How Seattle is building weather forecasting technology to detect heat waves

Seattle’s weather was in the sunny high 70s in mid-July, when weather forecasters saw a 90-degree high heat wave on its way this week.

This is a change from decades ago, when summer could suddenly be hit or miss. Advances in technology and technology have turned weather into a thriving part of the tech sector with the development of satellites, radar, and artificial intelligence.

Forecasters today can predict what the weather will be like with greater accuracy thanks to an improved system of weather satellites and increasingly complex algorithms. Opportunities for artificial intelligence-driven advancements and the increase in catastrophic weather events caused by climate change have attracted more innovators and entrepreneurs to weather forecasting, claiming they have access to more information and better technology than the government.

State climatologist Nick Bond of the University of Washington said the current heat wave coming into the Pacific Northwest was predicted using data from satellites that measure the atmosphere in parts of the Pacific Ocean. Satellites collected data on humidity, temperature and wind, and computers analyzed conditions through complex equations that predicted summer would soon hit the region.

“It’s really pretty remarkable what we can do like that, with satellites that are above the air,” Bond said.

Model making is not easy. According to journalist Andrew Blum in his book “The Weather Machine,” “landing a spacecraft on Mars requires dealing with hundreds of mathematical variables. Creating a global atmospheric model requires hundreds of thousands.”

Bond said weather-forecasting techniques were able to accurately predict the 2021 Pacific Northwest heat wave lasting from late June to early July. at least as a result of a heat wave 100 deaths due to heatAccording to the Washington State Department of Health.

There has always been a level of uncertainty in forecasting. For example, rain is difficult to predict because it can be patchy and hit different parts of the geographic grid, which forecasters analyze to tell the weather. Bond said that as extreme events such as thunderstorms and tornadoes become more intense due to climate change, forecasting becomes even more challenging.

He said the challenge is predicting enough for people to prepare or evacuate.

While the National Weather Service has long been, and continues to be, a major player in US forecasting, private sector companies including Microsoft are pursuing technologies they believe will be more accurate, more accurate. Can give weather reports.

Last year, Microsoft entered into an agreement with the US Army Corps of Engineers and the UK’s National Weather Service to build technology that will help modeling storms and other extreme weather.

Startups specializing in weather forecasting are also racing into space. Cambridge, Massachusetts-Based Key Predictions Raised $5.3 million in seed funding, Salient claims that its technology is more accurate than those offered by other companies and governments.

When Eric Moldstad founded Seattle-based Accurate Forecasts in 2003, private weather forecasts were scarce and difficult to access. Moldstad’s company emails them a list of paying customers every morning. Now, he said, boutique forecasts and satellite images are everywhere and available to almost everyone.

“Then there was some Internet information, but most of the information (forecast models, satellite imagery) was only available through a subscription,” Moldstadt said. He said the Internet has made weather forecasts more widely available.

Moldstadt said it uses information from radar, weather stations and satellites to create daily reports that are sent to customers. The report notes the weather from the previous day, the current weather and the forecast for the next day.

But the new technologies aim to outpace the lead time and accuracy of existing models. Testifying in Congress last monthBrad Coleman, director of weather strategy at Bayer, said “there is some slowing in forecasting skills improvement across all major global modeling efforts” as the technology reaches its limits. Bayer has a subsidiary, The Climate Corporation, which focuses on crop development.

Coleman said a system that includes ocean, glacier and land models would contribute to the expansion of forecasting skills, as the data would be available for a longer period of time.

UW Professor Dale Durran said artificial intelligence has been growing in the forecasting field for the past three years with the promise of increasing weather accuracy.

Computers processing datasets from satellites are limited in how much they can digest, and this can take a long time. AI will use more data from, for example, stressed crops, and process it more quickly as the machine learns from similar weather patterns that can be applied to the current season, Durran said.

The technology is still in development and may not be used yet, but it shows promise that forecasts can be more accurate. However, there is a limit to the time leading up to the forecast that AI cannot yet solve. The weather, Durran said, is “very chaotic”.

Still, weather forecasting has improved significantly since people had to sit down and use equations, Bond said. The models in use now were “only seen decades ago.”

Leave a Comment

%d bloggers like this: