Accurately simulating and predicting the urban expansion process, especially in expeditious urbanization areas, is an important aspect of managing limited land resources and adjusting flawed land use policies. This research was conducted on the basis of a high-temporal-resolution land use dataset to precisely model urban expansion in a rapidly developing zone by integrating the Artificial Neural Network (ANN), cellular automata (CA), and Markov Chain (MC). An urban suitability index (USI) map was created using ANN and fed to CA–MC to identify possible changed-to-urban cells. Two ANNs, multiple-layer perceptron (MLP) and long short-term memory network (LSTM), were implemented as simulation models for comparison. Due to its ability to capture more temporal information, LSTM outperformed MLP in modeling urban expansion dynamics over a short temporal interval. The simulated results were validated by (fuzzy) kappa simulation and the results revealed that the combination of ANN and CA–MC can precisely model the urban development locations due to its strength in revealing the nonlinear relationship between the expansion process and its drivers. The same model was applied to southern Auckland, and the compared results show that the most simulated variance is caused by the land use policies implemented by different types of governments.

Under China’s dual carbon strategy, low-carbon city construction is expected to help reduce urban flood risks. However, the flood resilience of low-carbon communities remains unclear, limiting effective disaster prevention. This study examines traditional and newly built low-carbon communities in Kunming, establishing indices for community flood resilience and low-carbon development according to current national and local standards. Flood resilience (UFR) and low-carbon development level (ULC) were measured using the critic–entropy weight and TOPSIS methods, and a coupling coordination analysis model was used to analyze their correlation and coordination. The results are as follows: (1) The two communities exhibit marked spatial heterogeneity in both UFR and ULC. On average, the UFR in traditional communities is 21.53% higher than in low-carbon communities, while the ULCs are 4.33% higher in low-carbon communities compared to traditional ones. (2) UFR and ULC showed a high coupling level in both communities (over 98%), indicating a strong correlation. (3) The Moran’s I index of 0.664 for coupling coordination indicates notable spatial dependence. These results suggest that, initially, low-carbon communities in Kunming may not exhibit stronger flood resilience, but low-carbon development can significantly improve flood resilience over time. This paper also provides recommendations for enhancing flood resilience in urban low-carbon communities.

With accelerating urbanization, the development of rail transit systems—particularly subways—has become a key strategy for alleviating urban traffic congestion. However, existing studies on subway station site selection often lack a spatially continuous evaluation of site suitability across the entire study area. This may lead to a disconnect between planning and actual demand, resulting in issues such as “overbuilt infrastructure” or the “island effect.” To address this issue, this study selects Kunming City, China, as the study area, employs the K-means++ algorithm to cluster existing subway stations based on passenger flow, integrates multi-source spatial data, applies a random forest algorithm for optimal positive sample selection and driving factor identification, and subsequently uses a LightGBM-SHAP explainable machine learning framework to develop a predictive model for station location based on mathematical modeling. The main findings of the study are as follows: (1) Using the random forest model, 20 key drivers influencing site selection were identified. SHAP analysis revealed that the top five contributing factors were connectivity, nighttime lighting, road network density, transportation service, and residence density. Among these, transportation-related factors accounted for three out of five and emerged as the primary determinants of subway station site selection. (2) The site selection prediction model exhibited strong performance, achieving an R² value of 0.95 on the test set and an average R² of 0.79 during spatial 5-fold cross-validation, indicating high model reliability. The spatial distribution of predicted suitability indicated that the core urban area within the Second Ring Road exhibited the highest suitability, with suitability gradually declining toward the periphery. High-suitability areas outside the Third Ring Road in suburban regions were primarily aligned along existing subway lines. (3) The cumulative predicted probability within a 300 m buffer zone around each station was positively correlated with passenger flow levels. Overlaying the predicted results with current station locations revealed strong spatial consistency, indicating that the model outputs closely align with the actual spatial layout and passenger usage intensity of existing stations. These findings provide valuable decision-making support for optimizing subway station layouts and planning future transportation infrastructure, offering both theoretical and practical significance for data-driven site selection.

With the rapid evolution of Digital Twins and Embodied AI, achieving fast, dense, and high-precision 3D perception in unknown environments has become paramount. However, existing Visual SLAM paradigms face a critical dilemma: geometry-based methods often fail in texture-less areas due to feature scarcity, while learning-based approaches frequently suffer from scale drift and unphysical deformations. To bridge this gap, we propose VGGT-Geo, a novel SLAM system that synergizes generative priors from Large Foundation Models with multi-modal geometric optimization. Distinguishing itself from simple cascaded architectures, we construct a Probabilistic Geometric Fusion framework, consisting of (1) Generative Warm-start, leveraging the holistic scene understanding capabilities of the VGGT, (2) Confidence-Aware Optimization to extract dense features via DINOv3 and predict their confidence map, and (3) a Multi-Modal Constraint Closure that fuses point-line features and metric depth priors to constrain rotational Degrees of Freedom in Manhattan Worlds. We conducted systematic evaluations on TUM, Replica, Tanks and Temples, and a challenging self-collected dataset featuring extreme lighting and texture-less walls. Experimental results demonstrate that VGGT-Geo exhibits superior robustness and accuracy in unseen environments. On our most challenging dataset, it achieves an Absolute Trajectory Error of 4–5 cm and a Relative Rotation Error of 0.79°, outperforming current state-of-the-art methods by approximately 50% in trajectory accuracy. This study validates that synergizing the intuition of Large Foundation Models with geometric rigor is a viable path toward next-generation robust SLAM.

Landslides represent a widespread global geological hazard, presenting significant risks to both human populations and critical infrastructure. The accuracy of landslide susceptibility evaluation models serves as a critical prerequisite for landslide hazard prediction and risk management, while insufficient landslide sample data may constrain the reliability of susceptibility modeling and evaluation results. To address the challenge of limited landslide samples in complex mountainous areas, this study proposes a novel landslide susceptibility evaluation method integrating environmental similarity theory with a backpropagation neural network (Environmental Similarity Model–BP Neural Network, ESM-BP). Taking the Baihetan reservoir area as the study region, the environmental similarity degrees between potential prediction points and historical landslide samples were calculated using eight environmental factors. A normal distribution approach was employed to classify similarity thresholds, thereby constructing an enhanced landslide sample dataset. The BP neural network model was subsequently applied for susceptibility assessment, with comparative validation against support vector machine (SVM) and random forest (RF) models. The experimental results demonstrate that (1) the integration of environmental similarity theory effectively expanded the dataset by 4398 samples with distinct susceptibility levels, resolving data scarcity issues and significantly enhancing the model’s generalization capabilities. (2) Among the three models tested with supplemented samples, the BP neural network achieved optimal performance, showing improvements in the accuracy values by 0.02 and 0.14 compared to SVM and RF, respectively, Kappa coefficient enhancements of 0.02 and 0.18, and RMSE reductions of 0.04 and 0.21. This methodology enhances the applicability and reliability of landslide susceptibility evaluation models in complex mountainous environments, providing innovative insights for related research in landslide susceptibility assessment.