Image super-resolution technology enhances image clarity and enriches image detail by improving image spatial resolution, enabling quality enhancement without changing hardware conditions. Given the large size, complex target features, and abundant details of remote sensing images, along with the need for efficient information acquisition, we propose a Diffusion Super-Resolution (DSR) algorithm based on a conditional diffusion model. This approach uses low-resolution remote sensing images from the same region as conditioning inputs to the diffusion model, while high-resolution images with added noise are concatenated as inputs. A deep noise training network was constructed with U-Net as the backbone, incorporating residual connections and self-attention mechanisms. The loss function was also improved for better super-resolution results. The DSR method was tested using high-resolution remote sensing images from multiple periods of the domestic Gaofen and SuperView satellite series. The super-resolution results demonstrated pixel dimension expansion from 32 to 128. Comparative experiments with Bicubic, SRGAN, Real-ESRGAN, and SwinIR super-resolution algorithms showed that the DSR method outperforms these algorithms in both PSNR and SSIM metrics. Additionally, the DSR method significantly improves the quality of multispectral remote sensing images. By leveraging the conditional diffusion model, it successfully preserves rich detail and enhances spatial resolution without compromising image clarity. This method offers an efficient solution for super-resolution reconstruction, ensuring effective information acquisition in remote sensing applications and fulfilling the requirements of various domains such as land use classification, environmental monitoring, and urban planning. Moreover, the DSR method also opens new avenues for future research by demonstrating the potential of diffusion models in remote sensing image processing. It overcomes the limitations of simple convolutional networks, which extract only shallow features, and avoids the convergence issues commonly seen in adversarial neural networks during training, ultimately improving the restoration of rich details in remote sensing images.

Compared with urban rainstorm hazardous events (such as waterlogging, flood, debris flow, etc.), existing studies pay less attention to the feature composition and objective assessment of risks associated with small-scale and diversified rainstorm cascading events (such as house damage, subway inundation, etc.), making is difficult to meet the goals of refined city management. At the same time, constructing risk assessment models for rainstorm cascading events faces constraints due to incomplete risk features in sample data. To address these issues, this paper proposes a risk assessment model for urban rainstorm cascading events that integrates risk features and spatial features, considering the spatial correlation between them. Firstly, for the risk scenarios of different rainstorm cascading events, the risk features are extracted from data sources such as grassroots officials' inspection, citizen reporting, and social media posts. Secondly, using the spatial localization of the original risk samples as a connection, an improved marginal Fisher method is employed to mine spatial features from multi-source spatial data to supplement the missing risk features. Finally, using a machine learning approach, the relationship between risk features and risk categories is established, leading to the construction of a risk assessment model for multi-category rainstorm cascading events. Experimental results from Wuhan, Hubei Province, China, show that the proposed method effectively addresses the problem of incomplete features in the construction of risk feature models through multi-source spatial feature mining, enabling the construction of diversified rainstorm cascading event risk assessment models. The overall accuracy, F₁-score and AUC increased by 23%, 24%, and 25%, respectively. Additionally, the complexity and diversity of spatial features highlighted the risks of subjective and arbitrary feature fusion, which can negatively affect the performance of machine learning model construction by adding irrelevant features. The proposed method mitigates this issue with an adaptive feature selection approach. Furthermore, grassroots officials’ inspection records contributed the most to the construction of urban rainstorm cascading event risk assessment models, followed by citizen-reported texts, and finally, social media data. Compared to traditional disaster event risk assessment methods, urban rainstorm cascading event risks have smaller risk granularity and involve more complex and diverse risk types and features. Traditional comprehensive evaluation models face challenges of subjectivity in manual evaluation, while traditional disaster loss curve methods encounter high experimental costs and data scarcity. The method proposed in this paper utilizes objective data to generate multidimensional risk features and establishes relationships between diverse risk levels, resulting in a machine learning-based risk prediction model that is more suitable for small-scale risk assessment scenarios.

Community jurisdictional boundaries are pivotal in the context of smart communities, where their prompt and accurate delineation is critical for providing high-quality grassroots services. Currently, the delineation of these boundaries relies heavily on manual labeling by grassroots workers, which poses considerable challenges, including substantial data collection barriers and delays in updating information. Utilizing spatially associated points within community jurisdictions offers a promising approach to address the complexities involved in generating accurate community boundaries. In this paper, we propose CB-GCN, a novel community boundary generation algorithm that integrates volunteered geographic information with graph neural network. This approach ensures the generation of high-quality, cost-effective, and timely community boundaries, even in the presence of complex point distributions and intricate regional divisions. CB-GCN consists of three fundamental components: semantic spatial feature extraction, spatial relationship graph construction, and jurisdictional area affiliation inference. In the initial phase of semantic feature extraction, the city area is partitioned into blocks using a multi-level road network. These blocks are then divided into spatial units based on the spatial coordinates of individual buildings. The use of semantic Areas of Interest (AOIs) and the multi-level road network blocks facilitates the extraction of containment and adjacency relationships between spatial units, which are crucial for constructing the spatial relation graph. During the phase of spatial relationship graph construction, edges are established between spatial units according to the extracted spatial semantic relationships, resulting in a comprehensive spatial relationship graph. The affiliation inference phase involves inferring proximity relationships between spatial units using graph convolutional networks. Spatially related point features of neighboring nodes are then aggregated with weighted adjustments based on these proximity relationships to accurately determine community affiliations. Based on the aggregation results, community affiliations of spatial units are classified, leading to the identification of definitive community jurisdictional boundaries. Experimental results demonstrate that CB-GCN substantially outperforms baseline methods in generating community jurisdictional boundaries, achieving notable improvements of 9.4% in F1-score and 14.4% in Intersection over Union (IoU). CB-GCN has also proven effective in complex scenarios involving fragmented jurisdictional areas, such as when a single AOI is intersected by multiple jurisdictional regions. Furthermore, CB-GCN can effectively generating regional AOIs despite variations in building distribution patterns and densities. By automating the generation of community jurisdictional boundaries, CB-GCN significantly enhances the efficiency of producing community boundary interest areas, representing a substantial advancement in boundary delineation methodologies.

Realizing convenient transfers between subway and regular bus systems is fundamental to advancing the integration and development of these two transportation networks, which is crucial for constructing a multi-modal and accessible public transportation system. This paper takes Shenzhen as a case study and innovatively combines mobile phone signal data with IC card data to identify the transfer characteristics between subway and regular bus systems. These characteristics include temporal and distance aspects, which effectively illustrate the daily travel patterns of transfer passengers. Through a detailed analysis of the overall transfer characteristics, this study establishes a distance threshold to estimate potential transfer demand and the gap in transfer demand at each subway station. Furthermore, this paper uses the Entropy Weight-TOPSIS Model to conduct a preliminary evaluation of the transfer supply conditions at various subway stations. Based on the evaluation results of the matching between transfer supply and demand, as well as the size of the transfer demand gap, this study proposes corresponding optimization strategies for subway stations, providing an effective method for identifying inefficient stations. The research findings indicate that, in Shenzhen, the subway stations with high potential demand for transfers to regular buses are mainly located near densely populated residential areas. The central urban area exhibits a high degree of matching between transfer supply and demand, with some old urban areas experiencing an oversupply due to the well-developed public transportation infrastructure. However, peripheral stations commonly face a situation where demand exceeds supply, necessitating focused attention on improving transfer supply conditions at these sites. Regarding the transfer demand gap, even among subway stations with the same level of transfer supply, variations in the size of the demand gap exist. Stations with insufficient transfer supply but efficient operations offer valuable lessons, while stations with large demand gaps and inefficient operations should be targeted for specific improvements based on their individual supply and demand matching situations. The results demonstrate that evaluating the alignment between potential subway-bus transfer demand and the level of transfer supply using multi-source data, and formulating optimization strategies in conjunction with the transfer demand gap, is of significant importance for enhancing the refined management level of subway and bus transfer services. Overall, the theory and calculation methods of transfer potential demand and transfer demand gap proposed in this study provide a new perspective and reference for transfer research, public transport planning, and urban planning in the field of public transportation.