Skilful precipitation nowcasting using deep generative models of radar

By Suman V. Ravuri, Karel Lenc, M. Willson, D. Kangin, Rémi R. Lam, Piotr Wojciech Mirowski, Megan Fitzsimons, M. Athanassiadou, Sheleem Kashem, Sam Madge and 10 more. Nature, 2021

1,048 citations recorded by the source corpus.

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. A deep generative model using radar observations is used to create skilful precipitation predictions that are accurate and support real-world utility.

Subfields: Atmospheric Science, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/f99de990f791799df398fcd38034c4b395d9b7e0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Global and Planetary Change

Citations in the corpus

ClimaX: A foundation model for weather and climate (2023, neutral): “Yet, with growing compute and datasets, there is emerging evidence that these models can achieve accuracies competitive with state-of-the-art numerical models in many scenarios, such as nowcasting of precipitation (Ravuri et al., 2021; Sønderby et al., 2020) and medium-range forecasting of variables”
A high-resolution canopy height model of the Earth (2022, neutral): “(Ravuri et al., 2021) and has great potential to advance environmental monitoring (Reichstein et al.”
Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks (2021, methodology): “[21] use a generative model that is radar-based only.”
Diffusion Probabilistic Modeling for Video Generation (2022, background): “Applications of such video prediction tasks include anticipating events [56], modelbased reinforcement learning [19], video interpolation [31], predicting pedestrians in traffic [6], precipitation nowcasting [44], neural video compression [20, 33, 1, 59, 60, 62], and many more.”
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency (2022, background): “Time series plays important roles in many areas, including clinical diagnosis, traffic analysis, and climate science [1, 2, 3, 4, 5, 6].”
GraphCast: Learning skillful medium-range global weather forecasting (2022, background): “, 2022) and precipitation nowcasting, both with and without NWP information (Espeholt et al., 2022; Ravuri et al., 2021; Shi et al., 2017; Sønderby et al., 2020).”
Earthformer: Exploring Space-Time Transformers for Earth System Forecasting (2022, methodology): “Recent studies on adding physical constraints [20, 26] and ensembling the predictions from a data-driven model and a physics-based model [32] imply that it is an active and promising research direction to pursue.”