Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step

Abstract

Nowcasting is an important technique for weather forecasting because sudden weather changes significantly affect human life. The encoding-forecasting model, which is a state-of-the-art architecture in the field of data-driven radar extrapolation, does not particularly focus on the latest data when forecasting natural phenomena. This paper proposes a weighted broadcasting method that emphasizes the latest data of the time step to improve the nowcasting performance. This weighted broadcasting method allows the most recent rainfall patterns to have a greater impact on the forecasting network by extending the architecture of the existing encoding-forecasting model. Experimental results show that the proposed model is 1.74% and 2.20% better than the existing encoding-forecasting model in terms of mean absolute error and critical success index, respectively. In the case of heavy rainfall with an intensity of 30 mm/h or higher, the proposed model was more than 30% superior to the existing encoding-forecasting model. Therefore, applying the weighted broadcasting method, which explicitly places a high emphasis on the latest information, to the encoding-forecasting model is considered as an improvement that is applicable to the state-of-the-art implementation of data-driven radar-based precipitation nowcasting.

Self-clustered GAN for precipitation nowcasting

“…Deep learning models have recently surpassed optical flow-based weather prediction systems in performance, leading to feasible real-world applications. Shi 20 were able to effectively predict the space-time evolution patterns of precipitation by combining convolution with RNN 22 , 23 . However, the algorithm has a limited ability to represent complex movements and the rotation of clouds.…”

Quality-Aware Conditional Generative Adversarial Networks for Precipitation Nowcasting

“…Results indicate that the addition of multi-head attention and residual connections to the CNN can precisely extract the local and global spatial features of the radar image. Some studies have used ConvLSTM for precipitation nowcasting [19][20][21]. Shi et al proposed two DL models, Trajectory Gated Recurrent Unit (TrajGRU) [22] and ConvLSTM [23], for precipitation nowcasting.…”

“…Then, we convert these values to binary values using a rainfall rate of 0.5 mm/h as a threshold, as outlined in previous research [19,23]. The SSIM equation is already shown in Equation ( 5), while the mathematical formulas for the other metrics are given in [21].…”

Multivariate Multi-Step Convection Nowcasting with Deep Neural Networks: The Novara Case Study

“…To date, we have studied and implemented Multi-Layer Perceptrons (MLP) as a forecasting baseline, and a special type of Recurrent Neural Networks (RNN), known as Long Short-Term Memory (LSTM) networks. The deep learning approach investigated in this work is inspired by [4] and [5] which introduced the novel architecture of the LSTM Encoder/Decoder (LSTM E/D) network [6,7] and provided evidence of improvement over traditional LSTMs.…”