Sunshine app promised more accurate weather forecasts
Sunshine app predicts weather forecasts by accessing the sensors on your smartphoneSunshine Technologies

Forget about Met Office predictions, a new app wants to give consumers accurate weather forecasts, updated to-the-second using crowd-sourced information from smartphone sensors. The Sunshine app, which is currently available to download for iOS users, uses your smartphone's barometric sensor to gather real-time data on weather conditions.

It then processes that data with its own weather algorithms to create forecasts on the ground, comparing what your phone senses to what someone else's phone senses, to create a central database of information. The information gathered is sufficient for the app to offer predictions about the weather 24 hours in advance, as well as morning summaries about the weather of the day at specific locations important to the user, such as their home or place of work.

This approach is vastly different from the method used by weather apps today, which are usually just repackaging government-issued reports that come from satellites and weather stations, which are far away and in scarce supply compared to how many people walk around with sophisticated computing devices in their pockets every day.

"Right now, all these apps are showing you a bunch of numbers, without actually taking into account how the weather feels to you, based on how you experience different types of weather," Sunshine Technologies cofounder and CEO Katerina Stroponiati told TechCrunch.

"The more users we have, with phones offering up sensor data and users submitting weather reports, the more accurate we will get. Like an almanac."

iPhone barometric sensor is key

The creators of the app are engineers and environmental designers who have been trying to improve the accuracy of weather forecasts for three years and hit their Eureka moment when Apple announced the barometric sensor for the iPhone in September 2014, as they realised that their data was 36% more accurate than that from traditional methods of weather measurement.

"We spent a year exploring the mobile sensors, building and iterating on forecasting models to make sense of the data," Sunshine's founders wrote on Medium.

"Our initial results were incredible. What we discovered was that smartphones can integrate all sorts of environmental sensors and collect all kinds of data about their surroundings. In fact, they can actually map out the entire atmosphere and provide us with the data that can accurately predict the weather on a scale that's never been possible until now."

Of course, the big problem with this solution is that people have to actually use it in order for the firm to gather the crowd-sourced information it needs for the app. The app is also free, and Sunshine Technologies hasn't disclosed how exactly it plans to make money.

Nevertheless, the San Francisco-based app has a huge amount of support behind it, having received $2m (£1.3m, €1.8m) in funding from a multitude of investors, including Maven Ventures, BBG Ventures, Morado Ventures, Greak Oats Ventures and the Winkelvoss.