Abstract
Defoliation by the northern tamarisk beetle (Diorhabda carinulata) causes changes in the reflectance of tamarisk (Tamarix spp.) canopies. Cross correlogram spectral matching was used to examine spectral separability of green, yellow desiccated, brown desiccated, and dead tamarisk canopy types. Using a feature selection technique (the instability index), four spectral regions were identified as important for canopy type discrimination, including one red (645-693 nm), one near infrared (735-946 nm), and two shortwave infrared regions (1,960-2,090 nm and 2,400-2,478 nm). The random forests decision tree algorithm was used to compare classification performances of full-range and feature-selected hyperspectral spectra as well as simulated WorldView-2 spectra. Classification results indicated that the process of feature selection can reduce data redundancy and computation time while improving accuracy of tamarisk canopy type classification.
| Original language | English |
|---|---|
| Pages (from-to) | 199-207 |
| Number of pages | 9 |
| Journal | Photogrammetric Engineering and Remote Sensing |
| Volume | 81 |
| Issue number | 3 |
| DOIs | |
| State | Published - 2015 |
| Externally published | Yes |
Fingerprint
Dive into the research topics of 'Spectroscopic analysis of green, desiccated and dead tamarisk canopies'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver