arXiv：cs.AI· Xiong Li, Xiaowei Zhou, Yanwei Yu, Qian Cui, Junyu Dong·· 6 小时前AI 评分30
基于 LLM 的文本环境上下文与空间图用于区域 SST 预测
Textual Environmental Context and Spatial Graphs for LLM-Based Regional SST Forecasting
AI 导读
研究将海表温度（SST）多步预测重构为大语言模型的条件数值生成任务：历史 SST 与异常序列、日期对齐的环境记录和静态海洋知识构成文本上下文，区域空间状态则通过连续图前缀注入 LLM 输入。
正文
Abstract:Sea surface temperature (SST) forecasting depends on local temporal persistence, regional spatial dependence, and environmental conditions that evolve with the forecast date. We study how these heterogeneous conditions can be presented to a large language model (LLM) for regional multi-step forecasting without serializing the full SST grid as text. We formulate forecasting as conditional numerical generation: historical SST and anomaly sequences, date-aligned environmental records, and static ocean knowledge form a textual context, while regional spatial state is supplied through continuous graph-derived prefixes. A static graph encodes persistent geographic--climatological relations, and a dynamic graph encodes recent SST correlations and localized tropical-cyclone influence. Two graph neural networks produce a target-node representation that is mapped by a spatial-prefix fusion and injected into the LLM input. On SST forecasting in the South China Sea, the complete configuration achieves the best MAE and $\Rtwo$ among the compared methods over ten forecast steps. Alongside the numerical forecast, a rule-based module matches predicted trends and environmental-factor directions with knowledge entries to return source-linked, post-hoc contextual explanations.
| Comments: | preprint |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07895 [cs.AI] |
| (or arXiv:2610.07895v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07895 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaowei Zhou [view email]
[v1]
Tue, 6 Oct 2026 07:42:51 UTC (4,981 KB)
来源：arXiv：cs.AI · arxiv.org