Machine learning creates more accurate global terrain maps by removing forest and building artifacts
In short: Researchers used machine learning to strip forest and building data from the Copernicus Digital Elevation Model. By training their algorithm on reference data from 12 different countries, they produced the first global elevation map at 30-meter resolution that accurately reflects true terrain heights.
This new approach is more versatile than previous models that relied on data from only one country. By reducing vertical errors in urban and forested areas, this method provides more precise terrain information for critical uses like flood simulations.
The researchers trained their algorithm using a diverse set of reference data covering various climate zones and urban environments.
Why it matters: More accurate terrain data improves the precision of environmental models like flood simulations.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Source: Research: Hawker et al. (2022). A 30 m global map of elevation with forests and buildings removed. Environmental Research Letters. · cc-by
To cite this card, link to https://intellectplus.co.uk/app/nature-research-machine-learning-creates-more-accurate-global-terrain-maps-b.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Nature · Latest · A–Z · All topics
