Delineating urban development boundaries in urban agglomeration: Integrating flow-based approach and U-Net deep learning

Urban development boundaries are efficient tools for coordinating urban–rural relations and ensuring sustainable development. From 2000 to 2020, the expansion rate of the built-up area in cities and towns throughout China reached 177%, far exceeding the urban population growth rate of 96.5% in the same period. As this spatial expansion seems to continue, there is a need to intervene and control urban boundaries. We believe using the urban–rural integration perspective to set (or reset) and maintain urban development boundaries will help manage urban expansion more effectively than present methods. This research, therefore, develops an urban development boundary delineation method from a macroscopic view for China. A new model for defining boundaries was developed based on the four dimensions of urban–rural interaction: economic demand, environmental protection, urban carrying capacity, and urban development resistance. And an empirical study was conducted in Guiyang City as an example. The results show that the resultant urban boundary can provide a more comprehensive and realistic growth model than current methods, making it more applicable for controlling and fostering sustainable urban and rural development.

Accelerated urbanization both promotes the rapid development of social economy and leads to a series of disadvantages, such as the excessive consumption of resources, environmental pollution, and food security threats. It is thus necessary to reasonably demarcate future urban development boundaries. Therefore, both the external supply and the elastic space of urban internal development need to be considered. In the present study, the current urban boundaries were first identified. Then, the urban rigid and elastic development boundaries in the next three decades were obtained by employing the minimal cumulative resistance (MCR) and CA-Markov models. Lastly, some suggestions were put forward for the implementation of future urban development boundaries. The results were the following. (1) The areas of the current urban boundaries of Haikou in 2000, 2010, and 2020 were 93.71, 124.26, and 260.41 km2, respectively. (2) By using the MCR model, the urban rigid development boundaries of Haikou in 2030, 2040, and 2050 were 361.27, 480.17, and 505.22 km2, respectively. (3) By using the CA-Markov model, the areas of urban elastic development boundaries in 2030, 2040, and 2050 were 381.86, 483.95, and 536.06 km2. (4) The increased elastic expansion space of urban development of Haikou while meeting the rigid constraint conditions in 2030, 2040, and 2050 was 20.59, 3.78, and 30.84 km2, respectively. (5) Suggestions need to be put forward on the implementation of future urban development boundaries from the aspects of technology, policy, and management. The results of demarcating the urban rigid and elastic development boundaries can not only prevent the excessive urban expansion and ensure the orderly, efficient and sustainable development of the city, but also more effectively protect important ecological resources, which could provide quantitative reference and decision-making basis for regional territorial space planning.

Containing urban sprawl in China: A cross-city evaluation of urban development boundaries using U-Net deep learning

Crack detection on historical surfaces is of significant importance for credible and reliable inspection in heritage structural health monitoring. Thus, several object detection deep learning models are utilized for crack detection. However, the majority of these models are powerful at most in achieving the task of classification, with primitive detection of the crack location. On the other hand, several state-of-the-art studies have proven that pixel-level crack segmentation can powerfully locate objects in images for more accurate and reasonable classification. In order to realize pixel-level deep crack segmentation in images of historical buildings, this paper proposes an automated deep crack segmentation approach designed based on an exhaustive investigation of several U-Net deep learning network architectures. The utilization of pixel-level crack segmentation with U-Net deep learning ensures the identification of pixels that are important for the decision of image classification. Moreover, the proposed approach employs the deep learned features extracted by the U-Net deep learning model to precisely describe crack characteristics for better pixel-level crack segmentation. A primary image dataset of various crack types and severity is collected from historical building surfaces and used for training and evaluating the performance of the proposed approach. Three variants of the U-Net convolutional network architecture are considered for the deep pixel-level segmentation of different types of cracks on historical surfaces. Promising results of the proposed approach using the U2−Net deep learning model are obtained, with a Dice score and mean Intersection over Union (mIoU) of 71.09% and 78.38% achieved, respectively, at the pixel level. Conclusively, the significance of this work is the investigation of the impact of utilizing pixel-level deep crack segmentation, supported by deep learned features, through adopting variants of the U-Net deep learning model for crack detection on historical surfaces.

Genting Highland is predominantly the mode of landslides, especially prevalent during and post monsoon seasons. Globally, landslides encapsulates the widespread hydro-geological disaster elucidating their causes, risks, and impacts on infrastructure and human life. Attributed  from Malaysia natural undulated terrain, torrential rainfall, expanding urbanization contributed to the increasing landslide occurrences. Laying the groundwork for a more efficient landslide mapping over a vast area underscores the imperative need of Artificial Intelligence (AI). Landslide mapping to-date transitions from conventional delineation to employing U-Net, a deep learning architecture, to automate and expedite the process of identifying landslides from remote sensing data towards the emphasizes on rapid landslide mapping. This study is to create detailed landslide inventory maps by mapping new and old landslide footprint for Genting Highlands, with U-Net Deep Learning as a pivotal tool. Entail a systematic process, to identify landslide structures according to predefined categories, using high-resolution satellite imagery to train the U-Net model, and ultimately producing validated landslide maps for the region. The stages for integrating U-Net Deep Learning with geospatial analysis include data acquisition, pre-processing, DL training, analysis, and the final output of landslide mapping. Spot-7 imagery as input to the U-Net and  landslide semantic shapes that consist of crown, transportation body and foot, whereby pixel by pixel are classified when introduced. The anticipated results, showcasing the validity and precision of the model's landslide automated delineation on other imageries. Verification involves the comparison between U-Net's projected landslides to a manually delineated landslide inventory for Genting Highlands. Hence, this research provide precise and efficient tools for identifying and forecasting landslides in landslide-prone areas. 

Informal settlement with its different effects on the cities in general andmetropolis specifically, indicates weaknesses in managerial programs andpolicies in different local, national and transnational level. This has beendefined as a challenge in managerial system of metropolis, influencing itsboundaries in different aspects. Informal settlement usually develops in themarginal parts of metropolis, beyond the urban development boundaries and in aself-driven manner. In this way it influences the standard boundaries ofmetropolis in different aspects. Tabriz metropolis has faced the problem indifferent periods of time, influenced and was influenced by it through itsstructural and performance system. In this paper we study the effective processin development of informal Tabriz metropolis settlements and determine theinteraction of informal settlement in this city. This is ananalytical-descriptive research in which data has been collected from therelative information from field and library studies. Research findings indicatethe fact that Tabriz metropolis, for its conditions and for centralization ofjob opportunities is the first city in the region experiencing informalsettlements. This has resulted in broad immigration from villages to the city,the main reasons of which can be economic poverty, unemployment in the originin one hand and economic and employment opportunities in destination(representing centralization of sources and services in destination). Theprocess has with time influenced by different structures, the spatial elementsof Tabriz metropolis and its urban boundaries.

The study of urban agglomeration boundaries is helpful to understand the internal spatial structure of urban agglomeration, evaluate the development level of urban agglomeration, and thus, assist in the formulation of regional planning and policies. However, previous studies often used only static spatial elements to delineate the boundaries of urban agglomerations, ignoring the spatial connections within urban agglomerations. In this study, night-time light and Tencent user location data were evaluated separately and fused to delineate urban agglomeration boundaries from both static and dynamic spatial perspectives. Additionally, it has been shown in the study results that the accuracy of urban agglomeration boundary delineated by night-time light data is 84.90%, with Kappa coefficient as 0.6348. The accuracy delineated by Tencent user location data is 82.40%, with Kappa coefficient as 0.5637, while the accuracy delineated by data fusion is 92.70%, with Kappa coefficient as 0.7817. Therefore, it can be concluded that the fusion of night-time light and Tencent user location data had the highest accuracy in delineating urban agglomeration boundaries, which verified that the fusion of dynamic spatial elements on a single static spatial element can supplement the spatial connection of urban agglomeration. Our findings enrich the understanding of urban agglomerations, and the accurate delineation of urban agglomerations boundaries can aid urban agglomeration planning and management.

Simulating large-scale urban land-use patterns and dynamics using the U-Net deep learning architecture

In order to control the development of urban space, it is important to explore scientific methods to provide a reference for regional territorial space planning. On the basis of the minimum cumulative resistance (MCR) model and the cellular automaton (CA)-Markov model, we constructed a new technical method for delineating urban development boundaries, exploring the temporal and spatial distribution characteristic of land use in Wuhan from 2010 to 2020 through nighttime and remote sensing images, and simulating the urban development boundaries of Wuhan from 2025 to 2035. The results show that: (1) the scales of Wuhan City’s built-up areas in 2010, 2015, and 2020 were 500 km2, 566.13 km2, and 885.11 km2, respectively, and the trends of expansion run to the east and southeast, and (2) on the basis of the MCR model, the urban development boundary scale of Wuhan City in 2025, 2030, and 2035 from the perspective of actual supply will be 903.52 km2, 937.48 km2, and 1021.44 km2, respectively, and based on the CA-Markov model, the urban development boundary scales of Wuhan City in 2025, 2030, and 2035 from the perspective of ideal land demand will be 912.75 km2, 946.40 km2, and 1041.91 km2, respectively. By combining the results of the two methods, we determined areas of 901.62 km2, 944.39 km2, and 1015.36 km2 as the urban development boundaries of Wuhan City in 2025, 2030, and 2035, respectively. According to the principle of supply–demand balance, the urban development boundary delineated by the integration of the MCR model and CA-Markov model, which is in line with the spatial expansion trend of growing cities, could optimize the urban development pattern; solve the contradiction between urban development, farmland protection, and ecological protection; and provide a methodological reference and decision-making basis for planning practice.

Amidst rapid urbanization, the conflict between urban population and land is intensifying due to ecological degradation and imbalanced supply and demand of land resources in and around cities. Demarcating the urban development boundary is a specific measure to regulate the scale and form of urban expansion while considering internal urban demand as well as ecological security. This study took Haikou City, China, as the study area, exploring a new way to take into account the external constraints and endogenous mechanisms of urban expansion, constructing a comprehensive ecological security pattern (ESP) using the MCR model, demarcating recent rigid development boundaries, and demarcating future elastic development boundaries using the CA–Markov model. The results were the following: (1) By identifying the current urban boundary in 2020, the urban land area of Haikou City was found to be 261.64 km2. (2) Using the MCR model to construct comprehensive ESP and demarcate a rigid development boundary revealed that the total area within the boundary was 398.37 km2, with an additional growth potential of up to 136.73 km2. (3) Demarcating elastic boundaries for Haikou City in 2030, 2040 and 2050 using the CA–Markov model while considering natural and socio-economic driving factors and constraints showed the internal areas within these boundaries to be calculated at 451.80, 489.46 and 523.37 km2, respectively, which were higher than that in 2020 by 190.16, 227.82 and 261.73 km2. (4) Some suggestions, such as establishing a comprehensive technical system, ensuring robust policy support and legal protection, and improving the responsibility management system, were proposed in the implementation of urban development boundaries. Scientifically and reasonably demarcating the recent rigid urban development boundary and future elastic urban development boundaries can ensure sustainable urban development while preserving the ecological environment and satisfying urban development demand.

Delineating urban growth boundaries by coupling urban interactions and ecological conservation

This study investigates how do urbanization, urban agglomeration, and largest city ratio affect CO2 emissions in 10 Asian Economies namely Bangladesh, India, Pakistan, Nepal, China, Indonesia, Malaysia, Thailand, the Philippines and Vietnam over the period 1990- 2020. Based on STIRPAT (Stochastic Impacts by Regression on Population, Affluence, and Technology) framework, we applied dynamic seemingly unrelated regression (DSUR) to establish long-run term effects. The empirical findings revealed that urbanization and urban agglomeration have inverted U shaped effect, meanwhile largest city ratio have U shaped. Urbanization and urban agglomeration improve environment quality in the long term and supports ecological modernization theory. Urbanization and urban agglomeration improves environmental quality after reaching a significant level of urban development due to efficient energy structures, population awareness, environmentally friendly technologies, and strict urban and environmental policies. However, the finding of largest city ratio revealed U shaped. This result rejects compact city theory. It implies that excessive concentration in the largest cities have severely affected the environmental quality and violates the notion of compact-city efficiencies which could be attributed to extreme population density, overcrowding, traffic congestion and extensive demand for energy consumption. The results of the panel granger causality approach unveil bidirectional causality in urban agglomeration and its quadaratic term of urban agglomeration, largest city ratio, and quadaratic term of largest city ratio on CO2 emissions. Bidirectional causality also found in GDP and CO2 emissions. Meanwhile, unidirectional causality found in energy intensity and CO2 emissions, trade openness and CO2 emissions, financial development and CO2 emissions, as well as urbanization and CO2 emissions. The current study has implications for policymakers and respective governments to green urban infrastructures, eco-friendly dwellings, smart cities, country-specific trade policies, and renewable energy options and to adhere more stringent urban planning to improve the environmental quality.

Based on constraining the spatial extent of urban expansion, the urban development boundary concept provides guidance on resource constraints and policy development for urban areas and aims to meet the new demands of urban development under the background of a new type of urbanization in China. We applied remote sensing and geographical information system (GIS) techniques, along with the slope, land use, exclusion, urban extent, transportation, and hill shade (SLEUTH) model, to identify urban growth boundaries in Changzhou City, China. We then comprehensively considered various land use regulation policies and the carrying capacity of land resources to construct an urban development boundary model. This model was tested using empirical data on the delineation of flexible and rigid urban development boundaries. We argue that China's position as the largest developing country in the world has resulted in significant uncertainties in its socioeconomic development; therefore, the construction of Chinese cities requires both flexible controls and a rigid management structure. The model developed in this study successfully meets the construction needs of China's urban development, particularly as it contains an optimal degree of generalizability.

Rapidly and accurately extracting built-up areas is an essential prerequisite of urbanization research. There have been many studies on the extraction of built-up areas using remote sensing technologies. So far, few studies have been conducted to evaluate the applicability of the deep learning method to extract built-up areas under the condition that only nighttime light (NTL) data are used. This study proposed a deep learning method to extract the built-up areas using NTL data, and applied the method to analyze the spatial and temporal changes of the built-up areas in Chinese two urban agglomerations from 2000 to 2020. The results show that the U-Net deep learning method can be used to extract built-up areas efficiently under the condition that only NTL data are used. The proposed method was able to improve the accuracy of built-up area extraction significantly compared to the existing method. For the extraction of built-up areas in large regions with long time series, the proposed method can facilitate the work and improve the processing efficiency. The gravity centre of the built-up areas in the Central Plains Urban Agglomeration migrated south-eastward, and the gravity centre of the built-up areas in the Shandong Peninsula Urban Agglomeration migrated south-westward, with these gravity centres gradually approaching the geometric centres of the corresponding urban agglomerations. The built-up areas in the Central Plains and Shandong Peninsula Urban Agglomerations grew rapidly, increasing by 4.14 times and 3.73 times from 2000 to 2020, respectively. The built-up areas in the Central Plains Urban Agglomeration expanded faster, while the urban development degree of the Shandong Peninsula Urban Agglomeration was higher. The urban distributions and development modes of these two urban agglomerations were quite different. The Central Plains Urban Agglomeration tended to further agglomerate, while the Shandong Peninsula Urban Agglomeration tended to disperse.

Accurate urban boundary data can directly reflect the expansion of urban space, help us accurately grasp the scale and form of urban space, and play a vital role in urban land development and policy-making. However, the lack of reliable multiscale and high-precision urban boundary data products and relevant training datasets has become one of the major factors hindering their application. The purpose of this study is to combine Sentinel-2 remote-sensing images and supplementary geographic data to generate a reliable high-precision urban boundary dataset for Henan Province (called HNUB2018). First, this study puts forward a clear definition of “urban boundary”. Using this concept as its basis, it proposes a set of operable urban boundary delimitation rules and technical processes. Then, based on Sentinel-2 remote-sensing images and supplementary geographic data, the urban boundaries of Henan Province are delimited by a visual interpretation method. Finally, the applicability of the dataset is verified by using a classical semantic segmentation deep learning model. The results show that (1) HNUB2018 has clear and rich detailed features as well as a detailed spatial structure of urban boundaries. The overall accuracy of HNUB2018 is 92.82% and the kappa coefficient reaches 0.8553, which is better than GUB (Henan) in overall accuracy. (2) HNUB2018 is well suited for deep learning, with excellent reliability and scientific validity. The research results of this paper can provide data support for studies of urban sprawl monitoring and territorial spatial planning, and will support the development of reliable datasets for fields such as intelligent mapping of urban boundaries, showing prospects and possibilities for wide application in urban research.