YoVDO

Earth System Emulation - Duncan Watson-Parris #CLIMATE-C21

Offered By: Kavli Institute for Theoretical Physics via YouTube

Tags

Earth System Science Courses Big Data Courses Machine Learning Courses Climate Change Courses Uncertainty Analysis Courses

Course Description

Overview

Explore Earth System Emulation in this 45-minute conference talk from the Machine Learning for Climate KITP conference. Delve into the challenges of informing society about future climate changes at regional and local scales, and discover how big data and machine learning algorithms are revolutionizing climate science. Learn about the opportunities for descriptive inference, causal questions, and theory validation in climate research. Examine the integration of machine learning with modeling experiments and model parameterizations to address complex climate questions. Gain insights into topics such as CMIP6 climate projections, sources of uncertainty, parametric uncertainty exploration, emulation techniques, and the Earth System Emulator (ESEm). Explore scenario uncertainty, various machine learning models including LSTM, and the causal effects of aerosols on cloud types. Understand the ClimateBench overview, implausibility concepts, and methods for evaluating cloud types along trajectories in this comprehensive presentation by Duncan Watson-Parris.

Syllabus

Intro
ML for Weather and Climate are worlds apart
Machine leaming for weather and dimate are worlds apart
Climate projections: CMIP6
Sources of uncertainty
Exploring parametric uncertainty
Emulation
Sampling
Constraining parametric uncertainty
ESEm: Earth System Emulator
Exploring scenario uncertainty
Hackathon Models
LSTM Model
Causal Effect of Aerosol on Cloud Type
Summary
ClimateBench overview
Implausibility
Cloud Types Along Trajectories
Evaluation


Taught by

Kavli Institute for Theoretical Physics

Related Courses

La Terre comme système : une approche géographique
Sorbonne University via edX
Earth System Science
CEC via Swayam
Machine Learning For Earth System Sciences
Indian Institute of Technology, Kharagpur via Swayam
A Deep Learning Parameterization of Gravity Wave Drag Coupled to an Atmospheric Global Climate Model - Aditi Sheshadri
Kavli Institute for Theoretical Physics via YouTube
Lessons and Outlook for ML Parameterization of Sub Grid Atmospheric Physics From the Vantage of Emulating Cloud Superparameterization - Mike Pritchard
Kavli Institute for Theoretical Physics via YouTube