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.
Highlights
Ensemble numerical weather prediction (NWP) systems, which simulate coupled physical equations of the atmosphere to generate multiple realistic precipitation forecasts, are natural candidates for nowcasting as one can derive probabilistic forecasts and uncertainty estimates from the ensemble of future predictions[7]
As a number of authors have noted[5,6], forecasts issued by current deep learning systems express uncertainty at increasing lead times with blurrier precipitation fields, and may not include small-scale weather patterns that are important for improving forecast value
We demonstrate improvements in the skill of probabilistic precipitation nowcasting that improves their value. To create these more skilful predictions, we develop an observations-driven approach for probabilistic nowcasting using deep generative models (DGMs)
Summary
Ensemble numerical weather prediction (NWP) systems, which simulate coupled physical equations of the atmosphere to generate multiple realistic precipitation forecasts, are natural candidates for nowcasting as one can derive probabilistic forecasts and uncertainty estimates from the ensemble of future predictions[7]. Established probabilistic nowcasting methods, such as STEPS and PySTEPS3,4, follow the NWP approach of using ensembles to account for uncertainty, but model precipitation following the advection equation with a radar source term In these models, motion fields are estimated by optical flow, smoothness penalties are used to approximate an advection forecast, and stochastic perturbations are added to the motion field and intensity model[3,4,12]. The ability of DGMs to both learn from observational data as well as represent uncertainty across multiple spatial and temporal scales makes them a powerful method for developing new types of operationally useful nowcasting These models can predict smaller-scale weather phenomena that are inherently difficult to predict due to underlying stochasticity, which is a critical issue for nowcasting research. Our model includes latent random vectors Z and parameters θ, described by
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
