Analysis of 2D airglow imager data with respect to dynamics using machine learning

Abstract

Abstract. We demonstrate how machine learning can be easily applied to support the analysis of large amounts of OH* airglow imager data. We use a TCN (temporal convolutional network) classification algorithm to automatically pre-sort images into the three categories “dynamic” (images where small-scale motions like turbulence are likely to be found), “calm” (clear-sky images with weak airglow variations) and “cloudy” (cloudy images where no airglow analyses can be performed). The proposed approach is demonstrated using image data of FAIM 3 (Fast Airglow IMager), acquired at Oberpfaffenhofen, Germany between 11 June 2019 and 25 February 2020, achieving a mean average precision of 0.82 in image classification. The attached video sequence demonstrates the classification abilities of the learned TCN. Within the “dynamic” category, we find a subset of 13 episodes of image series showing turbulence. As FAIM 3 exhibits a high spatial (23 m pixel−1) and temporal (2.8 s per image) resolution, turbulence parameters can be derived to estimate the energy diffusion rate. Similar to the results the authors found for another FAIM station (Sedlak et al., 2021), the values of energy dissipation rate range from 0.03 to 3.18 W kg−1.

Analysis of 2D airglow imager data with respect to dynamics using machine learning

“…Code and data availability. Both the software code and the data sets are archived in the World Data Center for Remote Sensing of the Atmosphere (WDC-RSAT; https://www.wdc.dlr.de, Sedlak et al, 2023a) within the German Remote Sensing Data Center (DFD) of the German Aerospace Center (DLR). Access can be granted on demand; contact Michael Bittner at michael.bittner@dlr.de.…”