1. A new global map of elevation with buildings and forests removed has been created using machine learning.
2. The map is more accurate than existing global elevation maps and will strengthen applications and models where high quality global terrain information is required.
3. The correction algorithm was trained on a unique set of reference elevation data from 12 countries, covering a wide range of climate zones and urban extents.
The article is generally reliable and trustworthy, as it provides detailed information about the research conducted by the authors to create a new global map of elevation with buildings and forests removed. The authors have provided evidence for their claims in the form of statistics, such as mean absolute vertical error in built-up areas being reduced from 1.61 to 1.12 m, and in forests from 5.15 to 2.88 m, which shows that their method is indeed more accurate than existing global elevation maps. Furthermore, the authors have also provided details about the training data used for their correction algorithm, which was sourced from 12 countries across different climate zones and urban extents, making it applicable to a wider range of applications compared to previous DEMs trained on data from a single country.
The only potential bias that could be identified in this article is that it does not explore any counterarguments or alternative methods for creating such a map, which could be seen as partiality towards the method proposed by the authors themselves. However, this does not significantly detract from the trustworthiness of the article since it provides sufficient evidence for its claims and does not make any unsupported statements or omit any important points of consideration regarding its topic.