<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><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:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Aptos;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;
mso-ligatures:standardcontextual;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:11.0pt;}
@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]-->
</head>
<body lang="EN-US" link="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal" align="center" style="mso-margin-top-alt:.35pt;margin-right:30.2pt;margin-bottom:8.0pt;margin-left:56.2pt;text-align:center;line-height:198%">
<span style="font-size:13.5pt;line-height:198%;font-family:"Arial",sans-serif;color:black"><img width="600" height="171" style="width:6.25in;height:1.7812in" id="Picture_x0020_1" src="cid:image001.png@01DB3491.78401710" alt="Dissertation Defense Announcement at the Cullen College of Engineering"></span><b><span style="font-size:12.0pt;line-height:198%;mso-ligatures:none"><o:p></o:p></span></b></p>
<p class="MsoNormal" align="center" style="mso-margin-top-alt:.35pt;margin-right:30.2pt;margin-bottom:8.0pt;margin-left:56.2pt;text-align:center;line-height:198%">
<b><span style="font-size:12.0pt;line-height:198%;color:red;mso-ligatures:none">Advanced Deep Learning Model for Reservoir Simulation and Well Placement Optimization Using Latent Deep Neural Operator</span></b><span style="font-size:12.0pt;line-height:198%;color:red;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" align="center" style="text-align:center;line-height:15.0pt;background:white">
<b><span style="font-size:13.5pt;font-family:"Aptos",sans-serif;color:black;border:none windowtext 1.0pt;padding:0in;mso-ligatures:none">Sameer Salasakar</span></b><span style="color:#424242;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" align="center" style="text-align:center;line-height:16.5pt;background:white">
<span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;border:none windowtext 1.0pt;padding:0in;mso-ligatures:none">November 13, 2024; 9 a.m. - 12 p.m. (CST) Technology Bridge Building 9 Room 140<br>
<b>Committee Chair:</b><br>
Dr. Ganesh Thakur</span><span style="color:#424242;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" align="center" style="text-align:center;line-height:16.5pt;background:white">
<b><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;border:none windowtext 1.0pt;padding:0in;mso-ligatures:none">Committee Members:</span></b><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;border:none windowtext 1.0pt;padding:0in;mso-ligatures:none"><br>
Dr. S.M. Farouq Ali | Dr. Guan Qin | Dr. Kyung Jae Lee | Dr. Mohamed Ibrahim Mohamed</span><span style="color:#424242;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;text-align:justify;line-height:106%">
<span style="font-size:12.0pt;line-height:106%;mso-ligatures:none"><o:p> </o:p></span></p>
<p class="MsoNormal" style="mso-margin-top-alt:11.25pt;margin-right:0in;margin-bottom:11.25pt;margin-left:0in;line-height:16.5pt">
<b><span style="font-size:12.0pt;font-family:"Arial",sans-serif;color:#C8102E;mso-ligatures:none">Abstract</span></b><span style="font-size:12.0pt;font-family:"Arial",sans-serif;color:#C8102E;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;text-align:justify;line-height:106%">
<span style="font-size:12.0pt;line-height:106%;mso-ligatures:none">Recent advances have seen the use of deep learning and physics-informed neural networks to tackle the complexities of fluid flow while capturing its underlying reservoir physics. Despite their
accuracy, these models often come with significant computational demands, particularly larger training time, which limits their practicality for large complex reservoir models. Training these models for full-field reservoir datasets can take considerable time
and computational resources. This study focuses on developing a deep learning-based model with two
</span><span style="font-size:12.0pt;line-height:106%;mso-ligatures:none">key steps to address two primary challenges: 1) reducing extensive training times and 2) predicting complex, discontinuous output functions. The two-step approach is applied to two intricate
problems to evaluate its capability to capture the complex dynamics of reservoirs, specifically the evolution of saturation in relation to space and time. The framework consists of dimensionality reduction combined with a Deep Neural Operator to capture the
reservoir dynamics with lesser training time. The developed model is coupled with a particle swarm optimization algorithm to solve well placement optimization for two complex problems. The results demonstrate that the developed method not only decreases the
number of simulation runs needed to determine optimal injection well locations, but it also effectively forecasts reservoir dynamics in the presence of complex geological faults.<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;text-align:justify;line-height:106%">
<span style="font-size:12.0pt;line-height:106%;mso-ligatures:none">The results indicate that the developed method reduces the number of simulation runs required to identify optimal injection well locations and effectively predicts reservoir dynamics in the
presence of complex geological faults. It reliably forecasts changes in saturation over time within large-scale reservoirs characterized by such faults. This underscores its potential applicability in real-world large-scale reservoir scenarios, facilitating
faster decision-making.</span><span style="font-size:12.0pt;line-height:106%;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>