Territorial spatial planning is the spatial blueprint of high-quality social and economic development. With the rapid development of geo-information science and technology, geo-information science and tech- nology has changed the way of territorial spatial planning. Its powerful capability in data acquisition, analysis, prediction, and management provides support in data, method, and platform for territorial spatial planning, thus enabling territorial spatial planning to be more scientific, operable, and forward-looking. Based on literature review, summary, and comparative analysis, this study analyzes the technical requirements of territorial spatial planning compilation, implementation, supervision, public participation, and intelligent transformation, and systematically expounded the application of geo-information science and technology in territorial spatial planning. This study expounds the contributions of geo-information science on China's territorial spatial planning from the following three aspects: (1) Geospatial data, remote sensing data, and socio-economic big data provide data basis for territorial spatial planning; (2) Geographic Information System (GIS) analysis method, geographic simulation method, and artificial intelligence method provide method support for territorial spatial planning; (3) The application of GIS platform, cloud computing, and urban intelligent platform promotes the intelligent transformation of territorial spatial planning. This study also points out shortages of different technologies. However, there are still some problems that need to be further explored: (1) The generation of socio-economic big data and its application scenarios in territorial spatial planning are concentrated in urban space; (2) Both traditional and modern technologies in territorial spatial planning have advantages and disadvantages. These technologies need to be effectively integrated to prepare more scientific territorial spatial planning; (3) The construction of territorial spatial planning platform has not been organically combined with the construction of City Information Modeling (CIM) and other intelligent society platforms, there is a huge space for mining in the future. According to the maturity of its application in territorial spatial planning, these technologies can be divided into mature technology and promising technology. With the promulgation of territorial spatial planning at all levels and types and the initial establishment of Chinese territorial spatial planning system in 2021, attention should be paid to the application of intelligent planning methods in agricultural space and ecological space, technical system construction of intelligent territorial spatial planning, and the improvement of territorial spatial planning intellectualization.

Under the background of territorial spatial planning in the new period, delimiting the urban development boundary scientifically and reasonably and establishing a sound territorial space use control system are important measures to guide all kinds of territorial space development and protection. Taking Fuzhou City as an example, this paper constructs a global multi-dimensional territorial space control system. Management and control constraints are embedded in the future land use pattern simulation. At the same time, considering the regional spatial heterogeneity and spatial-temporal dependence, this paper designs the Spatial-temporal Cellular Automata (ST-CA) model which integrates geographical partition strategy, deep learning technology, and the functional module of FLUS model to delimit the urban development boundary. Based on the existing achievements, this study integrates three zones and three lines to carry out the application research of spatial management and control under the thinking of "combination of planning and control". The results show that: (1) The ST-CA model considering regional spatial heterogeneity and spatial-temporal dependence can effectively improve the accuracy of land use change simulation and achieve a more realistic and accurate geographical simulation process. The overall accuracy of the model increased from 95.95% to 98.34%; (2) Control constraints are embedded in the process of geographical simulation, which can guide the rational layout and controllable scale of urban, agricultural, and ecological spaces. Delimitation of urban development boundary based on simulation results can effectively avoid occupation on protected land; (3) The future simulation results combined with the control early warning value show that the urban expansion situation in the main urban area and surrounding districts and counties of Fuzhou City is relatively severe. In the future, it is urgent to reasonably regulate the territorial space pattern of Fuzhou City; (4) The characteristics of boundary change trend show that the delimitation results are consistent with the long-term development planning of Fuzhou City, which is in line with regional development demands. The territorial space pattern presents a multi-axis development trend. The research results can provide scientific planning for the development and protection of territorial space and practical reference for territorial space control and optimization in Fuzhou City.

In the context of global climate change, extreme precipitation events are becoming more frequent and have an increasing impact on urban commutes. In this study, based on hourly rainfall data and metro OD passenger flow data, we use a prophet time-series model to forecast the regular values of commuting flow under rainfall events, and quantitatively assess the spatial-temporal changes of commuting flow caused by rainfall at station and OD levels. Our results show that (1) the commuting flow generally tends to decrease with increasing hourly rainfall. The fluctuation of commuting flow varies from one type of station to another. Rainfall can delay commuting departure time and lead to surge in metro flow in certain times. The higher the commuting demand for a station, the more its flow fluctuates. Flow fluctuation due to rainfall varies in different time periods. 7:00 and 17:00 show high fluctuation with more flexibility in commuting departure time, while 8:00—9:00 and 18:00—19:00 show high rigidity; (2) Rainfall can induce a significant increase in short commuting flow of less than 15 minutes, averaging to around 7.3%. In contrast, the impact on medium and long commuting flow is modest, with an overall decrease of 1.3%. Of the OD flows across various functional zones, fluctuation from residential to industrial stations is most notable during the morning commute, while less so from commercial to residential stations during the evening commute. Most of the departure stations of rainfall-sensitive metro lines during the morning commute are located around large residential areas, and around large industrial parks and commercial centers during the evening commute. Flow fluctuation in the evening commute is lower than that in the morning commute. Although total commuting flow is not significantly affected by rainfall, its surge in certain local regions and times should be highlighted. Our methodology and results will help to quantify the impact of rainfall on metro commutes and provide a basis for spatialized transport coping strategies.

For the current territory development planning in China, the Ministry of Natural Resources has put forward a method to evaluate the accessibility of urban centers based on isochrone maps. The use of dynamic traffic data in isochrone maps studies is becoming more and more recurrent, but comparative analyses between dynamic and static data are still rare. In this paper, Nanchang city is taken as a case study to generate the urban center isochrone maps using static and dynamic traffic data. The city is divided into 500 m×500 m grids, with each grid center point representing a given destination while Bayi Square and Greenland Central Square are set as origins. Using the above origins and destinations, the dynamic data were obtained daily from the Baidu open map platform at 15:00 and at 18:00 over nine days-time (Saturday-next Sunday). Subsequently, the confusion matrix and Kappa coefficient are used to test the consistency between the isochrone maps generated by the two datasets. The results suggest that most of Nanchang urban central areas are within a 60 min-circle and most of Nanchang's urban areas are within a 120 min-circle, when taking Bayi Square or Greenland Central Square as the origin. The isochrone maps generated by the static data has just a fair consistency with those generated by the dynamic data at evening peak time on workdays. Within the urban central areas, the isochrone maps generated by the static data have reached a substantial consistency with those generated by the dynamic data at off-peak time on workdays, indicating that the static data is more suitable for evaluating the urban center accessibility at off-peak time on workdays. Besides, the dynamic data can display the temporal characteristics of the isochrone maps. The isochrone maps of the dynamic data at 4 time-points show that the urban center accessibility at 15:00 on workdays is significantly better than others. But the proportions of isochrone surfaces to the total urban areas are found to increase with the drivetime, and their growth curves are in accordance with the trend of the Logistic curve. The key time nodes of each growth curve can provide more targeted division thresholds for isochrone maps. This research highlights the accuracy of the isochrone maps generated by the dynamic data and explores the applicability of the static data. The research also shows that using the key time nodes of the Logistic curve contributes to a more reasonable subdivision of the isochrone map.

With the rapid development of urbanization, urban construction land is becoming increasingly scarce. Therefore, as a macro-regulation policy for the intensive utilization and optimal allocation of land resources, land reserve is playing an increasingly important role. However, at present, land reserve decision-making lacks scientific basis and cannot effectively carry out resource allocation. In order to solve this problem, this paper puts forward seven intelligent decision-making models for land reserve through in-depth analysis of the basic services and decision-making processes of land reserves. The models are listed below. Firstly, Stock Land Monitoring Model based on the comprehensive quantitative evaluation method, which can dynamically monitor and discover the city stock land and then make recommendations for land reserve objects. Secondly, Land Reserve Cost Prediction Model based on the market comparison method, which can carry out a large range and efficiently predict the cost of stock land. Thirdly, Land Sale Price Prediction Model based on the Support Vector Machine (SVM), which can predict the reserve income of the land to be sold. Fourthly, Land Reserve Balance Analysis Model based on the gray forecast model, which can predict the amount of land reserve to promote coordinated regional development. Fifthly, Similar Land Query Model based on the comprehensive quantitative evaluation method, which can promote large-scale land development to form an agglomeration effect. Sixthly, Development Sequence Analysis Model based on the comprehensive quantitative evaluation method, which can optimize the spatial structure and formulate a reasonable development sequence to promote the continuous rolling of funds. Seventhly, Abnormal Land Identification Model based on spatial overlay analysis, which can improve the detection efficiency of various problematic plots. The purpose of this model set is to make the land reserve decision-making process scientific, quantitative, and model-based, which focuses on providing instructions for the overall arrangement of total land reserve, benefit, scale, structure, layout, and time sequence. In addition, through theoretical analysis and practical verification, we found that the model set has the characteristics of systematization, high efficiency, flexibility, and intelligence. It can serve the entire chain of land reserve service, meet the needs of real-time decision-making applications, and realize the independent update and evolution to ensure the timeliness of model computation. Finally, the model set has been engineered and applied to the Ningbo Land Reserve Intelligent Decision Support Platform. The effectiveness and practicality of the above decision-making models have been verified by simulating the entire land reserve decision-making processes based on this platform, indicating that the model set can provide a theoretical basis for the scientific decision-making of land reserves.

The extraction and change analysis of cultivated land covers based on multi-temporal images are important means to effectively manage and protect cultivated land resources. However, as far as the classification and extraction of multi-temporal cultivated land covers are concerned, the existing methods have limitations in the comprehensive expression of spatiotemporal features and the accurate modeling of spatiotemporal context relations among geographic objects, leading to the poor extraction accuracy of cultivated land covers. In addition, for the analysis of cultivated land change, the existing methods usually only focus on the statistical areal change of cultivated land cover based on administrative units, while consideration is seldom taken into the spatial correlation distribution characteristics of changes in cultivated land covers. Accordingly, first of all, this paper proposes a multi-temporal spatiotemporal context classification method, which comprehensively expresses and utilizes the multi-temporal spectral, texture, and spatial features of geographic objects, and models the contextual relations of features and semantics among geographic objects in both spatial and temporal dimensions of multi-temporal images, so as to improve the classification accuracy of cultivated land covers. Then, based on the extracted results of cultivated land covers, spatial statistical method of Geographic Information System (GIS) is used to analyze the spatial correlation characteristics of cultivated land changes in regular grids and administrative division units. Finally, Shunyi District of Beijing is taken as the study area while multi-temporal Sentinel-2 images in 2015-2019 are used as the data sources to conduct verification of the proposed method. The results show that, compared with the two existing common multi-temporal classification methods, the proposed method achieves the highest accuracies in the classification of multi-temporal cultivated lands. The average user's accuracy and producer's accuracy reach 91.21% and 90.53%, respectively, while the overall accuracy of all categories is 90.79%, indicating that the proposed method can accurately extract the multi-temporal cultivated land cover information. Furthermore, according to the analysis of the spatial distribution characteristics of cultivated land changes, this study found a phenomenon of regional aggregation of the cultivated land change in Shunyi District from 2015 to 2019, which mainly presents the characteristics of concentrated reduction. The aggregation reduction phenomena of cultivated land covers in Zhaoquanying Town, Gaoliying Town, Mulin Town, and Yang Town are especially obvious, indicating that the problems of cultivated land encroachment and reduction are quite serious in these areas.

Information empowerment to the territorial spatial planning has become a hot research field in the new era. However, research on territorial utilization evaluation using big data integration remains to be explored. The purpose of this paper is to carry out an empirical study on the efficiency assessment of residential land use in new urban area employing Tencent location-based big data. Assessment index of residential land use efficiency in each residential area have been proposed, supported by integration of multi-source geospatial data, to reveal the differences in land use efficiency among different residential areas in Changzhou city. The results show that, firstly, population size of hourly particle statistics within the residential area fluctuates periodically, reaching peak value at 21:00 generally, which is in line with the routine of daily going out and returning home for urban residents. There are also expected differences in population agglomeration degree and population size among residential buildings with different capacity rates. Secondly, the 29 residential areas are divided into five groups by year of construction, 1980s, 1990s, 2000s, 2010—2015, and post-2015. The average population size of efficiency index of group 1980s, 1990s, 2000s, 2010—2015, and post-2015 are 1.74, 2.45, 2.31, 0.95, and 0.91 per 100 m², respectively. Index values of residential areas built before 2010 are significantly higher than those built after 2010. Furthermore, residential areas built after 2010 are lower than the average level (population size of 2.06 per 100 m²in year 2018) of the entire urban residential areas. Thirdly, it is suggested that lower results of efficiency index is not fully equal to poor level of intensive land use. The main reasons of diverse land use efficiency of residential areas constructed in different periods include the growth periodicity of new urban area development in Changzhou city, and urban residents' desire for better living environment to enhance their quality of habitation. Research shows that location-based big data, as a source of population data with high solution, could reflect the temporal and spatial characteristics of resident aggregations objectively. Index constructed to assess urban residential land efficiency using location-based big data is both innovative and scientific, which could provide a new way for the analysis of high-quality land space utilization. In conclusion, regularity recognition of behavior characteristics from urban residents can provide support for spatial policy formulation during the urbanization process based on "putting people first" policy in China. What's more, new data sources, represented by location-based big data in this paper, will play an important role in decision-making mechanism of territorial spatial planning.

The essence of integrated territory consolidation is the process of readjusting the relationship between man and land. Under the background of rural revitalization strategy, integrated territory consolidation has been endowed with multiple functions and objectives. Pattern optimization, which contains the comprehensive process of timing arrangement, spatial organization, and goal coordination, is a way to achieve multi-objective integrated territory consolidation. This research analyzes the problem of multi-objective quantification for optimization of spatio-temporal patterns of multi-objective integrated territory consolidation. Using spatial vulnerability and timing urgency as the key points, the index system of social-ecosystem vulnerability and urgency evaluation in rural regions with target function as the main line was constructed. The EW-DEA model and improved multi-factor synthesis model of entropy weight were used to comprehensively evaluate vulnerability efficiency and urgency. Then, the hierarchical objective decomposition method and the attribution method of leading problems were used to construct four kinds of multi-objective pattern optimization of rural integrated territory consolidation. Four plans of prosperity of industrial plan, optimization of structure plan, ecological livability plan, and comprehensive rejuvenation plan, and quantitative analysis of multi-objective optimal decision were carried out using EW-TOPSIS analysis method. This research would achieve the goals of identifying and dividing the types of multi-objective pattern optimization of rural integrated territory consolidation from the perspective of limited multi-objective system selection and ranking, as well as to realize the purpose of constructing multi-objective pattern optimization system for rural integrated territory consolidation. This research took 184 administrative villages in Qingpu District of Shanghai City as examples and the following results were obtained. Firstly, EW-DEA model can effectively overcome the problem of high correlation between multiple administrative villages and improve the application accuracy of spatial suitability. EW-TOPSIS model can accurately divide the multi-objective pattern optimization scheme of rural integrated territory consolidation and refine the heterogeneity among the optimal schemes. Secondly, the mean value of social-ecosystem vulnerability of Qingpu District in the year of 2018 was shown as social subsystem vulnerability (0.605) > economic subsystem vulnerability (0.577)>ecosystem vulnerability (0.549). Vulnerability of social subsystems was an important reason for limiting vulnerability in the region. Thirdly, the vulnerability of social-ecosystem in administrative villages was increasing from central to north-south parts of the region, while the spatial agglomeration of the urgency of rural integrated territory consolidation was significant, with its threshold in [0.435, 0.785]. The urgency of agricultural industry was the maximum. Fourthly, according to the results of multi-objective decision-making evaluation of four multi-objective schemes based on vulnerability and urgency, pattern optimization types of rural integrated territory consolidation in Qingpu District can be divided into 16 types. The research results enrich the theory of rural geography and provide decision basis for rural regional governance, rural revitalization, and regional sustainable development.