Novel application of AI provides the most accurate model of the Earth’s surface publicly available

A new research paper has been published today, outlining the creation of a 30 m resolution representation of the Earth’s terrain more accurate than any other publicly available. The paper entitled ‘FathomDEM: An improved global terrain map using a hybrid vision transformer model’ outlines an improved method of modeling using a novel application of advanced AI techniques, which halves the error compared to the digital elevation models currently recognised as the most accurate. 

Existing digital elevation models (DEMs) are widely used across a range of sectors from engineering to natural hazards modeling and ecology. But they often suffer from systematic biases caused by instrument error and the presence of trees and buildings on the Earth’s surface, ultimately limiting their effectiveness.

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.  Notably, 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 spatial context instead of a disconnected pixel-by-pixel correction. 

In the paper, FathomDEM is compared with the elevation models numerous research papers previously ranked as the most accurate, and showed a marked improvement, even approaching the performance of ‘gold standard’ LiDAR data, when applied to a flood model.  

Innovative features of FathomDEM:

• Improved accuracy: Removing artifacts commonly found in other global models for a more realistic representation of the Earth’s surface, surpassing existing models in accuracy.  
• Novel methodology: Processing the digital elevation model as small images enables better recognition of spatial features. 
• Extensive inspection: When quantitatively evaluated against a reference dataset of LiDAR, graded against 23 landscape and landcover types, and qualitatively compared to maps from 10 countries, FathomDEM consistently achieved the best evaluation scores.  
• Outperforms more specialist digital elevation models: Despite being trained for all terrain types, the model has a stronger performance in coastal regions than specialist coastal models. 
• Validated for flood modeling: Terrain is a key determinant of where water will flow during floods. When tested, the skill of the models based on FathomDEM were of similar quality to the LiDAR-derived flood inundation maps. 

Dr Peter Uhe, lead author and Principal Scientific Developer, said:

“The AI computer vision tools we used to produce FathomDEM are a step up from previous methods. We’re excited to share this new terrain map which will be a hugely valuable resource for us and the wider academic community.”

Now the research is 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.

For media enquiries, contact [email protected]. 

For more information (including licensing queries), contact [email protected].