Current methods can predict ozone levels in the earth’s troposphere only three days in advance.

Researchers at the University of Houston’s Air Quality Forecasting and Modelling Lab have achieved a breakthrough in predicting the levels of ozone in the Earth’s troposphere, the lowest level of our atmosphere. Their new artificial intelligence system, which forecasts these levels up to two weeks in advance is a huge improvement on current methods that can do so for only three days ahead. (University of Houston)

Ozone and its impact on our lives

Ozone in the Earth’s stratosphere (“ozone layer”) is vital to our well-being because it shields us from harmful ultraviolet radiation from the sun. However, lower down, in the troposphere, which is the lowest layer of our atmosphere, high concentrations of this gas can be damaging to human health, particularly lungs and hearts.

According to doctoral student Alqamah Sayeed, a researcher in Choi’s lab and the first author of the research paper on this subject, ozone is a secondary pollutant and can affect humans badly. Typical symptoms include throat irritation, breathing difficulty, asthma, and even respiratory damage.

Predicting ozone levels has therefore become common in many weather reports. Unfortunately, the current process is slow, expensive, and has limited accuracy. It uses a numerical model that delivers its output based on the equation for the movement of gases and fluids in the atmosphere.

AI breakthrough

However, after years of effort, researchers at the University of Houston succeeded in harnessing artificial intelligence (AI) for ozone forecasting up to 2 weeks in advance.

“This was very challenging. Nobody had done this previously. I believe we are the first to try to forecast surface ozone levels two weeks in advance,” said Yunsoo Choi, professor of atmospheric chemistry and AI deep learning at UH’s College of Natural Sciences and Mathematics.

Choi and his team used 4 to 5 years of ozone data to teach the AI algorithm to recognize ozone conditions and generate forecasts. The algorithm started getting better over time.

“Applying deep learning to air quality and weather forecasting is like searching for the holy grail, just like in the movies,” says Choi. “In the lab, we went through some difficult times for a few years. There is a process. Finally, we’ve grasped the holy grail. This system works. The AI model ‘understands’ how to forecast. Despite the years of work, it somehow still feels like a surprise to me, even today.”

According to the researchers, learning from the innovative AI model could, over time, be applied to resolve the climate change issue.

Related Story:  AI Keeps Google’s Loon Balloons On Course In The Stratosphere