Deep learning has been widely applied in building segmentation from high-resolution remote sensing (HRS) images. However, HRS images suffer from insufficient complementary representation of target points in terms of capturing details and global information. To this end, we propose a novel building segmentation model for HRS images, termed C_ASegformer. Specifically, we design a Deep Layered Enhanced Fusion (DLEF) module to integrate hierarchical information from different receptive fields, thereby enhancing the feature representation capability of HRS information from global to detailed levels. Additionally, we introduce a Triplet Attention (TA) Module, which establishes dependency relationships between buildings and the environment through multi-directional rotation operations and residual transformations. Furthermore, we propose a Multi-Level Dilated Connection (MDC) Module to efficiently capture contextual relationships across different scales at a low computational cost. We conduct comparative experiments with several state-of-the-art models on three datasets, including the Massachusetts dataset, the INRIA dataset, and the WHU dataset. On the Massachusetts dataset, C_ASegformer achieves 95.42%, 85.69%, and 75.46% for OA, F1score, and mIoU, respectively. C_ASegformer shows more accurate performance, demonstrating the validity and sophistication of the model.

Building extraction is essential in applications such as urban planning and monitoring urban dynamics. In high-resolution remote sensing (HRS) images, the main body of buildings and their surrounding environments exhibit strong coupling and variability, which can easily lead to the loss and underutilization of multi-scale feature information. To address this issue, we proposed a compound multi-branch fusion model, termed MCMFformer, for building segmentation in HRS images. Firstly, we designed a Mixed Multi-Branch Feature Fusion (MMFF) module, which performs multi-dimensional weighted fusion on the feature information captured by the Transformer. By employing a U-shaped attention structure, the module enhances the dimensional representation of multi-scale features from each branch and multi-level features during the aggregation phase, thereby improving the representational capacity of the building feature information. Secondly, we employed a Supervised Attention Module (SAM) to perform supervised correction on the enhanced information, thereby suppressing redundant information generated in the front-end stages. Additionally, we designed a Mixconv to mitigate information conflicts between attention branches, achieving an optimal balance point across different dimensions. We conducted comparative experiments with several state-of-the-art models on the three datasets, including Massachusetts dataset, the INRIA dataset, and the NZ32km2 dataset. On the Massachusetts dataset, the MCMFformer model achieved an average mIoU improvement of 1.44%, 2.65%, 2.13%, and 1.04% over the mainstream building segmentation models CGSANet, Segformer, MANet, and HDNet, respectively. Experiments show the effectiveness of the MCMFformer model in the task of HRS image building segmentation.

Rapid urbanization has further expanded the scale of construction land in urban agglomerations. The encroachment of urban land on ecological land has led to severe ecological problems and threatened the stability of ecological security in urban agglomerations. Analyzing the characteristics of future urban multi-scenario expansion and its impacts on ecological security patterns (ESP) can provide guidance for formulating ecologically sustainable management and control Policies. Our study focuses on Changsha-Zhuzhou-Xiangtan (CZX) urban agglomeration as the study area and establishes an ESP. Additionally, a cellular automata (CA) was used to simulate future urban expansion patterns under three scenarios (i.e., natural development scenario, urban development scenario, and ecological conservation scenario). The subsequent analysis evaluates their impact on the ESP. The simulation results indicate that from 2020 to 2030, the CZX urban agglomeration will undergo rapid urban expansion under the natural development scenario and urban development scenario, characterized by outward growth surrounding the existing construction land. In the natural development scenario, urban expansion is primarily concentrated in the northwest and south directions of construction land, the proportion of construction land increased by 2.78%; in the urban development scenario, it is concentrated in the southeast direction of construction land, the proportion of construction land increased by 3.24%. Ecological conflicts in the aforementioned development scenarios primarily arise in the southwestern region of Changsha County, as well as the southern areas of Kaifu District and Furong District. Conversely, under the ecological conservation scenario, the rate of urban expansion has significantly decreased, environmental preservation is upheld at its highest level, and the proportion of construction land only increased by 0.04%. Based on the simulation results, we present targeted recommendations for urban land planning and growth management, as well as the protection, restoration, monitoring, and development of ecological land. These suggestions provide effective guidance for improving the stability of ESP in urban agglomerations and promoting high-quality development in Chinese urban agglomerations.

Urbanization significantly reshapes urban form, affecting the spatial and quantitative dynamics of urban land use under carbon constraints. However, the role of macro-scale urban form in guiding low-carbon urban expansion remains underexplored. Our study introduces an integrated Cellular Automata (CA) model to simulate urban land use patterns with regard to the low-carbon goal, focusing on urban form optimization. The model employs a top-down strategy to adjust future urban land demand by balancing urban development needs with carbon emission (CE) reduction targets. The adjusted demand is then used to optimize urban form parameters (i.e., the inverse S-shaped function) to predict future urban land patterns and allocate land increments within concentric rings. Subsequently, a bottom-up strategy incorporating carbon sequestration (CS) conservation is applied to refine urban land conversion. The CA model integrates a maximum probability transformation rule to allocate urban land efficiently. We used the model to simulate urban land use patterns under four scenarios (i.e., Low-carbon Urban Development Scenario (L-UDS), Top-up Urban Development Scenario (T-UDS), Bottom-up Urban Development Scenario (B-UDS), and inverse S-shaped constraint Urban Development Scenario (S-UDS)) for the Changsha–Zhuzhou–Xiangtan (CZX) urban agglomeration in 2035. Results show that the proposed model effectively reconciles the conflict between rapid urbanization and urban carbon management strategies, as evidenced by a 31.25% reduction in carbon emissions in the L-UDS and T-UDS relative to the S-UDS and B-UDS. Furthermore, urban form constraints promote the development of compact and dense urban structures, advancing sustainable urban development goals. This study not only proposes a simulation model capable of effectively promoting compact urban development at the theoretical level, but its findings also offer actionable policy insights for China to address urban sprawl and actively advance low-carbon urban development.