Wednesday , November 20 2019
Home / zimbabwe / Face recognition technology 'could improve weather forecasting', scientists say

Face recognition technology 'could improve weather forecasting', scientists say



<p class = "canvas-atom" canvas-text Mb (1.0em) Mb (0) – sm Mt (0.8em) – sm "type =" text "content =" Technology used for facial recognition could improve weather forecasts, with trials showing that technology can predict how severe & nbsp;hailstorms will data. "data-reactid =" 31 "> Technology used for facial recognition could improve weather forecasts, with trials showing that technology can predict how severe hailstorms will be.

Rather than training software to recognize human faces, scientists trained it to recognize the shape of storms.

Being able to recognize the 'features' of storms allows scientists to predict the formation of hail and how large the stones will be.

Traditional hail forecasting techniques help with both of these, the study found in the American Meteorological Society's Monthly Weather Review.

Extreme hail storm falling on the high plains of Nebraska (Stock image, Getty)

Lead author David John Gagne of NCAR said, 'We know that the structure of a storm affects whether the storm can produce hail.

READ MORE FROM YAHOO

<p class = "canvas-atom" canvas-text Mb (1.0em) Mb (0) – sm Mt (0.8em) – sm "type =" text "content ="Boo, the famously cute dog, has died 'of a broken heart'"data-reactid =" 57 ">Boo, the famously cute dog, has died 'of a broken heart'

<p class = "canvas-atom" canvas-text Mb (1.0em) Mb (0) – sm Mt (0.8em) – sm "type =" text "content ="Cute or creepy: why humans love some species, loathe others"data-reactid =" 58 ">Cute or creepy: why humans love some species, loathe others

<p class = "canvas-atom" canvas-text Mb (1.0em) Mb (0) – sm Mt (0.8em) – sm "type =" text "content ="Meet Kiera, the world's first Li-Liger"data-reactid =" 59 ">Meet Kiera, the world's first Li-Liger

'A supercell is more likely to produce hail than a squall line, for example. But most hail forecasting methods just look at a small slice of the storm and can't distinguish the broader form and structure. "

The shape of the storm is really important. In the past we have tended to focus on single points in a storm or vertical profile, but the horizontal structure is also really important. '

Gagne and his team used 'deep learning' techniques to spot patterns in the storm that predicted hail.

<p class = "canvas-atom" canvas-text Mb (1.0em) Mb (0) – sm Mt (0.8em) – sm "type =" text "content =" mathematical complexity of storms, but 'deep learning' techniques spot patterns by themselves within large amounts of data, & nbsp;Phys.org& nbsp; reported. "data-reactid =" 63 "> Traditional computer models struggle with such a task due to the mathematical complexity of the storms, but 'deep learning' techniques spot patterns by themselves within large amounts of data, Phys.org reported.


Source link