Traditional Geographic Information Systems (GIS) represent the environment under reductionist thinking, which disaggregates a geographic environment into independent geographic themes. The reductionist approach makes the spatiotemporal characteristics of geo-features explicit, but neglects the holistic nature of the environment, such as the hierarchical structure and interactions among environmental elements. To fill this gap, we integrate the concept geographic scenario with the fundamental principles of General System Theory to realize the environmental complexity in GIS. With the integration, a geographic scenario constitutes a hierarchy of spatiotemporal frameworks for organizing environmental elements and subserving the exploration of their relationships. Furthermore, we propose geo-characterization with ontological commitments to both static and dynamic properties of a geographic scenario and prescribe spatial, temporal, semantic, interactive, and causal relationships among environmental elements. We have tested the utility of the proposed representation in OWL and the associated reasoning process in Semantic Web Rule Language (SWRL) rules in a case study in Nanjing, China. The case study represents Nanjing and the Nanjing presidential palace to demonstrate the connections among environmental elements in different scenarios and the support for information queries, evolution process simulation, and semantic inferences. The proposed representation encodes geographic knowledge of the environment, makes the interactions among environmental elements explicit, supports geographic process simulation, opens opportunities for deep knowledge mining, and grounds a foundation for GeoAI to discover geographic complexity and dynamics beyond the support of conventional theme-centric inquiries in GIS.

Beijing is one of the most developed cities in China and has experienced a series of environmental problems. In accordance with the Major Function Zone planning, Beijing is divided into four zones in an attempt to coordinate development between urban areas and the eco-environment. Classic coupling model uses statistical data to evaluate the interactions of these two subsystems; however, it lacks the capability to express dynamic changes to land cover. Thus, we extracted land cover data from Landsat images and examined the urbanization and eco-environment level as well as the coupling coordination in Beijing and its functional zones. The main conclusions are as follows. (1) Between 2001 and 2011, both urbanization and the eco-environment level in Beijing and its functional zones grew steadily. Different zones coordinated together according to their own characteristics, and the overall coupling coordination of the city transformed from the “basically balanced” to the “superiorly balanced” stage of development. (2) After 2011, the condition of the eco-environment worsened in Beijing and in most of the function zones, while the coordination between increased urbanization and the worsened eco-environment may be a result of environmental lag. This study integrated land cover data into the coupling mode and fully utilized the advantages of spatiotemporal analysis and the coupling model. In other words, the spatiotemporal analysis explains the land cover changes visually over the research period, while the coupling model explores the interaction mechanisms between urbanization and the eco-environment. The land cover data enriches the coupling theory and provides a reference for evaluating the effectiveness of local development policy.

In current research, fully supervised Deep Learning (DL) techniques are employed to train a segmentation network to be applied to point clouds of buildings. However, training such networks requires large amounts of fine-labeled buildings’ point-cloud data, presenting a major challenge in practice because they are difficult to obtain. Consequently, the application of fully supervised DL for semantic segmentation of buildings’ point clouds at LoD3 level is severely limited. In order to reduce the number of required annotated labels, we proposed a novel label-efficient DL network that obtains per-point semantic labels of LoD3 buildings’ point clouds with limited supervision, named 3DLEB-Net. In general, it consists of two steps. The first step (Autoencoder, AE) is composed of a Dynamic Graph Convolutional Neural Network (DGCNN) encoder and a folding-based decoder. It is designed to extract discriminative global and local features from input point clouds by faithfully reconstructing them without any label. The second step is the semantic segmentation network. By supplying a small amount of task-specific supervision, a segmentation network is proposed for semantically segmenting the encoded features acquired from the pre-trained AE. Experimentally, we evaluated our approach based on the Architectural Cultural Heritage (ArCH) dataset. Compared to the fully supervised DL methods, we found that our model achieved state-of-the-art results on the unseen scenes, with only 10% of labeled training data from fully supervised methods as input. Moreover, we conducted a series of ablation studies to show the effectiveness of the design choices of our model.

Considerable attention has been paid to geographic process-based studies in geographic information science research. Finding appropriate methods to express geographic processes is challenging, and working to reveal the dynamic evolution and underlying mechanisms behind these processes is worthwhile. This research proposes a process-centric ontology model that describes the geographical environment from three perspectives, namely, geographic scenes, geographic processes and geographic elements. These three aspects are combined to represent the dynamic changes of geographic phenomena. This research proposes a framework and constructs ten sub-ontologies. These sub-ontologies include the Element ontology, Scene ontology, and Process ontology. A soil erosion process is then selected to demonstrate the applicability of this framework. The entire process is divided into three sub-processes (detachment, transport and deposition), and each sub-process is described by identifying when and where the process occurred, the elements and their reactions, and the changes in the geographic scene. Different relationships among elements, scenes and processes are defined to explain how and why soil erosion occurred. This proposed approach can reveal the underlying mechanisms of geographic scenes, can be used to explore the occurrence and causes of geographic processes and support the complex representation of geographic elements.