With the increasingly urgent demand for map conflation and timely data updating, data matching has become a crucial issue in big data and the GIS community. However, non-rigid deviation, shape homogenization, and uncertain scale differences occur in crowdsourced and official building data, causing challenges in conflating heterogeneous building datasets from different sources and scales. This paper thus proposes an automated building data matching method based on relaxation labelling and pattern combinations. The proposed method first detects all possible matching objects and pattern combinations to create a matching table, and calculates four geo-similarities for each candidate-matching pair to initialize a probabilistic matching matrix. After that, the contextual information of neighboring candidate-matching pairs is explored to heuristically amend the geo-similarity-based matching matrix for achieving a contextual matching consistency. Three case studies are conducted to illustrate that the proposed method obtains high matching accuracies and correctly identifies various 1:1, 1:M, and M:N matching. This indicates the pattern-level relaxation labelling matching method can efficiently overcome the problems of shape homogeneity and non-rigid deviation, and meanwhile has weak sensitivity to uncertain scale differences, providing a functional solution for conflating crowdsourced and official building data.

Microlandform classification of grid digital elevation models (DEMs) is the foundation of digital landform refinement applications. To solve the shortcomings of the traditional regular grid DEM microlandform classification method, including low automation and incomplete classification results, a support vector machine (SVM) classifier was designed for grid DEM microlandform classification, and an automatic grid-based DEM microlandform classification method based on the SVM method was created. The experiment applies the SVM-based grid DEM microlandform classification method to identify different hill positions, namely, the summit, shoulder, back-slope, foot-slope, toe-slope, and alluvium. The results show that this method is most efficient in identifying the toe-slope, with an accuracy rate of 99.60%, and least efficient in identifying the foot-slope, with an accuracy rate of 98.18%. The kappa coefficient and model evaluation index F1-score verify that the method and model are reliable when applied to grid DEM microlandform classification problems.

Maintaining the data freshness and completeness of road intersection information is the key task of urban road map production and updating. Compared to professional surveying methods, crowdsourced trajectory data provide a low-cost, wide-coverage and real-time data resource for road map construction. However, there may exist the problems of spatio-temporal heterogeneity and uneven density distribution in crowdsourced trajectory data. Hence, in light of road hierarchies, the paper proposes a hierarchical segmentation method to generate road intersections from crowdsourced trajectories. The proposed method firstly implements an adaptive density homogenization processing on raw trajectory data in order to decrease the uneven density discrepancy. Then, a hierarchical segmentation strategy is developed to extract multi-level road intersection elements from coarse scale to fine scale. Finally, the structural models of road intersections are delineated by an iterative piecewise fitting method. Experimental results show that the proposed method can accurately and completely extract road intersections of different shapes and scales, with an accuracy of about 87–90%. Particularly, the precision and recall of road intersection detection are obviously increased by about 7% and 20% by adaptive density homogenization, indicating the advantages of dealing with uneven trajectory data.

Aiming at the limited degree of revealing vegetation growth pattern by simple topographic factors, it is essential to find an index that can explain the vegetation cover mechanism to a greater extent. By introducing a certainty factor into vegetation cover evaluation, LSW, LS, topographic wetness index, and aspect were also chosen to carry out control group experiments. The grid digital elevation model of 10 disaster-stricken counties (cities) in Sichuan Province was used as the basis to obtain LSW, while vegetation susceptibility levels were categorized using the natural breaks classification. The results of the multi-factor analysis demonstrated that the certainty factor corresponding to LSW climbed linearly from negative to positive values as the susceptibility level rose, indicating that it was highly correlated with vegetation cover and had an obvious advantage in revealing the vegetation growth potential. Statistically, the vegetation occurrence rate increased regularly with the improvement of the susceptibility level, in which the high and very high susceptibility zones corresponded to 83.66% and 89.95% of vegetation coverage respectively, suggesting a good consistency between the delineated high susceptibility areas and the actual vegetation cover. The findings proved that LSW has a substantial advantage in evaluating vegetation cover, with an evaluation model accuracy of 72.9%. It has been established that LSW will serve as a promising new model for assessing vegetation restoration and planning.

Accurate extraction of mountaintop areas from grid digital elevation models (DEMs) is essential for terrain analysis, geomorphological research, hydrological modeling, natural disaster monitoring, and emergency communication site selection. However, existing deep-learning-based methods often suffer from inadequate representation of local details and limited global contextual awareness, leading to blurred boundaries and reduced segmentation accuracy in complex mountainous terrains. To address these limitations, this study proposes a dual-encoder and global-context-enhanced TransUNet framework, named DEGC-TransUNet, for automated mountaintop delineation. The architecture integrates a convolutional encoder to capture fine-grained local terrain features and a MaxViT-based encoder to model multi-scale global context by encoding low-dimensional topographic attributes such as slope and curvature. A dedicated feature fusion module harmonizes complementary representations from both encoding paths, while a BiFormer-based strategy is introduced at the bottleneck to strengthen long-range dependencies and enhance convergence. The experimental results demonstrate that DEGC-TransUNet significantly outperforms baseline models such as TransUNet, DE-TransUNet, and GC-TransUNet, with relative improvements of 19.8% in Intersection over Union (IoU), 10.4% in overall accuracy (ACC), and 10.9% in F1-score. These findings provide a robust solution for mountaintop extraction, with significant potential in analyzing geomorphological evolution, simulating soil erosion, modeling species distribution in “sky island” ecosystems, and optimizing strategic placements for communication base stations and wind energy infrastructures.