Publication Date

Fall 2019

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Ching-seh (Mike) Wu

Second Advisor

Teng Moh

Third Advisor

Eric Waller


Very High Resolution, wildfire burn severity, damage assessment, machine learning, Geographic Information Systems, remote sensing.


Wildfire damage assessments are important information for first responders, govern- ment agencies, and insurance companies to estimate the cost of damages and to help provide relief to those affected by a wildfire. With the help of Earth Observation satellite technology, determining the burn area extent of a fire can be done with traditional remote sensing methods like Normalized Burn Ratio. Using Very High Resolution satellites can help give even more accurate damage assessments but will come with some tradeoffs; these satellites can provide higher spatial and temporal resolution at the expense of better spectral resolution. As a wildfire burn area cannot be determined by traditional remote sensing methods with higher spatial resolution satellites, the use of machine learning can help predict the extent of the wildfire. This research project proposes an object-based classification method to train and compare several machine learning algorithms to detect the remaining burn scars after the event of a wildfire. Then, a building damage assessment approach is provided. The results of this research project shows that random forests can predict the burn scars with an accuracy of 86% using high resolution image data.