<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<span style="color: rgb(31, 73, 125); font-family: Calibri, sans-serif; font-size: 11pt;"> </span><br>
</div>
<div>
<div lang="EN-US">
<div class="x_WordSection1">
<h2 style="margin: 0in 0in 0.0001pt; text-align: center; break-after: avoid; font-size: 16pt; font-family: "Albertus Extra Bold";">
<span style="font-size:20.0pt; font-family:"Tahoma",sans-serif">The Petroleum Engineering Department</span></h2>
<h2 style="margin: 0in 0in 0.0001pt; text-align: center; break-after: avoid; font-size: 16pt; font-family: "Albertus Extra Bold";">
<span style="font-family:"Tahoma",sans-serif"> </span></h2>
<h2 style="margin: 0in 0in 0.0001pt; text-align: center; break-after: avoid; font-size: 16pt; font-family: "Albertus Extra Bold";">
<span style="font-family:"Tahoma",sans-serif">Invites the Cullen College of Engineering
</span></h2>
<h2 style="margin: 0in 0in 0.0001pt; text-align: center; break-after: avoid; font-size: 16pt; font-family: "Albertus Extra Bold";">
<span style="font-family:"Tahoma",sans-serif">To the </span></h2>
<h2 style="margin: 0in 0in 0.0001pt; text-align: center; break-after: avoid; font-size: 16pt; font-family: "Albertus Extra Bold";">
<span style="font-family:"Tahoma",sans-serif">PhD Dissertation Defense</span></h2>
<h2 style="margin: 0in 0in 0.0001pt; text-align: center; break-after: avoid; font-size: 16pt; font-family: "Albertus Extra Bold";">
<span style="font-family:"Tahoma",sans-serif">of </span></h2>
<h2 style="margin: 0in 0in 0.0001pt; text-align: center; break-after: avoid; font-size: 16pt; font-family: "Albertus Extra Bold";">
<i><span style="font-family:"Tahoma",sans-serif; font-weight:normal">Anand Selveindran</span></i></h2>
<p class="x_MsoNormal" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;">
<b><span style="font-family:"Tahoma",sans-serif"> </span></b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b><span style="font-size:14.0pt; font-family:"Tahoma",sans-serif">Topic: </span>
</b><i><span style="font-size:14.0pt; font-family:"Tahoma",sans-serif">Machine Learning Assisted Reservoir Management for Injection Projects</span></i></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<i><span style="font-size:14.0pt; font-family:"Tahoma",sans-serif"> </span></i></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b>Date: Dec 1, 2021</b><b></b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b> </b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b>Location: Zoom, </b><span style="color:black; background:white"><a href="https://urldefense.com/v3/__https://zoom.us/j/93356158645__;!!LkSTlj0I!Fe5eWo4lxqz8lJKqYGY3hbBzJME4q9tBIuMYfioGUVtWd10hCD21ucWaM_LkdXQ7CEIMmVga1Ok7crpKp6cYv-kcHnE$">https://zoom.us/j/93356158645</a></span><b></b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b>Time: </b>9.00 AM - 10.30 AM<b></b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b> </b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b>Committee Chair:<span style="color:#1F497D"> </span></b>Dr. Ganesh Thakur<b><span style="color:#1F497D"></span></b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b> </b></p>
<p class="x_MsoNormal" align="center" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;text-align:center">
<b>Committee Members:</b></p>
<p class="x_TitlePage" style="margin: 0in 0in 0.0001pt; text-align: center; font-size: 12pt; font-family: "Times New Roman", serif;">
<a name="x__Toc134716"><span style="font-size:11.0pt"> </span></a></p>
<p class="x_TitlePage" style="margin: 0in 0in 0.0001pt; text-align: center; font-size: 12pt; font-family: "Times New Roman", serif;">
<span style="font-size:11.0pt">Dr. S.M. Farouq Ali, Dr. Fred Aminzadeh, Dr. Kyung Jae Lee, and Dr. Avinash Wesley.</span></p>
<h1 align="center" style="margin: 24pt 0in 0.0001pt; line-height: 115%; break-after: avoid; font-size: 14pt; font-family: "Calibri Light", sans-serif; color: rgb(46, 116, 181);margin-bottom:13.8pt; text-align:center; line-height:105%">
<span style="color:windowtext">Abstract</span><span style="color:windowtext"></span></h1>
<p class="x_MsoBodyText" style="margin: 0in 0in 6pt; text-indent: 0.5in; line-height: 150%; font-size: 12pt; font-family: "Times New Roman", serif;text-align:justify">
Reservoir management is critical for optimal reservoir production performance. A key component of reservoir management is decision making utilizing numerical reservoir models. One downside of these models is the large computational footprint for development
and use. Recent developments in machine learning provide technologies that can augment traditional workflows. In this work, machine learning algorithms are used to optimize selection of injector well location, perform fluid production prediction and optimize
well controls. Selection of optimized water and gas injection well locations is a key challenge in secondary and tertiary recovery projects. Traditional approaches using numerical simulation require a high number of simulation runs with optimization algorithms.
This is further complicated if there is geological uncertainty (e.g., multiple geological models are required to capture the uncertainty range). An alternative approach is proposed, using machine learning algorithms trained on a geological ensemble. Well level
aggregations are proposed to efficiently reduce the number of injector well location evaluations. Proxies were trained with several target variables including waterflood oil recovery, oil production, and CO<sub>2</sub> storage. These proxies provide rapid
evaluations of injector locations within seconds at accuracies between 94 - 98% (R<sup>2</sup> score comparing machine learning proxy predictions and numerical simulation results). Blind tests with different geological realizations yielded results comparable
to numerical simulation. Posterior sampling was used to determine optimal injector locations across a large geomodel ensemble. To predict time varying production without numerical simulation, deep learning models including a Convolutional Neural Network (CNN)
were trained with well level data. These algorithms successfully predicted production from water and miscible flooded patterns. Models trained on several wells could predict production from a neighbor well within the same pattern area. Finally, a Graph Neural
Network (GNN) proxy was used within a Closed Loop Reservoir Management (CLRM) workflow to optimize oil production of a waterflood. Kriging was used to initialize the adjacency matrix, resulting in improved network performance. The GNN proxy was able to perform
monthly optimization over a period of one year within eight minutes, compared to 6 hours using traditional simulation.
</p>
<p class="x_MsoNormal" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;">
</p>
<p class="x_MsoNormal" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;">
<span style="font-size:11.0pt; font-family:"Calibri",sans-serif; color:#1F497D"> </span></p>
<p class="x_MsoNormal" style="margin: 0in 0in 0.0001pt; font-size: 12pt; font-family: "Times New Roman", serif;">
<span style="font-size:11.0pt; font-family:"Calibri",sans-serif; color:#1F497D"> </span></p>
</div>
</div>
</div>
</body>
</html>