用空间上下文弥补事件历史稀疏，提升预测稳定性
When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting
- 引入AlphaEarth嵌入作为线性空间上下文，增强模型泛化能力
- 历史越短，提升越明显：1-2周时性能提升2-6倍
- 适合事件稀疏区域的时空点过程预测任务
当局部事件历史稀疏时，时空点过程模型往往需跨区域泛化。本文研究外生空间上下文是否能在此类场景中起到补偿作用。基于固定的对数高斯柯西过程（log-Gaussian Cox process）框架，比较仅使用事件数据的模型与加入AlphaEarth（AE）嵌入作为线性空间上下文的模型。在8个未见区域、固定预测锚点及不同历史长度w下进行评估，仅使用每个锚点前可用的AE嵌入。结果表明，无论历史长度如何，加入AE均能提升跨区域预测性能；在历史稀缺时收益最大：1-2周时性能提升约2–6倍，随着历史长度增至20–104周，提升收敛至约10–20%。证明了上下文信息可在事件历史有限时显著稳定时空预测。
原文摘要 · Abstract (English)
Spatio-temporal point-process models must often generalise across space when local event histories are sparse. We study whether exogenous spatial context can compensate in such regimes. Using a fixed log-Gaussian Cox process backbone, we compare an event-only model with the same model augmented by AlphaEarth embeddings as linear spatial context. We evaluate spatial transfer on emergency medical services (EMS) forecasting across eight held-out regions, fixed forecast anchors, and a sweep over history length $w$, using only AlphaEarth (AE) embeddings available strictly before each anchor. AE improves out-of-region predictive performance across all history regimes, with the largest gains under scarce histories: approximately $2$--$6\times$ multiplicative improvements at $1-2$ weeks, tapering to roughly $10$--$20\%$ at $w=20$--$104$ weeks. These results show that contextual information can substantially stabilise spatially transferred point-process forecasts when event history is limited.
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。