<html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
  </head>
  <body text="#000000" bgcolor="#FFFFFF">
    <div class="moz-forward-container">
      
      <meta name="Generator" content="Microsoft Word 15 (filtered
        medium)">
      <style><!--
/* Font Definitions */
@font-face
        {font-family:"Cambria Math";
        panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
        {font-family:DengXian;
        panose-1:2 1 6 0 3 1 1 1 1 1;}
@font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
        {font-family:"\@DengXian";
        panose-1:2 1 6 0 3 1 1 1 1 1;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0in;
        margin-bottom:.0001pt;
        font-size:11.0pt;
        font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:#0563C1;
        text-decoration:underline;}
span.EmailStyle17
        {mso-style-type:personal-compose;
        font-family:"Calibri",sans-serif;
        color:windowtext;}
span.apple-converted-space
        {mso-style-name:apple-converted-space;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-family:"Calibri",sans-serif;}
@page WordSection1
        {size:8.5in 11.0in;
        margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
        {page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--><span style="font-size:14.0pt;font-family:"Times New
        Roman",serif;color:black">Dear Colleagues</span><span style="color:black"><o:p></o:p></span>
      <div class="WordSection1">
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black"> </span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black">We invite you to submit to
            our<span class="apple-converted-space"> </span>AGU<span class="apple-converted-space"> </span>session on <b>“</b><span style="background:white">App</span>l<span style="background:white">ications of </span>Machine<span style="background:white"> </span>L<span style="background:white">earning A</span>l<span style="background:white">gorithms in Mode</span>l<span style="background:white">ing Atmospheric Aeroso</span>l<span style="background:white">s, C</span>l<span style="background:white">ouds and Radiation</span><b>”</b>. 
            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.</span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black"> </span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black">Please share this information
            with those you think might also be interested.</span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black"> </span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black">All the best,</span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black">The Session Co-Conveners</span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black">Manish Shrivastava, Anthony
            Wexler, Ziheng Sun, Daniel Tong</span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black"> </span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><b><span style="font-size:14.0pt;font-family:"Times New
              Roman",serif;color:#262626">Session Title:</span></b><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black;background:white">App</span><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black">l<span style="background:white">ications of </span>Machine<span style="background:white"> </span>L<span style="background:white">earning A</span>l<span style="background:white">gorithms in Mode</span>l<span style="background:white">ing Atmospheric Aeroso</span>l<span style="background:white">s, C</span>l<span style="background:white">ouds and Radiation</span></span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><b><span style="font-size:14.0pt;font-family:"Times New
              Roman",serif;color:#262626"> </span></b><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><b><span style="font-size:14.0pt;font-family:"Times New
              Roman",serif;color:#262626">Session Description:</span></b><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:#262626;background:white">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.</span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black"> </span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:#262626">More info:</span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><strong><span style="font-size:14.0pt;font-family:"Calibri",sans-serif;color:black">Session
              ID:</span></strong><span class="apple-converted-space"><span style="font-size:14.0pt;font-family:"Times New
              Roman",serif;color:black;background:white"> </span></span><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black;background:white">105898<span class="apple-converted-space"> </span></span><span style="font-size:14.0pt;font-family:"Times New
            Roman",serif;color:black"><br>
            <strong>Session Title:</strong><span class="apple-converted-space"> </span>. Applications of<span class="apple-converted-space"> </span>Machine<span class="apple-converted-space"> </span>Learning Algorithms
            in Modeling Atmospheric Aerosols, Clouds and Radiation<span class="apple-converted-space"> </span><br>
            <strong>Section:</strong><span class="apple-converted-space"><span style="background:white"> </span></span><span style="background:white">Atmospheric Sciences<span class="apple-converted-space"> </span></span><br>
            <strong>View Session Details:</strong><span class="apple-converted-space"><span style="background:white"> </span></span><a href="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" title="https://agu.confex.com/agu/fm20/prelim.cgi/Session/105898" moz-do-not-send="true">https://agu.confex.com/agu/fm20/prelim.cgi/Session/105898</a></span><span style="color:black"><o:p></o:p></span></p>
        <p class="MsoNormal"><o:p> </o:p></p>
        <p class="MsoNormal"><o:p> </o:p></p>
      </div>
    </div>
  </body>
</html>