Preprints
https://doi.org/10.5194/hess-2021-432
https://doi.org/10.5194/hess-2021-432

  25 Aug 2021

25 Aug 2021

Review status: this preprint is currently under review for the journal HESS.

Quantifying the uncertainty of precipitation forecasting using probabilistic deep learning

Lei Xu1, Nengcheng Chen1,2, and Chao Yang1 Lei Xu et al.
  • 1National Engineering Research Center for Geographic Information System, School of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430074, China
  • 2State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan 430079, China

Abstract. Precipitation forecasting is an important mission in weather science. In recent years, data-driven precipitation forecasting techniques could complement numerical prediction, such as precipitation nowcasting, monthly precipitation projection and extreme precipitation event identification. In data-driven precipitation forecasting, the predictive uncertainty arises mainly from data and model uncertainties. Current deep learning forecasting methods could model the parametric uncertainty by random sampling from the parameters. However, the data uncertainty is usually ignored in the forecasting process and the derivation of predictive uncertainty is incomplete. In this study, the input data uncertainty, target data uncertainty and model uncertainty are jointly modeled in a deep learning precipitation forecasting framework to estimate the predictive uncertainty. Specifically, the data uncertainty is estimated a priori and the input uncertainty is propagated forward through model weights according to the law of error propagation. The model uncertainty is considered by sampling from the parameters and is coupled with input and target data uncertainties in the objective function during the training process. Finally, the predictive uncertainty is produced by propagating the input uncertainty and sampling the weights in the testing process. The experimental results indicate that the proposed joint uncertainty modeling and precipitation forecasting framework exhibits comparable forecasting accuracy with existing methods, while could reduce the predictive uncertainty to a large extent relative to two existing joint uncertainty modeling approaches. The developed joint uncertainty modeling method is a general uncertainty estimation approach for data-driven forecasting applications.

Lei Xu et al.

Status: open (until 20 Oct 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Lei Xu et al.

Lei Xu et al.

Viewed

Total article views: 314 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
245 67 2 314 1 2
  • HTML: 245
  • PDF: 67
  • XML: 2
  • Total: 314
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 25 Aug 2021)
Cumulative views and downloads (calculated since 25 Aug 2021)

Viewed (geographical distribution)

Total article views: 184 (including HTML, PDF, and XML) Thereof 184 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 19 Sep 2021
Download
Short summary
Precipitation forecasting has potential uncertainty due to data and model uncertainties. Here, an integrated predictive uncertainty framework is proposed by uncertainty propagation and random sampling. The results indicate an effective predictive uncertainty estimation for precipitation forecasting. The proposed approach fully considers uncertainty sources from predictor and predictand data and models, which has potential for numerous predictive applications.