[Esip-machinelearning] AGU session on Applications of Machine Learning Algorithms in Modeling Atmospheric Aerosols, Clouds and Radiation

[Ziheng Sun]

Dear Colleagues

We invite you to submit to ourAGUsession on *“*Applications of 
MachineLearning Algorithms in Modeling Atmospheric Aerosols, Clouds and 
Radiation*”*. Our motivation for this session is to foster talks and 
discussions that can enhance predictive understanding of Earth System 
Models by applications of novel machine learning algorithms and tools 
with a focus on improving the accuracy and speed of model predictions 
that are constrained by atmospheric physics and chemistry.   The 
deadline for abstract submission is Wednesday July 29th, 2020.

Please share this information with those you think might also be interested.

All the best,

The Session Co-Conveners

Manish Shrivastava, Anthony Wexler, Ziheng Sun, Daniel Tong

*Session Title:*

Applications of MachineLearning Algorithms in Modeling Atmospheric 
Aerosols, Clouds and Radiation

**

*Session Description:*

Recent breakthroughs in machine learning algorithms and artificial 
intelligence provide unprecedented tools for enhancing predictive 
understanding of the existing Earth System Models. These tools could be 
used for a wide range of problems, such as replacing computationally 
expensive modules, representing stochastic processes in radiative 
transfer models, using physics informed neural networks to understand 
unknown processes, and representing and propagating uncertainties in 
atmospheric models across different spatial and temporal scales. 
However, progress in scientific applications has been comparatively 
slow. It is challenging to generalize the ML models for a larger scale, 
interpret the trained models, and improve the reproducibility. We invite 
talks on innovative machine learning algorithms focused on modeling 
atmospheric aerosols, clouds and radiation. These could range from 
replacing existing computationally expensive modules to reducing model 
error, interpreting physical processes and uncertainty quantification, 
and integrating AI models into the established numeric models to achieve 
better quality and lower cost.

More info:

*Session ID:*105898
*Session Title:*. Applications ofMachineLearning Algorithms in Modeling 
Atmospheric Aerosols, Clouds and Radiation
*Section:*Atmospheric Sciences
*View Session 
Details:*https://agu.confex.com/agu/fm20/prelim.cgi/Session/105898 
<https://secure-web.cisco.com/1g6gVXaBC-aYVDnmRQ3DDmzcOm-gAlOL4QyBlGEHca257ED7k5rB4o9Npdx2d-jWoT9MiW5u9EOjtFPNY3-6IfRuzbgVxXxsiMUotHFZL7TW3ANPJmi08XM-1RBz43hbIeiGqyLrvTukj2oL4mazSohw75-BfCjVl5loJORPQWlKJGlEygGfoTL45SRhsWtUlBk1GmMMyGPwBZ5w9NSLMOqkb1PdPpuLWU2lHsAp5Xq-jsO4HqlI5mWesbZcJGxYkRFiygRztLUvHMV7sQ726jF1S0p5y0UU8Q8CzcOK3w_rv9-rcVBYA3sFZ0JKt-5ADyvmy71ZShcZCrwRh1--dXQgDNNb9SFXo8YKCxeH_uXYcmgF4uIOvTKYgBh4LVX5dOMFqukCMCduGMhCJ8aF5cF2Qd95j50VS1J2pTyv7py95xSi5JNvzOqHM5vGsAjPw/https%3A%2F%2Fagu.confex.com%2Fagu%2Ffm20%2Fprelim.cgi%2FSession%2F105898>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.esipfed.org/pipermail/esip-machinelearning/attachments/20200702/555e8aeb/attachment.htm>