@ARTICLE\{IMM2019-07148,
    author       = "D. Malmgren-Hansen and V. Laparra and A. A. Nielsen and G. Camps-Valls",
    title        = "Statistical Retrieval of Atmospheric Profiles with Deep Convolutional Neural Networks",
    year         = "2019",
    month        = "nov",
    keywords     = "Atmospheric measurements, Neural networks, Infrared measurements, Information retrieval",
    pages        = "231-240",
    journal      = "{ISPRS} Journal of Photogrammetry and Remote Sensing",
    volume       = "158",
    editor       = "",
    number       = "",
    publisher    = "Elsevier",
    url          = "http://www2.compute.dtu.dk/pubdb/pubs/7148-full.html",
    abstract     = "Infrared atmospheric sounders, such as {IASI,} provide an unprecedented source of information for atmosphere monitoring and weather forecasting. Sensors provide rich spectral information that allows retrieval of temperature and moisture profiles. From a statistical point of view, the challenge is immense: on the one hand, {''}underdetermination{''} is common place as regression needs to work on high dimensional input and output spaces; on the other hand, redundancy is present in all dimensions (spatial, spectral and temporal). On top of this, several noise sources are encountered in the data.

In this paper, we present for the first time the use of convolutional neural networks for the retrieval of atmospheric profiles from {IASI} sounding data. The first step of the proposed pipeline performs spectral dimensionality reduction taking into account the signal to noise characteristics. The second step encodes spatial and spectral information, and finally prediction of multidimensional profiles is done with deep convolutional networks. We give empirical evidence of the performance in a wide range of situations. Networks were trained on orbits of {IASI} radiances and tested out of sample with great accuracy over competing approximations, such as linear regression (+32\%). We also observed an improvement in accuracy when predicting over clouds, thus increasing the yield by 34\% over linear regression. The proposed scheme allows us to predict related variables from an already trained model, performing transfer learning in a very easy manner. We conclude that deep learning is an appropriate learning paradigm for statistical retrieval of atmospheric profiles."
}