发表机构
Beihang University; Shanghai Artificial Intelligence Laboratory; The Chinese University of Hong Kong; Tsinghua University（北京航空航天大学; 上海人工智能实验室; 香港中文大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对全球台站天气预报中现有方法的局限，提出三轴状态空间模型TSSM，通过时间可变历史范式纳入历史数据，设计扫描捕捉多种特性，在多数据集上性能优异，尤其在长期和迭代预测及应对缺失观测方面优势明显。
AI 中文摘要
全球台站天气预报对于关键区域的局部和极端天气预报至关重要。尽管努力利用回溯窗口，但现有方法在准确性提升方面有限，且在极端事件和误差累积方面存在困难。这些限制源于对短期模式的过度依赖，不足以捕捉混沌天气动态。为解决此问题，我们提出了一种新颖的三轴状态空间模型（TSSM），具有历史增强的时间可变历史范式，纳入周期对齐的历史天气数据以补偿时间回溯窗口之外的长期、大规模周期性和全窗口天气模式。具体而言，TSSM将历史样本堆叠成周期对齐的批次，预测由历史和当前观测因果支持。设计了时间、可变和历史扫描以捕捉轴向时间依赖性、可变相关性和历史演变。这种结构分层共享以对季节性到极端事件进行建模，同时减轻历史模式之间的错位。TSSM在Weather-5K（迄今为止最大的台站天气数据集）上实现了SOTA性能，在准确性和极端事件指标上分别提高了10%和61%，在人工参与的数据集上获得了95%的最佳或次佳结果。其优势在长期和迭代预测中更为明显，在240小时时增益达到37.5%，在48小时×5次迭代设置下高达103.5%。此外，与基线的<43%相比，TSSM在高达80%的缺失观测下仍保持>90%的性能，展示了在全球原位观测网络中进行可靠全球台站天气预报的稳健性和实际潜力。
英文摘要
Global Station Weather Forecasting (GSWF) is pivotal for localized and extreme weather prediction over key regions. Despite efforts to exploit look-back windows, existing methods show limited accuracy gains and struggle with extreme events and error accumulation. These limitations stem from overreliance on short-term patterns, which are insufficient to capture chaotic weather dynamics, especially under partial observations. To address this problem, we propose a novel Triaxial State Space Model (TSSM) with a history-enhanced Temporal-VariableHistorical paradigm, which incorporates period-aligned historical weather data to compensate for long-term, large-scale periodic, and full-window weather patterns beyond the temporal lookback window. Specifically, TSSM stacks historical samples into period-aligned batches, where forecasting is causally supported by historical and current observations. Temporal, variable, and historical scanning are designed to capture axial temporal dependencies, variable correlations, and historical evolution. This structure is hierarchically shared to model seasonal to extreme events while alleviating misalignment across historical patterns. TSSM achieves SOTA performance on Weather-5K, the largest station weather dataset to date, with 10% and 61% gains in accuracy and extreme event metrics, and obtains 95% best or second-best results on human-involved datasets. Its advantages are more pronounced in long-horizon and iterative forecasting, reaching a 37.5% gain at 240h and up to 103.5% under a 48h times 5 iterative setting. Moreover, TSSM retains > 90% performance under up to 80% missing observations, compared with < 43% for baselines, demonstrating robustness and practical potential for reliable GSWF in global in-situ observation networks.
