학술논문
Improved Vegetation and Wildfire Fuel Type Mapping Using NASA AVIRIS-NG Hyperspectral Data, Interior AK
Document Type
Conference
Source
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Geoscience and Remote Sensing Symposium, IGARSS 2020 - 2020 IEEE International. :1307-1310 Sep, 2020
Subject
Language
ISSN
2153-7003
Abstract
In Alaska, wildfire map products have traditionally been generated from lower spatial and spectral resolution Landsat imagery such as LANDFIRE Program's Existing Vegetation Type (EVT) resulting in products that do not accurately assess fire fuel types for local sites. In this study we demonstrate the efficacy of AVIRIS-NG hyperspectral data for mapping Interior Alaska's vegetation and fuel type. Based on an evaluation of field plot data collected by the project team in 2019, the new vegetation map derived from AVIRIS-NG at Viereck IV level resulted in a 73% classification accuracy compared to the 32% accuracy of the LANDFIRE's product EVT derived from Landsat 8. Not only did our product more accurately classify fire fuels, it was also able to identify 20 dominant vegetation classes (percent cover > 1%) while the EVT product only identified eight dominant classes within the study area.