Thesis defense by Chris Smith on research funded by the Alaska EPSCoR Boreal Fires Team.
Wildfires in Alaska have been increasing in frequency, size, and intensity putting a strain on communities across the state, especially remote communities lacking fire fighting infrastructure to address large scale fire events. Advances in remote sensing techniques and data provide an opportunity to generate high quality map products that can better inform fire managers to allocate resources to areas of most risk and inform scientists how to predict and understand fire behavior. The overarching goal of this thesis is therefore to build insight into methods that can be applied to create highly detailed fire statistic map products in Alaska. To address this overarching goal we tested several methods for generating fire fuel, burn severity, and wildfire hazard maps that were validated using data collected in the field. We found that with Airborne Visible/Infrared Imaging Spectrometer Next-Generation (AVIRIS-NG) hyperspectral data and the random forest classifier generate fire fuel maps with an 81% accuracy at Bonanza Creek Experimental Forest. We then tested various supervised machine learning classifiers, post fire standard spectral indices, and differenced spectral indices performance on assessing burn severity. We found that supervised machine learning classifiers outperform other products when there is an adequate amount of field data. Using the support vector machine and random forest classifiers we were able to generate burn severity maps with 83% accuracy at the 2019 Shovel Creek Fire. Lastly we integrated information on previous fire events in order to generate a wildfire hazard map for the Fairbanks area. Overall these products can be used by fire managers and scientists to help predict fire events, limit the damages caused by wildfires through adequate resource allocation, and provide the guidelines for creating future high quality fire fuel maps.
Please email Zav.Grabinski@Alaska.edu for zoom link and passcode