AI Techniques for Improving Predictive Understanding of Climate Modes of Variability and Their Teleconnections
AI Techniques for Improving Predictive Understanding of Climate Modes of Variability and Their Teleconnections
Session ID#: 124653
Session Description:
The traditional understanding of low-frequency modes of climate
variability and their teleconnections using principally linear
approaches have demonstrably limited our predictive understanding of
the climate system. A prominent example of this is the poor prediction
of precipitation over California during the 2015-16 ENSO event, which
is generally attributable to the limited understanding of the
evolution of the diverse forms of ENSO and their varied impacts.
Creative application of AI techniques to earth system science data
(both from observations and models) for predictions and facilitating
mechanistic understanding in recent studies shows promise. With the
purpose of collecting the current state of knowledge, we invite all
submissions focused on using such non-traditional approaches to
advance predictive understanding of different modes of climate
variability and their teleconnections.
variability and their teleconnections using principally linear
approaches have demonstrably limited our predictive understanding of
the climate system. A prominent example of this is the poor prediction
of precipitation over California during the 2015-16 ENSO event, which
is generally attributable to the limited understanding of the
evolution of the diverse forms of ENSO and their varied impacts.
Creative application of AI techniques to earth system science data
(both from observations and models) for predictions and facilitating
mechanistic understanding in recent studies shows promise. With the
purpose of collecting the current state of knowledge, we invite all
submissions focused on using such non-traditional approaches to
advance predictive understanding of different modes of climate
variability and their teleconnections.
Index Terms:
0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
3337 Global climate models [ATMOSPHERIC PROCESSES]
3339 Ocean/atmosphere interactions [ATMOSPHERIC PROCESSES]
3373 Tropical dynamics [ATMOSPHERIC PROCESSES]
Primary Convener: Linsey Passarella, University of Tennessee, Knoxville, TN, United States
Conveners: Salil Mahajan, Oak Ridge National Laboratory, Computational Sciences and Engineering Division and Climate Change Science Institute, Oak Ridge, United States, Min Xu, Oak Ridge National Laboratory, Oak Ridge, TN, United States and Muralikrishnan Gopalakrishnan Meena, Oak Ridge National Lab, Oak Ridge, TN, United States
Primary Liaison: Linsey Passarella, University of Tennessee, Knoxville, TN, United States
See more of: Atmospheric Sciences