Preprints
https://doi.org/10.5194/hess-2022-432
https://doi.org/10.5194/hess-2022-432
 
02 Jan 2023
02 Jan 2023
Status: this preprint is currently under review for the journal HESS.

Statistical post-processing of precipitation forecasts using circulation classifications and spatiotemporal deep neural networks

Tuantuan Zhang1, Zhongmin Liang1, Wentao Li1,2, Jun Wang1, Yiming Hu1, and Binquan Li1 Tuantuan Zhang et al.
  • 1College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China
  • 2CMA-HHU Joint Laboratory for HydroMeteorological Studies, Nanjing, Jiangsu

Abstract. Statistical post-processing techniques are widely used to reduce systematic biases and quantify forecast uncertainty in numerical weather prediction (NWP). In this study, we propose a method to correct the raw daily forecast precipitation by combining large-scale circulation patterns with local spatiotemporal information such as topography and meteorological factors. Particularly, we first use the self-organizing map (SOM) model to classify large-scale circulation patterns for each season, then build the convolutional neural network (CNN) model to extract spatial information (e.g., elevation, specific humidity, and mean sea level pressure) and long short-term memory network (LSTM) model to extract time series (e.g., t, t-1, t-2), and finally correct local precipitation for each circulation pattern separately. Furthermore, the proposed method (SOM-CNN-LSTM) is compared with other benchmark methods (i.e., CNN, LSTM, and CNN-LSTM) in the Huaihe River basin with a lead time of 15 days from 2007 to 2021. The results show that the proposed SOM-CNN-LSTM post-processing method outperforms other benchmark methods for all lead times and each season with the largest correlation coefficient improvement (32.30 %) and root mean square error reduction (26.58 %). Moreover, the proposed method can effectively capture the westward and northward movement of the western Pacific subtropical high (WPSH), which impacts the basin's summer rain. The results illustrate that incorporating large-scale circulation patterns with local spatiotemporal information is a feasible and effective post-processing method to improve forecasting skills, which would benefit hydrological forecasts and other applications.

Tuantuan Zhang et al.

Status: open (until 27 Feb 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2022-432', Anonymous Referee #1, 17 Jan 2023 reply
  • RC2: 'Comment on hess-2022-432', Anonymous Referee #2, 28 Jan 2023 reply
  • RC3: 'Comment on hess-2022-432', Anonymous Referee #3, 29 Jan 2023 reply

Tuantuan Zhang et al.

Tuantuan Zhang et al.

Viewed

Total article views: 334 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
246 76 12 334 23 3 3
  • HTML: 246
  • PDF: 76
  • XML: 12
  • Total: 334
  • Supplement: 23
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 02 Jan 2023)
Cumulative views and downloads (calculated since 02 Jan 2023)

Viewed (geographical distribution)

Total article views: 302 (including HTML, PDF, and XML) Thereof 302 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Feb 2023
Download
Short summary
We use circulation classifications and spatiotemporal deep neural networks to correct the raw daily forecast precipitation by combining large-scale circulation patterns with local spatiotemporal information. We find that the method not only captures the westward and northward movement of the western Pacific subtropical high but also shows substantially higher bias correction capabilities than existing standard methods in terms of space-scale, time-scale, and intensity.