---
id: 20260307-T0-06
title: "时空预测新方法：联合频域学习"
title_en: "New Spatiotemporal Prediction via Joint Frequency Learning"
url: https://ai.daily.yangsir.net/daily/20260307-T0-06
issue_date: 2026-03-07
publish_date: 2026-03-06T05:00:00.000Z
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2603.04418
---

# 时空预测新方法：联合频域学习

Decorrelating the Future提出时空预测新范式，通过联合频域学习捕捉图结构信号的复杂依赖。该方法在交通流量预测任务中，MAE指标降低23%，优于传统时间序列模型20%。论文展示了频域分解如何有效解决时空数据的周期性耦合问题，特别适用于智慧城市、气象预测等场景。代码已开源，可集成至现有预测框架。

## English Version

**New Spatiotemporal Prediction via Joint Frequency Learning**

Decorrelating the Future introduces a new spatiotemporal prediction paradigm using joint frequency learning to capture complex dependencies in graph-structured signals. The method reduces MAE by 23% in traffic flow prediction, outperforming traditional time series models by 20%. The paper demonstrates how frequency decomposition effectively resolves periodic coupling in spatiotemporal data, particularly suitable for smart cities and weather forecasting scenarios. Code is open-source for integration into existing frameworks.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2603.04418)

**详情页**：https://ai.daily.yangsir.net/daily/20260307-T0-06

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*