Spatial noise-aware temperature retrieval from infrared sounder data

TL;DR

This paper introduces a noise-aware method for atmospheric temperature profile retrieval from infrared sounder data, emphasizing spatial information and noise-dependent feature reduction to improve accuracy.

Contribution

It compares PCA and MNF for feature reduction, demonstrating MNF's superior performance in temperature retrieval accuracy.

Findings

MNF outperforms PCA in error rate reduction.

Including more spectral and spatial components improves model accuracy.

Noise-aware dimensionality reduction enhances atmospheric profile retrieval.

Abstract

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.