分解城市多变量数据，用图网络提升长期预测精度
Forecasting Multivariate Urban Data via Decomposition and Spatio-Temporal Graph Analysis
- 先分解时间序列成分，再分别建模趋势、季节和残差
- 在多类城市数据上实现2.89%至9.10%的准确率提升
- 适合做城市能源、环境等长周期预测的研究者
长时间序列的多变量城市数据预测面临巨大挑战，因其内在复杂的时空依赖关系。本文提出DST模型，结合图注意力与时间卷积，在图神经网络中分别捕捉空间与时间依赖性。为提升性能，引入基于分解的预处理步骤，将时间序列拆分为趋势、季节和残差成分，从而为不同成分学习独立的图结构。在真实城市数据集（包括电力需求、气象指标、碳强度与空气污染）上的大量实验表明，DST在从数天到一个月的不同预测周期下均表现优异，相较现有最优模型平均提升2.89%至9.10%的长期预测准确率。
原文摘要 · Abstract (English)
Long-term forecasting of multivariate urban data poses a significant challenge due to the complex spatiotemporal dependencies inherent in such datasets. This paper presents DST, a novel multivariate time-series forecasting model that integrates graph attention and temporal convolution within a Graph Neural Network (GNN) to effectively capture spatial and temporal dependencies, respectively. To enhance model performance, we apply a decomposition-based preprocessing step that isolates trend, seasonal, and residual components of the time series, enabling the learning of distinct graph structures for different time-series components. Extensive experiments on real-world urban datasets, including electricity demand, weather metrics, carbon intensity, and air pollution, demonstrate the effectiveness of DST across a range of forecast horizons, from several days to one month. Specifically, our approach achieves an average improvement of 2.89% to 9.10% in long-term forecasting accuracy over state-of-the-art time-series forecasting models.
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。