Hill-shading, also referred to as relief shading, is an important visualization method in small- and medium-scale topographic mapping. Although analytical hill-shading methods offer high generation efficiency, they often suffer from terrain detail overload. Some deep learning generative models have introduced terrain priors, but they still have deficiencies in the controllable representation and reasonable simplification of terrain structures. This study proposes a Swiss-style hill-shading method based on hierarchical terrain structure lines. By introducing ridgelines with hierarchical semantics as priors, a synergistic regulation mechanism of enhancement and suppression is constructed to emphasize major terrain structures while moderately weakening secondary details. The model adopts a hybrid architecture integrating a Transformer encoder and a convolutional decoder to model global terrain structures. In the testing phase, by adjusting the combinations of different levels of ridgelines, the controllable adjustment of the level of detail and structural significance in hill-shading representation is realized. Multi-region experimental results show that the proposed method can generate hill-shading results with clear structural hierarchies and distinct primary–secondary relationships. Compared with other models, the proposed method demonstrates more stable performance in achieving reasonable hierarchical representation of terrain structures and detail simplification, approaching the visual style of Swiss-style manual hill-shading.

Geographic information generalization underpins multi-scale spatial databases and cartography, and reliable DEM downscaling is critical to maintaining geomorphological consistency across map scales. Traditional DEM simplification and resampling methods rely on local geometric filtering and overlook global terrain structures, frequently causing structural distortions such as broken ridges and deformed slopes. This study proposes DD-GAN, a generative adversarial network constrained by terrain morphological factors for high-fidelity DEM downscaling. Built on a GAN architecture, the model embeds local relief and gradient as physical loss terms to prioritize major geomorphic skeletons and suppress trivial micro-terrain during resolution reduction, avoiding the indiscriminate over-smoothing of conventional sampling approaches. Multi-scale experiments covering downscaling factors ranging from 2× to 5× are conducted using mountainous datasets from Chongqing, Alaska, and Colorado. Quantitative and visual comparisons against raster interpolation, TIN-based simplification, and ordinary CNN show that DD-GAN mitigates terrain structural distortion and better retains elevation extremes and slope features, with more prominent strengths under large downscaling multiples. This physics-constrained deep learning paradigm provides an automated DEM downscaling solution that facilitates multi-scale terrain representation, supporting cartographic production and geomorphometric analysis.

Geographic information generalization is central to multi-scale spatial database construction and cartographic representation. The quality of terrain generalization for Digital Elevation Models (DEMs) directly determines geomorphological fidelity during scale transformation. However, existing DEM generalization methods, which are mostly limited to local geometric filtering or surface simplification, lack global awareness of macroscopic terrain structures. This limitation often causes “geographic alienation,” such as ridge breakage and gradient distortion. To address this issue, we propose TG-GAN, a terrain morphological factor-constrained multi-rate deep learning model for DEM generalization. This model overcomes the indiscriminate smoothing of conventional downsampling by embedding the “structure-first” principle into a deep learning framework. Specifically, a Generative Adversarial Network is used to enhance the generator's simulation capacity. Terrain morphological factors, including local relief and gradient, are innovatively incorporated as physical error terms into the loss function, guiding the network to adaptively reinforce primary terrain skeletons while smoothing secondary micro-terrain features during downscaling. A multi-objective loss function integrating elevation fidelity and gradient preservation enables intelligent terrain generalization in a physically constrained manner. Experiments conducted in mountainous regions of Chongqing, China, Alaska, USA, and Colorado, USA, with downscaling factors of 2× to 5× demonstrate that TG-GAN achieves robust multi-rate generalization while preserving the overall terrain structure. Compared with traditional interpolation methods, TG-GAN effectively avoids over-smoothing and structural breakage, excelling in preserving elevation extremes and slope morphology. Compared with conventional CNN-based methods, TG-GAN shows significant advantages in MAE, RMSE, and SSIM, especially under high downscaling factors. Overall, the proposed model offers a new data- and physics-driven paradigm for automated, multi-scale, and high-fidelity DEM generalization, supporting multi-scale mapping and related geomorphological analysis.

Terrain generalization—the scale-driven abstraction of digital elevation models (DEMs) that retains dominant landforms while filtering trivial microtopography—has long been dominated by rule-based algorithms, whereas deep learning has mainly targeted the inverse task of DEM super-resolution. This study proposes TG-CNN, a feature-fusion convolutional neural network for DEM down-scaling generalization. The network compresses the high-resolution DEM through a max- or average-pooling front end, combines normalized elevation with slope and sine–cosine circularly encoded aspect as complementary input channels, and is trained with a composite elevation–slope–aspect loss. Training, validation, and testing are conducted on geographically independent mountainous areas under a leave-one-area-out scheme, followed by adjustable IDW fusion post-processing. On the test region, classical bilinear interpolation retains the best elevation accuracy, while the standalone TG-CNN does not reach a comparable level; fused accuracy improves monotonically as the IDW share increases, indicating that the fusion benefit originates from the interpolation component. On the ridge–valley structure, however, TG-CNN behaves as an aggressive yet reliable filter: it achieves the highest precision and the smallest positional offset among all compared methods but retains only part of the reference skeleton, leaving its F1-score below the interpolation baseline. TG-CNN thus realizes a genuine, controllable terrain-abstraction effect, yet deep learning does not yet surpass mature interpolation in pixel-level elevation accuracy—a negative result that clarifies current limitations and points toward residual learning and information-preserving architectures.