Deep neural network regression for normalized digital surface model generation with Sentinel-2 imagery
Please always quote using this URN: urn:nbn:de:bvb:20-opus-349424
- 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 deriveIn 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%.…
Author: | Konstantin MüllerORCiD, Robert LeppichORCiD, Christian Geiß, Vanessa BorstORCiD, Patrick Aravena Pelizari, Samuel KounevORCiD, Hannes TaubenböckORCiD |
---|---|
URN: | urn:nbn:de:bvb:20-opus-349424 |
Document Type: | Journal article |
Faculties: | Fakultät für Mathematik und Informatik / Institut für Informatik |
Language: | English |
Parent Title (English): | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
ISSN: | 1939-1404 |
Year of Completion: | 2023 |
Volume: | 16 |
Pagenumber: | 8508-8519 |
Source: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2023) 16:8508-8519. DOI: 10.1109/JSTARS.2023.3297710 |
DOI: | https://doi.org/10.1109/JSTARS.2023.3297710 |
Dewey Decimal Classification: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Tag: | Deep learning; multiscale encoder; sentinel; surface model |
Release Date: | 2024/04/18 |
Licence (German): | CC BY: Creative-Commons-Lizenz: Namensnennung 4.0 International |