用大模型生成气象时间序列，让文字能精准控制天气变化
Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data
- 构建百亿级气象数据集，搭配专家级文本描述
- 通过频谱提示生成器实现文字到多频段信号的精准映射
- 在少样本和零样本下仍保持高精度，适用于多种时间序列
文本到时间序列生成在气象学中尤为重要，自然语言可直观控制复杂的多尺度大气动力。现有方法受限于缺乏大规模、物理一致的多模态数据集，以及忽视天气信号的频谱-时序结构。本文提出统一框架，实现文本引导的气象时间序列生成。首先构建MeteoCap-3B，一个百亿规模的气象数据集，结合通过多智能体协作标注（MACC）流程生成的信息密集且物理一致的专家级描述。基于此数据集，提出MTransformer，一种基于扩散模型的方法，通过频谱提示生成器将文本描述映射为多波段频谱先验，并利用频率感知注意力机制实现精确语义控制。在真实世界基准测试中，该方法展现领先生成质量、准确的跨模态对齐、强语义可控性，并在数据稀疏与零样本设置下显著提升下游预测性能。在通用时间序列基准上的附加结果表明，该框架可泛化至气象以外领域。
原文摘要 · Abstract (English)
Text-to-time-series generation is particularly important in meteorology, where natural language offers intuitive control over complex, multi-scale atmospheric dynamics. Existing approaches are constrained by the lack of large-scale, physically grounded multimodal datasets and by architectures that overlook the spectral-temporal structure of weather signals. We address these challenges with a unified framework for text-guided meteorological time-series generation. First, we introduce MeteoCap-3B, a billion-scale weather dataset paired with expert-level captions constructed via a Multi-agent Collaborative Captioning (MACC) pipeline, yielding information-dense and physically consistent annotations. Building on this dataset, we propose MTransformer, a diffusion-based model that enables precise semantic control by mapping textual descriptions into multi-band spectral priors through a Spectral Prompt Generator, which guides generation via frequency-aware attention. Extensive experiments on real-world benchmarks demonstrate state-of-the-art generation quality, accurate cross-modal alignment, strong semantic controllability, and substantial gains in downstream forecasting under data-sparse and zero-shot settings. Additional results on general time-series benchmarks indicate that the proposed framework generalizes beyond meteorology.
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。