Artificial intelligence (AI) is seeing rapid adoption in the telecoms sector, with approximately 90% of telecom companies having integrated AI into their operations as of 2024. Autonomous and AI-native network management, including self-optimising networks and predictive maintenance, is a central focus, aiming to cut downtime by up to 30%.
For many telecoms operators, it's essential that network maintenance is done as safely as possible, avoiding any risk to field workers while also following regulatory compliance. But with the sector pursuing AI-native operations and autonomous networks, precision is just as important.
Location data is being used to address these evolving safety requirements, and enhance worker protection. Access to geospatial intelligence can help organisations anticipate hazards, mitigate risks, and optimise safety protocols, all while enabling efficient field operations across challenging terrain.
Navigating safety challenges
Telecoms infrastructure is frequently deployed in remote or challenging environments, making them dangerous for workers to reach for maintenance or repair. Urban rooftops to remote rural installations, each presents unique safety considerations. Workers face risks including working at height, proximity to high-voltage equipment, challenging weather conditions, and difficult site access.
With network maintenance being a core priority, it's essential that this activity is done as efficiently as possible, while keeping employees, contractors, and the public safe.
Traditional maintenance planning often relies on basic site information and historical records, leaving safety considerations to be assessed upon arrival. Unforeseen hazards and subsequent failed site visits can result in operational delays and increased costs, leaving telecoms companies to operate at risk.
Here, accurate location data can inform site visits, and whether automated systems can be dispatched directly.
Optimising site visits with OS data
OS location data provides detailed information about over 40 million properties throughout Great Britain, including specific attributes such as building heights, roof configurations, and proximity to roads and public spaces. The data is updated continuously, assuring operators that their safety assessments are based on current information, and each location includes comprehensive topographical and structural data, helping to identify potential hazards before arriving on site.
Every property across Great Britain receives a distinct identifier, known as a Unique Property Reference Number (UPRN). The UPRN can be used to link data to specific addresses — in this case, OS data from the National Geographic Database (NGD). The data in OS NGD is split into distinct themes, for example, Land Use, Buildings, and Address themes.
Building data can be used to assess roof height and slant for a specific property, while Land Use can identify potential dangers around the home or asset, informing maintenance planning for that location. This dataset can act as a single source of truth for safety planning and risk assessment, reducing uncertainty and improving efficiency with maintenance operations.
Additionally, with trusted data comes enhanced autonomous capabilities. By using OS datasets, operators can direct automated systems precisely to problem areas without human guidance, reducing exposure to risk while maintaining operational effectiveness.
Ensuring a safe future for the telecoms industry
As adoption of autonomous network management and AI continues in the telecoms industry, it will help operations to increase efficiencies, and ensure the safety of telecoms workers during maintenance of assets in more difficult-to-reach or perilous locations.
To identify where human maintenance is viable, location data will be key. By leveraging OS data, operators can build confidence in safety protocols, filling in any gaps that more traditional approaches may miss.
With trusted data, telecoms companies can deliver safer, more efficient maintenance operations, and protect workers at every stage of network expansion.
