Search

With the rapid development of the world city network, the traditional location theory has gradually been disproven, and the advantages of the flow space over the traditional vertical organizational structure are gradually being revealed. Therefore, from corporate branch networks and corporate investment networks, 21 cities in urban agglomerations of Guangdong are taken as case studies for this paper. Furthermore, in this paper, 5 representative types of corporate contact data (catering service, financial service, life service, sports and leisure and accommodation service) are selected, the social network analysis (SNA) method is used to quantitatively analyze the network structure characteristics of urban agglomerations, and a spatial interaction model is constructed to explore the factors influencing. The results indicate that secondary networks have developed in Guangdong. The financial service network is the most complex, followed by the life services, sports and leisure and catering networks. The accommodation service network structure is the simplest. Among all kinds of networks, Guangzhou and Shenzhen have the highest status. The catering and accommodation corporations in Yangjiang in the west have a relatively major external development. Shantou in the east has many branches of various types, while most of the capital exchange in the region is concentrated in Heyuan and Qingyuan in the north. The coefficients of geographical proximity and the urban development level play a significant role in promoting the development of networks. However, administrative capacity limits the attractiveness of origin cities to a certain extent. [ABSTRACT FROM AUTHOR]

This paper is situated within the discussion of mega-urbanization, a particular urbanization process that entails a large-scale agglomeration. In this paper, our focus is on urbanization in Java, Indonesia's most dynamic region. We add to the literature by investigating the change and prediction of the land use/land cover (LULC) of mega-urbanization in Java. This research uses a vector machine approach to support the classification of land cover change dynamics, cellular automata-Markov (CA Markov), and the Klassen typology technique. This paper indicates that major metropolitan areas are still expanding in terms of built-up areas, generating a larger urban agglomeration. However, attention should be also given to the urbanization process outside existing metropolis' boundaries given that more than half of the built-up land coverage in Java is located in non-metropolitan areas. In terms of future direction, the projection results for 2032 show that the Conservative scenario can reduce and slow down the increase in built-up land on the island of Java. On the other hand, the Spatial Plan (RTRW) scenario facilitates a rapid increase in the LULC of built-up land from 2019. The urban spatial dynamics in Java raises challenges for urban and regional planning as the process is taking place across multiple administrative authorities. [ABSTRACT FROM AUTHOR]

Since 1971, remote sensing techniques have been used to map and monitor phenomena and parameters of the coastal zone. However, updated reviews have only considered one phenomenon, parameter, remote data source, platform, or geographic region. No review has offered an updated overview of coastal phenomena and parameters that can be accurately mapped and monitored with remote data. This systematic review was performed to achieve this purpose. A total of 15,141 papers published from January 2021 to June 2023 were identified. The 1475 most cited papers were screened, and 502 eligible papers were included. The Web of Science and Scopus databases were searched using all possible combinations between two groups of keywords: all geographical names in coastal areas and all remote data and platforms. The systematic review demonstrated that, to date, many coastal phenomena (103) and parameters (39) can be mapped and monitored using remote data (e.g., coastline and land use and land cover changes, climate change, and coastal urban sprawl). Moreover, the authors validated 91% of the retrieved parameters, retrieved from remote data 39 parameters that were mapped or monitored 1158 times (88% of the parameters were combined together with other parameters), monitored 75% of the parameters over time, and retrieved 69% of the parameters from several remote data and compared the results with each other and with available products. They obtained 48% of the parameters using different methods, and their results were compared with each other and with available products. They combined 17% of the parameters that were retrieved with GIS and model techniques. In conclusion, the authors addressed the requirements needed to more effectively analyze coastal phenomena and parameters employing integrated approaches: they retrieved the parameters from different remote data, merged different data and parameters, compared different methods, and combined different techniques. [ABSTRACT FROM AUTHOR]

Increased urbanization and population lead to increased consumption of manufactured goods. This ultimately results in increased production of waste. Identifying its composition is crucial for planning an effective solid waste management strategy. This study assesses the characteristics and composition of the waste generated within the Uyo Capital City Development Area of Akwa Ibom State, Nigeria. This is to aid in developing a scientifically supported waste management pilot system for the state. Direct waste sorting and characterization were conducted on the municipal solid waste arriving at the landfill during the study period. Over 50% of the generated wastes are recyclables and composed of plastics, metals, and paper, while the fraction of organic waste is over 30%. Similarly, the waste generation per capita is 1.34 kg/person/day, while the generation forecast over the next ten years is estimated to increase by approximately 40%. Furthermore, over 9,000 surveys were completed by residents to establish a problem statement about the existing waste collection and disposal system, and possible solutions. Importantly, a majority of survey respondents were willing to source-separate their wastes and supported paying a fee for adequate waste collection. This strongly indicates that an integrated waste management system could be established to generate value from the collected waste. Supplementary revenue can be generated through composting, recycling, and land reclamation. [ABSTRACT FROM AUTHOR]

As one of the four major bay areas in the world, the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) is a highly integrated mega urban agglomeration and its unparalleled urbanization has induced prominent land contradictions between humans and nature, which hinders its sustainability and has become the primary concern in this region. In this paper, we probed the historical characteristics of land use and land cover change (LUCC) in the GBA from 2005 to 2015, and forecasted its future land use pattern for 2030, 2050, and 2070, using a cellular automata–Markov (CA–Markov) model, under three typical tailored scenarios, i.e., urban development (UD), cropland protection (CP), and ecology security (ES), for land use optimization. The major findings are as follows: (1) The encroachments of build-up land on the other land uses under rapid urbanization accounted for the leading forces of LUCCs in the past decade. Accordingly, the urban sprawl was up to 1441.73 km2 (23.47%), with cropland, forest land, and water areas reduced by 570.77 km2 (4.38%), 526.05 km2 (1.76%), and 429.89 km2 (10.88%), respectively. (2) Based on the validated CA–Markov model, significant differences are found in future land use patterns under multiple scenarios, with the discrepancy magnified over time and driven by different orientations. (3) Through comprehensive comparisons and tradeoffs, the ES scenario mode seems optimal for the GBA in the next decades, which optimizes the balance between socio-economic development and ecological protection. These results serve as an early warning for future land problems and can be applied to land use management and policy formulation to promote the sustainable development of the GBA. [ABSTRACT FROM AUTHOR]

Phase models of gentrification play a prominent role in German-language urban geography textbooks and in shaping discussions on urban gentrification. Their empiric validity however, remains a topic for debate. To contribute to this debate, we conduct a comprehensive literature review of English- and German-language gentrification research over the past 40 years, with a specific focus on phase models. We examined 4,262 papers on gentrification, employing keyword searches and forward citation to pinpoint those that reference the phase models. Out of these, 223 papers mentioned the phase models or relevant key terms, but upon closer examination, only 56 directly addressed the model, forming the basis for our qualitative content analysis. We then assess the evolution of scientific discourse on phase models and their empirical validation. Despite their widespread reference, our study reveals that only a small fraction of gentrification research explicitly engages with these models, with limited empirical evidence to support their comprehensive validity. We argue that, although these models offer a framework for understanding gentrification, they are not universally applicable and neglect important elements such as, amongst others, supply-side factors and the diversity of gentrification trajectories. We advocate for a more nuanced approach to gentrification studies, calling for empirical research that encompasses a wider array of socio-ecological factors and recognizes the heterogeneity of gentrification patterns. Furthermore, there is a need for improved integration of urban research findings into educational materials, proposing a more critical presentation of gentrification models in school textbooks to reflect their limitations and the complex realities of urban development. [ABSTRACT FROM AUTHOR]

Urban carbon emissions are an important area for addressing climate change, and it is necessary to establish scientific and effective carbon emission prediction models to formulate reasonable emission reduction policies and measures. In this paper, a novel model based on Lasso regression, an ARIMA model, and a BPNN is proposed. Lasso regression is used to screen the key factors affecting carbon emissions, and the ARIMA model is used to extract the linear components of the carbon emission sequences, while the BPNN is used to predict the residuals of the ARIMA model. The final result is the sum of that from the ARIMA model and the BPNN. The carbon peak, carbon neutralization time, and emissions were analyzed under different scenarios. Taking Suzhou City as an example, the results show that the electricity consumption of the whole population is one of the key drivers of carbon emissions; the carbon emission prediction accuracy and stability of the ARIMA-BPNN combined model are better than those of the single model, which improves the reliability as well as the accuracy of the model's prediction. However, under the constraints of the current policies, the goal of achieving carbon peaking by 2030 in Suzhou City may not be realized as scheduled. This novel carbon emission prediction model built was validated to provide a scientific basis for low-carbon urban development. This study presents an important reference value for predicting carbon emissions and formulating emission reduction measures in other cities. [ABSTRACT FROM AUTHOR]

In the process of global urban development, there are urgent ecological security and environmental pollution problems, green development is the fundamental way for urban sustainable development, economic transformation and mitigation of ecological and environmental problems. Based on the panel data of 283 cities at prefecture level and above in China from 2003 to 2017, this paper analyzes spatial–temporal evolution characteristics of urban green development efficiency (UGDE) and the peer effects of UGDE between cities of different grades. It is found that during the study period, in terms of temporal evolution, the average UGDE in China increased from 0.47 in 2003 to 0.61 in 2017, with a cumulative growth rate of 29.79%, showing a rising trend in general. In terms of spatial evolution, the number of low-efficiency cities and medium-efficiency cities continued to decrease. The eastern region has always been the main distribution area of higher-efficiency cities and high-efficiency cities; in the central region, UGDE in most cities improved significantly; in the western region, UGDE has always lagged behind that in the eastern and central regions. In addition, the center of gravity of UGDE presented a trend of northwest migration in general, with a total displacement of 100.07 km, and UGDE showed a spatial dispersion trend. The empirical results indicate that the improvement of UGDE in large cities has a driving effect on that in neighboring medium cities and small cities through the positive peer effect, and the growth of UGDE in medium cities has a promoting effect on that in neighboring small cities through the positive peer effect; the increase of UGDE in medium cities has a positive peer effect on that in neighboring large cities, and the growth of UGDE in small cities has a positive peer effect on that in neighboring medium cities; UGDE promotes each other between large cities through the positive peer effect. [ABSTRACT FROM AUTHOR]

With the world's rapid urban development, it has been observed that space for sociability has decreased. To overcome the impact of the same, streets should develop as an urban space along transit corridors. These spaces encourage meaning and identity creation by offering visual quality to everyone. This paper focuses on assessing parameters through which an urban streetscape along transit corridor can be analyzed to enhance visual quality. The authors suggest nine essential parameters based on literature review and expert interviews. [ABSTRACT FROM AUTHOR]

The significance of air quality monitoring for analyzing impact on public health is growing worldwide. A crucial part of smart city development includes deployment of suitable air pollution sensors at critical locations. Note that there are various air quality measurement instruments, ranging from expensive reference stations that provide accurate data to low-cost sensors that provide less accurate air quality measurements. In this research, we use a combination of sensors and monitors, which we call hybrid instruments, and focus on optimal placement of such instruments across a region. The objective of the problem is to maximize a satisfaction function that quantifies the weighted closeness of different regions to the places where such hybrid instruments are placed (here weights for different regions are quantified in terms of the relative population density and relative PM 2.5 concentration). Note that there can be several constraints such as those on budget, the minimum number of reference stations to be placed, or the set of important regions where at least one sensor should be placed. We develop two algorithms to solve this problem. The first one is a genetic algorithm that is a metaheuristic and that works on the principles of evolution. The second one is a greedy algorithm that selects the locally best choice in each iteration. We test these algorithms on different regions from India with varying sizes and other characteristics such as population distribution, PM 2.5 emissions, or available budget. The insights obtained from this paper can be used to quantitatively place reference stations and sensors in large cities rather than using ad hoc procedures or rules of thumb. [ABSTRACT FROM AUTHOR]

This paper applies Fuzzy Cognitive Maps (FCMs) to understand the diverse behavior of municipal governments in Ecuador to find common elements that influence the well-being of citizens in the short and long term. Information gathering was conducted in two stages: in the first one, a group of 16 national experts was consulted to develop the initial FCM; in the second stage, local experts from 220 municipalities were interviewed to collect information on the general validity of initial FCMs and specific values given to concepts and relationships in their municipalities. Results show the importance of certain concepts for long-term municipal performance, such as the need for a competitive entrepreneurial sector, improving human resources in the municipality, and, particularly, having a competent mayor with leadership skills and a forward-looking vision that enables the development of municipal projects required to reach an efficient and equitable coverage of goods and services throughout the city. Through the application of genetic algorithms, the FCM was calibrated to ascertain the long-term dynamics of municipal development and the optimal values of the concepts that would optimize the attainment of the set objectives. The derived outcomes suggest the desirability of the maintenance of, in principle, unwanted structures like financial transfers from the central government and the need to exploit natural resources to attain urban development. [ABSTRACT FROM AUTHOR]

China has experienced significant urbanization during the past 40 years, which exerts impacts on regional climates through changing land surface properties. Previous studies mainly focused on the Pearl River Delta, the Yangtze River Delta, and the Beijing-Tianjin-Hebei areas, while less attention has been paid to central China. In this paper, the regional climate effects of urbanization around the greater Wuhan area were investigated using the WRF model. High resolution, satellite-derived, impervious datasets were used to generate two realistic scenarios representing urban surface states of the years 1986 and 2018. By comparing the simulation results of two sensitivity experiments from 1 July 2015 to 12 July 2015, the spatial and diurnal changes in surface air temperature, surface skin temperature, and surface energy budget were analyzed. Our results reveal that urban expansion leads to 2 m air temperature and surface skin temperature increases by approximate 0.63 °C and 0.83 °C, respectively. Surface sensible heat flux increases, while latent heat flux decreases, with much greater effects in daytime than nighttime. The planetary boundary layer height (PBLH) increases with its maximum value over 100 m, and a 2 m water vapor mixing ratio decreases with a peak value around −2 g/kg. These findings provide knowledge to improve the understanding of land–atmospheric interactions and pave the way to studying urban expansion effects under future climate change scenarios. [ABSTRACT FROM AUTHOR]

In line with the European Commission's target, land take in Germany has to be reduced to net zero by 2050. This not only presupposes greater inner urban development and more efficient development outside existing settlements, but also puts a greater planning and political focus on renaturation. The aim of this paper is to investigate the implementation of no net land take policy using the example of the highly dense and urbanised federal state of North Rhine-Westphalia in Germany. Based on an online survey, the current and potential use of (planning) instruments to implement this policy in all 396 municipalities in North Rhine-Westphalia was investigated. The findings suggest that the municipalities are not yet in a position to consistently implement no net land take. Particularly in the field of renaturation, this is often due to a lack of experience and uncertainties in the use of the existing (planning) instruments, but also to lacking awareness of the problem and a lack of political and social acceptance for higher housing densities. Since the necessary instruments are defined in current legislation and the concepts for implementation are generally known, it is important to support municipalities in using the available instruments and concepts even without direct pressure to act. [ABSTRACT FROM AUTHOR]

The rapid expansion of cities in developing countries has led to many environmental problems, and the mechanism of urban expansion (UE), as a more complex human-land coupled system, has always been a difficult issue to research. This paper introduces a new approach by establishing an analytical framework for spatiotemporal pattern mining, exemplified by studying the urban growth of Changsha City from 1990 to 2019. Initially, an emerging hotspot analysis model (EHA) is employed to examine the spatiotemporal changes of urban growth on a macro scale. Mathematical models are subsequently utilized to quantify the correlations between urban expansion and selected infrastructural and topographical factors. Building on these findings, the paper constructs mathematical models to further quantify the spatiotemporal evolution of various urban sprawl patterns across different regions, aiming to elucidate and quantify the significant variations in UE over time and space. The study reveals that, as an emerging city, Changsha's hotspots of urban expansion prior to 2003 were primarily concentrated in the city centre, subsequently spreading to the periphery. The radial influence of metro stations on UE is notably less than that of railway stations—approximately 3 km versus 8 km—and the impact diminishes rapidly before gradually tapering off. Moreover, UE in Changsha predominantly occurs on slopes with gradients ranging from 1.1° to 7.5°, and significant development capacity is observed at elevations between 36.1 m and 78.3 m above sea level, with a tendency for urban sprawl to migrate to lower elevations. The paper also identifies three distinct patterns of urban expansion across different regions: an initial slow-growth phase, followed by a rapid escalation to a peak, and subsequently a swift decline to near stagnation. Additionally, it highlights a significant correlation between the proportion of built-up areas at the micro-regional scale and the stages of UE. This correlation was quantitatively analysed by constructing a logistic function, which demonstrated a robust fit that effectively captures spatiotemporal heterogeneity in the dynamics of UE. These insights enhance the selection of drivers in urban simulation models and deepen the understanding of the complex dynamics that influence urban development. • New applications of spatiotemporal pattern mining and emerging hotspot analysis in urban expansion. • Exploring the impact of key infrastructure and topographical factors on urban expansion. • Focusing on revealing and quantifying the different inherent expansion mechanisms within various micro scales of cities. • The saturation of built-up areas in local regions correlates with the stages of urban expansion. [ABSTRACT FROM AUTHOR]

Projecting future urban CO 2 emissions is of paramount importance in comprehending and addressing climate change, as well as evaluating the impact of various policies on future greenhouse gas emissions. While previous studies on projecting CO 2 emissions have primarily focused on large administrative scales, fine-resolution mapping of CO 2 emissions is also vital for identifying CO 2 emission hotspots and delineating emission reduction responsibilities. In this paper, we projected the future CO 2 distribution at a fine-resolution (1 km) under the shared socioeconomic pathways (SSPs) scenario framework, based on which we assessed the peak time, peak volume, spatial distribution, and CO 2 emission intensity (emissions per unit building volume) for cities in the Pearl River Delta (PRD) region. We first simulated the future three-dimensional (3D) spatial patterns of cities by using the FLUS-3D model, and then projected fine-resolution CO 2 emissions by combining the 3D information and socioeconomic factors. Results show that the total CO 2 emissions in the PRD region will reach 180–345 million tons (Mt) by 2030, and 67% of cities in the PRD region will peak CO 2 emissions before 2030 under all five SSP scenarios. Three cities (Jiangmen, Zhongshan and Foshan) will witness a continual rise in CO 2 emissions after 2030 under the SSP5 scenario. Additionally, we found that the time (2010) to reach maximum CO 2 emission intensity of different urban functional types precedes the peak time (2010−2030) of city-level CO 2 emissions. This suggests that the escalation in CO 2 emissions since 2010 will be primarily driven by urban expansion and population growth, rather than an increase in the CO 2 emission intensity of buildings. These findings provide extensive knowledge for future spatial distribution of CO 2 emissions and contribute to the construction of low-carbon cities. • Future gridded CO 2 emissions (1 km resolution) are projected under the shared socioeconomic pathways (SSPs). • The future evolution of three-dimensional urban structures is considered in CO 2 emission projection. • Most cities in the PRD will peak CO 2 emissions before 2030 under all five SSPs. • The CO 2 emission intensity of urban lands declines since 2010 for most of cities. [ABSTRACT FROM AUTHOR]

Ground-borne vibrations are increasing at a rapid rate due to the rise in urban expansion and industrial activities. The current solution to mitigate the unwanted vibrations is limited to the use of single trenches that require unrealistic depths. This paper presents the possibilities of using dual open and infilled trenches to mitigate the vibrations generated due to continuous harmonic motions. Full-scale field tests and comprehensive numerical studies were performed to systematically design dual trenches. The field vibration tests were performed under a wide range of frequencies using the Lazan-type mechanical oscillator. Similarly, numerical studies have been performed using finite element analysis software, PLAXIS 2D. Expanded polystyrene (EPS) geofoams of different densities, bentonite, ceramsite, concrete, and sand-rubber mixture were used as the infill materials. The normalized depths of 0.40 and 0.50 were observed as the optimal values to reach an average amplitude reduction ratio (average ARR) of 0.25 for the dual open and EPS15-infilled trenches, respectively. The isolation efficiency of EPS15-infilled trenches was observed to be 178 % higher compared to the EPS48-infilled trenches. The performance difference between EPS15 and ceramsite-filled dual trenches was observed to be only 4 % in terms of average ARR , the former being superior. [ABSTRACT FROM AUTHOR]

In this paper we examine the evolution of urban spatial structure in U.S. metropolitan areas over nearly two decades. Using annual block-level data from the Longitudinal Employment Household Dynamics database, we introduce a technique for identifying regional employment centers that both adheres to urban economic theory and pays homage to classic contributions in local spatial statistics. Centers are defined as local spatial statistical outliers on the network-based job accessibility surface. We proceed by identifying the location and employment makeup of centers for each metropolitan region in the USA from 2002 to 2019 and discuss emergent trends across time and space. Critically, we not only explore empirical patterns, but we discuss the relationship between polycentricity, the evolution of urbanization and localization economies, and regional specialization. We confirm again the pattern of polycentricity in U.S. metros and show that the structure of metropolitan employment is largely stable over time. We also document a continuing trend away from urbanization economies into more specialized subcenters. • We develop a new technique for identifying employment subcenters combining spatial statistics, network analysis, and computational geometry. • the technique generates bespoke polygons that can be used for further analysis or designated as targets for urban development. • We apply our method to 20 years of annual census block -level employment from LEHD and discuss the trend toward increasing polycentric development in the U.S. • We document the increasing prominence of more specialized localization economies. • The methodology we contribute is generalizeable and can be applied anywhere in the world (we provide a Python software package for reproducing the results) [ABSTRACT FROM AUTHOR]

A rich volume of research has detected urban growth by quantifying the land use/land cover (LU/LC) changes based on remote sensing technologies. However, the research has limitations in identifying various formats of urban growth, particularly small-scale urban growth, such as infill development or redevelopment in urban areas, prompted by smart growth and sustainable urban development. This paper aims to design a framework for the accurate detection of residential infill development in the City of Los Angeles by employing a deep-learning method that has been increasingly applied to analyze phenomena in cities. In order to do so, this paper develops six models that reflect the variations of image classification methods, deep-learning algorithms, and estimation types. The results from the models emphasize the potential of the deep-learning models for the detection of micro-urban growth at a city scale. However, there is room for the improvement of estimation accuracy in the cases that detect some new developments and replacements as not developed parcels. The findings suggest that the performance of the models depends primarily on the articulations of the training dataset rather than the types of deep-learning algorithms. Findings from the models provide the city with insights into land use and transportation planning decision-making based on a better understanding of the spatial distribution patterns of urban growth and development. • Remote sensing data and geospatial technologies are limited in identifying small-scale urban growth due to the low resolutions of satellite data. • Deep-learning methods can be used to detect infill development by automatically classifying and labeling longitudinal satellite images. • The model performance primarily depends on the articulations of the training dataset rather than the types of deep-learning algorithms. [ABSTRACT FROM AUTHOR]

[Display omitted] • A water-type classification procedure integrating shape, landscape patterns, topography, and phenology was proposed. • The distribution and transition of various wetlands in the middle and lower reaches of the Yangtze River Basin were mapped. • Nearly half of the wetlands experienced a significant trend of decrease in water inundation frequency from 1990 to 2020. • Farmland reclamation was the primary anthropogenic factor in natural wetland loss and degradation. Wetlands are crucial to diverse societies and ecosystems but are threatened globally. Natural wetlands in the middle and lower reaches of the Yangtze River Basin (MLRYRB) have long been exploited to meet the increasing food and energy demands, especially in recent decades. However, how their landscapes and hydrological patterns changed over time was poorly qualified, which was crucial to conserving biodiversity and ecosystems. In this study, we proposed a new wetland classification procedure taking advantage of the shape, topography, landscape patterns, and phenology to map the distribution of six wetland types in the MLRYRB in 1990 and 2020 with Landsat images. The transitions among different wetland types and associated driving factors were examined. Artificial wetlands expanded by 3907.6 km2 while natural wetlands decreased by 423.2 km2, resulting in a net area increase of 3484.4 km2. Farmland reclamations, aquacultural activities, urban expansion, and dam constructions induced 70 % of the area's loss of natural wetlands. Meanwhile, spatiotemporal patterns in wetland inundation dynamics were determined with agglomerative hierarchical cluster analysis. Widespread transitions from perennial water to seasonal wetlands were detected. Notably, 47.8 % of the natural wetlands experienced significant drying trends, and as a result, the mean yearly inundated periods for natural wetlands decreased from 303 days in 1990 to 272 days in 2020. Given the substantial structural alterations, wetland destruction was more severe than the area reflected. Our results suggested that category-based changes in wetland areas, inundation patterns, associated driving forces, and underlying ecological consequences should be comprehensively assessed to conduct scientific conservation and prevent "paper offsets." [ABSTRACT FROM AUTHOR]

Road networks in the past are imperative for understanding evolution of transportation infrastructure, urban sprawl, and route planning, etc. Various approaches have been developed for road extraction from historical maps, among which deep learning techniques stand out as the most effective ones. However, little attention has been paid to investigating road vectorization and classification from historical maps. Moreover, road classification via machine learning methods usually requires large amounts of dedicated training data. To address these issues, this paper proposes a novel and comprehensive framework for road vectorization and classification on the basis of road segmentation from historical maps. First, deep learning is used to get pixel-wise raster road segmentation results, which are further skeletonized using morphological operations. Then, considering that each road class is represented with a certain symbol, a painting function is defined for each class able to paint the corresponding symbol. These painting functions are then used to draw road segments along the skeletons. Since the start and end points in each painting function are used to vectorise the segment, this method achieves vectorization and classification at the same time. Our method is validated on four Siegfried map sheets in Switzerland, and evaluated via both visual and quantitative assessments. The results indicate that the method is capable of classifying roads accurately. In particular, two evaluation metrics completeness and correctness achieve 90.69% and 72.71% respectively for road class 2 which accounts for the highest portion in the map. Moreover, the results of this method avoid the saw-toothed issue of vectorised road lines. This research is beneficial for creating complete vector road network datasets with class information to support decision-making in urban planning and transportation. • A novel framework is proposed to vectorise and classify roads from historical maps. • Deep CNNs are utilized to systematically and accurately extract roads. • Road classification and vectorization are achieved simultaneously by symbol painting. • Visual and quantitative assessments validate the effectiveness and robustness of the framework. [ABSTRACT FROM AUTHOR]