Preprints
https://doi.org/10.5194/amt-2020-464
https://doi.org/10.5194/amt-2020-464

  23 Dec 2020

23 Dec 2020

Review status: a revised version of this preprint was accepted for the journal AMT and is expected to appear here in due course.

Can machine learning correct microwave humidity radiances for the influence of clouds?

Inderpreet Kaur1, Patrick Eriksson1, Simon Pfreundschuh1, and David Ian Duncan2 Inderpreet Kaur et al.
  • 1Department of Space, Earth and Environment, Chalmers University of Technology, Gothenburg, Sweden
  • 2European Centre for Medium Range Weather Forecasts, Reading, United Kingdom

Abstract. A methodology based on quantile regression neural networks (QRNN) is presented that identifies and corrects the cloud impact on microwave humidity sounder radiances at 183 GHz. This approach estimates the posterior distributions of noise free clear-sky (NFCS) radiances, providing nearly bias-free estimates of clear-sky radiances with a full posterior error distribution. It is first demonstrated by application to a present sensor, the MicroWave Humidity Sounder-2 (MWHS-2), then the applicability to sub-millimeter (sub-mm) sensors is also analysed. The QRNN results improve upon what operational cloud filtering techniques like a scattering index can achieve, but are ultimately imperfect due to limited information content on cirrus impact from traditional microwave channels – the negative departures associated with high cloud impact are successfully corrected, but thin cirrus clouds cannot be fully corrected. In contrast, when sub-mm observations are used, QRNN successfully corrects most cases with cloud impact, with only 2–6 % of the cases left partially corrected. The methodology works well even if only one sub-mm channel (325 GHz) is available. When using sub-mm observations, cloud correction usually results in error distributions with standard deviation less than typical channel noise values. Furthermore, QRNN outputs predicted quantiles for case-specific uncertainty estimates, successfully representing the uncertainty of cloud correction for each observation individually. In comparison to deterministic correction or filtering approaches, the corrected radiances and attendant uncertainty estimates have great potential to be used efficiently in assimilation systems due to being largely unbiased and adding little further uncertainty to the measurements.

Inderpreet Kaur et al.

 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Inderpreet Kaur et al.

Model code and software

typhon: tools for atmospheric research Oliver Lemke, Lukas Kluft, John Mrziglod, Simon Pfreundschuh, Gerrit Holl, Richard Larsson, Takayoshi Yamada, Theresa Mieslinger, and Jakob Doerr https://doi.org/10.5281/zenodo.3626449

Inderpreet Kaur et al.

Viewed

Total article views: 276 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
215 58 3 276 3 2
  • HTML: 215
  • PDF: 58
  • XML: 3
  • Total: 276
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 23 Dec 2020)
Cumulative views and downloads (calculated since 23 Dec 2020)

Viewed (geographical distribution)

Total article views: 257 (including HTML, PDF, and XML) Thereof 256 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 15 Apr 2021
Download
Short summary
Currently, cloud contamination in microwave humidity channels is addressed using filtering schemes. We present an approach to correct the cloud affected microwave humidity radiances using a Bayesian machine learning technique. The technique combines orthogonal information from microwave channels to obtain a probabilistic prediction of the clear-sky radiances. With this approach, we are able to predict bias free clear-sky radiances with well represented case-specific uncertainty estimates.