Ordnance Survey (OS) has harnessed the power of STFC Hartree Centre’s powerful supercomputer to try to make the mapping service more efficient.
As part of a new partnership with the Hartree Centre, the OS has used the supercomputer Scafell Pike to test and develop machine learning techniques as a way to get more information from aerial images.
Using machine learning in this way could bring annual efficiencies of more than £2million for OS – and they anticipate this to rise to £8million per year by 2024.
Ordnance Survey Chief Operating Officer, John Clarke, said: “Machine learning has the potential to revolutionise the way OS detects change. We already have the most detailed maps in the world, but extra detail, such as roof tops, roof types, solar panels, street furniture and further data at street level, alongside other AI work we are developing, will be crucial to ushering in new technologies like 5G and self-driving vehicles. We envisage this extra richness in rural and urban areas will enable a variety of industries to improve upon what they already do and unlock opportunity for them.”
The OS is also hoping that developing a machine learning algorithm to easily create accurate and detailed maps will help to address a global challenge – as at least two-thirds of the land in the world is unmapped and unregistered, and this technique could help to overcome this.
More information on the partnership is available here.
Last updated: 27 September 2019