FathomDEM
An improved global terrain map using a hybrid vision transformer model
Bibliographic Data
| ID | 15547659 |
|---|---|
| Authors | Peter Uhe (0000-0003-4644-8559, Clifton Hospital, corresponding author), Chris Lucas (0000-0003-1101-7249, Clifton Hospital), Laurence Hawker (0000-0002-8317-7084, University of Bristol), Malcolm Brine (Clifton Hospital), Hamish Wilkinson (0009-0001-3593-0502, Clifton Hospital), Anthony Cooper (0000-0002-7864-2981, Clifton Hospital), Alex A Saoulis (0009-0005-1486-8681, Clifton Hospital), James Savage (0000-0003-4807-0916, Clifton Hospital), Christopher C Sampson (0000-0003-4094-2724, Clifton Hospital), Christopher Sampson |
| Year | 2025 |
| Volume | 20 |
| Issue | 3 |
| Pages | 034002-034002 |
| Publication date | 2025-01-13 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Environmental Research Letters (JOURNAL) |
| Journal identifiers | ISSN: 1748-9326 • E-ISSN: 1748-9326 |
| Publisher | IOP Publishing (PUBLISHER • GB) |
| DOI | 10.1088/1748-9326/ada972 |
| OpenAlex | W4406313924 |
| Language | EN |
| Citations received | 2 |
| References cited | 43 |
The Earth’s terrain is linked to many physical processes, and gaining the most accurate representation is key to work in many sectors from engineering to natural hazards modeling and ecology. Existing global digital elevation models (DEMs) are widely used, however often suffer from systematic biases caused by trees, buildings and instrumentation error, ultimately limiting their effectiveness. We present here, FathomDEM, a new global 30 m DEM produced using a novel application of a hybrid vision transformer model. This model removes surface artifacts from a global radar DEM, Copernicus DEM, aligning it more closely with true topography. In addition to improving on other global DEMs, FathomDEM also has reduced error compared to coastal-focussed DEMs such as the recent DeltaDTM. This demonstrates its impressive capacity to perform for specific landscapes, while being trained globally to model a wide range of terrain types. FathomDEM has been tested on the downstream task of flood modeling, showing increased accuracy compared to those run with the previous best global DEM, FABDEM, approaching the performance of LiDAR based flood modeling. This improvement is attributed to FathomDEM’s smaller error and substantial reduction in artifacts. This shows the suitability of FathomDEM for applied tasks and strengthens our evaluation compared to one based on vertical error alone
Atmospheric sciences · Carbon dioxide · Carbon sequestration · Climate change · Physics · Atmospheric and Environmental Gas Dynamics · Chemistry · Climate Change Policy and Economics · Environmental Science · Geology
The Shuttle Radar Topography Mission
Least squares quantization in PCM
Mapping global forest canopy height through integration of Gedi and Landsat data
Image quality assessment
A high‐accuracy map of global terrain elevations
Who Belongs in the Family
A 30 m global map of elevation with forests and buildings removed
| Citations per year | 2 |
|---|---|
| Citation span | 2026 - 2026 (1) |
| Highly cited | No |