How Weather Apps Could Predict Your COVID Risk


August 17, 2022 – Tapio Schneider is a climate scientist and his wife is a mechanical engineer. In many ways, they were like many other families affected by COVID: two young children who weren’t in school and endless Zoom meetings from home. But the two didn’t just bake sourdough bread and go for walks during lockdown: they considered how they could help with their expertise.

“We were hiding at home like everyone else, talking about how to avoid isolation or lockdowns,” recalls Schneider, a professor of environmental science and engineering at the California Institute of Technology and a senior research scientist at NASA’s Jet Propulsion Laboratory.

At the time, lockdowns were the only known way to control the virus, but Schneider felt they didn’t work well.


“Even at the peak of the pandemic, 1 or 2% of the population was actually infectious,” he says. “Ninety-eight percent wouldn’t need to isolate themselves.” But the problem was figuring out who these contagious people were.

Then it hit him: what if he could make a COVID “prediction” using the same technology that weather apps use?

Schneider’s wife, who is also a Caltech professor, studied body temperature sensors. Perhaps, they argued, data from similar devices could be combined with COVID test data to predict a person’s likelihood of contracting the virus. Send that data to an app and each user could have their own personalized risk pushed straight to their smartphone.


This idea became a study in PLOS Computational Biology. Schneider teamed up with a global team — including a computer scientist from Germany and a disease modeler from Columbia University in New York City — to see if an app like this could help control a pandemic like COVID. And the results are promising.

How a COVID forecast app works

If you’ve ever used a weather app, you’ve probably noticed that Monday’s weekend forecast can look very different than Friday’s. And that’s not because meteorologists don’t know what they’re doing: it reflects the huge deluge of data that’s constantly being imported, increasing the accuracy of the forecast as the actual date gets closer.


Weather apps run an analysis every 12 hours. The first step captures the current atmospheric state — things like temperature, humidity, and wind speed, as measured by sources like weather stations and satellites. This information is mixed with the forecast from 12 hours earlier and then plugged into an atmospheric model. An algorithm predicts what conditions will be like in another 12 hours, the weather app is updated, and half a day later the cycle repeats itself.

Imagine an app that uses a similar method, except it plugs COVID data into a disease tracking model, charting the path of those at risk, exposed, infectious, and eventually recovered, hospitalized, or deceased. The data would include the obvious — rapid test and antigen test results, self-reported symptoms — as well as the more unexpected, like data from smartphones and the amount of virus in local sewage, which is fast becoming a valuable tool for predicting COVID outbreaks.

See also  The Narcissist in my Bedroom

“What matters is that this is person-specific,” explains Schneider. The app would not only predict the percentage of people in your city who are infected; Rather, it would use the data your Bluetooth-enabled device picks up to estimate your individual risk of contracting the virus.


Existing notification apps, which are more used in Europe and Asia than in the US, ping you after exposure to the virus, but they don’t update you between alerts. Schneider envisions using the data these apps use more efficiently, drawing on other data sources, providing a regularly updated infectivity forecast, and advising you to self-isolate after a likely exposure.

How effective would the app be?

In the study, Schneider and his team created a simulation city designed to mimic New York City in the early stages of the pandemic. This web of data included thousands of intersections, each representing a person—some with many daily interactions, others with few. Each has been assigned an age as age affects the path that COVID takes.


What their simulations found: If 75% of people used a COVID forecasting app and self-isolated as recommended, the pandemic could be effectively controlled — as long as diagnostic testing rates are high.

“It’s just as effective as a lockdown, except only a small fraction of the population is isolating at any given time,” says Schneider, noting that in this case a “small fraction” is about 10% of the population. “Most people could go about their lives normally.”

But as sluggish COVID vaccination rates have shown, near-universal compliance may be a goal that cannot be reached.

Another potential challenge: overcoming privacy concerns even though the data would be anonymized. Starting with smaller communities, like college campuses or workplaces, wider adoption could be encouraged, Schneider says, as people see the benefit of sharing their data. Younger people seem more comfortable with health information disclosure, meaning they may be more willing to use such an app, especially if it could stave off another lockdown.

The Future of Infectious Disease Tracking: Empowering Every Person

Mathematical modeling of infectious diseases is nothing new. During the H1N1 (swine flu) pandemic of 2009, the CDC used data from multiple sources to help slow the spread of the flu. During the Zika surge of 2016-2017, modeling helped researchers early identify the link between the virus and microcephaly, or a condition in which a baby’s head is much smaller than normal. According to a 2022 journal article in Clinical Infectious Diseases, mathematical predictions have been useful for everything from the flu to HIV.

See also  How to Improve Your Gut Health and Microbiome

Then came COVID-19 – the worst pandemic in US history, which required a new level of number crunching.

In collaboration with the University of Massachusetts at Amherst, the CDC created The Hub, a data archive that brought together multiple independent forecasts to predict COVID cases, hospitalizations and deaths. Not only did this massive undertaking help inform public policy — it also showed the importance of rapid contact tracing: if identifying close contacts took more than 6½ days after exposure, it was pretty much useless.

Schneider echoes that concern with what was once touted as a method for COVID control. In his team’s app-based forecasting simulations, “you’re reducing mortality rates by a factor of 2 to 4 just because you’re identifying more people who are likely to be infectious than you would through testing, tracing and isolation,” he says. Contact tracing has limited ability to control the spread of COVID due to the high asymptomatic transmission rate and short latency of the virus. By combining multiple data sources with a disease transmission model, you become more efficient.

“They know how it propagates across the network,” says Schneider. “And once you build that in, you get more effective control over the epidemic.”

Applying this mathematical approach to individuals – rather than entire populations – is the true innovation in Schneider’s vision. For example, in the past we could predict the chance of finding an infectious person anywhere in New York City. But the app Schneider hopes to develop would determine each user’s unique chance of infectivity. This makes it possible to make informed decisions – Am I going out tonight? Am I isolating myself? – more directly in everyone’s hands.

“We have technology here that can lead to the management of epidemics and even contain them altogether if adopted widely enough and combined with testing,” says Schneider, “and that’s just as effective as our lockdowns without isolating too much of it.” must the population.”

This innovation could help track down infectious diseases like the flu or even contain the next COVID, says Schneider.

“You want to control epidemics, you want to minimize disease and suffering,” he says. “At the same time, you want to minimize economic disruption and disruption to life and schooling. The hope is that through digital means like the ones we have outlined, you can achieve both of those goals.”


Leave a Reply

Your email address will not be published.