Fine-grained urban land use simulation: Integrating spatial dynamic modeling with a pre-trained vision-language model

The Greater Mekong Subregion (GMS) has experienced rapid economic growth and urbanization. However, few studies have paid attention to urban land use dynamics, especially spatiotemporal patterns of urban expansion and land use change, in this region. This research aimed to conduct a comprehensive study of urban land use change in Xishuangbanna, Yangon, Vientiane, Phnom Penh, Bangkok, and Ho Chi Minh City, from 1990 to 2015. The analysis was based on land use maps derived from Landsat satellite products and employed urban expansion intensity, sector analysis, gradient-direction analysis, and landscape metrics. The results show Xishuangbanna, Yangon, Vientiane, Phnom Penh, Bangkok, and Ho Chi Minh City all experienced dramatic urban expansion and land use change since 1990, with urban expansion intensities of 15.01, 5.26, 9.15, 1.56, 11.88 and 11.91, respectively. The landscape metrics analysis indicated that urban areas were always aggregated and self-connected, while other land use types showed trends of disaggregation and fragmentation. In the process of urban expansion, paddy and natural land use types were commonly transformed to built up area. The results further reveal several common issues in urban land use, e.g., land fragmentation and loss of natural land use types. Finally, the discussion on the relationship between government policy and land use change for these cities shows land reform and attitude toward foreign direct investments played important roles in urban land use change in GMS.

It is common to see urban land expansion worldwide, and its characteristics, mechanisms, and effects are widely known. As socio-economic transition and the change of land use policies may reverse the trend of urban expansion, in-depth research on the process of urban land use change is required. Through a process perspective, this paper reveals the change paths, development stages, and spatial patterns of urban residential land use with data from 323 cities in China from 2009 to 2016. The results show that: (1) theoretically, urban residential land use change can be divided into four development stages: an initial stage (Ⅰ), a rapid development stage (Ⅱ), a transition stage (Ⅲ), and a later stage of transition (Ⅳ). The rate of land use change is low—increase—decrease—approaching zero. (2) In about 68.7% of China’s cities, urban residential land is experiencing a transition, shifting from accelerating growth to decelerating growth. Given the distinctive transition process, it has been suggested that urban planning and land use policies should give timely responses to the new trends and spatial differences.

The accessibility provided by the transportation system plays an essential role in driving urban growth and urban functional land use changes. Conventional studies on land use simulation usually simplified the accessibility as proximities and adopted the grid-based simulation strategy, leading to the insufficiencies of characterizing spatial geometry of land parcels and simulating subtle land use changes among urban functional types. To overcome these limitations, an Accessibility-interacted Vector-based Cellular Automata (A-VCA) model was proposed for the better simulation of realistic land use change among different urban functional types. The accessibility at both local and zonal scales derived from actual travel time data was considered as a key driver of fine-scale urban land use changes and was integrated into the vector-based CA simulation process. The proposed A-VCA model was tested through the simulation of urban land use changes in the City of Toronto, Canada, during 2012–2016. A vector-based CA without considering the driving factor of accessibility (VCA) and a popular grid-based CA model (Future Land Use Simulation, FLUS) were also implemented for comparisons. The simulation results reveal that the proposed A-VCA model is capable of simulating fine-scale urban land use changes with satisfactory accuracy and good morphological feature (kappa = 0.907, figure of merit = 0.283, and cumulative producer’s accuracy = 72.83% ± 1.535%). The comparison also shows significant outperformance of the A-VCA model against the VCA and FLUS models, suggesting the effectiveness of the accessibility-interactive mechanism and vector-based simulation strategy. The proposed model provides new tools for a better simulation of fine-scale land use changes and can be used in assisting the formulation of urban and transportation planning.

Detailed urban land use information is the prerequisite and foundation for implementing urban land policies and urban land development, and is of great importance for solving urban problems, assisting scientific and rational urban planning. The existing results of urban land use mapping have shortcomings in terms of accuracy or recognition scale, and it is difficult to meet the needs of fine urban management and smart city construction. This study aims to explore approaches that mapping urban land use based on multi-source data, to meet the needs of obtaining detailed land use information and, taking Lanzhou as an example, based on the previous study, we proposed a process of urban land use classification based on multi-source data. A combination road network dataset of Gaode and OpenStreetMap (OSM) was synthetically applied to divide urban parcels, while multi-source features using Sentinel-2A images, Sentinel-1A polarization data, night light data, point of interest (POI) data and other data. Simultaneously, a set of comparative experiments were designed to evaluate the contribution and impact of different features. The results showed that: (1) the combination utilization of Gaode and OSM road network could improve the classification results effectively. Specifically, the overall accuracy and kappa coefficient are 83.75% and 0.77 separately for level I and the accuracy of each type reaches more than 70% for level II; (2) the synthetic application of multi-source features is conducive to the improvement of urban land use classification; (3) Internet data, such as point of interest (POI) information and multi-time population information, contribute the most to urban land use mapping. Compared with single-moment population information, the multi-time population distribution makes more contributions to urban land use. The framework developed herein and the results derived therefrom may assist other cities in the detailed mapping and refined management of urban land use.

The extent of anthropogenic land use in watersheds determines the amount of pollutants discharged to streams. This indirectly and directly affects stream water quality and biological health. Most studies have therefore focused on ways to reduce non-point pollution sources to streams from the surrounding land use in watersheds. However, the mechanistic pathways between land use and the deterioration of stream water quality and biological assemblages remain unclear. This study estimated a structural equation model (SEM) representing the impact of agricultural and urban land use on water quality and the benthic macroinvertebrate index (BMI) using IBM AMOS in the Nam-Han river systems, South Korea. The estimated SEM showed that the percent of urban and agricultural land in the watersheds significantly affected both the water quality and the BMI of the streams. Specifically, a higher percent of urban land use had directly increased the biochemical oxygen demand (BOD) and total phosphorus (TP), and deteriorated the BMI of streams. Similarly, higher proportions of agricultural land use had also directly increased the BOD, total nitrogen (TN), and total phosphorus (TP) concentrations, and lowered the BMI of streams. In addition, it was observed that the percent of urban and agricultural land use had indirectly deteriorated the BMI through increased BOD. However, we were not able to observe any significant indirect effect of the percent of urban and agricultural land use through increased nutrients including TN and TP. These results indicate that increased urban and agricultural land use in the watersheds had directly and indirectly affected the physicochemical characteristics and benthic macroinvertebrate communities in streams. Our findings emphasize the need to develop more elaborate environmental management and restoration strategies to improve the water quality and biological status of streams.

Change in urban construction land use is an important factor when studying urban expansion. Many scholars have combined cellular automata (CA) with data mining algorithms to perform relevant simulation studies. However, the parameters for rule extraction are difficult to determine and the rules are simplex, and together, these factors tend to introduce excessive fitting problems and low modeling accuracy. In this paper, we propose a method to extract the transformation rules for a CA model based on the Classification and Regression Tree (CART). In this method, CART is used to extract the transformation rules for the CA. This method first adopts the CART decision tree using the bootstrap algorithm to mine the rules from the urban land use while considering the factors that impact the geographic spatial variables in the CART regression procedure. The weights of individual impact factors are calculated to generate a logistic regression function that reflects the change in urban construction land use. Finally, a CA model is constructed to simulate and predict urban construction land expansion. The urban area of Xinyang City in China is used as an example for this experimental research. After removing the spatial invariant region, the overall simulation accuracy is 81.38% and the kappa coefficient is 0.73. The results indicate that by using the CART decision tree to train the impact factor weights and extract the rules, it can effectively increase the simulation accuracy of the CA model. From convenience and accuracy perspectives for rule extraction, the structure of the CART decision tree is clear, and it is very suitable for obtaining the cellular rules. The CART-CA model has a relatively high simulation accuracy in modeling urban construction land use expansion, it provides reliable results, and is suitable for use as a scientific reference for urban construction land use expansion.

Impact of land use compactness on the habitat services from green infrastructure in Wuhan, China

Intensive land use assessment is a key research topic in urban land use, and most of the existing studies focus on macro-level assessment. There is a lack of research on the micro-level assessment of intensive urban land use, especially at the parcel level. The objective of this research is to propose a method for the parcel-based evaluation of urban commercial land intensification. The study uses a multidimensional evaluation framework and index system, comprehensive evaluation, and spatially exploratory analysis of urban commercial intensive land use based on “building intensity, use efficiency, compatibility, and diversity”. The study finds that (1) the average value of intensive use of urban commercial land is 13.01, the standard deviation is 5.11, and the median value is 13, which generally indicate a medium level. (2) The degree of intensive use of commercial land has obvious characteristics of a high, medium, and low level. The study shows that when evaluating the degree of land use intensification at the parcel level, it is also necessary to consider the influence of the compatibility and diversity of external land use. The research results can provide a basis for spatial planning and the optimal design of urban land resources to improve urban vitality.

Detailed urban land use mapping requires high-resolution remotely sensed data. The pan-sharpened multispectral IKONOS imagery of 1 m pixel resolution is experimented with for urban land use classification. With the increase of spatial resolution, between-class spectral confusion and within-class spectral variation increase. Spectral-based traditional image classification methods cannot be directly applied to the IKONOS data for urban land use mapping. In this study, a rule-based urban land use inferring method is proposed and tested on 36 samples of typical land use classes and an IKONOS subscene of various classes in London, Ontario, Canada. The proposed method includes two general steps. First, the conventional multispectral classification method is applied to produce a preliminary land cover map. Second, urban land use information is inferred from the combination of several land cover classes existing in a neighbourhood by a rule-based modelling process. The inferring rules involve the percent composition ranges of compatible land cover categories for a certain land use class, the interrelationship of the compatible land covers, and exclusion of incompatible land covers. The results show that the proposed method has successfully identified level II and level III land use classes using the U.S. Geological Survey land use classification system. The proposed method has successfully identified the land use classes in the sample image with over 90% accuracy. For the subscene, the proposed method has produced a land use map with 88.5% overall accuracy.

Land cover and land use change analysis using multi-spatial resolution data and object-based image analysis

Analysis on coupling relationship of urban scale and intensive use of land in China

The impacts of rail transit on future urban land use development: A case study in Wuhan, China

The aim of this thesis is to advance the characterization of urban land and urban land dynamics to further the understanding of urban areas in data scarce regions. In order to achieve this, this thesis will answer the following research questions: RQ1: How can the integration of satellite imagery and socioeconomic data contribute to mapping urban land use (at a large spatial scale)? RQ2: How can we further the understanding of urban structure in cities located in data scarce regions? RQ3: What insights do building-level changes provide in urban dynamics? Chapter 2 uses a combination of open-source satellite imagery and socioeconomic data to classify urban land use at a national scale, using a deep learning approach. Combining Sentinel-2 and Sentinel-1 imagery with statistics from POIs and road networks increases the overall accuracy of the classification for the Netherlands by 3 percentage points. The Netherlands was divided into four regions, to test whether the combination of data types increased the transferability of the approach. When trained on three regions and tested on the independent fourth one the results showed a clear increase in classification accuracy between 3 and 5 percentage points relative to only using satellite data. However, when trained on one region and testing on another the results varied more strongly with differenced between 0 and 9 percentage points. Chapter 3 produces urban land use maps of three East African cities from satellite imagery and building footprint data. This chapters shows that the required amount of reference data needed when classifying new cities, using a combination of data sources, can be reduced by an order of magnitude by using a transfer learning approach. The combination of freely available PlanetScope satellite data, and publicly available Google building footprint data means that this approach is more cost effective compared to using VHR imagery. Despite using lower resolution imagery, the achieved classification accuracy was comparable to studies using VHR imagery. Chapter 4 develops new land use maps for multiple cities in East Africa, and uses these to compare the spatial structure of cities in this region with cities in Europe and the USA. By using urban land use maps, building footprint, and population data, several metrics were calculated in order to quantify the differences between cities of across three regions. Cities in East Africa, on average, have smaller building footprints compared to cities in the USA and Europe, but regarding to land use clustering, built-up density, and population distribution the variations within regions are higher than between them. These results indicate that the city structure of East African cities is not consistently different than cities from other continents, yet the variability found between cities of the same region challenge the idea that there is such a thing as a relevant city model. Chapter 5 uses VHR imagery to analyse different types of building-level changes in Nairobi, Kenya, between 2010 and 2021. Buildings were manually mapped to investigate whether they newly appeared, persisted, changed, were replaced, or removed. Over this period, removal, replaced, and renewal combined made up as much as 29% of the total mapped building area in 2010. In addition, the majority of newly build structures and buildings replacing other buildings are significantly larger than removed and replaced buildings. The observed changes, for example, relate to the removal of informal settlements and urban renewal policies. Due to the relative share of buildings affected, as well as the importance of the related change processes for sustainability, the study argues for the need to further develop automated methods that are able to detect multiple types of urban change on a large scale.

Does urban mixed use development approach explain spatial analysis of inner city decay?

China’s urban land use has shifted from incremental expansion to inventory eradication. The traditional extensive management mode is difficult to maintain, and the fundamental solution is to improve land use efficiency. Xi’an, the largest central city in Western China, was selected as the research area. The super-efficiency data envelopment analysis (DEA) model and Malmquist index method were used to measure the land use efficiency of each district and county in the city from the micro perspective, and the spatial-temporal change characteristics and main influencing factors of land use efficiency were analyzed, which not only made up for the research content of urban land use efficiency in China’s underdeveloped areas, but also pointed out the emphasis and direction for the improvement of urban land use efficiency. The results showed that: (1) The land use efficiency of Xi’an reflected the land use intensive level of the underdeveloped areas in Western China, that is, the overall intensive level was not high, the gap between the urban internal land use efficiency was large, the land use efficiency of the old urban area and the mature built-up area was relatively high, and the land use efficiency of the emerging expansion area and the edge area was relatively low. (2) Like the eastern economically developed areas, the land use efficiency of western economically underdeveloped areas was generally on the rise, while Xi’an showed the U-shaped upward evolution characteristics, and there were four types of changes in the city, that is, highly intensive, medium intensive, high–medium–low-intensive, and intensive–extensive. (3) Various cities should configure resources and optimize mechanism to improve their land use efficiency based on economic and social development. During the study period, Xi’an showed the law of evolution from the south edge area and the emerging expansion area to the main urban area. (4) The improvement of technological progress was the main contribution factor of the land use efficiency in underdeveloped areas of China, and the low-scale efficiency was the main influence factor that caused low land use efficiency. In future urban land use, efforts should be made to optimize and upgrade technology and strictly control the extensive use of land.