CLGAN: A GAN-based video prediction model for precipitation nowcasting

Abstract

Abstract. The prediction of precipitation patterns at high spatio-temporal resolution up to two hours ahead, also known as precipitation nowcasting, is of great relevance in weather-dependant decision-making and early warning systems. In this study, we are aiming to provide an efficient and easy-to-understand model - CLGAN, to improve the nowcasting skills of heavy precipitation events with deep neural networks for video prediction. The model constitutes a Generative Adversarial Network (GAN) architecture whose generator is built upon an u-shaped encoder-decoder network (U-Net) equipped with recurrent LSTM cells to capture spatio-temporal features. A comprehensive comparison among CLGAN, and baseline models optical flow model DenseRotation as well as the advanced video prediction model PredRNN-v2 is performed. We show that CLGAN outperforms in terms of scores for dichotomous events and object-based diagnostics. The ablation study indicates that the GAN-based architecture helps to capture heavy precipitation events. The results encourage future work based on the proposed CLGAN architecture to improve the precipitation nowcasting and early-warning systems.

Deep Learning for Daily 2‐m Temperature Downscaling

“…It shows promise in terms of both accuracy and efficiency, surpassing previous methods (Höhlein et al., 2020). However, the use of deep learning methods in the field of meteorological downscaling is still in its early stages and faces challenges such as inadequate description of complex features and poor performance in extreme events (Baño‐Medina et al., 2020; Y. Ji, Gong, et al., 2022; Y. Ji, Zhi, et al., 2022; Y. Ji, Zhi, et al., 2023; Vandal et al., 2019). Therefore, further practical exploration and research are needed to address these issues.…”

“…He et al., 2016; Wilby et al., 1998). With the advent of the big data era, deep learning has the potential to discover features in high‐dimensional data and capture the underlying nonlinear relationships between various meteorological variables (Y. Ji, Gong, et al., 2022; Y. Ji, Zhi, et al., 2022; Yuan et al., 2020; Zhi & Wang, 2023; Zhi et al., 2022). It shows promise in terms of both accuracy and efficiency, surpassing previous methods (Höhlein et al., 2020).…”

Precipitation forecast using RNN variants by analyzing Optimizers and Hyperparameters for Time-series based Climatological Data

“…ML algorithms, such as Regression [15], Support Vector Machine (SVM) [7], Decision Trees (DT) [16,17], Naive Bayes [18] and K-Nearest Neighbors (KNN) [19] have been effectively used to construct precipitation prediction or classification models in a variety of domains. DL algorithms, such as Artificial Neural Networks (ANN) [20], Recurrent Neural Networks (RNN) [21,22], Convolutional Neural Networks (CNN) [23] and Generative Adversarial Networks (GAN) [24] play an essential role in processing and analyzing massive amounts of precipitation data to deliver meaningful information. Venkatesh, et al (2021) [25] constructed a precipitation prediction system using GAN with a CNN upon time-series annual precipitation data of 36 subdivisions in India from 1901 to 2015.…”

Deep Learning for Daily 2-m Temperature Downscaling

“…It shows promise in terms of both accuracy and efficiency, surpassing previous methods (Höhlein et al, 2020). However, the use of deep learning methods in the field of meteorological downscaling is still in its early stages and faces challenges such as inadequate description of complex features and poor performance in extreme events (Baño-Medina et al, 2020;Ji et al, 2022;Ji et al, 2023b;Vandal et al, 2019). Therefore, further practical exploration and research are needed to address these issues.…”