Preprints
https://doi.org/10.5194/egusphere-2024-647
https://doi.org/10.5194/egusphere-2024-647
04 Apr 2024
 | 04 Apr 2024
Status: this preprint is open for discussion.

Technical Note: A simple feedforward artificial neural network for high temporal resolution classification of wet and dry periods using signal attenuation from commercial microwave links

Erlend Øydvin, Maximilian Graf, Christian Chwala, Mareile Astrid Wolff, Nils-Otto Kitterød, and Vegard Nilsen

Abstract. Two simple feedforward neural networks (MLPs) are trained to classify wet and dry periods using signal attenuation from commercial microwave links (CMLs) as predictors and high temporal resolution reference data as target. MLPGA is trained against nearby rain gauges and MLPRA is trained against gauge-adjusted weather radar. Both MLPs perform better than existing methods, showcasing their effectiveness in capturing the intermittent behaviour of rainfall. This study is the first using both radar and rain gauges for training and testing for CML wet-dry classification. Where previous studies has mainly focused on hourly reference data, our findings show that it is possible to predict wet and dry periods with a higher temporal precision.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Erlend Øydvin, Maximilian Graf, Christian Chwala, Mareile Astrid Wolff, Nils-Otto Kitterød, and Vegard Nilsen

Status: open (until 17 Jun 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-647', Anonymous Referee #1, 02 May 2024 reply
  • RC2: 'Comment on egusphere-2024-647', Anonymous Referee #2, 23 May 2024 reply
Erlend Øydvin, Maximilian Graf, Christian Chwala, Mareile Astrid Wolff, Nils-Otto Kitterød, and Vegard Nilsen
Erlend Øydvin, Maximilian Graf, Christian Chwala, Mareile Astrid Wolff, Nils-Otto Kitterød, and Vegard Nilsen

Viewed

Total article views: 272 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
209 45 18 272 11 13
  • HTML: 209
  • PDF: 45
  • XML: 18
  • Total: 272
  • BibTeX: 11
  • EndNote: 13
Views and downloads (calculated since 04 Apr 2024)
Cumulative views and downloads (calculated since 04 Apr 2024)

Viewed (geographical distribution)

Total article views: 263 (including HTML, PDF, and XML) Thereof 263 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 28 May 2024
Download
Short summary
Two simple neural networks are trained to detect rainfall events using signal loss from commercial microwave links. Whereas existing rainfall event detection methods have focused on hourly resolution reference data, this study uses weather radar and rain gauges with 5 minutes and 1 minute temporal resolution respectively. Our results show that the developed neural networks can detect rainfall events with a higher temporal precision than existing methods.