用流匹配方法实现高效全球天气预测，30天预报精度接近大模型。
Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching
- 在隐空间中通过自回归生成天气图，用可训练位置编码增强长时序依赖建模。
- 276万参数模型在30天预报上性能媲美16亿参数的LaDCast，推理速度更快。
- 适合需要高效率、长周期天气预测的研究与应用，如气候监测与灾害预警。
由于大气固有的混沌特性，准确的次季节性天气预报仍面临重大挑战，传统模型在中长期（约15天）后预测能力显著下降。本文提出 extit{Marchuk}，一种用于全球天气预报的生成式隐空间流匹配模型，覆盖从中期到次季节性时间尺度，预测时长可达30天。Marchuk 以当日天气图为条件，自回归地在学习到的隐空间中预测后续各日的天气图。我们用可训练的位置嵌入替代旋转位置编码（RoPE），并扩展时间上下文窗口，从而增强模型对长时序依赖的表示与传播能力。Marchuk 具备两大优势：计算效率高且预测性能强。尽管其参数量仅27600万，性能却可媲美参数量达16亿的LaDCast模型，同时推理速度显著提升。我们已开源推理代码与模型：https://v-gen-ai.github.io/Marchuk/
原文摘要 · Abstract (English)
Accurate subseasonal weather forecasting remains a major challenge due to the inherently chaotic nature of the atmosphere, which limits the predictive skill of conventional models beyond the mid-range horizon (approximately 15 days). In this work, we present \textit{Marchuk}, a generative latent flow-matching model for global weather forecasting spanning mid-range to subseasonal timescales, with prediction horizons of up to 30 days. Marchuk conditions on current-day weather maps and autoregressively predicts subsequent days' weather maps within the learned latent space. We replace rotary positional encodings (RoPE) with trainable positional embeddings and extend the temporal context window, which together enhance the model's ability to represent and propagate long-range temporal dependencies during latent forecasting. Marchuk offers two key advantages: high computational efficiency and strong predictive performance. Despite its compact architecture of only 276 million parameters, the model achieves performance comparable to LaDCast, a substantially larger model with 1.6 billion parameters, while operating at significantly higher inference speeds. We open-source our inference code and model at: https://v-gen-ai.github.io/Marchuk/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。