Integrating Drone and Satellite Imaging with Machine Learning for Green Stormwater Infrastructure Condition Assessments - Thesis Abstract

Aug 4, 2026

Upload by Hazel

Green Stormwater Infrastructure (GSI) is increasingly used to strengthen urban stormwater management, yet asset performance declines over time without proper maintenance. Rising operations and maintenance costs for complex new networks strain municipal budgets and limit progress toward stormwater goals. This study evaluates automated monitoring by applying supervised machine learning to drone and satellite imagery, using 2022–2023 high-resolution data to classify 12 Milwaukee GSI sites into four land-cover categories and to support 2023 maintenance need identification across 93 sites.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages126

Reading Time5 h 18 min

AccessFree to download

Abstract

Acknowledgements

Master's Theses (2009-) Dissertations, Theses, and Professional Projects Integrating drone and satellite imaging with machine learning for green stormwater infrastructure condition assessments Matthew Dupasquier Marquette University Follow this and additional works at: [https://epublications.marquette.edu/theses_open](https://epublications.marquette.edu/theses_open) Part of the Water Resource Management Commons Recommended Citation Dupasquier, Matthew, "Integrating drone and satellite imaging with machine learning for green stormwater infrastructure condition assessments" (2024) . Master 's Theses (2009-). 792. [https://epublications.marquette.edu/theses_open/792](https://epublications.marquette.edu/theses_open/792) INTEGRATING DRONE AND SATELLITE IMAGING WITH MACHINE LEARNING FOR GREEN STORMWATER INFRASTRUCTURE CONDITION ASSESSMENTS By Matthew Dupasquier A Thesis submitted to the Faculty of the Graduate School, Marquette University, in Partial Fulfillment of the Requirements for the Degree of Master of Science Milwaukee, Wisconsin May 2024 ABSTRACT INTEGRATING DRONE AND SATELLITE IMAGING WITH MACHINE LEARNING FOR GREEN STORMWATER INFRASTRUCTURE CONDITION ASSESSMENTS Matthew Dupasquier Marquette University, 2024 Green Stormwater Infrastructure (GSI) has been increasingly utilized to improve urban stormwater management strategies. However, the performance and utility of GSI decrease overtime if the infrastructure is not properly maintained. In recent history, the intrinsic operations and maintenance costs associated with the complex networks of new infrastructure have placed a burden on municipalities, ultimately prohibiting many from reaching the full extent of their stormwater management goals. One way for cities to achieve cost savings is through automated monitoring that can quickly assess the condition of GSI assets; however, existing cost-effective technologies are limited. Drones and satellites may be able to meet this gap through large-scale, high-resolution data that can potentially provide information on overland site conditions that can augment or replace in-person GSI inspections. The goal of this study is to apply machine learning classification methods to remotely sensed satellite and drone data to classify the land cover of GSI for use in maintenance and operations efforts. To do this, high-resolution drone and satellite imagery collected in 2022-2023 was utilized to classify 12 GSI sites in Milwaukee, WI into 4 landcover categories (healthy plants, unhealthy plants, dead plants and organic material, and inorganic material) using various supervised machine learning classification models. Results found that classification methods yielded accurate results when classifying both drone imagery (74% -95%) and high-resolution satellite imagery (60% -78%) . Similar models were then used in the summer of 2023 to identify the maintenance needs of 93 GSI sites in Milwaukee, WI with 73% accuracy. Overall, this study provides a comprehensive overview of the integration of remote sensing and machine learning methods as a pathway for GSI monitoring data collection. In doing so, it highlights the strengths of each data source, the boundary of applicability for each technology, and the need for continued research and development. i ACKNOWLEDGEMENTS Matthew Dupasquier I would like to express my sincere gratitude to all those who have had a hand in supporting me through my thesis and who have helped me grow as an individual. First and foremost, I would like to thank my advisor, Dr. Walter McDonald, who has greatly altered the course of my life. He introduced me to research and ultimately persuaded me to do something I never pictured myself doing (getting my master’s degree) . He has continuously challenged me to develop and hone my skills within engineering and in many other areas of my life. His weekly support provided consistent structure and guidance to my research and professio

FAQs

What problem does this thesis address about green stormwater infrastructure (GSI)?

GSI performance declines over time without proper maintenance, and the complex infrastructure creates high operations and maintenance costs that can limit municipalities’ monitoring and upkeep efforts.

How does the study use drone and satellite data?

It applies supervised machine learning classification to high-resolution drone and satellite imagery to classify land cover associated with GSI conditions and to infer maintenance needs.

What classification results does the study report?

Classification accuracy is reported as 74%–95% for drone imagery and 60%–78% for high-resolution satellite imagery, with maintenance need identification across 93 sites achieving 73% accuracy.

Aug 4, 2026

Upload by Hazel