Nowadays, the deployment of sensing technology permits to collect massive spatio-temporal data in urban 1 cities. These data can provide comprehensive traffic state conditions for an urban network and for a particular day. 2 However, they are often too numerous and too detailed to be of direct use, particularly for applications like delivery 3 tour planning, trip advisors and dynamic route guidance. A rough estimation of travel times and their variability may 4 be sufficient if the information is available at the full city scale. The concept of spatio-temporal speed cluster map is 5 a promising avenue for these applications. However, the data preparation for creating these maps is a challenging 6 and rarely discussed topic. In this paper, we address this challenge by introducing generic methodologies for 7mapping the data to a Geographic Information System (GIS) network, coarsening the network for reducing the 8 network complexity at the city scale and also estimating the speed from the travel time data, including missing data. 9We demonstrate this on a large scale urban network of Amsterdam with real travel time data. The preprocessed data 10 is used to build the spatio-temporal speed cluster using three partitioning techniques -Normalized cut, DBSCAN 11and Growing Neural Gas (GNG). A new post-treatment methodology is introduced for DBSCAN and GNG, which 12 are based on data point clustering, to generate connected zones. A preliminary cross comparison of the clustering 13 techniques shows that GNG performs best in generating zones with minimum internal variance, Normalized Cut 14 computes 3D zones with the best inter-cluster dissimilarity and GNG has the faster computation time. 15 16

In this paper, we investigate the day-to-day regularity of urban congestion patterns. We first partition link speed data every 10 min into 3D clusters that propose a parsimonious sketch of the congestion pulse. We then gather days with similar patterns and use consensus clustering methods to produce a unique global pattern that fits multiple days, uncovering the day-to-day regularity. We show that the network of Amsterdam over 35 days can be synthesized into only 4 consensual 3D speed maps with 9 clusters. This paves the way for a cutting-edge systematic method for travel time predictions in cities. By matching the current observation to historical consensual 3D speed maps, we design an efficient real-time method that successfully predicts 84% trips travel times with an error margin below 25%. The new concept of consensual 3D speed maps allows us to extract the essence out of large amounts of link speed observations and as a result reveals a global and previously mostly hidden picture of traffic dynamics at the whole city scale, which may be more regular and predictable than expected.Studying human mobility in large cities is critical for multiple applications from transportation engineering to urban planning and economic forecasting. In recent years, the availability of new data sources, e.g. mobile-phone records and global-positioning-system data, has generated new empirically driven insights on this topic. A central question at large spatial and temporal scales is which (dynamic) components of human mobility can be considered as predictable and thus suitable for explanatory and predictively valid mathematical models, and which part is unpredictable. Earlier studies of human trips shows that traveled distance can be described by random walks and more precisely as Lévy-flights 1 . Latter studies partly amend this theory by recognizing some regularity features in peoples' trips. Individuals obviously frequently move between specific locations, such as home or work 2 . Such patterns are also regular in time 3,4 meaning that the most frequent locations are likely to be correlated with daily hours and dates. Regularity can also come from decomposition by transportation modes 5 . Human mobility can be studied at the microscopic level, i.e. through person trajectories, but also at the macroscopic level, for example by estimating commuting flows between different regions (origins to destinations) or on the different links of a transportation network 6,7 . Such collective mobility patterns can be explained for example by distances between regions 8,9 , trip purposes 10 and road attractiveness related to road types, e.g. freeways, or locations, e.g. in major business districts 11 . Predicting commuting flows often requires local data for calibration 12 meaning that results cannot easily be transferable to other regions or cities. Recent findings 13 , however, show that a scale-free approach corresponding to an extension of the radiation model can successfully be applied to commuting flow estimation. This means that some...

The fundamental challenge of the origin-destination (OD) matrix estimation problem is that it is severely under-determined. In this paper we propose a new data driven OD estimation method for cases where a supply pattern in the form of speeds and flows is available. We show that with these input data, we do not require an iterative dynamic network loading procedure that results in an equilibrium assignment, nor do we need an assumption on the kind of equilibrium that emerges from this process. The minimal number of ingredients which are needed are (a) a method to estimate/predict production and attraction time series; (b) a method to compute the N shortest paths from each OD zone to the next; and (c) two-possibly OD-specific-assumptions on the magnitude of N; and on the proportionality of path flows between these origins and destinations, respectively. The latter constitutes the most important behavioral assumption in our method, which relates to how we assume travelers have chosen their routes between OD pairs. We choose a proportionality factor that is inversely proportional to realized travel time, where we incorporate a penalty for path overlap. For large networks, these ingredients may be insufficient to solve the resulting system of equations. We show how additional constraints can be derived directly from the data by using principal component analysis, with which we exploit the fact that temporal patterns of production and attraction are similar across the network. Experimental results on a toy network and a large city network (Santander, Spain) show that our OD estimation method works satisfactorily, given a reasonable choice of N, and the use of so-called 3D supply patterns, which provide a compact representation of the supply dynamics over the entire network. Inclusion of topological information makes the method scalable both in terms of network size and for different topologies. Although we use a neural network to predict production and attraction in our experiments (which implies ground-truth OD data were needed), there are straightforward paths to improve the method using additional data, such as demographic data, household survey data, social media and or movement traces, which could support estimating such ground-truth baseline production and attraction patterns. The proposed framework would fit very nicely in an online traffic modeling and control framework, and we see many paths to further refine and improve the method. ☆ This paper has been accepted for a podium presentation at the 23rd International Symposium on Transportation and Traffic Theory (ISTTT23)

No abstract

No abstract