Reference Shapefiles and Pre-trained Random Forest Classification Models for Detecting Aufeis on the North Slope of Alaska in Landsat Imagery ...

• Main Authors: Dann, Julian, Zwieback, Simon, Bolton, Bob, Leonard, Paul
• Format: Dataset
• Language: English
• Published: Environmental System Science Data Infrastructure for a Virtual Ecosystem; Next-Generation Ecosystem Experiments (NGEE) Arctic 2025
• Subjects: 54 ENVIRONMENTAL SCIENCES; EARTH SCIENCE > CRYOSPHERE > SNOW/ICE; EARTH SCIENCE > CRYOSPHERE; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > SNOW/ICE; EARTH SCIENCE > LAND SURFACE > LAND USE/LAND COVER > LAND USE/LAND COVER CLASSIFICATION; EARTH SCIENCE > CLIMATE INDICATORS > CRYOSPHERIC INDICATORS > ICE EXTENT; EARTH SCIENCE > CRYOSPHERE > SNOW/ICE > ICE EXTENT; north slope; Alaska
• Online Access: https://dx.doi.org/10.15485/2519690; https://www.osti.gov/servlets/purl/2519690/

This dataset provides shapefiles and trained machine learning models used for aufeis detection at four sites on the North Slope of Alaska. It includes reference data for evaluating Landsat-based detection methods, supporting research on remote sensing approaches for identifying aufeis. The ReferenceData folder contains ArcGIS shapefiles of semi-automated land cover classifications for 217 Landsat Collection 2 images, categorizing pixels into six classes: aufeis, snow, ground, none, water, and cloud. The SiteBuffers.zip file includes 10-kilometer buffer shapefiles defining regions of interest around four aufeis fields (Canning21, FH1, Firth, and Kuparuk), used to test three detection techniques. Additionally, the TrainedRFModels folder contains six pre-trained Scikit-Learn Random Forest classifiers (100 trees, max depth = 30) designed to predict aufeis presence in Landsat Collection 2 Surface Reflectance images using Red, Blue, SWIR2, NDVI, and NDWI bands. This dataset supports the development and validation ...