FuXi: A cascade machine learning forecasting system for 15-day global weather forecast

2023/06/22 by Lei Chen, Xiaohui Zhong, Chen, Lei +11 · 80 citations
Earth and Planetary Sciences · Environmental Science · #Artificial Intelligence (cs.AI) #Atmospheric and Oceanic Physics (physics.ao-ph) #Climate variability and models #FOS: Computer and information sciences #FOS: Physical sciences #Hydrological Forecasting Using AI #Machine Learning (cs.LG) #Meteorological Phenomena and Simulations

paper · pdf · doi:10.48550/arxiv.2306.12873

openalex publication_date 2023/06/22 · openalex created_date 2023/06/24 · openalex updated_date 2026/07/28

Abstract

Over the past few years, due to the rapid development of machine learning (ML) models for weather forecasting, state-of-the-art ML models have shown superior performance compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution forecast (HRES) in 10-day forecasts at a spatial resolution of 0.25 degree. However, the challenge remains to perform comparably to the ECMWF ensemble mean (EM) in 15-day forecasts. Previous studies have demonstrated the importance of mitigating the accumulation of forecast errors for effective long-term forecasts. Despite numerous efforts to reduce accumulation errors, including autoregressive multi-time step loss, using a single model is found to be insufficient to achieve optimal performance in both short and long lead times. Therefore, we present FuXi, a cascaded ML weather forecasting system that provides 15-day global forecasts with a temporal resolution of 6 hours and a spatial resolution of 0.25 degree. FuXi is developed using 39 years of the ECMWF ERA5 reanalysis dataset. The performance evaluation, based on latitude-weighted root mean square error (RMSE) and anomaly correlation coefficient (ACC), demonstrates that FuXi has comparable forecast performance to ECMWF EM in 15-day forecasts, making FuXi the first ML-based weather forecasting system to accomplish this achievement.

Cited by

• Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models
• Zhinv: Real-time hub-height wind field reconstruction using only local sparse observations
• Huayu: Advanced Real-Time Precipitation Estimation from Geostationary Satellite
• WaveSim: A Wavelet-based Multi-scale Similarity Metric for Weather and Climate Fields
• Evaluating Weather Forecasts from a Decision Maker's Perspective
• Bridging Artificial Intelligence and Data Assimilation: The Data-driven Ensemble Forecasting System ClimaX-LETKF
• Evaluating Adversarial Attacks on Federated Learning for Temperature Forecasting
• Skillful Subseasonal-to-Seasonal Forecasting of Extreme Events with a Multi-Sphere Coupled Probabilistic Model
• China Regional 3km Downscaling Based on Residual Corrective Diffusion Model
• FuXi-Nowcast: Environment-conditioned deep learning for severe convection nowcasting
• S²-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting
• Agentic AI Framework for Cloudburst Prediction and Coordinated Response
• OceanForecastBench: A Benchmark Dataset for Data-Driven Global Ocean Forecasting
• On the Predictive Skill of Artificial Intelligence-based Weather Models for Extreme Events using Uncertainty Quantification
• SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earth
• AI-Based Regional Emulation for Kilometer-Scale Dynamical Downscaling
• Revealing the Potential of Learnable Perturbation Ensemble Forecast Model for Tropical Cyclone Prediction
• CSU-PCAST: A Dual-Branch Transformer Framework for medium-range ensemble Precipitation Forecasting
• Signature Kernel Scoring Rule: A Spatio-Temporal Diagnostic for Probabilistic Weather Forecasting
• OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
• An Operational Deep Learning System for Satellite-Based High-Resolution Global Nowcasting
• Deploying Atmospheric and Oceanic AI Models on Chinese Hardware and Framework: Migration Strategies, Performance Optimization and Analysis
• DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space
• Zeeman: A Deep Learning Regional Atmospheric Chemistry Transport Model
• Learning more physically realistic dynamics in machine-learning based weather forecasting with latent-space constraints
• A Weather Foundation Model for the Power Grid
• Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
• Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts
• Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models
• Climate-Adaptive and Cascade-Constrained Machine Learning Prediction for Sea Surface Height under Greenhouse Warming
• Communications to Circulations: Real-Time 3D Wind Field Prediction Using 5G GNSS Signals and Deep Learning
• STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
• A data-driven global ocean forecasting model with sub-daily and eddy-resolving resolution
• Accurate typhoon intensity forecasts using a non-iterative spatiotemporal transformer model
• FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Solver
• AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
• SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators
• MoWE : A Mixture of Weather Experts
• Intelligent Shanghai Typhoon Model (ISTM): A generative probabilistic emulator for typhoon hybrid modeling
• LUCIE-3D: A three-dimensional climate emulator for forced responses
• FuXi-TC: A generative framework integrating deep learning and physics-based models for improved tropical cyclone forecasts
• IndiaWeatherBench: A Dataset and Benchmark for Data-Driven Regional Weather Forecasting over India
• Large Model Driven Solar Activity AI Forecaster: A Scalable Dual Data-Model Framework
• MeteorPred: A Meteorological Multimodal Large Model and Dataset for Severe Weather Event Prediction
• SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA
• Data-driven global ocean model resolving ocean-atmosphere coupling dynamics
• AtmosMJ: Revisiting Gating Mechanism for AI Weather Forecasting Beyond the Year Scale
• A comparison of stretched-grid and limited-area modelling for data-driven regional weather forecasting
• The Impact of Tropical Convective Heating on the Amundsen Sea Low in a Deep-Learning Weather Forecasting Model
• Global weather forecasting through deep learning: applications and challenges
• FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
• MVAR: MultiVariate AutoRegressive Air Pollutants Forecasting Model
• XiChen: A global weather observation-to-forecast machine learning system via four-dimensional variational gradient-guided flexible assimilation
• SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
• Deep Learning Atmospheric Models Reliably Simulate Out-of-Sample Land Heat and Cold Wave Frequencies
• Imposing the Fundamental Dynamical Constraint of Hydrostatic Balance to Improve Global ML Weather Prediction
• FuXi-Air: Urban Air Quality Forecasting Based on Emission-Meteorology-Pollutant multimodal Machine Learning
• Finetuning a Weather Foundation Model with Lightweight Decoders for Unseen Physical Processes
• Forecast error diagnostics in neural weather models
• Arnoldi Singular Vector perturbations for machine learning weather prediction
• Constructing Extreme Heatwave Storylines with Differentiable Climate Models
• FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
• A machine learning model for skillful climate system prediction
• Non-collective Calibrating Strategy for Time Series Forecasting
• Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
• NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation
• PEAR: Equal Area Weather Forecasting on the Sphere
• Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model
• Terrain-aware Deep Learning for Wind Energy Applications: From Kilometer-scale Forecasts to Fine Wind Fields
• LanTu: Dynamics-Enhanced Deep Learning for Eddy-Resolving Ocean Forecasting
• Predicting Beyond Training Data via Extrapolation versus Translocation: AI Weather Models and Dubai's Unprecedented 2024 Rainfall
• Physics-Assisted and Topology-Informed Deep Learning for Weather Prediction
• U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
• Towards Fair Comparisons of AI- and Physics-Based Weather Models for Extreme Events via the Weighted Potential CRPS
• Machine Learning (ML)-Physics Fusion Model Outperforms Both Physics-Only and ML-Only Models in Typhoon Predictions
• Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation
• EnsAI: An Emulator for Atmospheric Chemical Ensembles
• A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science
• TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology State
• KunPeng: A Global Ocean Environmental Model

Related

• FuXi Weather: A data-to-forecast machine learning system for global weather
• FuXi-S2S: A machine learning model that outperforms conventional global subseasonal forecast models
• FuXi-2.0: Advancing machine learning weather forecasting model for practical applications
• FuXi-ENS: A machine learning model for medium-range ensemble weather forecasting
• FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model