Skillful 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 socio-economic needs of many sectors reliant on weather-dependent decision-making. 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 initiations. Recently introduced deep learning methods use radar to directly predict future rain rates, free of physical constraints. 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 more rare medium-to-heavy rain events. To address these challenges, we present a Deep Generative Model for the probabilistic nowcasting of precipitation from radar. Our model produces realistic and spatio-temporally consistent predictions over regions up to 1536 km x 1280 km and with lead times from 5-90 min ahead. In a systematic evaluation by more than fifty expert forecasters from the Met Office, our generative model ranked first for its accuracy and usefulness in 88% of cases against two competitive methods, demonstrating its decision-making value and ability to provide physical insight to real-world experts. 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.

arXiv comment46 pages, 17 figures, 2 tables

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Self-Attention Generative Adversarial Networks
• On Calibration of Modern Neural Networks
• Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
• Axial Attention in Multidimensional Transformers
• MetNet: A Neural Weather Model for Precipitation Forecasting
• Machine Learning for Precipitation Nowcasting from Radar Images
• Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
• Adversarial Video Generation on Complex Datasets
• Classification Accuracy Score for Conditional Generative Models
• A review of radar-based nowcasting of precipitation and applicable machine learning techniques
• Precipitation Nowcasting with Satellite Imagery
• Precipitation Nowcasting with Star-Bridge Networks
• RainBench: Towards Global Precipitation Forecasting from Satellite Imagery

Cited by in corpus (47)

• A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts
• SocialVAE: Human Trajectory Prediction using Timewise Latents
• The Need for Ethical, Responsible, and Trustworthy Artificial Intelligence for Environmental Sciences
• Short-term precipitation prediction using deep learning
• SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
• Nowcasting-Nets: Deep Neural Network Structures for Precipitation Nowcasting Using IMERG
• Hybrid physics-AI outperforms numerical weather prediction for extreme precipitation nowcasting
• Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast
• Warmth and competence in human-agent cooperation
• Accelerating Material Design with the Generative Toolkit for Scientific Discovery
• A Machine Learning Tutorial for Operational Meteorology, Part II: Neural Networks and Deep Learning
• Global Extreme Heat Forecasting Using Neural Weather Models
• Seamless lightning nowcasting with recurrent-convolutional deep learning
• When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• A neural network-based scale-adaptive cloud-fraction scheme for GCMs
• Machine learning applications for weather and climate need greater focus on extremes
• Generative machine learning methods for multivariate ensemble post-processing
• A Machine Learning Tutorial for Operational Meteorology, Part I: Traditional Machine Learning
• MetroGAN: Simulating Urban Morphology with Generative Adversarial Network
• RNDiff: Rainfall nowcasting with Condition Diffusion Model
• Ensemble flow reconstruction in the atmospheric boundary layer from spatially limited measurements through latent diffusion models
• Realistic galaxy images and improved robustness in machine learning tasks from generative modelling
• Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
• Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination
• Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
• Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model
• Black Hole Weather Forecasting with Deep Learning: A Pilot Study
• Interpretable AI-Driven Discovery of Terrain-Precipitation Relationships for Enhanced Climate Insights
• Improvements to short-term weather prediction with recurrent-convolutional networks
• Explainable AI-Based Interface System for Weather Forecasting Model
• GPTCast: a weather language model for precipitation nowcasting
• Deep Vision in Analysis and Recognition of Radar Data: Achievements, Advancements and Challenges
• A Comprehensive Survey on Deep Learning Solutions for 3D Flood Mapping
• Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks
• Deep Probability Estimation
• Improving ensemble extreme precipitation forecasts using generative artificial intelligence
• How to derive skill from the Fractions Skill Score
• Probabilistic Hierarchical Forecasting with Deep Poisson Mixtures
• First-Passage Approach to Optimizing Perturbations for Improved Training of Machine Learning Models
• Weighted Quantum Channel Compiling through Proximal Policy Optimization
• Example-Based Concept Analysis Framework for Deep Weather Forecast Models
• Machine Learning Estimation of Maximum Vertical Velocity from Radar
• Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperature
• Downscaling Extreme Precipitation with Wasserstein Regularized Diffusion
• Inferring Thunderstorm Occurrence from Vertical Profiles of Convection-Permitting Simulations: Physical Insights from a Physical Deep Learning Model
• Generative Network-Based Reduced-Order Model for Prediction, Data Assimilation and Uncertainty Quantification