<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)">
<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:Aptos;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:12.0pt;
font-family:"Aptos",sans-serif;
mso-ligatures:standardcontextual;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#467886;
text-decoration:underline;}
span.EmailStyle18
{mso-style-type:personal-compose;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@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="#467886" vlink="#96607D" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt">We cordially invite you to attend Madhukar Kuchavaram's Research Proposal. Your support would be great!<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">RESEARCH PROPOSAL SEMINAR NOTICE </span></b><span style="font-size:11.0pt"><o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">GEOSPATIAL COMPUTER SCIENCE PROGRAM<o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">COLLEGE OF ENGINEERING AND COMPUTER SCIENCE<o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">TEXAS A&M UNIVERSITY-CORPUS CHRISTI</span></b><span style="font-size:11.0pt"><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">SUBJECT:</span></b><span style="font-size:11.0pt"> GEOAI-ENABLED FRAMEWORK FOR MOSQUITO SURVEILLANCE AND VECTOR-CONTROL DECISION SUPPORT<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">SPEAKER</span></b><span style="font-size:11.0pt">: Madhukar Kuchavaram<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">ADVISOR</span></b><span style="font-size:11.0pt">: Dr. Yuxia Huang<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">COMMITTEE</span></b><span style="font-size:11.0pt">: Dr. Wenlu Wang, Dr. Rajesh Melaram, Dr. Zheng Wei, and Dr. Lei Jin (Graduate Faculty Representative)<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">DATE</span></b><span style="font-size:11.0pt">: October 16, 2026 (Friday)<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">TIME</span></b><span style="font-size:11.0pt">: 1:00 PM Central Time (US and Canada)<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">PLACE</span></b><span style="font-size:11.0pt">: NRC 1232 Conference Room at CBI<o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">Microsoft Teams Link: </span></b><span style="font-size:11.0pt"><a href="https://nam12.safelinks.protection.outlook.com/ap/t-59584e83/?url=https%3A%2F%2Fteams.microsoft.com%2Fmeet%2F239076420565400%3Fp%3D9La9C9GkMNkLcDmYjU&data=05%7C02%7Ccosc-grad-students-list%40listserv.tamucc.edu%7C4cb96937ab73419b053c08df2943ddea%7C34cbfaf167a64781a9ca514eb2550b66%7C0%7C0%7C639275043626970755%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=%2B8lpTpm86M1bK89CqIc3t8Lt1puxR0OI08Fpy3IcKow%3D&reserved=0" originalsrc="https://teams.microsoft.com/meet/239076420565400?p=9La9C9GkMNkLcDmYjU">https://teams.microsoft.com/meet/239076420565400?p=9La9C9GkMNkLcDmYjU</a><o:p></o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">Meeting ID: </span></b><span style="font-size:11.0pt">239 076 420 565 400<b><br>
Passcode: </b>48Fp6rp7<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt">Abstract</span></b><span style="font-size:11.0pt"><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">Mosquito-borne diseases such as West Nile virus and dengue remain a persistent public health burden. In the United States, municipal and county vector-control programs conduct mosquito surveillance and control.
These programs depend on labor-intensive manual counting and on scarce taxonomic expertise for species identification, while trap counts, laboratory results, and field operations are often held in separate records. Although automated counting and image-based
identification have advanced, few tools have been evaluated within an operating program, and the spatial interpretation of sparse trap networks remains limited. This dissertation develops an integrated GeoAI-enabled framework for mosquito surveillance and
vector-control decision support, built in collaboration with the Vector Control program of the Corpus Christi–Nueces County Public Health District, Texas. The research begins with the design and deployment of MOSAIC, a web-based geospatial platform that links
each trap collection to its location, photograph, count, laboratory results, and expert determinations. The platform provides computer-vision-assisted counting, while an associated offline evaluation examines multimodal large language model (LLM) species identification
using a local species list, taxonomic knowledge, and labeled exemplars against expert-reviewed reference labels. Building on these records, the study interprets trap evidence spatially, using mixed-effects models and rank-concordance statistics to quantify
differences between trap locations and their persistence, and a capture-probability model adapted from MGSurvE to identify areas weakly represented by the trap network. Trap evidence and spatial context are then integrated in a two-stage multi-criteria framework,
with expert-elicited weights and Stochastic Multicriteria Acceptability Analysis, to prioritize weekly inspection. Finally, the proposed work extends the framework to network design, formulating trap placement as a constrained optimization problem to improve
modeled coverage in areas weakly represented by the existing network. Together, these components integrate AI-assisted specimen processing, spatial interpretation, and network design within a common surveillance framework, offering an interpretable, evidence-based
approach that vector-control programs can adapt to their own data and operational needs.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
</div>
</body>
</html>