城市是区域人口、产业等要素集聚的主要空间载体，系统揭示黄河流域城市建设用地结构演化及其驱动机制对于深入推进黄河流域生态保护和高质量发展战略落实具有重要意义。基于黄河流域2007—2019年城市建设用地数据，论文运用信息熵模型分析了黄河流域城市建设用地结构的时空演化特征，并用随机森林模型探讨其驱动机制。结果表明：① 2007—2019年，黄河流域城市建设用地面积快速增长，年均增速达5.34%，但城市建设用地结构信息熵不断降低，经历了“高位无序—相对稳定—低位有序”的变化过程；② 黄河上、中、下游城市建设用地规模增速依次加大，年均增速分别达到3.91%、5.06%、6.22%；中游地区城市建设用地结构信息熵下降最多，上游地区和下游地区降幅相近；③ 黄河流域各类建设用地主要配置在省会及经济发达城市；黄河流域城市用地结构信息熵存在空间异质性，省会城市及经济发达城市建设用地结构信息熵存在降低趋势，而欠发达城市的信息熵逐步增大；④ 城市用地规模和城市人口规模对城市建设用地结构演化的作用最强，产业结构升级和财政支出规模的作用强度次之，经济发展水平和政策支持力度的作用较小，上中下游影响因子的作用强度存在异质性；⑤ 城市用地规模、城市人口规模、财政支出规模与城市建设用地结构信息熵呈正向变动关系，经济发展水平和产业结构升级与城市建设用地结构信息熵呈负向变动关系，政策支持力度则与城市建设用地结构信息熵呈现出“倒U”型关系。

Cities are the main spatial carriers for the agglomeration of regional population, industry and other factors, and systematically revealing the evolution of urban construction land structure and its driving mechanism is of great significance for further promoting the implementation of ecological conservation and high-quality development strategy of the Yellow River Basin. Based on the urban construction land data of the Yellow River Basin from 2007 to 2019, the spatiotemporal change characteristics and differentiation patterns of the construction land structure in the basin were analyzed by using the information entropy model, and the formation mechanism of the driving factors was examined by using the random forest model. The results show that: 1) From 2007 to 2019, the area of urban construction land in the Yellow River Basin continued to grow, with an average annual growth rate of 5.34%, but the information entropy of urban construction land structure decreased, and experienced a change process of high-level disorder, relatively stable, and low-level orderly. 2) The growth rate of urban construction land use in the upper, middle, and lower reaches of the Yellow River increased successively, with the annual growth rate reaching 3.91%, 5.06% and 6.22% respectively. The information entropy of urban construction land use structure in the middle reaches of the Yellow River decreased the most, and the decline rates in the upper reaches and lower reaches were similar. 3) All types of construction land in the basin are mainly distributed in provincial capitals and cities in economically developed areas, and there is a clear spatial heterogeneity in the information entropy of urban construction land use structure in the region. The information entropy of urban construction land use structure in provincial capital cities and economically developed cities showed a decreasing trend, while the information entropy of less developed cities gradually increased. 4) The scale of urban land use and the size of urban population have the strongest effect on the change of urban construction land use structure, followed by the intensity of industrial structure upgrading and scale of fiscal expenditure. The role of economic development level and policy support is small, and the intensity of impact of upstream, middle reaches, and downstream influencing factors is heterogeneous. 5) The scale of urban land use, the size of urban population, and the scale of fiscal expenditure showed a positive change relationship with the information entropy of urban construction land use structure, the level of economic development and industrial structure upgrading showed a negative change relationship with the information entropy of urban construction land use structure, and the policy support showed an inverted U-shaped change relationship with the information entropy of urban construction land use structure.

在区域一体化及黄河流域生态保护和高质量发展战略背景下，黄河下游滩区将承担更加多元的生态与社会功能，滩区周边城镇空间进入新的快速成长期。基于城镇空间扩展差异指数、紧凑度、相关维数的定量测算探析2000—2020年黄河下游滩区周边城镇空间扩展格局及形态特征，在此基础上耦合随机森林回归算法与重心-时空地理加权回归（GTWR）模型，采用“主成分分析-重要性判断-驱动空间识别”的分析方法对城镇空间扩展时空变化进行驱动机制的多维度解析。结果表明：① 黄河下游滩区周边地区城镇空间呈圈层式扩展，时空分异与空间溢出特征显著；2005—2010年为高速发展期，此后众多城镇空间重心向靠近黄河与中心城市方向迁移，局部地区城镇空间沿河流方向轴向拓展，区域一体化发展不断加强。② 研究范围内城镇空间形态在波动变化中不断演进，经历了多点集中式扩展-局部线性蔓延-组团化协同发展的变化过程，城镇间联系日趋紧密，簇群结构日渐完善。③ 社会经济、产业结构、自然条件构成了滩区周边城镇扩张的内驱力，政策战略与水利工程形成了城镇发展的外驱力，二者耦合协同推动滩区周边城镇扩展格局与空间形态的不断变化。社会经济与产业结构是城镇扩张的主导驱动力，区域发展政策带动作用愈加显著。基于城镇空间扩展特征与驱动机制的研究，提出了滩区周边区域空间发展格局的优化建议。研究成果可为滩区周边城镇空间布局优化与政策制定提供科学支撑，助力高质量高标准建设沿黄城市群的发展目标。

With the implementation of ecological conservation and high-quality development of the Yellow River Basin, the urban space of cities and towns around the river floodplain area has entered into a new period of rapid growth. This research calculated the Urban Expansion Differentiation Index (UEDI), Compactness Index (C), and Correlation Dimension (Dc) of urban land around the Yellow River floodplain area. Based on the index calculation, this paper analyzed the urban land expansion pattern and morphological characteristics of urban space in the research area from 2000 to 2020. After that, coupled with Random Forests Regression and Geographically and Temporally Weighted Regression model (GTWR), the urban land expansion was regarded as a spatiotemporal system for the driving mechanism analysis in multiple dimensions. The results showed that: (1) Urban land in the research area is expanding in a circle pattern, with significant characteristics of spatiotemporal differentiation and spatial overflow. From 2005 to 2010, cities and towns in this area ushered in a period of high-speed development. Since then, the gravity centers of urban land tended to move towards the Yellow River or adjacent big cities. Urban spaces have developed along the river and the town agglomerations tended to be integrated. (2) The urban land spatial forms in this area evolved in fluctuation. The urban space has gone through the process of multi-point centralized development, local linear spread, and cluster coordinated development. In this process, the connections between cities and towns are becoming closer and closer, and the cluster structure is constantly improving. (3) Economic-social, industrial structure, and natural factors constitute the internal driving force, while the external driving force is composed of flood control projects, policies, and regulations. The coupling of internal and external driving forces promotes the evolution of urban land expansion around the Yellow River floodplain area. On the whole, urban spatial expansion is more dependent on economic development and industrial structure, and regional development policies also play a significant role. Based on the evolving characteristics of urban land expansion and its mechanism, we proposed optimization suggestions for the development pattern of cities and towns in the research area. The research results can provide scientific support for the optimization of spatial layout and policy formulation of cities and towns around the floodplain of the Lower Yellow River, promoting the construction of high-quality urban agglomeration along the Yellow River.

基于快速城镇化背景下秦淮河流域土地利用历史状况,选择CLUE-S模型对其2020年土地利用情况进行模拟预测。分别使用线性回归、Markov模型、灰色GM（1,1）模型预测CLUE-S模型非空间模块的土地利用需求量,再嵌入CLUE-S中得到3种预测结果,对预测结果进行比较。另外设定“自然发展”情景与考虑规划政策影响的“优化格局”情景,模拟2020年不同情景下秦淮河流域土地利用格局情况,并进行景观格局分析。结果表明：线性回归模型、Markov模型、灰色GM（1,1）模型的Kappa指数分别为0.866、0.849、0.867,3种方法均满足模型精度要求;自然发展情景中2020年水域、水田、林地、城镇用地、旱地面积相对于2010年分别变化21.5%、-15.3%、-9.0%、51.5%、-28.9%,而优化格局情景下水域、水田、林地、城镇用地、旱地面积分别变化3.1%、-1.6%、10.8%、6.3%、-10.6%,相比于自然发展情景,优化情景土地利用状况更符合保护基本农田、增加生态用地连通性、提高雨水下渗能力以及缓解城市热岛效应的要求,为后期土地利用规划提供了依据。

Under the background of rapid urbanization in the Qinhuai River Watershed, models of land use change are primary tools for analyzing the causes and consequences of land use changes. We choose CLUE-S model to simulate the land use situation of it in 2020. We use linear regression model, Markov model and the gray GM (1, 1) model respectively to predict the demand for land use which is needed by the non-spatial module of CLUE-S model, then we compared the three forecast results.In order to further verify the influence of policy on land use change, two prediction scenarios were established, one is "natural development" scenario where land use will change according to historical trend and the other is "optimization" scenario which considered the effects of planning policy. We simulated the Qinhuai River Watershed land use pattern in 2020 under different scenarios, and analyze the landscape pattern of it. The results shows that the Kappa index of Linear regression model, Markov model, the gray GM (1, 1) model are 0.866, 0.849, 0.867 respectively, so three methods all satisfy the requirements of model accuracy; In “natural development” scenario, the water area, paddy field, forest land, urban land and the dry farm change, compared to 2010, by 21.5%, 15.3%, 9.0%, 9.0%, 9.0%, respectively, while in “optimization” scenario water area, paddy field, forest land, urban land and the dry farm change by 3.1%, 1.6%, 10.8%, 6.3%, 10.8%, respectively; Under the “optimization” scenario, the land use condition can meet the requirement of protection of basic farmland and ecological land, increasing infiltration capacity of rainwater, and alleviating the urban heat island effect. This work could be the reference for the choice of the method of non-spatial module and provide scientific support for land use planning and managements of the watershed.

通过将中国划分为4个生态区，在综合考虑社会经济和自然因素的前提下，利用系统动力学的原理和方法，选取对土地利用变化影响最大的驱动因素，分区构建中国土地利用变化系统动力学模型并模拟4种发展情景下2050年中国土地利用变化情况。结果表明：在不同情景设定下，土地利用变化差异较大，其中平稳发展情景较理想，生态用地保持良好，城市扩张较为合理；建设用地发展给予的压力以及气候条件的不断恶化，使得4种情景下水域面积在2045年前都呈现减少趋势，需要管理者严控城市扩张，提早规划布局以应对相应挑战；气温和降水对4个生态区的林地和草地影响程度不同，水域面积主要受到降水影响，而技术进步带来的粮食单产提高是影响耕地面积变化的重要因素。

大都市郊区是快速城镇化进程中空间演变最为频繁、人地矛盾最为突出的区域,尤其在中国加快推进“就地就近”城镇化战略的背景下,把握大都市郊区小城镇土地利用时空变化过程及其演变机制,对制定科学合理的管控政策和优化都市空间结构具有重要的现实意义。约束性元胞自动机(constrained Cellular Automata, constrained CA)能够通过简单的规则模拟复杂的城市动态演化过程。本文将土地利用总体规划指标、城镇空间发展战略布局、土地利用开发适宜性等,嵌入约束性CA的转换规则中,采用Logistic逐步回归法分析土地利用空间影响因素,对严格约束下的武汉市江夏区2020年土地利用进行情景模拟分析,并提出城市增长管控手段。结果表明：①研究时段内,江夏区城镇用地呈低效外延式扩张,土地利用集约节约程度较低,其人口规模并未有较大增长,对主城区人口的分散作用尚未真正形成;②约束性CA在模拟大都市郊区演化方面具有较高的可靠性,能够真实反映近郊小城镇的未来空间布局与结构,模拟结果与土地利用规划和城市规划较为契合;③将规划目标导向与现实发展趋势下的模拟结果进行叠加分析,可确定城镇增长需求与规划指标调控间冲突的空间分布,从而划定土地督察的重点监测区域,为加强大都市近郊区的违法用地监查和土地利用管控提供先验的预警知识。

This paper introduces an urban growth simulation model applied to the full scope of China. The model uses a multicriteria decision analysis to calculate the land conversion probability and then integrates it with a cellular automata model. A nonlinear relationship is incorporated in to the model to interpret the impacts of different Land Use and Cover Change driving forces. The Analytical Hierarchical Process is also implemented to compute the variance between weights of different factors. Multiple sizes of neighborhood and different urban ratios in the model rules are tested, and a 5 × 5 neighborhood and an urban threshold of 0.33 are chosen. The study demonstrates the importance of spatial analysis on socioeconomic factors, population, and Gross Domestic Product in land use change simulation modeling. The model fills the gap between the purely economic theory simulation model and the geographic simulation model. The nationwide urban simulation is an example that addresses the lack of urban simulation studies in China and among large-scale simulation models.

城市群是具有网络关系与层级性的区域空间,一直是中国推进城镇化与区域协调发展的主体单元。本文综合考虑城市群的网络与层级性特征,运用城市流刻画城际网络交互作用,采用分层广义线性模型（HGLM）揭示城市群分层驱动机制。同时,选取长江中游城市群开展实证研究,通过与元胞自动机（CA）耦合,构建HGLM-CA模型模拟城市群空间扩展。将模拟结果与Logistic-CA模型、BBO-CA模型进行比对,据此评析HGLM-CA模型的优劣与改进方向。实证结果表明：城市群空间扩展是多层驱动因素共同作用的结果,城市流不仅会推动城市群空间扩展,而且对元胞层因素起到重要的调节作用,使之具有城际分异性;HGLM-CA模型相比Logistic-CA模型模拟精度更高,说明顾及城市流与层级性的城市群空间扩展模拟结果更为精准;与智能模型BBO-CA相比,HGLM-CA模型模拟精度较低,但其便于从层级性角度把握城市群空间扩展机制。

Since the launch of China's reform and opening up policy, the process of urbanization in China has been accelerated. With the development of cities, inter-city interactions have become increasingly close, and urban agglomerations tend to be integrated. Urban agglomerations are regional spaces with network relationships and hierarchies, and have always been the main units for China to promote urbanization and coordinated regional development. In this paper, we comprehensively consider the network and hierarchical characteristics of an urban agglomeration, while using urban flow to describe the interactions of the inter-city networks and the hierarchical generalized linear model (HGLM) to reveal the hierarchical driving mechanism of the urban agglomeration. By coupling the HGLM with a cellular automata (CA) model, we introduce the HGLM-CA model for the simulation of the spatial expansion of an urban agglomeration, and compare the simulation results with those of the logistic-CA model and the biogeography-based optimization CA (BBO-CA) model. According to the results, we further analyze the advantages and disadvantages of the proposed HGLM-CA model. We selected the middle reaches of the Yangtze River in China as the research area to conduct this empirical research, and simulated the spatial expansion of the urban agglomeration in 2017 on the basis of urban land-use data from 2007 and 2012. The results indicate that the spatial expansion of the urban agglomeration can be attributed to various driving factors. As a driving factor at the urban level, urban flow promotes the evolution of land use in the urban agglomeration, and also plays an important role in regulating cell-level factors, therefore, the cell-level factors of different cities show different driving effects. The HGLM-CA model can obtain a higher simulation accuracy than the logistic-CA model, which indicates that the simulation results for urban agglomeration expansion considering urban flow and hierarchical characteristics are more accurate. Compared with the intelligent algorithm model, i.e., BBO-CA, the HGLM-CA model obtains a lower simulation accuracy, but it can analyze the interaction of the various driving factors from a hierarchical perspective. It also has a strong explanatory effect for the spatial expansion mechanism of urban agglomerations.

城镇用地扩展格局及驱动力研究对城市群发展规划与决策具有重要意义。以京津冀地区为例,基于城镇用地扩展强度指数、城镇用地扩展差异指数、分形维数、土地城镇化率和重心转移模型,多维解析了城市群城镇用地扩展格局特征,并耦合重心转移模型和时空地理加权回归（GTWR）模型构建重心-GTWR模型,在对空间格局进行长时间序列多维度指标分析的基础上,运用该模型依序对其特征进行驱动力解读,进而总结凝练京津冀区域发展的主导模式与城市核心驱动力。主要结论为：① 1990-2015年,京津冀城市群城镇用地扩展强度呈现“下降—上升—下降”的趋势,高峰时期在2005-2010年,在2005年之前高速发展城市集中在北京、天津、保定和廊坊,2005年之后集中在邢台和邯郸;② 城市群城镇用地重心虽呈现出发散态势,但城市之间的局部相互作用力逐渐增强,城镇用地扩展驱动力表现出空间溢出特征;③ 京津冀城市群空间发展模式由以北京和天津为中心的双核发展模式向多核发展模式转变,并出现北部资源运输核心、中部经济发展核心和南部投资发展核心三大功能核心组团,城市群趋向于多核功能协同发展模式;④ 重心-GTWR模型结合了时空非平稳性和城市空间相互作用,将城市群城镇用地扩展作为一个时空变化系统进行分析,经验证,该模型在城镇用地扩展格局驱动力分析研究中具有可行性。

Research into urban expansion patterns and their driving forces is of great significance. Under the background of the integrated development of the Beijing-Tianjin-Hebei (Jing-Jin-Ji) urban agglomeration, it is important to study the temporal and spatial patterns of urban land expansion and the driving forces development. This paper uses land-use data of the Jing-Jin-Ji urban agglomeration from 1990 to 2015 and reveals the multi-dimensional characteristics of the urban land expansion patterns. We then combine the urban spatial interaction and the spatial and temporal nonstationarity of the urban land expansion process and build the center of gravity-geographically and temporally weighted regression (GTWR) model by coupling the center of gravity model with the GTWR model. Using the center of gravity-GTWR model, we analyze the driving forces of urban land expansion at the city scale, and summarize the dominant mode and core driving forces of the Jing-Jin-Ji urban agglomeration. The results show that: (1) Between 1990 and 2015, the expansion intensity of the Jing-Jin-Ji urban agglomeration showed a down-up-down trend, and the peak period of expansion was in 2005-2010. Before 2005, high-speed development was seen in Beijing, Tianjin, Baoding, and Langfang, which were then followed by rapid development in Xingtai and Handan. (2) Although the center of gravity of cities in the Jing-Jin-Ji urban agglomeration showed a divergent trend, the local interaction between cities was enhanced, and the driving forces of urban land expansion showed a characteristic of spatial spillover. (3) The spatial development mode of the Jing-Jin-Ji urban agglomeration changed from a dual-core development mode to a multi-core development mode, which was made up of three function cores: the transportation core in the northern part, the economic development core in the central part, and the investment core in the southern part. The integrated development between functional cores led to the multi-core development mode. (4) The center of gravity-GTWR model analyzes urban land expansion as a space-time dynamic system. The model proved to be feasible in the analysis of the driving forces of urban land expansion.

The dynamics of the ethnic residential distribution in the Yaffo area of Tel Aviv, which is jointly occupied by Arab and Jewish residents, is simulated by means of an entity-based (EB) model. EB models consider householders as separate entities, whose residential behavior is defined by the properties of the surrounding infrastructure and of other householders. The power of the EB approach lies in its ability to interpret directly different forms of decisionmaker behavior in the model's terms. Several scenarios of residential interactions between members of local ethnic groups are compared on the basis of detailed georeferenced data taken from Israel's 1995 Population Census. The model simulates very closely the residential dynamics during the period 1955–95; the importance of the qualitative aspects of residential choice, as captured by the EB approach, is demonstrated by this correspondence.

The two prerequisites for monitoring SDG11.A “support positive economic, social and environmental links between urban, peri-urban and rural areas by strengthening national and regional development planning” are the classification of the urban–rural continuum and the extraction of spatial links. However, the complexity and diversity of urban patch distribution make it difficult to achieve a global rapid assessment. Based on the self-developed high-resolution global impervious surface area 2021 (Hi-GISA 2021) product, this study combined the complex network with remote sensing technology to propose a new method to delineate and evaluate the pattern and inner spatial links of the urban–rural continuum for five typical urban agglomerations in China, including the Beijing–Tianjin–Hebei urban agglomeration (BTHUA), the Yangtze River Delta urban agglomeration (YRDUA), the Greater Bay Area (GBAUA), the Chengdu–Chongqing urban agglomeration (CYUA), and the Middle Reaches of Yangtze River urban agglomeration (MRYRUA). The research results are in good agreement with Chinese government documents. First, the five urban agglomerations are all small-world networks with a low degree of overall polycentricity, and the urbanization degrees of GBAUA and YRDUA are higher than BTHUA, CYUA, and MRYRUA. Second, the imbalanced development of YRDUA is higher than the other regions, and the siphon effects of BTHUA and MRYRUA are more significant than YRDUA, CYUA, and GBAUA. Third, some multi-centers show significant siphon effects. The urbanization degree is highly correlated with the urbanization potential but not positively correlated with the degree of balanced development. The results can provide data, methods, and technical support for monitoring and evaluating SDG11.A.

Local differential privacy has become the gold-standard of privacy literature for gathering or releasing sensitive individual data points in a privacy-preserving manner. However, locally differential data can twist the probability density of the data because of the additive noise used to ensure privacy. In fact, the density of privacy-preserving data (no matter how many samples we gather) is always flatter in comparison with the density function of the original data points due to convolution with privacy-preserving noise density function. The effect is especially more pronounced when using slow-decaying privacy-preserving noises, such as the Laplace noise. This can result in under/over-estimation of the heavy-hitters. This is an important challenge facing social scientists due to the use of differential privacy in the 2020 Census in the United States. In this paper, we develop density estimation methods using smoothing kernels. We use the framework of deconvoluting kernel density estimators to remove the effect of privacy-preserving noise. This approach also allows us to adapt the results from non-parametric regression with errors-in-variables to develop regression models based on locally differentially private data. We demonstrate the performance of the developed methods on financial and demographic datasets.

With the capacity to represent irregular geographical entities precisely, vector‐based cellular automata (VCA) have been extensively employed in urban land change simulation at the land parcel level. However, while more driving factors are considered, modeling the complicated nonlinear relationship between land parcel attributes and multiple land‐use changes is increasingly difficult. Moreover, in VCA, the driving factors are unstructured and cannot be directly modeled by traditional deep learning methods, which can only be applied to structured data processing. In order to address these problems, a new VCA model DF‐VCA that adopts the deep forest (DF) algorithm for mining CA transition rules was proposed to simulate urban land‐use change at the parcel level. The DF algorithm is a new deep learning method that can directly mine high‐level features from unstructured data and obtain accurate land‐use transition rules. The proposed DF‐VCA model was applied to simulate the urban land change in Shenzhen, China. Compared with several traditional VCA models, the DF‐VCA model achieved the best simulation performance at parcel‐level (Figure of Merit = 39.88%), pattern‐level (similarity = 96.47%), and community‐level (correlation coefficient = 0.9269). The results show that the DF‐VCA model with strong representative learning ability could simulate urban land change at fine scales precisely. Furthermore, the proposed DF‐VCA model was applied in Shenzhen's future land change simulations to guide sustainable urban development.

Land-use change is a typical geographic evolutionary process characterized by spatial heterogeneity. As such, the driving factors, conversion rules, and rate of change vary for different regions around the world. However, most cellular automata (CA) models use the same transition rules for all cells in the model space when simulating land-use change. Thus, spatial heterogeneity change is ignored in the model, which means that these models are prone to over- or under simulation, resulting in a large deviation from reality. An effective means of accounting for the influence of spatial heterogeneity on the quality of the CA model is to establish a partitioned model based on cellular space partitioning. This study established a partitioned, dual-constrained CA model using the area-weighted frequency of land-use change (AWFLUC) to capture its spatial heterogeneity. This model was used to simulate the land-use evolution of the Dianchi Lake watershed. First, the CA space was divided into subzones using a dual-constrained spatial clustering method. Second, an artificial neural network (ANN) was used to automatically acquire conversion rules to construct an ANN-CA model of land-use change. Finally, land-use changes were simulated using the ANN-CA model based on data from 2006 to 2016, and model reliability was validated. The experimental results showed that compared with the non-partitioned CA model, the partitioned counterpart was able to improve the accuracy of land-use change simulation significantly. Furthermore, AWFLUC is an important indicator of the spatial heterogeneity of land-use change. The shapes of the division spaces were more similar to reality and the simulation accuracy was higher when AWFLUC was considered as a land-use change characteristic.