Feature‐Driven DEM Generation With Enhanced Detail Preservation and Noise Mitigation Using Conditional GANs
- 10 March 2026
- journal article
- Published by Wiley in Transactions in GIS
- Vol. 30 (2)
Abstract
Despite the widespread application of Digital Elevation Models (DEMs) in Geographic Information Systems (GIS) and terrain analysis, generating high‐fidelity virtual terrain from sketches remains a significant challenge, particularly regarding feature recognition and realistic pattern generation. This paper proposes a novel method based on Conditional Generative Adversarial Networks (CGANs) for virtual terrain synthesis, effectively addressing key issues in feature extraction, denoising, and preservation. Specifically, the Feature Enhancement Module (FEM) leverages deep learning‐based attention mechanisms to refine terrain features, maintaining the integrity of both global and local patterns. The Elevation Denoising Module (EDM) detects and eliminates noise artifacts introduced during generation, while the Collaborative Loss Module (CLM) optimizes feature preservation. Evaluated on a comprehensive dataset of 15,680 sub‐DEM tiles from six geographically distinct regions, our experiments demonstrate the model's effectiveness. Quantitative results show that our method achieves a Root Mean Square Error (RMSE) of 9.38 m. Furthermore, our approach outperforms existing deep learning models, showing performance improvements of 7.3% over Diffusion, 8.6% over FEN, 10.9% over TFaSR, and 15.3% over IETA. Beyond numerical metrics, the proposed model exhibits superior qualitative advantages, particularly in preserving hydrological connectivity—achieving a mean Intersection over Union (mIoU) of 85.01% for valley lines—and effectively mitigating high‐frequency generative artifacts.Keywords
Funding Information
- National Natural Science Foundation of China (42371446)
- Natural Science Foundation of Hubei Province (2024AFD412)
This publication has 40 references indexed in Scilit:
- A continuous digital elevation representation model for DEM super-resolutionISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Intelligent terrain generation considering global information and terrain patternsComputers & Geosciences, 2023
- Geomorphometry and terrain analysis: data, methods, platforms and applicationsEarth-Science Reviews, 2022
- Terrain feature-aware deep learning network for digital elevation model superresolutionISPRS Journal of Photogrammetry and Remote Sensing, 2022
- Flood hazard assessment in large plain basins with a scarce slope in the Pampean Plain, ArgentinaEnvironmental Monitoring and Assessment, 2021
- Automated mapping of cultural heritage in Norway from airborne lidar data using faster R-CNNInternational Journal of Applied Earth Observation and Geoinformation, 2021
- Improving Semantic Segmentation via Decoupled Body and Edge Supervision2020
- Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networksLandslides, 2020
- Physically-based landslide prediction over a large region: Scaling low-resolution hydrological model results for high-resolution slope stability assessmentEnvironmental Modelling & Software, 2020
- Application of remote sensing data and GIS for landslide risk assessment as an environmental threat to Izmir city (west Turkey)Environmental Monitoring and Assessment, 2011