Nowadays, cities have emerged as one of the core elements for the sustainable development of human society. This also aligns well with the United Nations Sustainable Development Goals on sustainable cities. The pivotal role of cities is also demonstrated by the rapid development of big data and artificial intelligence technologies. There have been more and more studies dedicated to the realm of data-driven urban sustainability, in which the complex processes of urban sustainable development, encompassing social, economic, and ecological dimensions, are monitored, interpreted, and evaluated through massive urban data from multiple sources. However, a common limitation is that most existing studies concentrate on individual application scenarios and singular data sources and ignore the intricate interconnections among diverse urban data sources and multiple urban elements, making it challenging to explore findings across diverse urban sustainability contexts. Therefore, to address this critical gap, in this paper, we propose a novel approach for urban sustainable development driven by Urban Business Area/Region Knowledge Graph (UKG). This approach incudes two fundamental steps: the construction of a comprehensive ontology for the UKG based on massive multi-source urban data, and the subsequent synthesis of knowledge guided by this ontology to create the UKG. The construction of the UKG ontology captures important elements in cities as well as their complex interconnections, e.g., people, locations, and organizations, and their relationships in terms of spatiality, function, and association. This ontological architecture lays the foundation for the subsequent knowledge fusion, ultimately leading to the construction of UKG. The practical applications of UKG in driving urban sustainability are manifold, ranging from real-time status monitoring and nuanced interpretation of urban phenomena to the holistic evaluation of decisions made for urban sustainability. To verify the effectiveness and efficiency of the proposed approach, the paper introduces a novel cross-modality contrastive learning framework that incorporates semantic knowledge for urban sustainability. The proposed framework includes a semantic encoder and a visual encoder to capture information from UKG and urban images (satellite images and street view images), respectively. Based on the assumption that the semantic representation of UKG entities should be close to their corresponding image representations, the proposed framework successfully incorporate semantic knowledge into visual encoder, which further enhances the predictive capabilities of urban socioeconomic indicators derived from urban images. Through empirical validation, this study demonstrates the real-world applicability and generalizability of the UKG framework for urban sustainability.

Urban areas often suffer from varying degrees of land surface deformation due to infrastructure construction and resources exploitation, which threatens the safety of residents' lives and property. So regular monitoring of urban surface deformation is of great significance for preventing related geological disasters. However, urban surface deformation has the characteristics of small-scale and continuous-slow change, it is necessary to process the error carefully in order to improve the monitoring accuracy. This paper proposes a high-precision surface deformation extraction method combining the principal component spatiotemporal analysis and time-series Interferometric Synthetic Aperture Radar (InSAR). Through the mining and analysis of time-series InSAR signals, a surface deformation model combined with polynomial functions is constructed to realize the hierarchical estimation of error and noise signals. Then the high-precision, small-scale surface deformation information is extracted. Taking Xuzhou, a typical city prone to geological disasters, as the research area, the results show that the proposed method can accurately separate the surface deformation information and error in the time-series InSAR signal, and the deformation monitoring accuracy is 10%~57% higher than other existing methods. The deformation rate from 2018 to 2022 is about -17~35 mm/a in Xuzhou, which is mainly distributed in the urban area, along the subway and in the old goaf. In recent 8 years, urban construction has continuously triggered local subsidence areas, the secondary deformation of the old goaf can last for more than 6 years, and the surface of several mining areas is still in an unstable state. The results can provide important technical support and decision support for high-precision monitoring of urban surface deformation and prevention of potential geological disasters.

The segmentation of fruit tree canopy based on Unmanned Aerial Vehicle (UAV) visible spectral images is greatly influenced by complex background information such as topographic relief, shrubs, and weeds. Although existing deep neural networks can improve the robustness of canopy segmentation to a certain extent, they ignore the global context and local detailed information of the canopy due to limited receptive field and information interaction, which restricts the improvement of canopy segmentation accuracy. To address these issues, this paper introduces the Canopy Height Model (CHM) and deep learning algorithms, and proposes a fruit tree canopy segmentation method that couples Convolutional Neural Networks (CNN) and Attention Mechanisms (AM) based on UAV photogrammetry. This method first constructs a coupled deep neural network based on CNN and AM through transfer learning to extract both the local and global high-level contextual features of fruit tree canopies. Meanwhile, considering the correlation between deep semantic features and the position information of fruit tree canopies, a local and global feature fusion module is designed to achieve collaborative tree canopy segmentation of attributes and spatial positions. Taking the citrus tree canopy segmentation as an example, the experimental results demonstrate that the use of the CHM can effectively suppress the influence of topographic relief. Our proposed method can also significantly reduce the interference of underlying weeds or shrubs on canopy segmentation, and achieves the highest Overall Accuracy (OA), F1 score, and mean Intersection over Union (mIoU) of 97.57%, 95.49%, and 94.05%, respectively. Compared with other state-of-the-art networks such as SegFormer, SETR_PUP,TransUNet, TransFuse, and CCTNet, the mIoU obtained by the proposed method increases by 1.79%, 8.83%, 1.16%, 1.43%, and 1.85%, respectively. The proposed method can achieve high-precision segmentation of fruit tree canopies with complex background information, which has important practical value for understanding the growth status of fruit trees and fine management of orchards.

The explosive growth of multisource Remote Sensing (RS) data poses challenges to the application of fusion analysis. Discrete Global Grid System (DGGS) is a digital earth reference model supporting integration and analysis of multisource and multiscale geospatial data. In this study, a Rhombic Triacontahedron (RT) hexagonal DGGS is chosen as the basic digital framework to improve the overall fitting accuracy to the Earth and the spatial sampling efficiency of the grid which is conceptually equivalent to pixel. A mathematical model of hexagonal pixels of RS images is established, and the storage scheme of hexagonal pixels compatible with open-standard format is also proposed. First, the RS images are gridded according to the geographical location, and the hexagonal DGGS modeling of RS image was completed. Secondly, a rigorous correspondence between hexagon and rectangular pixels is established geometrically to preserve the neighborhood information of hexagon pixels by improving the way of double offset coordinates mapped to the rectangular array. Then, the GeoTIFF open-standard format is used to accurately store the hexagonal pixel values, projection and transformation parameters. Finally, a multiscale hexagonal DGGS generation algorithm based on the hexagonal DGGS standard dataset is designed. Experiment results show that using RT hexagonal equal area grid to organize global scale RS images can realize uniform sampling of global data, ensure the overall consistency of cells in different latitudes, avoid drastic changes of cells in high latitudes, and be more suitable for global scale data processing and analysis. The proposed storage scheme can not only ensure that the hexagon pixel RS image dataset is compatible with the standard file format, but also ensure that the rectangular pixels correspond to the hexagon pixels one by one. Hexagonal pixels could be stored in the open-standard format GeoTIFF with a fixed pattern in the form of rectangular arrays for data access, with transformation parameters and metadata used to reconstruct the hexagons. The image information and spatial distribution characteristics of hexagonal DGGS data are preserved well, which is more advantageous than the Soil Moisture and Ocean Salinity (SMOS) data organization scheme. This scheme break through the hexagonal with rectangular pixels in RS image data organization barriers, GIS/RS software that can be read using common hexagon pixels in RS image, and can complete the hexagonal pixels by the operation of the rectangular pixel equivalent processing, is expected to promote hexagon global discrete grid systems in RS data organization, processing, sharing, and other applications.