The operational medium-range deterministic weather forecasting can be extended beyond a 10-day lead time
By Kan Chen, Tao Han, Junchao Gong, Lei Bai, Fenghua Ling, Jingyao Luo, Xi Chen, Lei Ma, Tianning Zhang, Rui Su and 4 more. Communications Earth & Environment, 2023
338 citations recorded by the source corpus.
Given the complexity of the atmospheric system, current numerical weather prediction models struggle with accurate forecasts. Here we present FengWu, an Artificial-Intelligence-driven global medium-range forecasting system employing multi-modal and multi-task learning to simulate atmospheric dynamics at 0.25° spatial resolution across 13 pressure levels. To decrease the error accumulation problem, a replay buffer mechanism has been implemented with high computational efficiency. These enhancements allow FengWu to outperform deterministic forecasts produced by European Centre for Medium-Range Weather Forecasts High-Resolution Model, Pangu-Weather, and GraphCast. Additionally, to address predictive uncertainty, we develop FengWu-Ensemble, using conditional diffusion model that generates reliable multi-member forecasts based on deterministic predictions. Comparative evaluations against the Integrated Forecasting System Ensemble show that FengWu-Ensemble achieves superior performance across multiple meteorological variables and evaluation metrics. These results indicate that FengWu holds strong potential for improving both deterministic and probabilistic weather forecasting. A new deep learning-based global medium-range weather forecasting model outperforms existing machine learning models and the European Centre for Medium-Range Weather Forecasts model, producing accurate global weather forecasts beyond ten days.
Subfields: Atmospheric Science, Global and Planetary Change
View Paper: https://www.semanticscholar.org/paper/2b344095e31a27fcf02b86196f128745a4746b04
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
- Foundation Models for Time Series Analysis: A Tutorial and Survey (2024, neutral): “…time series modeling strategy gains the advantages of inherent simplicity and bypasses the challenges of handling modality gaps, yet frequently demonstrates excellent empirical results across a wide range of real-world applications, such as traffic [58, 82] and climate forecasting [13, 69].”
- A foundation model for the Earth system (2025, positive): “In 2023, a breakthrough came with Pangu-Weather 2 , in which a neural network replaced a numerical solver, outperforming state-of-the-art forecasting systems and sparking a wave of weather prediction models based on AI 3,16–18 .”
- Probabilistic weather forecasting with machine learning (2024, neutral): “We transform log noise levels into a vector of sine– cosine Fourier features at 32 frequencies with base period 16 and pass them through a two-layer MLP to obtain 16-dimensional noise-level encodings.”
- FuXi: a cascade machine learning forecasting system for 15-day global weather forecast (2023, background): “Chen et al. [19] proposed a reply buffer mechanism to mimic the long-lead autoregressive forecasts with improved computational efficiency and reduced memory costs.”