发表机构
City University of Hong Kong (Dongguan); City University of Hong Kong; Zhuhai College of Science and Technology; Northwestern Polytechnical University（香港城市大学（东莞）; 香港城市大学; 珠海科技学院; 西北工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对传感器扩展导致连续时空预测性能下降的问题，提出STFO方法，将预测知识参数化为共享场演化算子，通过坐标归一化聚合和频谱描述符适应动态变化，在三个数据集上取得最先进性能。
AI 中文摘要
连续时空预测支持在动态演变和传感器网络扩展下的交通管理与环境监测。然而，传统的基于图的连续学习方法将预测表示与当前传感器布局绑定，因此传感器扩展可能改变已学习空间关系的表示。我们的关键洞察是，传感器扩展改变了关于某个过程可获得的证据，而不一定改变需要学习的动态。我们提出STFO（时空场算子），它将预测知识参数化为一个共享的场演化算子，并通过观测和查询接口处理变化的传感器布局。基于归一化坐标的聚合将不规则传感器历史提升到固定的潜在网格上，使得学习到的空间图能够在不同观测集之间重用，而无需传感器特定的参数。为了适应过程漂移，一个频谱描述符总结了跨空间尺度的变化，并调节傅里叶传播和注意力，以使算子响应适应当前空间状态。基于坐标的解码在传感器位置查询演化后的场，并将空间修正与局部历史预测相结合。在PEMS-Stream、CA-Stream和AIR-Stream上的实验展示了最先进的平均预测性能。STFO-Large在PEMS-Stream上将平均MAE相对于DOL降低了8.4%，在CA-Stream上降低了4.7%。我们的代码可在该https URL获取。
英文摘要
Continual spatio-temporal forecasting supports traffic management and environmental monitoring under evolving dynamics and expanding sensor networks. However, conventional graph-based continual learning methods tie forecasting representations to the current sensor layout, so sensor expansion can alter the representation of learned spatial relationships. Our key insight is that sensor expansion changes the evidence available about a process without necessarily changing the dynamics to be learned. We propose STFO (Spatio-Temporal Field Operator), which parameterizes forecasting knowledge as a shared field-evolution operator and handles changing sensor layouts through observation and query interfaces. Normalized coordinate-based aggregation lifts irregular sensor histories onto a fixed latent grid, enabling reuse of learned spatial maps across observation sets without sensor-specific parameters. To accommodate process drift, a spectral descriptor summarizes variation across spatial scales and conditions Fourier propagation and attention to adapt operator responses to the current spatial regime. Coordinate-based decoding queries the evolved field at sensor locations and combines spatial corrections with local-history predictions. Experiments on PEMS-Stream, CA-Stream, and AIR-Stream demonstrate state-of-the-art average forecasting performance. STFO-Large reduces average MAE over DOL by 8.4% on PEMS-Stream and 4.7% on CA-Stream. Our code is available at https://github.com/Xielewei/Spatio-Temporal-Field-Operator.
