16 November 2023 in npj Climate and Atmospheric Science
Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has led to state-of-the-art ML models that have superior performance compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)’s high-resolution forecast (HRES), which is widely considered as the world’s best physics-based weather forecasting system. Specifically, ML models have outperformed HRES in 10-day forecasts with a spatial resolution of 0.25∘. However, the challenge remains in mitigating the accumulation of forecast errors for longer effective forecasts, such as achieving comparable performance to the ECMWF ensemble in 15-day forecasts. Despite various efforts to reduce accumulation errors, such as implementing autoregressive multi-time step loss, relying on a single model has been found to be insufficient for achieving 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 at a temporal resolution of 6 hours and a spatial resolution of 0.25∘. FuXi is developed using 39 years of the ECMWF ERA5 reanalysis dataset. The performance evaluation demonstrates that FuXi has forecast performance comparable to ECMWF ensemble mean (EM) in 15-day forecasts. FuXi surpasses the skillful forecast lead time achieved by ECMWF HRES by extending the lead time for Z500 from 9.25 to 10.5 days and for T2M from 10 to 14.5 days. Moreover, the FuXi ensemble is created by perturbing initial conditions and model parameters, enabling it to provide forecast uncertainty and demonstrating promising results when compared to the ECMWF ensemble.
30 July 2024 in Nature Communications
Skillful subseasonal forecasts are crucial for various sectors of society but pose a grand scientific challenge. Recently, machine learning-based weather forecasting models outperform the most successful numerical weather predictions generated by the European Centre for Medium-Range Weather Forecasts (ECMWF), but have not yet surpassed conventional models at subseasonal timescales. This paper introduces FuXi Subseasonal-to-Seasonal (FuXi-S2S), a machine learning model that provides global daily mean forecasts up to 42 days, encompassing five upper-air atmospheric variables at 13 pressure levels and 11 surface variables. FuXi-S2S, trained on 72 years of daily statistics from ECMWF ERA5 reanalysis data, outperforms the ECMWF’s state-of-the-art Subseasonal-to-Seasonal model in ensemble mean and ensemble forecasts for total precipitation and outgoing longwave radiation, notably enhancing global precipitation forecast. The improved performance of FuXi-S2S can be primarily attributed to its superior capability to capture forecast uncertainty and accurately predict the Madden-Julian Oscillation (MJO), extending the skillful MJO prediction from 30 days to 36 days. Moreover, FuXi-S2S not only captures realistic teleconnections associated with the MJO but also emerges as a valuable tool for discovering precursor signals, offering researchers insights and potentially establishing a new paradigm in Earth system science research.
25 July 2025 in Medical Image Analysis
19 July 2025 in Nature Communications
Weather forecasting traditionally relies on numerical weather prediction (NWP) systems that integrate global observations, data assimilation (DA), and physics-based models. However, further advances are increasingly constrained by high computational costs, the underutilization of vast observational datasets, and challenges in obtaining finer resolution. Recent advances in machine learning present a promising alternative, but still depend on the initial conditions generated by NWP systems. Here, we introduce FuXi Weather, a machine learning-based global forecasting system that assimilates multi-satellite data and is capable of cycling DA and forecasting. FuXi Weather generates reliable 10-day forecasts at 0.25° resolution using fewer observations than conventional NWP systems. It demonstrates the value of background forecasts in constraining the analysis during DA. FuXi Weather outperforms the European Centre for Medium-Range Weather Forecasts high-resolution forecasts beyond day one in observation-sparse regions such as central Africa, highlighting its potential to improve forecasts where observational infrastructure is limited.
14 September 2023 in IEEE Transactions on Knowledge and Data Engineering
Graph Neural Networks (GNNs) have attracted much attention due to their superior learning capability. Despite the successful applications of GNNs in many areas, their performance suffers heavily from the long-tailed node degree distribution. Most prior studies tackle this issue by devising sophisticated model architectures. In this article, we aim to improve the performance of tail nodes (low-degree or hard-to-classify nodes) via a generic and light normalization method. In detail, we propose a novel normalization method for GNNs, termed as ResNorm, which Res hapes a long-tailed distribution into a normal-like distribution via Norm alization. The ResNorm includes two operators. First, the scale operator reshapes the distribution of the node-wise standard deviation (NStd) so as to improve the accuracy of tail nodes. Second, the analysis of the behavior of the standard shift indicates that the standard shift serves as a preconditioner on the weight matrix, increasing the risk of over-smoothing. To address this issue, we design a new shift operator for ResNorm, which simulates the degree-specific parameter strategy in a low-cost manner. Extensive experiments on various node classification benchmark datasets have validated the effectiveness of ResNorm in improving the performance of tail nodes as well as the overall performance.
27 March 2026 in Nature Computational Science