Refine
Has Fulltext
- yes (5)
Is part of the Bibliography
- yes (5)
Document Type
- Journal article (4)
- Doctoral Thesis (1)
Keywords
- Deep learning (1)
- Entscheidung bei Risiko (1)
- Fernerkundung (1)
- Remote Sensing (1)
- Stadt (1)
- Vulnerabilität (1)
- West African refugee crisis (1)
- big earth data (1)
- diurnal (1)
- environmental justice (1)
- land surface temperature (LST) (1)
- land use/cover pattern (LUCP) (1)
- multiscale encoder (1)
- news media reporting (1)
- review (1)
- risk management (1)
- satellite remote sensing (1)
- seasonal (1)
- sentinel (1)
- spatio-thematic coverage (1)
- surface model (1)
- surface urban heat island (SUHI) (1)
- urban areas (1)
- urban environments (1)
- urbane Räume (1)
- vulnerability assessment (1)
In recent history, normalized digital surface models (nDSMs) have been constantly gaining importance as a means to solve large-scale geographic problems. High-resolution surface models are precious, as they can provide detailed information for a specific area. However, measurements with a high resolution are time consuming and costly. Only a few approaches exist to create high-resolution nDSMs for extensive areas. This article explores approaches to extract high-resolution nDSMs from low-resolution Sentinel-2 data, allowing us to derive large-scale models. We thereby utilize the advantages of Sentinel 2 being open access, having global coverage, and providing steady updates through a high repetition rate. Several deep learning models are trained to overcome the gap in producing high-resolution surface maps from low-resolution input data. With U-Net as a base architecture, we extend the capabilities of our model by integrating tailored multiscale encoders with differently sized kernels in the convolution as well as conformed self-attention inside the skip connection gates. Using pixelwise regression, our U-Net base models can achieve a mean height error of approximately 2 m. Moreover, through our enhancements to the model architecture, we reduce the model error by more than 7%.