Skip to content

Commit

Permalink
Updated BayesOpt section of Research page
Browse files Browse the repository at this point in the history
  • Loading branch information
@cote3804
cote3804 committed Jan 4, 2025
1 parent dedfcea commit 7d851eb
Show file tree
Hide file tree
Showing 12 changed files with 70 additions and 36 deletions.
7 changes: 7 additions & 0 deletions biography.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -62,4 +62,11 @@
});
});
</script>

<div id="content">
<h1>Biography</h1>
<p>This is my biography</p>
</div>


</body>
Binary file added images/EC_white.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/PF6_white.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/bayesopt.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/bayesoptsmalltrans.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/mean-acqf-EC-PF6.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added images/molsets_diagram.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
26 changes: 11 additions & 15 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -48,55 +48,51 @@
</nav>
</div>
<!-- Background image for desktop screen sizes -->
<div class="container-fluid text-center z-n1 position-absolute d-none d-sm-block">
<div class="container-fluid text-center z-n1 position-absolute d-none d-md-block">
<div class="row bg-dark bg-gradient nopadding opacity-50 z-n1">
<div class="fullscreen-image-container">
<img src="./images/surface_transparent_zoomed_out.png" class="fullscreen-image z-n1" alt="Main Image">
</div>
</div>
</div>
<!-- Background image for mobile screen sizes -->
<div class="container-fluid text-center z-n1 position-absolute d-block d-sm-none">
<div class="container-fluid text-center z-n1 position-absolute d-block d-md-none">
<div class="row bg-dark bg-gradient nopadding opacity-50 z-n1">
<div class="mobile-image-container">
<img src="./images/surface_transparent_zoomed_out.png" class="fullscreen-image z-n1" alt="Main Image">
</div>
</div>
</div>
<!-- Main Content for desktop -->
<div class="container-fluid d-flex flex-column custom-vh-75 z-2 position-relative text-center d-none d-sm-block">
<div class="container-fluid d-flex flex-column custom-vh-75 z-2 position-relative text-center d-none d-md-block">
<div class="row flex-grow-1"> <!-- Title and other info -->
<!-- <div class="col-1"></div> -->
<div class="col-3 transparent-column" style="min-height:100vh">
<div class="container-fluid">
<div class="row flex-grow-1">
<div class="row flex-grow-1 align-items-center">
<p class="name-fontsize fw-bold text-center text-light">Cooper Tezak</p>
<div class="col-2"></div>
<div class="col-8 align-self-center">
<div class="col-12 align-self-center">
<img src="/images/headshot_atoms_circle.png", class="image-fluid", style="max-width: 100%;">
</div>
<div class="col-2"></div>
<div class="row flex-grow-1">
<p class="fs-2 text-light">PhD Student, CU Boulder</p>
<p class="fs-2 text-light">PhD Candidate, CU Boulder</p>
<p class="fs-2 text-light">Atomic Broker</p>
<div class="row flex-grow-1 p-3">
<div class="col-3"></div>
<div class="col-2">
<div class="row flex-grow-1 p-3 align-items-center justify-content-center">
<div class="col">
<a href="https://www.linkedin.com/in/cooper-tezak-75a15b165/" class="text-light" target="_blank">
<img src="/images/linkedin-app-white-icon.png" class="img-fluid" alt="LinkedIn">
</a>
</div>
<div class="col-2">
<div class="col">
<a href="https://github.com/cote3804" class="text-light" target="_blank">
<img src="/images/github-logo-white.webp" class="img-fluid" alt="GitHub">
</a>
</div>
<div class="col-2">
<div class="col">
<a href="https://scholar.google.com/citations?user=XBZAHmIAAAAJ&hl=en" class="text-light" target="_blank">
<img src="/images/scholar_logo_white.png" class="img-fluid" alt="GitHub">
</a>
</div>
<div class="col-3"></div>
</div>
</div>
</div>
Expand Down Expand Up @@ -129,7 +125,7 @@
</div>
</div>
<!-- Main mobile content -->
<div class="container-fluid d-block d-sm-none">
<div class="container-fluid d-block d-md-none">
<div class="row">
<div class="col-1"></div>
<div class="col-10>
Expand Down
20 changes: 17 additions & 3 deletions research.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -116,11 +116,18 @@
adsorbate frontier orbital energies, which lead to substantially different degrees of bonding for materials with similar d-band centers.
To correctly precict trends in binding energy across complex material spaces, it is necessary to incorporate the geometry of the surface.
<br><br>
<div class="h3 text-light">Bayesian Optimization of Battery Electrolyte Compositions</div>
<div class="h3 text-light">Battery Electrolyte Composition Optimization</div>
I have recently begun working with
<a href="https://www.colorado.edu/lab/ban/">Chunmei Ban</a>
on optimizing experimental electrolyte composition for Na-ion batteries. I lead the effort to develop a Bayesian optimization framework
that uses a gaussian process to estimate the charge capacity at a given cycle based on the mass weights of electrolyte components.
on optimizing experimental electrolyte composition for Na-ion batteries. I have succesfully implemented
information theoretic and simple expected improvement acquisiton functions on top of a gaussian process
surrogate model to efficiently explore compositions experimentally. However, the design space for electrolyte compositions
is huge and experiments are expensive. I am currently working on incorporating molecular features into the model using
graph neural networks to featurize molecular structures and attention mechanisms to create mixture level representations
from the constituent molecular features.
<a href="https://arxiv.org/abs/2312.16473">[7]</a>
The architecture of the model is summarized as <br> <br>
<img src="/images/molsets_diagram.png" class="img-fluid" alt="Molsets Architecture">
<br><br>
</div>
</div>
Expand All @@ -139,6 +146,13 @@
to have less occupied d-orbitals that were capable of strongly reducing the \( N_2 \) triple bond. However, all materials were
inevitably limited by the desorption of \( NH_3* \) from the surface. <br> <br>
</p>
<img src="/images/mean-acqf-EC-PF6.png" class="img-fluid" alt="Bayesian Optimization">
<p class="fs-6 px-5 text-light" style="text-align: justify;">
Bayesian Optimization model for battery electrolyte compositions. X and Y axes are fractions of chemicals
EC and NaPF6. The left panel shows the mean of the model and the right shows the
acquisiton function value, which is the
<a href="https://arxiv.org/abs/2310.20708">log expected improvement</a>
. <br> <br>
</div>
</div>
<script>
Expand Down
7 changes: 7 additions & 0 deletions source/biography.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,4 +21,11 @@

</div>
@@include('navbar_js.html')

<div id="content">
<h1>Biography</h1>
<p>This is my biography</p>
</div>


</body>
26 changes: 11 additions & 15 deletions source/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,55 +17,51 @@
@@include('navbar.html')
</div>
<!-- Background image for desktop screen sizes -->
<div class="container-fluid text-center z-n1 position-absolute d-none d-sm-block">
<div class="container-fluid text-center z-n1 position-absolute d-none d-md-block">
<div class="row bg-dark bg-gradient nopadding opacity-50 z-n1">
<div class="fullscreen-image-container">
<img src="./images/surface_transparent_zoomed_out.png" class="fullscreen-image z-n1" alt="Main Image">
</div>
</div>
</div>
<!-- Background image for mobile screen sizes -->
<div class="container-fluid text-center z-n1 position-absolute d-block d-sm-none">
<div class="container-fluid text-center z-n1 position-absolute d-block d-md-none">
<div class="row bg-dark bg-gradient nopadding opacity-50 z-n1">
<div class="mobile-image-container">
<img src="./images/surface_transparent_zoomed_out.png" class="fullscreen-image z-n1" alt="Main Image">
</div>
</div>
</div>
<!-- Main Content for desktop -->
<div class="container-fluid d-flex flex-column custom-vh-75 z-2 position-relative text-center d-none d-sm-block">
<div class="container-fluid d-flex flex-column custom-vh-75 z-2 position-relative text-center d-none d-md-block">
<div class="row flex-grow-1"> <!-- Title and other info -->
<!-- <div class="col-1"></div> -->
<div class="col-3 transparent-column" style="min-height:100vh">
<div class="container-fluid">
<div class="row flex-grow-1">
<div class="row flex-grow-1 align-items-center">
<p class="name-fontsize fw-bold text-center text-light">Cooper Tezak</p>
<div class="col-2"></div>
<div class="col-8 align-self-center">
<div class="col-12 align-self-center">
<img src="/images/headshot_atoms_circle.png", class="image-fluid", style="max-width: 100%;">
</div>
<div class="col-2"></div>
<div class="row flex-grow-1">
<p class="fs-2 text-light">PhD Student, CU Boulder</p>
<p class="fs-2 text-light">PhD Candidate, CU Boulder</p>
<p class="fs-2 text-light">Atomic Broker</p>
<div class="row flex-grow-1 p-3">
<div class="col-3"></div>
<div class="col-2">
<div class="row flex-grow-1 p-3 align-items-center justify-content-center">
<div class="col">
<a href="https://www.linkedin.com/in/cooper-tezak-75a15b165/" class="text-light" target="_blank">
<img src="/images/linkedin-app-white-icon.png" class="img-fluid" alt="LinkedIn">
</a>
</div>
<div class="col-2">
<div class="col">
<a href="https://github.com/cote3804" class="text-light" target="_blank">
<img src="/images/github-logo-white.webp" class="img-fluid" alt="GitHub">
</a>
</div>
<div class="col-2">
<div class="col">
<a href="https://scholar.google.com/citations?user=XBZAHmIAAAAJ&hl=en" class="text-light" target="_blank">
<img src="/images/scholar_logo_white.png" class="img-fluid" alt="GitHub">
</a>
</div>
<div class="col-3"></div>
</div>
</div>
</div>
Expand Down Expand Up @@ -98,7 +94,7 @@
</div>
</div>
<!-- Main mobile content -->
<div class="container-fluid d-block d-sm-none">
<div class="container-fluid d-block d-md-none">
<div class="row">
<div class="col-1"></div>
<div class="col-10>
Expand Down
20 changes: 17 additions & 3 deletions source/research.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -85,11 +85,18 @@
adsorbate frontier orbital energies, which lead to substantially different degrees of bonding for materials with similar d-band centers.
To correctly precict trends in binding energy across complex material spaces, it is necessary to incorporate the geometry of the surface.
<br><br>
<div class="h3 text-light">Bayesian Optimization of Battery Electrolyte Compositions</div>
<div class="h3 text-light">Battery Electrolyte Composition Optimization</div>
I have recently begun working with
<a href="https://www.colorado.edu/lab/ban/">Chunmei Ban</a>
on optimizing experimental electrolyte composition for Na-ion batteries. I lead the effort to develop a Bayesian optimization framework
that uses a gaussian process to estimate the charge capacity at a given cycle based on the mass weights of electrolyte components.
on optimizing experimental electrolyte composition for Na-ion batteries. I have succesfully implemented
information theoretic and simple expected improvement acquisiton functions on top of a gaussian process
surrogate model to efficiently explore compositions experimentally. However, the design space for electrolyte compositions
is huge and experiments are expensive. I am currently working on incorporating molecular features into the model using
graph neural networks to featurize molecular structures and attention mechanisms to create mixture level representations
from the constituent molecular features.
<a href="https://arxiv.org/abs/2312.16473">[7]</a>
The architecture of the model is summarized as <br> <br>
<img src="/images/molsets_diagram.png" class="img-fluid" alt="Molsets Architecture">
<br><br>
</div>
</div>
Expand All @@ -108,6 +115,13 @@
to have less occupied d-orbitals that were capable of strongly reducing the \( N_2 \) triple bond. However, all materials were
inevitably limited by the desorption of \( NH_3* \) from the surface. <br> <br>
</p>
<img src="/images/mean-acqf-EC-PF6.png" class="img-fluid" alt="Bayesian Optimization">
<p class="fs-6 px-5 text-light" style="text-align: justify;">
Bayesian Optimization model for battery electrolyte compositions. X and Y axes are fractions of chemicals
EC and NaPF6. The left panel shows the mean of the model and the right shows the
acquisiton function value, which is the
<a href="https://arxiv.org/abs/2310.20708">log expected improvement</a>
. <br> <br>
</div>
</div>
@@include('navbar_js.html')
Expand Down

0 comments on commit 7d851eb

Please sign in to comment.