蒸馏环路检测器数据集的信息本质：网络级交通预测是否渴求更多数据？
Distil the informative essence of loop detector data set: Is network-level traffic forecasting hungry for more data?
AI总结：
本文提出不确定性感知的交通预测框架，结合交通流理论与图神经网络及证据学习，蒸馏环路检测器数据本质，证明仅约20%样本即可保持同等预测能力。
摘要：
网络级交通状况预测已被深入研究数十年。尽管随着新兴深度学习模型和不断扩展的交通数据，预测精度持续提升，但交通预测在实践中仍面临诸多挑战。这些挑战包括数据驱动模型的鲁棒性、交通动态固有的不可预测性，以及进一步提升交通预测是否需要更多传感器数据。本文聚焦于后一个问题，尤其关注来自环路检测器的数据。为回答这一问题，我们提出一个不确定性感知的交通预测框架，以探索环路数据中究竟有多少样本对训练预测模型真正有效。首先，模型设计将交通流理论与图神经网络相结合，确保预测的鲁棒性和不确定性量化。其次，采用证据学习在单次前向传播中量化不同来源的不确定性。估计出的不确定性被用于“蒸馏”数据集的本质，使其充分覆盖信息内容。围绕阿姆斯特丹周边高速公路网络的案例研究结果表明，从2018年到2021年，白天超过80%的数据可以被移除。剩余20%的样本在训练模型时具有同等的预测能力。这一结果表明，大型交通数据集确实可以被细分为显著更小但信息量相同的数据集。基于这些发现，我们得出结论：所提出的方法在评估大型交通数据集的真实信息内容方面具有价值。进一步的扩展，例如提取更小且空间上非冗余的数据集，也可以通过该方法实现。
英文摘要：
Network-level traffic condition forecasting has been intensively studied for decades. Although prediction accuracy has been continuously improved with emerging deep learning models and ever-expanding traffic data, traffic forecasting still faces many challenges in practice. These challenges include the robustness of data-driven models, the inherent unpredictability of traffic dynamics, and whether further improvement of traffic forecasting requires more sensor data. In this paper, we focus on this latter question and particularly on data from loop detectors. To answer this, we propose an uncertainty-aware traffic forecasting framework to explore how many samples of loop data are truly effective for training forecasting models. Firstly, the model design combines traffic flow theory with graph neural networks, ensuring the robustness of prediction and uncertainty quantification. Secondly, evidential learning is employed to quantify different sources of uncertainty in a single pass. The estimated uncertainty is used to "distil" the essence of the dataset that sufficiently covers the information content. Results from a case study of a highway network around Amsterdam show that, from 2018 to 2021, more than 80\% of the data during daytime can be removed. The remaining 20\% samples have equal prediction power for training models. This result suggests that indeed large traffic datasets can be subdivided into significantly smaller but equally informative datasets. From these findings, we conclude that the proposed methodology proves valuable in evaluating large traffic datasets' true information content. Further extensions, such as extracting smaller, spatially non-redundant datasets, are possible with this method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
