Skip to Content

How’s the Weather There? Crowdsourcing App Promises Better Forecasts

An app called Sunshine taps into users’ smartphone sensors to provide localized weather predictions.
March 10, 2015

An app called Sunshine wants you to help it create more accurate, localized weather forecasts.

The app, currently in a private beta test, combines data from the National Oceanic and Atmospheric Administration (NOAA) with atmospheric pressure readings captured by a smartphone. The latest iPhones, and some Android smartphones, include barometers for measuring atmospheric pressure. These sensors are generally used to determine elevation for navigation, but changes in air pressure can also signal changes in the weather.

Sunshine will also rely on users to report sudden weather hazards like fog, cofounder Katerina Stroponiati says. About 250 people spread out among the Bay Area, New York, and Dallas are now using Sunshine, she says, and the team behind it plans to release the app publicly at the end of March for the iPhone. It will be free, though some features may eventually cost extra.

While weather predictions have gotten more accurate over the years, they’re far from perfect. Weather information usually isn’t localized, either. The goal of Sunshine is to better serve places like its home base of San Francisco, where weather can be markedly different over just a few blocks.

Stroponiati aims for Sunshine to get enough people sending in data—three per square mile would be needed, according to experiments the team has conducted—that the app can be used to make weather prediction more accurate than it tends to be today. Some other apps, like PressureNet and WeatherSignal, already gather data entered manually by users, but they don’t yet offer crowdsourced forecasts.

I checked out the private beta version of the app, which showed me weather-app basics like an hourly forecast for the current day and basic weather details for the days ahead. The app showed my current weather as clear and 64 degrees, and said the data was gathered from 37 devices in the area.

Cliff Mass, an atmospheric science professor at the University of Washington, cautions that while crowdsourced barometer data can help provide detailed weather statistics, making forecasts is trickier: for that, all those data points must be used with weather-data models. This is the kind of thing he’s working on with the use of smartphone barometric readings that come in via the PressureNet and WeatherSignal apps.

Sunshine’s small team doesn’t include any meteorologists, but the company is looking to hire some weather experts, and Stroponiati says it is running numeric models on the data collected through the app. 

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.