Conference paper
Spatial noise-aware temperature retrieval from infrared sounder data
In this paper we present a combined strategy for the retrieval of atmospheric profiles from infrared sounders. The approach considers the spatial information and a noise-dependent dimensionality reduction approach. The extracted features are fed into a canonical linear regression. We compare Principal Component Analysis (PCA) and Minimum Noise Fraction (MNF) for dimensionality reduction, and study the compactness and information content of the extracted features.
Assessment of the results is done on a big dataset covering many spatial and temporal situations. PCA is widely used for these purposes but our analysis shows that one can gain significant improvements of the error rates when using MNF instead. In our analysis we also investigate the relationship between error rate improvements when including more spectral and spatial components in the regression model, aiming to uncover the trade-off between model complexity and error rates.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2017 |
Pages: | 17-20 |
Proceedings: | 2017 IEEE International Geoscience and Remote Sensing Symposium |
Series: | Ieee International Geoscience and Remote Sensing Symposium Proceedings |
ISBN: | 1509049509 , 1509049517 , 1509049525 , 9781509049509 , 9781509049516 and 9781509049523 |
ISSN: | 21537003 and 21536996 |
Types: | Conference paper |
DOI: | 10.1109/IGARSS.2017.8126882 |
ORCIDs: | Nielsen, Allan Aasbjerg |
Atmospheric modeling Eigenvalues and eigenfunctions Feature extraction Infrared Atmospheric Sounding Interferometer (IASI) Linear regression Minimum Noise Fractions Principal Component Analysis (PCA) Principal component analysis Statistical retrieval Temperature distribution Temperature measurement
atmospheric profiles atmospheric techniques atmospheric temperature big dataset canonical linear regression feature extraction geophysical image processing infrared sounder data minimum noise fraction noise-dependent dimensionality reduction approach principal component analysis regression analysis regression model remote sensing spatial noise-aware temperature retrieval