EGU23-14066, updated on 10 Jan 2024
https://doi.org/10.5194/egusphere-egu23-14066
EGU General Assembly 2023
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

An improved MSG SEVIRI wet-dry product based on a convolutional neural network

Rebecca Wiegels1, Andreas Wagner2, Julius Polz1, Luca Glawion1, and Christian Chwala1,2
Rebecca Wiegels et al.
  • 1Institute of Meteorology and Climate Research, Karlsruhe Institute of Technology, Campus Alpin, Garmisch-Partenkirchen, Germany (rebecca.wiegels9@kit.edu)
  • 2Institute of Geography, University of Augsburg, Augsburg, Germany

Adequate spatial coverage of precipitation measurements is not available for large regions. Many countries are only equipped with networks of meteorological stations to measure precipitation based on sparse point measurements. Attenuation data from commercial microwave links (CML) allow precipitation estimates over existing networks, such as the cellular network. However, the processing of the data requires a distinction between wet and dry. Here, satellite data in countries of the Global South play a significant role, as they can be used in place of conventional reference data to distinguish between dry periods and precipitation events.

Deep Learning (DL) can be used to develop a dry indicator based on geostationary satellite data that can be applied for dry-wet classification in CML processing. A convolutional neural network is used to process visual and infrared cloud information from geostationary satellites and to create a dry indicator. Satellite derived products exist, such as the NWC SAF products PC and PC-Ph, and are utilized as baseline products. The baseline products and the DL based dry indicator developed in this work (DL product) are evaluated with radar and station data in Germany.

The evaluation shows that the developed DL product improves the performance at day and especially at nighttime. Limitations in detecting the correct rain field area is reduced by the DL product. In total the DL product improves the Matthews Correlation Coefficient value by about 0.05 compared to the PC-Ph product. 

How to cite: Wiegels, R., Wagner, A., Polz, J., Glawion, L., and Chwala, C.: An improved MSG SEVIRI wet-dry product based on a convolutional neural network, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-14066, https://doi.org/10.5194/egusphere-egu23-14066, 2023.