|
11. |
Comparison of broadband and high-spectral resolution infrared observations |
|
International Journal of Remote Sensing,
Volume 14,
Issue 15,
1993,
Page 2875-2882
S. A. ACKERMAN,
W. L. SMITH,
H. E. REVERCOMB,
Preview
|
PDF (165KB)
|
|
摘要:
This note compares observations from two instruments with different spectral resolutions. The High-resolution Interferometer Sounder (HIS) observed radiances have a spectral resolution capable of differentiating individual absorption bands within the 600-2700cm−(3. 7-l7μ m) regime, the Earth Radiation Budget Experiment (ERBE) measures broadband (4-200μ m) longwave fluxes. To derive broadband fluxes, ERBE processing must account for the spectral response function of the scanning instrument. As the HIS has the spectral resolution to simulate various filter response functions, the HIS observations arc employed in a cross-validation of the spectral correction algorithm applied by the ERBE software processing. This is the only independent method of cross validating the first step in the processing of ERBE measurements. In addition, the HIS spectral measurements arc integrated and compared with the ERBE broadband longwave fluxes. These comparisons demonstrate the complimentary nature of the two instruments for studying Earth radiation budget processes.
ISSN:0143-1161
DOI:10.1080/01431169308904315
出版商:Taylor & Francis Group
年代:1993
数据来源: Taylor
|
12. |
Conjugate-gradient neural networks in classification of multisource and very-high-dimensional remote sensing data |
|
International Journal of Remote Sensing,
Volume 14,
Issue 15,
1993,
Page 2883-2903
J. A. BENEDIKTSSON,
P. H. SWAIN,
O. K. ERSOY,
Preview
|
PDF (381KB)
|
|
摘要:
Application of neural networks to classification of remote sensing data is discussed. Conventional two-layer backpropagation is found to give good results in classification of remote sensing data but is not efficient in training. A more efficient variant, based on conjugate-gradient optimization, is used for classification of multisource remote sensing and geographic data and very-high-dimensional data. The conjugate-gradient neural networks give excellent performance in classification of multisource data but do not compare as well with statistical methods in classification of very-high-dimcnsional data.
ISSN:0143-1161
DOI:10.1080/01431169308904316
出版商:Taylor & Francis Group
年代:1993
数据来源: Taylor
|
|