey Bay, Seaside, CA, United States, Jeremy P Metcalf, Naval Postgraduate School, physics, Monterey, United States and Theodore A Ayoub, Naval Postgraduate School, Computer Science, Monterey, United States
 
Discerning abandoned farmland using harmonic time-series and machine learning analysis of Sentinel-2A imagery- A case study of Gwanyang city, South Korea (513850)
Heeyeun Yoon, Seoul National University, Department of Landscape Architecture and Rural Systems Engineering, College of Agriculture and Life Science, Seoul, Korea, Republic of (South) and Soyoun Kim, Seoul National University, Department of Landscape Architecture and Rural Systems Engineering, Seoul, Korea, Republic of (South)
 
A comprehensive analysis of model outputs characterizes and compares machine-learning-enabled classification of rivers in seven distinct regions of California (USA) (519222)
Hervé Guillon1, Colin Francis Byrne1, Belize Arela Albin Lane2, Samuel Sandoval Solis1 and Gregory B Pasternack1, (1)University of California Davis, Land, Air, and Water Resources, Davis, CA, United States, (2)Utah State University, Logan, UT, United States
 
Advancing geomechanical analyses with deep learning to predict landslide susceptibility from spatially explicit strength and stress states (520640)
Samuel G. Roy1, Peter Ortquist Koons1, Gregory E Tucker2 and Phaedra Upton3, (1)University of Maine, School of Earth and Climate Sciences, Orono, ME, United States, (2)Univ Colorado, Boulder, CO, United States, (3)GNS Science, Lower Hutt, New Zealand
 
Combining a stochastic climate emulator with surrogate models of dynamic coastal simulators to drive coastal flood impacts research (538087)
Peter Ruggiero1, Dylan Anderson2,3, Fernando J. Mendez4, Tyler Anderson5, Ana Rueda4, Laura Cagigal6, John J Marra7, Patrick Barnard8 and Mark Merrifield9, (1)Oregon State University, Corvallis, OR, United States, (2)Oregon State University, Civil and Construction Engineering, Corvallis, OR, United States, (3)Oak Ridge Institute for Science and Education, Kitty Hawk, NC, United States, (4)University of Cantabria, Ciencias y Tecnicas del Agua y del Medio Ambiente, Santander, Spain, (5)Oregon State University, Civil and Construction Engineering, Corvallis, United States, (6)University of Cantabria, Santander, Spain, (7)NOAA Honolulu, Honolulu, HI, United States, (8)USGS, Santa Cruz, CA, United States, (9)SCRIPPS, San Diego, United States
 
Modelling global river dissolved silicon export using machine learning (538322)
Anna Phillips and Sharon A Cowling, University of Toronto, Toronto, ON, Canada
 
Digital Soil Mapping using Machine Learning in the Bob Marshall Wilderness, Montana (542403)
Claire E Simpson1, Suzann Kienast-Brown2, Jay Skovlin3, Robert Vaughan1, Jane Karinen4, Vincent Archer5, Eva Muller2, Larry Laing6, Nathan Pugh7 and Kevin Megown8, (1)RedCastle Resources, onsite contractor to USDA Forest Service, Geospatial Technology and Applications Center (GTAC), Salt Lake City, UT, United States, (2)Natural Resources Conservation Service (NRCS) Region 4, Bozeman, MT, United States, (3)Natural Resources Conservation Service Major Land Resource Area (NRCS MLRA), Missoula, MT, United States, (4)Natural Resources Conservation Service Major Land Resource Area (NRCS MLRA), Missoula, United States, (5)US Forest Service Missoula, Missoula, United States, (6)US Forest Service Washington DC, Washington, DC, United States, (7)US Forest Service, Geospatial Technology and Applications Center (GTAC), Salt Lake City, UT, United States, (8)US Forest Service, Geospatial Technology and Applications Center (GTAC), Salt Lake City, United States
 
Supervised, Color-enhanced Multiscale Curvature Classification of Lidar and Structure-from-Motion Point Clouds for Geomorphic Applications (544130)
Robert Sare and George E Hilley, Stanford University, Geological Sciences, Stanford, CA, United States
 
Developing a probabilistic model of sediment resuspension over oscillatory ripples (567895)
Margaret Palmsten1, Allison Penko2, Samuel P Bateman3 and Donya P Frank2, (1)US Naval Research Laboratory, Washington, DC, United States, (2)Naval Research Lab Stennis Space Center, Stennis Space Center, MS, United States, (3)Naval Research Laboratory, Stennis Space Center, MS, United States
 
A machine learning approach for identifying dune toes on beach profile transects (570133)
Tomas Beuzen, University of New South Wales, Sydney, NSW, Australia, Joshua Simmons, Water Research Laboratory, UNSW Sydney, School of Civil and Environmental Engineering, Sydney, NSW, Australia, Mitchell Harley, UNSW Australia, Australia, Nathaniel G Plant, USGS, Saint Petersburg, FL, United States and Hilary F Stockdon, US Geological Survey, Saint Petersburg, FL, United States
 
Supervised Deep Learning based approach for Automated Segmentation and Tracking of Lobes Deposited by Turbidity Currents. (572577)
Sharad Shashank1, Huafei Sun2, David C J D Hoyal2, Mrugesh Shringarpure2 and Amit Kushwaha2, (1)ExxonMobil Services & Technology Private Limited, Bengaluru, India, (2)ExxonMobil Upstream Research Company, Houston, TX, United States
 
Deep Learning Super-Resolution for Satellite Image Spatial-Resolution Enhancement Using Hyper-Spatial Resolution UAS Imagery for Wetland Monitoring (575450)
Michael J Starek, Texas A&M University Corpus Christi, School of Engineering and Computing Sciences, Corpus Christi, TX, United States and Mohammad Pashaei, Texas A&M University Corpus Christi, Computing Sciences, Corpus Christi, United States
 
Assessing the Transferability of Cloud Detection Algorithm Built from Machine Learning among Optical Remote Sensing Imageries (590589)
Hung-Hsien Wan, National Central University, Taoyuan, Taiwan and Kuo-Hsin Tseng, National Central University, Center for Space and Remote Sensing Research, Taoyuan, Taiwan
 
Finding Anthropogenic Dark Earth in the Amazon Basin Using Fully Convolutional Networks (597206)
Luiz Fernando Leal1,2, Morgan J. Schmidt2, Samuel Lukens Goldberg2, J Taylor Perron3, Dorothy Hosler4, Michael Heckenberger5, Wetherbee Bryan Dorshow6, Bruno Moraes7, Eduardo Kazuo Tamahana8, Kumessi Waura9, Wate Kuikuro9 and Afukaka Kuikuro9, (1)Florida Institute of Technology, Aerospace, Physics and Space Sciences, Melbourne, FL, United States, (2)Massachusetts Institute of Technology, Earth, Atmospheric and Planetary Sciences, Cambridge, MA, United States, (3)Massachusetts Institute of Technology, EAPS, Cambridge, MA, United States, (4)Massachusetts Institute of Technology, Materials Science and Engineering, Cambridge, MA, United States, (5)University of Florida, Anthropology, Gainesville, FL, United States, (6)Organization Not Listed, Washington, DC, United States, (7)University of Pittsburgh, Anthropology, Pittsburgh, United States, (8)Mamirauá Institute for Sustainable Development, Amazonas, Brazil, (9)Kuikuro Indigenous Association of the Upper Xingu (AIKAX), Ipatse, Brazil
 
deep learning techniques for riverine bathymetry and flow velocity estimation (598858)
Hojat Ghorbanidehno1, Jonghyun Harry Lee2, Matthew Farthing3, Ty Hesser4, Peter K Kitanidis5 and Eric F Darve1, (1)Stanford University, Mechanical Engineering, Stanford, CA, United States, (2)University of Hawai‘i at Mānoa, Civil and Environmental Engineering, Honolulu, HI, United States, (3)US Army Corps of Engineers, Coastal and Hydraulics Laboratory, Vicksburg, MS, United States, (4)US Army Corps of Engineers, Vicksburg, MS, United States, (5)Stanford University, Department of Civil and Environmental Engineering, Stanford, CA, United States
 
Machine learning as supporting method for UXO mapping and detection (600361)
Jens Greinert, Mareike Kampmeier, Patrick Michaelis and Everardo Gonzalez, GEOMAR Helmholtz Centre for Ocean Research Kiel, Marine Geosystems - DeepSea Monitoring, Kiel, Germany
 
Identifying Anomalies in Surface Water Quality Using Isolation Forest (600568)
Armin Mehrabian1 and Nima Pahlevan1,2, (1)NASA Goddard Space Flight Center, Greenbelt, MD, United States, (2)Science Systems and Applications, Inc., Lanham, MD, United States
 
Analysis of Machine Learning in Earth Science Using Network Visualization and Natural Language Processing (602898)
Laura Yu Zheng1, Arif Albayrak2, William L Teng3, Mohammad G Khayat1 and Long Pham4, (1)NASA Goddard Space Flight Center, Greenbelt, MD, United States, (2)ADNET Systems Inc. Greenbelt, Greenbelt, MD, United States, (3)NASA GES DISC (ADNET Systems), Greenbelt, MD, United States, (4)NASA - GSFC, Greenbelt, MD, United States
 
Using the Twitter Record from Hurricane Irma to Investigate Coastal Storm Impacts (607847)
Evan B Goldstein1, Saed Sayedahmed2 and Somya Mohanty2, (1)University of North Carolina Greensboro, Greensboro, NC, United States, (2)University of North Carolina at Greensboro, Department of Computer Science, Greensboro, United States
 
Using artificial neural networks to quantify erosion by mega-floods and the implications for paleoflood discharge reconstruction (608188)
Scott Robert David1, Isaac J Larsen2 and Michael P. Lamb2, (1)University of Massachusetts Amherst, Department of Geological Sciences, Amherst, MA, United States, (2)California Institute of Technology, Pasadena, CA, United States
 
Interpreting Sediment Provenance, Transport, Diagenesis, and Basinal Evolution Using Positive Matrix Factorization of XRF Data from Drill Cores (608447)
Tyler Jacob Rust and Jeffrey Pietras, Binghamton University, Binghamton, NY, United States
 
Applications of Deep Neural Network to Near-shore Bathymetry with Sparse Measurements (610198)
Yizhou Qian, Stanford University, Institute for Computational and Mathematical Engineering, Stanford, CA, United States, Hojat Ghorbanidehno, Stanford University, Stanford, CA, United States, Jonghyun Harry Lee, University of Hawai‘i at Mānoa, Civil and Environmental Engineering, Honolulu, HI, United States, Matthew Farthing, US Army Corps of Engineers, Coastal and Hydraulics Laboratory, Vicksburg, MS, United States, Ty Hesser, US Army Corps of Engineers, Vicksburg, MS, United States, Peter K Kitanidis, Stanford University, Department of Civil and Environmental Engineering, Stanford, CA, United States and Eric F Darve, Stanford University, Mechanical Engineering, Stanford, CA, United States
 
Identifying surface grain size distributions from images using computer vision and machine learning methods (618751)
Tobias Müller, Northwest Hydraulic Consultants Ltd., North Vancouver, Canada and Marwan A Hassan, Univ British Columbia, Vancouver, BC, Canada
 
Machine Learning Application to Sand Dune Model Prediction Using Generative Adversarial Networks (GANs) (624279)
Jenna Horrall, James Madison University, Computer Science, Chesapeake, VA, United States, Divya Mohan, University of California, Berkeley, College of Engineering, Berkeley, CA, United States, Kelly Kochanski, University of Colorado at Boulder, Geological Sciences, Boulder, CO, United States and Barry Rountree, Lawrence Livermore National Laboratory, Computation Division, Livermore, United States
 
New Model to Identify Air Pollution Sources with Machine-learning Technique (629412)
Yong Pyo Kim, Ewha Womans University, Department of Chemical Engineering and Materials Science, Seoul, South Korea, Insun KIM, Ewha Womans University, Seoul, Korea, Republic of (South) and Daehyun Wee, Ewha Womans University, Department of Environmental Science and Engineering, Seoul, South Korea
See more of: Earth and Planetary Surface Processes
<< Previous Session Proposal | Next Session Proposal >>