AI 中文总结
本文提出名为SPALT的方法，通过线性模型树与结合时空局部性的剪枝策略，建模地理参照时间序列的时空局部性，在3个真实数据集的多步能源产量预测中，性能优于树模型和融合时空的最先进神经网络。
AI 中文摘要
从地理分布式传感器预测未来测量值在诸多领域都至关重要。然而，这些传感器的空间分布带来了多重挑战，主要源于空间自相关现象，该现象会在邻近位置间引入相互依赖关系，因此无法将这些位置视为独立个体。尽管部分现有方法能够捕捉此类现象，但它们通常会在所有位置上全局建模空间维度。另一方面，本文提出的名为SPALT的方法专注于捕捉具有相似趋势的时间序列间的空间关系，即便这些时间序列出现在不同时刻，从而实现时空局部性建模。SPALT利用线性模型树，使我们能够在局部考虑空间自相关：在树构建过程中，采用的启发式方法将具有相似趋势的时间序列分组到同一节点中，在此节点上选择性注入考虑空间维度的额外特征。此外，我们提出了一种基于减少误差剪枝（Reduced Error Pruning）的新型剪枝策略，该策略在树简化过程中也会考虑时空局部性。SPALT专为多步场景设计，可同时预测多个传感器在多个未来时间步的数值。SPALT展现出的特性能在测量数据来自分布式传感器的不同领域中带来显著益处。本文聚焦于多个可再生能源发电厂的传感器产生的数据，这些传感器会定期以短间隔测量能源产量。对3个真实世界数据集的实验表明，SPALT在不同时间尺度上预测能源产量的有效性，以及其在与基于树的模型和同时融合时空维度的最先进神经网络相比时的优越性能。
英文摘要
Forecasting future measurements from geographically distributed sensors is essential across many domains. However, the spatial distribution of these sensors raises multiple challenges, primarily due to spatial autocorrelation phenomena, that introduce inter-dependencies among nearby locations, that cannot therefore be treated independently. While some existing approaches can capture such phenomena, they generally model the spatial dimension globally across all locations. On the other hand, the method we propose in this paper, called SPALT, focuses on capturing spatial relationships among time series with similar trends, even if they occur at different times, thus modeling the spatio-temporal locality. SPALT leverages linear model trees, which allow us to consider the spatial autocorrelation locally: during the tree-building process, the adopted heuristics group time series exhibiting similar trends into the same node, on which additional features considering the spatial dimension are selectively injected. Additionally, we propose a new pruning strategy, based on Reduced Error Pruning, that also considers the spatio-temporal locality during the tree simplification. Designed for a multi-step setting, SPALT provides forecasts for multiple future time steps across multiple sensors simultaneously. The characteristics exhibited by SPALT can provide significant benefits in different domains, where measurements come from distributed sensors. In this paper, we focus on data produced by sensors located in multiple renewable power plants measuring their energy production at regular, short intervals. Experiments on 3 real-world datasets demonstrate the effectiveness of SPALT in forecasting the production of energy at different time horizons, and its superior performance in comparison with tree-based models and state-of-the-art neural networks that incorporate both temporal and spatial dimensions.
Journal refMachine Learning, Volume 114, article number 231 (2025)
DOI：10.1007/s10994-025-06875-1
