Прогнозирование загруженности участков улично-дорожной сети по данным из открытых источников

During the transformation of city road network, with the change of the local road network capacity and the section nature, the road capacity is affected, travel time is changed, the traveler's route choice behavior changes too. The travel time characteristics under different conditions are discussed based on the basic travel behavior characteristics research during the city road network reconstruction. Mining the state and The relationship between the reliability of travel time, traveler route choice behavior and road network capacity is studied. The research has values on traffic control and management, especially when city road is being rebuild. With the size and population expanding of city, large cities becoming more and more congestion, road network needs to be optimized. How to maintain traffic flow smoothly is a big problem during the road network reconstruction. In order to maintain traffic flow smoothly during the road network reconstruction, the travelers' psychology and action need to know clearly when they were not under normal traffic conditions and their traffic choice behavior will affect the local road network operation even in a whole. So it is very necessary to discuss road network capacity, travelers path selection behavior, and relationship between travel time and the other parameters. And traveler behavior regularity should be studied too to keep road network effective. 1. The Traveler Behavior Characteristics in Road Network Rebuilding During city road network transformation period, the local even the whole network operation is affected. Travelers' psychology subject to certain interference, their travel behavior appear difference from the normal state. These characters are as follows: (1) The traffic flow's spatial-temporal heterogeneity: in network transformation period, local sections or interval exists the problem of traffic congestion, cause traveler abnormal travel psychology and behavior. This will easily cause the adjacent traffic flow suddenly scattered and suddenly collected, and the situation is obvious space-time inhomogeneity. (2)The short-term change of traveler psychology: during network transformation, some road sections can be limited for travel, causing local road network interruption, this make traveler's psychology changed. The travelers will optimize their road selections based on individual cognition and intelligent transportation system. (3) The expected shortest travel time in psychology: travel space and time

The road network of the city of Kryvyi Rih is an example of the adaptation of the street and road network to their historical and economic development. The city was formed as a result of the historical unification of the territories of individual mining villages and microdistricts that arose around the mines, which were located along narrow (up to several kilometers) iron ore strips stretching from north to south for more than 100 km. In fact, the modern elongated linear structure of the city is the result of this historical process, which is considered a key factor in almost all aspects of its development and primarily influenced the development of motor highways. Thus, the main transport highways of the city of Kryvyi Rih stretch from north to south, which significantly increases the distances between districts and creates a significant load on the main transport arteries. The purpose of the study is to conduct a geospatial analysis of the road network of the city of Kryvyi Rih in order to improve its functionality. The work is based on geodata on the city's street and road network, which were obtained from the crowdsourced platform Open Street Map in Shape file format. Geospatial analysis of the city's road network was performed using the open source QGIS program. The city actually consists of several separate districts, interconnected by highways of various types - from wide main streets of city and district significance, which provide connections within the settlement, to residential streets and driveways, the main purpose of which is access to buildings and structures. In addition, important main roads connecting different regions of Ukraine pass through the city. Geospatial analysis of the Kryvyi Rih highway network has shown that different types of city highways differ in their structure. Thus, main roads form a radial scheme, which is characterized by a network of roads in the form of radial lines, which diverge in the form of rays from three centers. Main streets of city and district significance form a combined scheme and are a combination of several structures. It is based on a radial structure, which is unloaded by means of highways in the form of rectangular and linear structures. The rectangular structure of the city street and road network dominates in the organization of motor transport traffic on residential streets, especially newly built microdistricts of the residential area. For thoroughfares, a free structure scheme with a disordered street and road network is characteristic. The density of the road network within the city varies unevenly. The largest number of roads is observed along two conditional axes (vertical and horizontal), each of which divides the city, respectively, into two parts. These "hot" zones actually provide the majority of intra-city and transit passenger and freight traffic. The basis of these zones are highways and main roads, which carry the main load of motor vehicle traffic. Residential and through roads provide the interconnection between main roads and their connection with the territories of residential areas. In Kryvyi Rih, road crossings and junctions are carried out mainly at the same level, at the expense of intersections. The city's road network includes almost 26 thousand intersections, which corresponds to a density of 60 intersections per km². It should be noted its significant spatial correlation with the road density indicator: the largest number of intersections is along the transport axis connecting the north and south of the city. The general street and road network differs from the network of highways and main streets of city and district significance by an abnormally high number of intersections in the historical center of the city. There are two "hot" zones, which correspond mainly to intersections formed by residential and through roads. The influence of natural and anthropogenic relief on the city's road network is limited mainly to determining the directions of highways and main roads. The development of the road network of the city of Kryvyi Rih lags behind its real needs; today the network is unable to simultaneously and effectively pass the number of vehicles that are in the city. The uneven development of the road network and its topology on the territory of the city has been revealed, which often does not correspond to the dynamic capabilities and directions of the predominant movement of intra-city and transit transport. The lack of a sufficient number of alternative routes for connecting highway and main road nodes characterizes the network as one that has a low level of redundancy. This primarily concerns the movement of transit transport, most of which moves through the central areas of the city. Keywords: geospatial monitoring; geographic information systems; network structure; road density; intersection density; network efficiency; digital terrain model; relief slope map.

Prelims

In urban planning and transportation management, the centrality characteristics of urban streets are vital measures to consider. Centrality can help in understanding the structural properties of dense traffic networks that affect both human life and activity in cities. Many cities classify urban streets to provide stakeholders with a group of street guidelines for possible new rehabilitation such as sidewalks, curbs, and setbacks. Transportation research always considers street networks as a connection between different urban areas. The street functionality classification defines the role of each element of the urban street network (USN). Some potential factors such as land use mix, accessible service, design goal, and administrators’ policies can affect the movement pattern of urban travelers. In this study, nine centrality measures are used to classify the urban roads in four cities evaluating the structural importance of street segments. In our work, a Stacked Denoising Autoencoder (SDAE) predicts a street’s functionality, then logistic regression is used as a classifier. Our proposed classifier can differentiate between four different classes adopted from the U.S. Department of Transportation (USDT): principal arterial road, minor arterial road, collector road, and local road. The SDAE-based model showed that regular grid configurations with repeated patterns are more influential in forming the functionality of road networks compared to those with less regularity in their spatial structure.

Minimizing Data Waste: Conservation in the Big Data Era

Open Environmental Data in Developing Countries: Who Benefits?

Transportation has become a vital part of economic development of a country. Poor transportation planning and management is not only waste valuable time but also wastes lot of energy and creates unnecessary air pollution. In recent years, Sri Lanka also has experienced a high growth rate in urban population and the number of private vehicles. Most evident feature of such a trend is urban road congestion. Most of the main roads and local roads in some urban areas are facing unexpectedly high traffic flows which cause time waste in transit, environmental pollution and huge losses to the economy of the country. Therefore, efficient route planning has become one of an important study area because governments also have identified that build new roads is not the only solution for the traffic congestion problem.One of the main reasons for traffic congestion is that concentration of vehicles to selected few roads, may be due to shorter length or may be due to their condition. In optimum route planning, it is essential that to identify alternative routes available to connect different origins and destinations that can be used to divert the traffic from congested road links. However, the number of vehicles that can be diverted will depend on the condition of the road links, existing traffic level and also the land use pattern along the routes. This implies that if the routes are planned well and assign traffic accordingly it will help to minimize the congestion on a road network.The objective of this paper is to present a GIS based model which is called “Integrated Highway Management System” (IHMS) that has been developed by customizing the ArcGIS software using Visual Basic (VB 6) to handle national road network in Sri Lanka. The model is capable of determining the minimum distance or minimum time/cost path between any two node pairs and determining alternate paths avoiding any or all nodes or links between any selected node pair. The model is capable of estimating the traffic flows on road links if the travel demand between the node pair is known. Model is capable of approximately estimating the emission level on road links in addition to the travel time. Moreover, the model has the features of changing the level of operation of a road by using different adjustment factors by considering the road conditions and land use pattern. This facilitate the designers to plan the road network in an efficient manner that will help to minimize the traffic congestion by identifying the routes which should improved or vehicles should or should not be diverted.

Given an urban development plan and the historical traffic observations over the road network, the Conditional Urban Traffic Estimation problem aims to estimate the resulting traffic status prior to the deployment of the plan. This problem is of great importance to urban development and transportation management, yet is very challenging because the plan would change the local travel demands drastically and the new travel demand pattern might be unprecedented in the historical data. To tackle these challenges, we propose a novel Conditional Urban Traffic Generative Adversarial Network (Curb-GAN), which provides traffic estimations in consecutive time slots based on different (unprecedented) travel demands, thus enables urban planners to accurately evaluate urban plans before deploying them. The proposed Curb-GAN adopts and advances the conditional GAN structure through a few novel ideas: (1) dealing with various travel demands as the "conditions" and generating corresponding traffic estimations, (2) integrating dynamic convolutional layers to capture the local spatial auto-correlations along the underlying road networks, (3) employing self-attention mechanism to capture the temporal dependencies of the traffic across different time slots. Extensive experiments on two real-world spatio-temporal datasets demonstrate that our Curb-GAN outperforms major baseline methods in estimation accuracy under various conditions and can produce more meaningful estimations.

Background: Road network data are crucial in various applications, such as emergency response, urban planning, and transportation management. The recent application of deep neural networks has significantly boosted the efficiency and accuracy of road network extraction based on remote sensing data. However, most existing methods for road extraction were designed at local or regional scales. Automatic extraction of large-scale road datasets from satellite images remains challenging due to the complex background around the roads, especially the complicated land cover types. To tackle this issue, this paper proposes a land cover background-adaptive framework for large-scale road extraction. Method: A large number of sample image blocks (6820) are selected from six different countries of a wide region as the dataset. OpenStreetMap (OSM) is automatically converted to the ground truth of networks, and Esri 2020 Land Cover Dataset is taken as the background land cover information. A fuzzy C-means clustering algorithm is first applied to cluster the sample images according to the proportion of certain land use types that obviously negatively affect road extraction performance. Then, the specific model is trained on the images clustered as abundant with that certain land use type, while a general model is trained based on the rest of the images. Finally, the road extraction results obtained by those general and specific modes are combined. Results: The dataset selection and algorithm implementation were conducted on the cloud-based geoinformation platform Google Earth Engine (GEE) and Google Colaboratory. Experimental results showed that the proposed framework achieved stronger adaptivity on large-scale road extraction in both visual and statistical analysis. The C-means clustering algorithm applied in this study outperformed other hard clustering algorithms. Significance: The promising potential of the proposed background-adaptive network was demonstrated in the automatic extraction of large-scale road networks from satellite images as well as other object detection tasks. This search demonstrated a new paradigm for the study of large-scale remote sensing applications based on deep neural networks.

This paper addresses the problem of automatically generating city street networks from a possibly inaccurate vector description of their blocks. The street network, represented as a graph structure with attributes related to both streets and crossings, is a fundamental data structure for a large number of applications, including urban planning and transport management. The considered inaccuracies derive from the typical errors introduced during hand digitizing; i.e., undershooting, overshooting, stacking, and layer misplacing. Extracting the street net when all these possible errors are present is not an easy task because of the huge amount of particular cases to be considered. The presented algorithm is based on the translation of the vector information directly into a run-length encoded binary image. Then, corrections of the above errors and of the street net extraction can be expressed in terms of well known, simple, morphological operations. In order to lower computational costs, the key idea has been to carry out these operations directly on the encoded image. The result is an algorithm that is faster than expected, easy to implement, and, as a consequence, more generally applicable.

Road Network Traffic Congestion Evaluation Simulation Model based on Complex Network

The article is dedicated to the theme of coordinating transport policies and land-use regulation as a means of achieving sustainable development in Russian cities. Particular attention is paid to the concept of sustainable mobility, which emphasizes the importance of creating compact and functionally diverse urban spaces through smart land use policies focused on increasing the accessibility of population centers. The author emphasizes the importance of ensuring integrated planning and development in the areas of land use and transport for Russian cities, the planning structures of which bear traces of the Soviet period. The article examines in detail the regulatory framework for integrating transport planning and development with land use planning in Russian cities, including the existing system of territorial and transport planning documents. The author analyzes the master plans of the largest cities in Russia, presenting an overview of the plans' content and the experience of their implementation. The analysis indicates that transport planning in Russian cities is often carried out in isolation from land use planning, which leads to negative consequences for urban mobility. The population of most cities continues to face problems associated with the inability to harmonize urban development in the areas of transport and land use, including the growing mismatch between travel demand and transport services. The author offers recommendations for overcoming the identified discrepancies in the development of these two areas, including assessing the role of master plans in increasing the integration of planning in the fields of land use and transport. The need for an integrated approach to urban development planning, combining transport planning and land use regulation, is highlighted as a key factor in ensuring sustainable mobility and environmental balance in Russian cities.

Land use is of great importance for urban planning, environmental monitoring, and transportation management. Several methods have been proposed to obtain land use maps of urban areas, and these can be classified into two categories: remote sensing methods and social sensing methods. However, remote sensing and social sensing approaches have specific disadvantages regarding the description of social and physical features, respectively. Therefore, an appropriate fusion strategy is vital for large-area land use mapping. To address this issue, we propose an efficient land use mapping method that combines remote sensing imagery (RSI) and mobile phone positioning data (MPPD) for large areas. We implemented this method in two steps. First, a support vector machine was adopted to classify the RSI and MPPD. Then, the two classification results were fused using a decision fusion strategy to generate the land use map. The proposed method was applied to a case study of the central area of Beijing. The experimental results show that the proposed method improved classification accuracy compared with that achieved using MPPD alone, validating the efficacy of this new approach for identifying land use. Based on the land use map and MPPD data, activity density in key zones during daytime and nighttime was analyzed to illustrate the volume and variation of people working and living across different regions.

The paper analyzes factors and problems of open data implementation in terms of open data belonging to large Russian cities (populated over 100 000). The study analyzes legal and organizational aspect of development of Russian open data sector and formulates legal, technological, and infrastructural problems. According to the study data, incomprehensiveness of innovation transfer leads to isolation of the open data development direction thus failing to achieve expected result, which is usage of demanded and sound open data based on governmental information for development of applications and services demanded by business and/or wide public. Having performed content analysis for Russian cities' informational resources, we conclude that most cities have not even begun publishing open data.

The road network (RN) is an essential element of urban infrastructure. A competently structured RN facili-tates rapid and safe passenger and cargo transportation and reduces the risk of traffic jams, thereby im-proving quality of life in a city. Currently, Russian cities are faced with a large number of transport problems arising from the inconsistency of the approach to the classification and design of the RN combined with a high level of car usage and correspondingly dense traffic flows. In this regard, a new approach is needed to the assessment of traffic patterns in urban environments. The key parameter of RN in urban planning is the throughput capacity of city streets and roads. Currently, this problem is dealt with by specialists from the State Autonomous Institution “Genplan Institute of Moscow”, Moscow State National Research University of Civil Engineering, Moscow Automobile and Road Construction State Technical University (MADI). The im-mediate plans of these specialists include the large-scale research work on the example of the RN of Mos-cow. The aerial video-tape-assisted method is widely used in their study to obtain simultaneous and contin-uous measurements of traffic flow parameters. By this means, data on the composition of the flow and ranges of values of throughput capacity were obtained. A well as the multiband ratio for lanes on a three-lane magistral. The article is devoted to the relevance of the research of throughput capacity of city streets and roads. The content includes the results of a “pilot” study for establishing the values of throughput ca-pacity on the example of two urban settlement sections of a strategic trunk road.