How Brits could know the exact temperature in their back garden – as Met Office trials AI forecast

How Brits could know the exact temperature in their back garden – as Met Office trials AI forecast

It is good news for anyone who likes to sunbathe close to home. Bosses at the Met Office say weather forecasts could soon become ‘hyper local’ – even predicting the temperature in your back garden.

By using artificial intelligence and data collected by amateur forecasters, the new model was able to predict precisely how hot it will get down to the level of an individual street.

The Met Office’s standard forecasting model divides the UK into grid squares of 1.5km.

By using AI techniques, the new method is able to predict the weather within 100 metre squares ‘showing the potential for hyper-local forecasts for temperature, even within the same street,’ the Met Office said.

The new forecasting technique uses a computer program to predict temperatures at a local scale using records from eight spells of hot weather in London between 2019-2021.

Bosses at the Met Office say weather forecasts could soon become ‘hyper local’ – even predicting the temperature in your back garden (stock picture)

Holidaymakers enjoy a day out at the beach in Bournemouth in the cloudy conditions yesterday

Holidaymakers enjoy a day out at the beach in Bournemouth in the cloudy conditions yesterday

A rower passes the SS Great Britain on Bristol Harbourside in the early morning sun on Tuesday

A rower passes the SS Great Britain on Bristol Harbourside in the early morning sun on Tuesday

People relax on the beach during hot weather at Walton-on-the-Naze in Essex on Tuesday

People relax on the beach during hot weather at Walton-on-the-Naze in Essex on Tuesday

An AI technique called machine learning was used to analyse Met Office weather readings from five official sites combined with data from 133 amateur weather stations across London as well as finely detailed information about land use in the study area.

The amateur sites all submit regular data to the Met Office’s Weather Observation Website.

The ‘trained’ system was then tested to see how well it predicted heatwaves within the period.

The study found that machine learning methods of forecasting urban heatwaves improved prediction of air temperatures by up to 11 per cent compared to the original weather forecast data.

The research, carried out with the University of Reading and the Australian Bureau of Meteorology, could help warn people that they might be at greater risk of heatwaves due to their immediate surroundings. It could also be used by councils to identify hotspots which could do with additional shading – perhaps by planting trees.

People sunbathe at Green Park in London on Tuesday during a heatwave

People sunbathe at Green Park in London on Tuesday during a heatwave 

A group of people observe pedalo riders by the Serpentine in London's Hyde Park on Tuesday

A group of people observe pedalo riders by the Serpentine in London’s Hyde Park on Tuesday

The beach at Weymouth in Dorset busy with holidaymakers and sunbathers on Tuesday

The beach at Weymouth in Dorset busy with holidaymakers and sunbathers on Tuesday

Lead author and Met Office urban modelling expert Lewis Blunn said: ‘The prediction of urban heat at hyper-local scale has often been tricky for operational weather forecast models due to the complexity of urban areas.

‘By combining quality-controlled citizen observations and land cover data with forecast models and machine learning, this paper demonstrates the potential for enhanced temperature forecasts in urban areas at a much higher resolution.

‘Being able to accurately predict heat in cities could help better inform decision-makers on where to direct resources during heatwaves, enabling improved protection of human health and infrastructure.’

0 Shares:
Leave a Reply

Your email address will not be published. Required fields are marked *

You May Also Like