This paper presents a dedicated Deep Neural Network (DNN) architecture that reconstructs space-time traffic speeds on freeways given sparse data. The DNN is constructed in such a way, that it learns heterogeneous congestion patterns using a large dataset of sparse speed data, in particular from probe vehicles. Input to the DNN are two equally sized input matrices: one containing raw measurement data, and the other indicates the cells occupied with data. The DNN, comprising multiple stacked convolutional layers with an encoding-decoding structure and feed-forward paths, transforms the input into a full matrix of traffic speeds. The proposed DNN architecture is evaluated with respect to its ability to accurately reconstruct heterogeneous congestion patterns under varying input data sparsity. Therefore, a large set of empirical Floating-Car Data (FCD) collected on German freeway A9 during two months is utilized. In total, 43 congestion distinct scenarios are observed which comprise moving and stationary congestion patterns. A data augmentation technique is applied to generate input-output samples of the data, which makes the DNN shift-invariant as well as capable of managing varying data sparsities. The DNN is trained and subsequently applied to sparse data of an unseen congestion scenario. The results show that the DNN is able to apply learned patterns, and reconstructs moving as well as stationary congested traffic with high accuracy; even given highly sparse input data. Reconstructed speeds are compared qualitatively and quantitatively with the results of several state-of-the-art methods such as the Adaptive Smoothing Method (ASM), the Phase-Based Smoothing Method (PSM) and a standard Convolutional Neural Network (CNN) architecture. As a result, the DNN outperforms the other methods significantly.
Estimating link level traffic emissions: enhancing MOVES with open-source data
Department of Civil and Environmental Engineering（土木与环境工程系）；Northeastern University（东北大学）；Massachusetts Institute of Technology（麻省理工学院）；Laboratory for Information & Decision Systems（信息与决策系统实验室）
Uncertainty Quantification for Traffic Forecasting: A Unified Approach
Aalborg University（奥尔堡大学）；University of Electronic Science and Technology of China（电子科技大学）；Southern University of Science and Technology（南方科技大学）
不确定性是时间序列预测任务的重要考虑因素。在这项工作中，我们特别关注量化交通预测的不确定性。为了实现这一目标，我们开发了深度时空不确定性量化（DeepSTUQ），它可以估计任意和认知的不确定性。我们首先利用时空模型来模拟交通数据的复杂时空相关性。随后，两个独立的子神经网络最大化的异质对数似然估计任意的不确定性。为了估计认知不确定性，我们分别通过集成Monte Carlo dropout和Adaptive Weight Averaging再训练方法，结合了变分推理和深度集成的优点。最后，我们提出了一种基于温度标度的后处理校准方法，提高了模型估计不确定性的泛化能力。在四个公共数据集上进行了大量的实验，实验结果表明，该方法在点预测和不确定性量化方面都优于最先进的方法。
Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
Institute of Advanced Research in Artificial Intelligence (IARAI)（高级人工智能研究院（IARAI））；ETH Zurich（苏黎世联邦理工学院）；Layer 6 AI（Layer 6人工智能公司）；ITMO University（圣彼得堡国立信息技术机械与光学大学）；JetBrains Research（JetBrains研究院）；HSE University（圣彼得堡国立高等经济大学）；Monash University（莫纳什大学）；CSIRO’s Data61（联邦科学与工业研究组织Data61研究所）；Kongju National University（公州国立大学）；Bielefeld University（比勒费尔德大学）；Khalifa University（哈利法大学）；Alchera Data Technologies Ltd（Alchera数据技术有限公司）；HERE Technologies（HERE技术公司）；Silesian University of Technology（西里西亚工业大学）
ZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Network
大规模移动流量分析对于数字基础设施配置、公共交通、活动规划和其他领域变得至关重要。然而，监控全市范围的移动流量是一个复杂而昂贵的过程，依赖于专用探头。其中一些探测器的精度或覆盖范围有限，另一些每天收集数十GB的日志，这些日志独立提供有限的见解。提取细粒度的模式涉及昂贵的测量、存储和后处理的空间聚合。在本文中，我们提出了一种移动流量超分辨率技术，克服了这些问题，通过推断狭隘的本地化的流量消费从粗糙的测量。我们从图像处理中汲取灵感，设计了一个针对移动网络的深度学习架构，它结合了Zipper网络（ZipNet）和生成对抗神经网络（GAN）模型。这使得能够唯一地捕获在广泛覆盖区域上常规监测的交通量快照（“低分辨率”）与通常在密集计算之后获得的0.05 km $^2$水平上的相应消耗（“高分辨率”）之间的时空关系。我们进行的实验与现实世界的数据集表明，拟议的ZipNet（-GAN）推断流量消耗具有显着的准确性和高达100 $\times$更高的粒度相比，标准的探测，同时优于现有的数据插值技术。据我们所知，这是第一次将超分辨率概念应用于大规模移动交通分析，我们的解决方案是第一个从粗聚合物中推断细粒度城市交通模式的解决方案。
IncidentNet: Traffic Incident Detection, Localization and Severity Estimation with Sparse Sensing
Arizona State University（亚利桑那州立大学）；School for Engineering of Matter, Transport and Energy（物质、运输与能源工程学院）；School of Computing and Augmented Intelligence（计算与增强智能学院）
Exploratory Data Analysis of a Network Telescope Traffic and Prediction of Port Probing Rates
International University of Rabat（拉巴特国际大学）；Mohammed V University of Rabat（拉巴特穆罕默德五世大学）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林信息学及其应用研究实验室）
Traffic Data Imputation using Deep Convolutional Neural Networks
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；New York University Abu Dhabi（纽约大学阿布扎比分校）；New York University Tandon School of Engineering（纽约大学坦登工程学院）
