Submitted as: development and technical paper
25 Oct 2023
Submitted as: development and technical paper |  | 25 Oct 2023
Status: this preprint is currently under review for the journal GMD.

A deep learning method for convective weather forecasting: CNN-BiLSTM-AM (version 1.0)

Jianbin Zhang, Zhiqiu Gao, Yubin Li, and Yuncong Jiang

Abstract. This work developed a CNN-BiLSTM-AM model for convective weather forecasting using deep learning algorithms based on reanalysis and forecast data from the NCEP GFS, the performance of the model was evaluated. The results show that: (1) Compared to traditional machine learning algorithms, the CNN-BiLSTM-AM model has the ability to automatically learn deeper nonlinear features of convective weather. As a result, it exhibits higher forecasting accuracy on the convective weather dataset. Furthermore, as the forecast lead time increases, the information value provided by this model also changes. (2) In comparison to subjective forecasts by forecasters, the objective forecasting approach of the CNN-BiLSTM-AM model demonstrates advantages in metrics such as Probability of Detection (POD), False Alarm Rate (FAR), Threat Score (TS), and Missing Alarm Rate (MAR). Specifically, the average TS score for heavy precipitation reaches 0.336, which is a 33.2 % improvement compared to the forecaster's score of 0.252. Moreover, due to the CNN-BiLSTM-AM model's ability to automatically extract classification features based on a large sample dataset and consider a comprehensive range of convective parameters, it effectively reduces the FAR. (3) The interpretability study of the machine learning-based convective weather mechanism reveals that the importance ranking of convective weather forecasting factors arranged by machine learning methods largely aligns with the subjective understanding of forecasters. For example, the total precipitable water (PWAT) is identified as a critical factor for short-term heavy precipitation forecasting, regional factors have significant impacts on convective weather, and vertical motion at 300 hPa provides dynamic lifting conditions for convection. This objective analysis of factor ranking not only further confirms the effectiveness of machine learning in automatically extracting convective weather features but also validates the rationality of the sample set construction. Overall, the use of the CNN-BiLSTM-AM model in convective weather forecasting demonstrates superior performance compared to traditional machine learning algorithms and subjective forecasting methods.

Jianbin Zhang et al.

Status: open (until 20 Dec 2023)

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

Jianbin Zhang et al.

Jianbin Zhang et al.


Total article views: 228 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
165 57 6 228 2 2
  • HTML: 165
  • PDF: 57
  • XML: 6
  • Total: 228
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 25 Oct 2023)
Cumulative views and downloads (calculated since 25 Oct 2023)

Viewed (geographical distribution)

Total article views: 220 (including HTML, PDF, and XML) Thereof 220 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 06 Dec 2023
Short summary
This study developed a deep learning model called CNN-BiLSTM-AM for convective weather forecasting. The results showed that the CNN-BiLSTM-AM model outperformed traditional machine learning algorithms in predicting convective weather, with higher accuracy as the forecast lead time increased. When compared to subjective forecasts by forecasters, the objective approach of the CNN-BiLSTM-AM model also demonstrated advantages in various metrics.