A41H:
Novel Methods for Combining Physical Simulation, Machine Learning, and Data-Driven Analysis in Climate Studies and Geophysical Sciences II Posters

Submit an Abstract to this Session



Session ID#: 30687

Session Description:
Simulation of physical processes through solution of differential equations, or mechanistic models, serves as a core tool of geophysical studies. In contrast to cause and effect-driven Physical Simulation (PS), Machine Learning (ML) models instantiate pattern recognition techniques and often operate as a black box. Additionally, advances in data collection and data-driven analysis provide new opportunities for insights in the climate sciences and beyond. Novel data-based techniques offer new approaches to uncertainty and error quantification, pattern recognition, and high-dimensional data analysis. Questions of how to combine PS and ML solutions and use data-driven analysis to advance understanding of physical systems and improve predictive models are the focus of this session. Cross-disciplinary presentations that demonstrate applied combinations or specific applications of PS with ML and data-driven analysis are encouraged. Examples may include data assimilation, filtering, use of PS to develop training data sets for ML and approaches to classification of PS outputs.
Primary Convener:  Sean A McKenna, IBM Ireland, Dublin, Ireland
Conveners:  Ronni Grapenthin, University of Alaska Fairbanks, Geophysical Institute, Fairbanks, AK, United States, Mollie Van Gordon, University of California Berkeley, Berkeley, CA, United States and Zhaohua Wu, Florida State University, Tallahassee, United States
Chairs:  Mollie Van Gordon, University of California Berkeley, Berkeley, CA, United States and Sean A McKenna, IBM Ireland, Dublin, Ireland
OSPA Liaison:  Zhaohua Wu, Florida State University, Tallahassee, United States

Cross-Listed:
  • B - Biogeosciences
  • H - Hydrology
  • NG - Nonlinear Geophysics
  • S - Seismology
Index Terms:

0430 Computational methods and data processing [BIOGEOSCIENCES]
1816 Estimation and forecasting [HYDROLOGY]
3315 Data assimilation [ATMOSPHERIC PROCESSES]
7212 Earthquake ground motions and engineering seismology [SEISMOLOGY]

Abstracts Submitted to this Session:

Defining Higher-Order Turbulent Moment Closures with an Artificial Neural Network and Random Forest (216037)
Jeremy McGibbon, Allen Institute for AI, Seattle, United States and Christopher Stephen Bretherton, Univ Washington, Seattle, WA, United States
3D Cloud Field Prediction using A-Train Data and Machine Learning Techniques (218777)
Chelsea Leigh Johnson, Georgia Institute of Technology Main Campus, Atlanta, GA, United States
Machine learning of atmospheric chemistry. Applications to a global chemistry transport model. (238341)
Mathew J Evans, University of York, Wolfson Atmospheric Chemistry Laboratories, Department of Chemistry, York, United Kingdom; National Centre for Atmospheric Science, York, United Kingdom and Christoph Andrea Keller, Global Modeling and Assimilation Office, Global Modeling and Assimilation Office, Greenbelt, United States
Tracing the source of numerical climate model uncertainties in precipitation simulations using a feature-oriented statistical model (262331)
Yun Xu, Lawrence Berkeley National Laboratory, Berkeley, CA, United States, Andrew D Jones, Lawrence Berkeley National Laboratory, Climate and Ecosystem Sciences Division, Berkeley, United States and Alan Rhoades, Lawrence Berkeley National Laboratory, Berkeley, United States
High resolution tempo-spatial ozone prediction with SVM and LSTM (266815)
Duanfeng Gao1, Yawen Zhang1, Zhen Qu2, Kira Sadighi3, Evan Coffey4, Qi LIU1, Michael Hannigan4, Daven K Henze5, Robert Dick6, Li Shang1 and Qin Lv1, (1)University of Colorado Boulder, Boulder, CO, United States, (2)University of Colorado, Mechanical Engineering, Boulder, United States, (3)University of Colorado-Boulder, Boulder, CO, United States, (4)University of Colorado at Boulder, Boulder, CO, United States, (5)University of Colorado Boulder, Department of Mechanical Engineering, Boulder, United States, (6)Madison, AL, United States
Machine Learning Classification of Heterogeneous Fields to Estimate Physical Responses (272590)
Sean A McKenna1, Albert Akhriev2, Carlos Alzate2 and Sergiy Zhuk2, (1)IBM Ireland, Dublin, Ireland, (2)IBM Research Ireland, Dublin, Ireland
Using Perturbed Physics Ensembles and Machine Learning to Select Parameters for Reducing Regional Biases in a Global Climate Model (282884)
Sihan Li1, David E Rupp2, Linnia Hawkins3, Philip Mote4, Doug J McNeall5, Sparrow Sarah1, David Wallom6 and Richard Arthur Betts5, (1)Oxford e-Research Centre, Oxford University, Oxford, United Kingdom, (2)Oregon Climate Change Research Institute, CEOAS/OSU, Corvallis, OR, United States, (3)Oregon State University, Forest Ecosystems and Society, Corvallis, OR, United States, (4)Oregon Climate Change Research Institute, Corvallis, OR, United States, (5)Met Office Hadley Centre, Exeter, United Kingdom, (6)OeRC, University of Oxford, United Kingdom
Coupling a Neural Network with Atmospheric Flow Simulations to Locate and Quantify CH4 Emissions at Well Pads (300553)
Bryan Travis, Planetary Science Institute, Tucson, AZ, United States, Jeremy Sauer, NSF National Center for Atmospheric Research, Boulder, United States and Manvendra Krishna Dubey, Los Alamos National Laboratory, Earth and Environmental Science Division, Los Alamos, NM, United States
Application of Recurrent Neural Networks on El Nino Impact on California Climate (301337)
Justin Le1, Hesham Mohamed El-Askary2 and Mohamed Allali1, (1)Chapman University, Orange, CA, United States, (2)Alexandria University, Department of Environmental Science, Faculty of Science, Alexandria, Egypt
A Big Data Approach for Situation-Aware estimation, correction and prediction of aerosol effects, based on MODIS Joint Atmosphere product (collection 6) time series data (225792)
Ananjay Kumar Singh and Durga Toshniwal, Indian Institute of Technology Roorkee, Computer Science and Engineering, Roorkee, India
Antarctic Temperature Extremes from MODIS Land Surface Temperatures: New Processing Methods Reveal Data Quality Puzzles (233099)
Glenn Grant and David W Gallaher, National Snow and Ice Data Center, Boulder, CO, United States
Spectral Analysis: From Additive Perspective to Multiplicative Perspective (250037)
Zhaohua Wu, Florida State University, Tallahassee, United States
Global Warming and Geographically Scalar Climatic Objects Exist: An Ontologically Realist and Object-Oriented Analysis of the Daymet TMAX Climate Summaries for North America (287149)
Charles Parsons Jackson, New Mexico State University Main Campus, Las Cruces, NM, United States
Global Climatic Indices Influence on Rainfall Spatiotemporal Distribution : A Case Study from Morocco (301366)
Mahmoud Zemzami1, Racha Elkadiri1 and Josh Phillips2, (1)Middle Tennessee State University, Murfreesboro, TN, United States, (2)Middle Tennessee State University, Computer Science, Murfreesboro, TN, United States
Using Machine Learning as a fast emulator of physical processes within the Met Office's Unified Model (244617)
Alberto Arribas1, Jacob Tomlinson1, Rachel Prudden2 and Niall Robinson1, (1)Met Office, Informatics Lab, Exeter, United Kingdom, (2)Met Office, Informatics lab, Exeter, United Kingdom

See more of: Atmospheric Sciences