WHDL - 00010044
WHDL - 00010044
Submitted to the Department of Mathematics and Computer Science in partial fulfillment of the requirements for the degree of Bachelor of Arts.Wildland fires can be destructive to properties and dangerous to people in close proximity, with the cost of some large fires exceeding $1 billion. They are a threat to the economy, property, and the public safety. Wildfires are however an essential component for the ecology of many vegetation types and it is important to understand when fires are beneficial and when they are destructive. The goal of the Fire Monitoring and Assessment Platform (FireMAP) is to provide fire managers with the tools and knowledge for acquiring, analyzing, and managing hyperresolution imagery to map burn severity in a faster, safer, and more affordable manner than is currently possible. This will allow for quicker and more educated decisions on how to proceed with recovery after a wildland fire. The FireMAP Spectral Analysis focuses on vegetation common to Idaho and the Pacific Northwest as well as ash from post-burn sites. This effort investigated whether spectral reflectance can be utilized to differentiate between classes of vegetation and ash. Following spectral and statistical analysis, spectral separability of classes of ash and vegetation was discovered in the visible light range of the electromagnetic spectrum. With this information, fire severity and extent can be determined from hyper resolution imagery using machine learning classifiers focusing on the visible light spectrum.