Skilful precipitation nowcasting using deep generative models of radar

Abstract

Precipitation nowcasting, the high-resolution forecasting of precipitation up to two hours ahead, supports the real-world socioeconomic needs of many sectors reliant on weather-dependent decision-making1,2. State-of-the-art operational nowcasting methods typically advect precipitation fields with radar-based wind estimates, and struggle to capture important non-linear events such as convective initiations3,4. Recently introduced deep learning methods use radar to directly predict future rain rates, free of physical constraints5,6. While they accurately predict low-intensity rainfall, their operational utility is limited because their lack of constraints produces blurry nowcasts at longer lead times, yielding poor performance on rarer medium-to-heavy rain events. Here we present a deep generative model for the probabilistic nowcasting of precipitation from radar that addresses these challenges. Using statistical, economic and cognitive measures, we show that our method provides improved forecast quality, forecast consistency and forecast value. Our model produces realistic and spatiotemporally consistent predictions over regions up to 1,536 km × 1,280 km and with lead times from 5–90 min ahead. Using a systematic evaluation by more than 50 expert meteorologists, we show that our generative model ranked first for its accuracy and usefulness in 89% of cases against two competitive methods. When verified quantitatively, these nowcasts are skillful without resorting to blurring. We show that generative nowcasting can provide probabilistic predictions that improve forecast value and support operational utility, and at resolutions and lead times where alternative methods struggle.

Rad-cGAN v1.0: Radar-based precipitation nowcasting model with conditional Generative Adversarial Networks for multiple domains

“…The video GAN model contains sequential components in the generator, while the discriminator uses a dual architecture that distinguishes the real and generated frames to ensure both temporal and spatial consistency. From the case study of connective cells over eastern Scotland, it was observed that using video GAN in the model significantly improved the quality of precipitation forecasts (Ravuri et al, 2021). These studies indicate that the performance of precipitation nowcasting models can be improved by advanced machine learning techniques.…”

“…Rüttgers et al (2019) showed that typhoon tracks and cloud patterns over the Korean Peninsula could be successfully predicted using cGAN architecture with satellite cloud images. Ravuri et al (2021) developed a precipitation nowcasting model using a deep generative model inspired by the video GAN model (Clark et al, 2019). The video GAN model contains sequential components in the generator, while the discriminator uses a dual architecture that distinguishes the real and generated frames to ensure both temporal and spatial consistency.…”

A Machine-Learning Approach Combining Wavelet Packet Denoising with Catboost for Weather Forecasting

“…If the time features such as month and hour are also set by the one-hot encoding method, a large feature space will be occupied. Moreover, the temporal continuity such as between December and January will be destroyed if the month feature (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12) is directly mapped into the interval of 0-1. In this work, clock projection is utilized to extract the temporal features.…”

“…Weather prediction is of great importance and can affect some aspects of daily life, such as air quality, travel plans, energy supply, and so on [1][2][3][4]. A conventional prediction method is numerical weather prediction (NWP) method, which solves the numerical solutions of atmospheric hydro-thermo dynamic equations to predict meteorological dynamics [5][6][7].…”

Forecasting the Daily Maximal and Minimal Temperatures from Radiosonde Measurements Using Neural Networks

“…The NNs were shown to be particularly successful in precipitation nowcasting. For example, Ravuri et al [21] used radar data to perform short-range probabilistic predictions of precipitation, while Sønderby et al [22] combined radar data with the satellite data.…”