Improved Statistically Based Retrievals via Spatial-Spectral Data Compression for IASI Data

Abstract

In this paper we analyze the effect of spatial and spectral compression on the performance of statistically based retrieval. Although the quality of the information is not completely preserved during the coding process, experiments reveal that a certain amount of compression may yield a positive impact on the accuracy of retrievals. We unveil two strategies, both with interesting benefits: either to apply a very high compression, which still maintains the same retrieval performance as that obtained for uncompressed data; or to apply a moderate to high compression, which improves the performance. As a second contribution of this work, we focus on the origins of these benefits. On the one hand, we show that a certain amount of noise is removed during the compression stage, which benefits the retrievals performance. On the other hand, we analyze the effect of compression on spectral/spatial regularization (smoothing). We quantify the amount of information shared among the spatial neighbours for the different methods and compression ratios. We also propose a simple strategy to specifically exploit spectral and spatial relations and find that, when these relations are taken into account beforehand, the benefits of compression are reduced. These experiments suggest that compression can be understood as an indirect way to regularize the data and exploit spatial neighbours information, which improves the performance of pixel-wise statistics based retrieval algorithms.

Competitive Segmentation Performance on Near-Lossless and Lossy Compressed Remote Sensing Images

“…Results revealed that the classification accuracy was still reliable after the compression stage, even at high compression ratios. Similar conclusions were yielded for anomaly detection [12], [13] for linear spectral unmixing [14], [15], and for statistical retrieval algorithms [16]- [18]. To the best of our knowledge, a similar study on the impact of compression on image segmentation has not been presented.…”

Statistical retrieval of atmospheric profiles with deep convolutional neural networks

“…• Accounting for noisy and spatial features. Recently, in [8,9], great improvement in the performance of retrieval methods was reported when applying standard compression algorithms to the images. Although this result may appear counterintuitive since compression implies reduction on the amount of information in the images, a certain level of compression is actually beneficial because: 1) compression removes information but also noise, and it could be useful to remove the components with low signal-to-noise ratio (SNR); and 2) spatial compression introduces information about the neighbouring pixels in an indirect yet simple way.…”

Discrete Atomic Transform-Based Lossy Compression of Three-Channel Remote Sensing Images with Quality Control

“…In the latter case, it can be stated that, e.g., lossy compression should not lead to sufficient reduction of image classification accuracy (although even in this case "sufficient" can be described quantitatively). Here, it is worth recalling that considerable attention has been paid to the classification of lossy compressed images [17,[26][27][28][29][30][31][32][33]. It has been shown that lossy compression can sometimes improve classification accuracy or, at least, the classification of compressed data provides approximately the same classification accuracy as classification of uncompressed data [34][35][36].…”