Land Cover Mapping Background: Training Data and Classification Methods Southwest Regional GAP Project Arizona, Colorado, Nevada, New Mexico, Utah 2004, Las Vegas, Nevada: Transdisciplinary Challenges in Landscape John Lowry, Douglas Ramsey, Jessica Kirby, Lisa Langs and Wendy Rieth Remote Sensing/GIS Laboratory Utah State University Logan, Utah
26
Embed
Land Cover Mapping Background: Training Data and Classification Methods
Land Cover Mapping Background: Training Data and Classification Methods. John Lowry, Douglas Ramsey, Jessica Kirby, Lisa Langs and Wendy Rieth Remote Sensing/GIS Laboratory Utah State University Logan, Utah. Southwest Regional GAP Project Arizona, Colorado, Nevada, New Mexico, Utah. - PowerPoint PPT Presentation
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Land Cover Mapping Background: Training Data and Classification Methods
Southwest Regional GAP ProjectArizona, Colorado, Nevada, New Mexico, Utah
US-IALE 2004, Las Vegas, Nevada: Transdisciplinary Challenges in Landscape Ecology
John Lowry, Douglas Ramsey, Jessica Kirby, Lisa Langs and Wendy Rieth
Mapping Zone Identification Began by Refining Bailey’s Ecoregions over a Color Shaded Relief Map
Mapping Zone Identification Began by Refining Bailey’s Ecoregions over a Color Shaded Relief Map
• 40 Mapping zones
• Spectrally consistent
• Eco-regionally distinct
• Labor divided among 5 state teams
UTNV
CO
AZ NM
NVC Formation
NVC Alliance
NVC Association
Gap Analysis ProgramMRLC 2000
Proposal
~1,800 units
National Park Mapping
~ NVC Class/Subclass
~10units
NatureServe Ecological Systems
~5,000 units
~700 units
(Natural/Semi-natural types)
~300 units
(Slide Courtesy Pat Comer, Nature Serve)
Thematic Target LegendDeveloped with NatureServe
Groups of plant communities and sparsely vegetated habitats unified by similar ecological processes, substrates, and/or environmental gradients...and spectral characteristics.
Ecological Systems
Elevation Landform
Predictor Datasets: DEM derived
July-Aug Sept-Oct
ETM Bands 5, 4, 3 ETM Bands 5, 4, 3
Predictor Datasets: Imagery Derived
• Data-mining software for decision-making and exploratory data analysis
• Identifies complex relationships between multiple independent variables to predict a single categorical class
• Predictor variables may be categorical or continuous
• Recursively “splits” the predictor data to create prediction rules or a decision tree.
• Software packages available: See5, SPLUS, CART
II. Mapping Methods: Classification Trees
Mining the Predictor Layers
Fall Brightness
Summer NDVI
Elevation
Landform
Etc….
Output table
SAMPLE SITESImagery: Landsat 7 ETM (1999-2002) for spring, summer & fall