Theses and Dissertations

ORCID

https://orcid.org/0009-0003-2596-0091

Advisor

Gudla, Charan

Committee Member

Huang, Yanbo

Committee Member

Chen, Zhiqian

Date of Degree

5-15-2026

Original embargo terms

Visible MSU Only 6 months

Document Type

Graduate Thesis - Campus Access Only

Major

Computer Science (Research Computer Science)

Degree Name

Master of Science (M.S.)

College

James Worth Bagley College of Engineering

Department

Department of Computer Science and Engineering

Abstract

This study presents a Flask-based web application designed to make machine learning and remote sensing more accessible to users without programming experience. The platform integrates data preprocessing, exploratory data analysis, model training, and geospatial image processing into a unified browser-based interface. It includes over fifteen pre-configured machine learning algorithms, automated data quality checks, guided workflows, and one-click preprocessing recommendations to simplify complex analytical tasks while maintaining methodological rigor. Domain-specific remote sensing tools, including vegetation index extraction (NDVI, EVI), image classification, and explainable AI visualizations using SHAP and LIME, are also incorporated. The system is fully containerized for streamlined deployment and supports session persistence for improved usability. By reducing technical barriers, the application enables researchers, students, and analysts to independently perform data-driven investigations in machine learning and geospatial analysis through an accessible web platform.

Download

Share

COinS