EVOLUTIONARY COMPUTATION AND POST-WILDFIRE LAND-COVER MAPPING WITH MULTISPECTRAL IMAGERY.
- Steven W.
- Leslie A.
The Cerro Grande Los Alamos wildfire devastated approximately 43,000 acres (17,500 ha) of forested land, and destroyed over 200 structures in the town of Los Alamos. The need to monitor the continuing impact of the fire on the local environment has led to the application of a number of advanced remote sensing technologies. During and after the fire, remote-sensing data was acquired fiorn a variety of aircraft- and satellite-based sensors, including Landsat 7 Enhanced Thematic Mapper (ETM+). We now report on the application of a machine learning technique io the automated classification of land cover using multispectral imagery. We apply a hybrid gertelic programminghupervised classification technique to evolve automatic feature extraction algorithms. We use a software package we have developed at Los Alamos National Laboratory, called GENIE, to carry out this evolution. We use multispectral imagery fiom the Landsat 7 ETM+ instrument fiom before and after the wildfire. Using an existing land cover classification based on a Landsat 5 TM scene for our training data, we evolve algorithms that distinguish a range of land cover categories, along with clouds and cloud shadows. The details of our evolved classification are compared to the manually produced land-cover classification. Keywords: Feature Extraction, Genetic programming, Supervised classification, Multi-spectral imagery, Land cover, Wildfire.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE
- OSTI ID:
- 975712
- Report Number(s):
- LA-UR-01-4847; TRN: US201018%%800
- Resource Relation:
- Journal Volume: 4545; Conference: "Submitted to: SPIE Remote Sensing Symposium, Toulouse, France, Sep. 17-21."
- Country of Publication:
- United States
- Language:
- English
Similar Records
Empirical comparison of Landsat 7 and IKONOS multispectral measurements for selected Earth Observation System (EOS) validation sites
Remote sensing inland wetlands: a multispectral approach