A new research paper outlines the creation of a 30m-resolution digital elevation model of the Earth’s terrain that is more accurate than any other publicly available.
The paper, entitled ‘FathomDEM: An improved global terrain map using a hybrid vision transformer model,’ is said to describe an improved method of modelling using a novel application of advanced AI techniques, which halves the error compared to the digital elevation models (DEMs) currently recognised as the most accurate.
According to the authors, existing DEMs often suffer from systematic biases caused by instrument error and the presence of trees and buildings, limiting their effectiveness.
The ‘gold standard’ for elevation modelling is LiDAR, however it is only freely available for an estimated 8.2% of the Earth’s surface.
The new model, FathomDEM, removes these surface artifacts from the global radar digital elevation model, Copernicus DEM, resulting in an improvement on both global and coastal DEMs.
FathomDEM relies on the novel application of a hybrid vision transformer model — an advanced machine learning technique that removes biases from the underlying terrain measurements by simultaneously predicting corrections for small regions by considering their spatial correlation.
In short, it uses the spatial context of the surrounding landscape instead of a disconnected pixel-by-pixel correction.
“The AI computer vision tools we used to produce FathomDEM are a step up from previous methods,” said Dr Peter Uhe, lead author and principal scientific developer.
“We’re excited to share this new terrain map which will be a hugely valuable resource for us and the wider academic community.”
With the research complete, flood risk intelligence firm Fathom will underpin the next iteration of its flood maps with the new digital elevation model, available later this year.
FathomDEM will be available for license commercially from Fathom and also under a Creative Commons Attribution Non-Commercial license for academic research purposes.
