Skillful subseasonal forecasts beyond 2 weeks are crucial for a wide range of applications across various sectors of society. Recently, state-of-the-art machine learning based weather forecasting models have made significant advancements, outperforming the high-resolution forecast (HRES) from the European Centre for Medium-Range Weather Forecasts (ECMWF). However, the full potential of machine learning models in subseasonal forecasts has yet to be fully explored. In this study, we introduce FuXi Subseasonal-to-Seasonal (FuXi-S2S), a machine learning based subseasonal forecasting model that provides global daily mean forecasts up to 42 days, covering 5 upper-air atmospheric variables at 13 pressure levels and 11 surface variables. FuXi-S2S integrates an enhanced FuXi base model with a perturbation module for flow-dependent perturbations in hidden features, and incorporates Perlin noise to perturb initial conditions. The model is developed using 72 years of daily statistics from ECMWF ERA5 reanalysis data. When compared to the ECMWF Subseasonal-to-Seasonal (S2S) reforecasts, the FuXi-S2S forecasts demonstrate superior deterministic and ensemble forecasts for total precipitation (TP), outgoing longwave radiation (OLR), and geopotential at 500 hPa (Z500). Although it shows slightly inferior performance in predicting 2-meter temperature (T2M), it has clear advantages over land area. Regarding the extreme forecasts, FuXi-S2S outperforms ECMWF S2S globally for TP. Furthermore, FuXi-S2S forecasts surpass the ECMWF S2S reforecasts in predicting the Madden Julian Oscillation (MJO), a key source of subseasonal predictability. They extend the skillful prediction of MJO from 30 days to 36 days.

翻译：超过2周的高技巧次季节预报对于社会各领域广泛应用至关重要。近期，基于机器学习的最先进天气预报模型取得了显著进展，其表现优于欧洲中期天气预报中心（ECMWF）的高分辨率预报（HRES）。然而，机器学习模型在次季节预报中的全部潜力尚未被充分发掘。在本研究中，我们提出FuXi次季节至季节（FuXi-S2S）模型，这是一种基于机器学习的次季节预报模型，能够提供长达42天的全球日平均预报，涵盖13个气压层上的5个高层大气变量和11个地表变量。FuXi-S2S通过增强型FuXi基础模型集成扰动模块，实现对隐特征中流依赖扰动的处理，并引入佩林噪声扰动初始条件。该模型基于ECMWF ERA5再分析数据72年的日统计数据进行开发。与ECMWF次季节至季节（S2S）再预报相比，FuXi-S2S在总降水量（TP）、射出长波辐射（OLR）和500hPa位势高度（Z500）的确定性预报和集合预报中均展现出更优性能。尽管在预测2米温度（T2M）方面表现略逊一筹，但它在陆地区域具有明显优势。在极端预报方面，FuXi-S2S在全球范围内的TP预报优于ECMWF S2S。此外，FuXi-S2S在预测次季节可预报性关键来源——马登-朱利安振荡（MJO）方面超越了ECMWF S2S再预报，将MJO的高技巧预测时限从30天延长至36天。