{"id":1608,"date":"2023-07-31T10:17:00","date_gmt":"2023-07-31T10:17:00","guid":{"rendered":"https:\/\/live-usc-dornsife.pantheonsite.io\/wrigley\/?p=1608"},"modified":"2025-07-08T21:38:08","modified_gmt":"2025-07-08T21:38:08","slug":"artificial-intelligence-can-teach-us-about-air","status":"publish","type":"post","link":"https:\/\/dornsife.usc.edu\/wrigley\/2023\/07\/31\/artificial-intelligence-can-teach-us-about-air\/","title":{"rendered":"What artificial intelligence can teach us about the air we breathe \u2013 and what we have to teach it"},"content":{"rendered":"\n\n\n\n\n \n \n\n\n\n\n\n\n\n
\n\n \n
\n \n \n
\n \n \n
\n\n \n

What artificial intelligence can teach us about the air we breathe \u2013 and what we have to teach it<\/h1>\n\n\n<\/div>\n \n \n By<\/span>Obin Sturm<\/strong>\n \n July 31, 2023<\/span>\n <\/div>\n<\/div>\n\n\n <\/div><\/div>\n\n \n \n\n\n\n\n\n\n\n
\n\n \n
\n \n \n Share\n <\/span>\n \n \n <\/svg>\n <\/span>\n Copy Link<\/span>\n <\/a>\n \n \n <\/svg>\n <\/span>\n Facebook<\/span>\n <\/a>\n \n \n \n\n<\/svg>\n\n <\/span>\n X<\/span>\n <\/a>\n \n \n <\/svg>\n <\/span>\n LinkedIn<\/span>\n <\/a>\n \n \n \n \n <\/svg>\n <\/span>\n Bluesky<\/span>\n <\/a>\n \n \n <\/svg>\n <\/span>\n Email<\/span>\n <\/a>\n <\/span>\n <\/div>\n\n <\/div><\/div>\n \n\n\n\n \n \n\n\n\n\n\n\n\n
\n\n \n \n
\n\n \n

Changes in our atmosphere, driven by societal emissions, have begun to affect our daily existence. Air polluted with ozone and particulate matter is linked to the deaths of millions of people a year. Increased temperatures caused by global climate change have led to many more public health risks, including increasingly severe wildfires, which emit vast amounts of particulate matter that is transported by the wind across state and international borders. These linked environmental issues drive a system of complex interactions on a regional and global scale. Understanding these interactions is crucial for scientifically informed environmental policy. Computer simulations of atmospheric processes help us predict future environmental effects of our present-day societal decisions.<\/p>\n

At the same time, artificial intelligence or AI, a set of algorithms that learn patterns from data, has started to creep into our everyday lives. Recommender systems control social media feeds, images can be generated from text prompts, and large language models like ChatGPT can help us write convincing emails, articles, and blog posts. Though these are exciting new developments, one challenge of AI models like ChatGPT is knowing when to trust them. Even when the data doesn\u2019t lie, the data-driven algorithm can.<\/p>\n

My name is Obin Sturm, and I\u2019m a 2023 Sonosky Fellow working at the intersection of air quality and AI in the\u00a0Earth Data Science and Atmospheric Composition<\/a>\u00a0group led by Professor Sam Silva. My research focuses on how we can use AI and other data-driven approaches to improve air quality and climate models. I think it\u2019s very important to ensure these data-driven algorithms deliver scientifically trustworthy results.<\/p>\n

\"\"
Obin Sturm conducts most of his research by talking to computers. Though some of the work can be done on a laptop, often the laptop is securely connected to supercomputers for larger Earth system simulations that require high performance computing. Sturm runs atmospheric forecasts using the Discover supercomputing cluster at the NASA Center for Climate Simulation, which is capable of 8,100 trillion floating-point operations a second: enough to run many, many, Earth system simulations at the same time. (Courtesy of Obin Sturm)<\/figcaption><\/figure>\n

How can AI improve atmospheric simulations? What can it teach us?<\/b><\/h4>\n

Some data-driven algorithms are good at finding simple patterns in complex data. This enables more realistic yet efficient simulations of complex processes. One project I worked on (published this spring<\/a>\u00a0in Journal of Advances in Modeling Earth Systems for a special issue on machine learning!) found patterns in the concentrations of secondary organic aerosol, which is an important component of particulate pollution. This allows a simple representation of particulate matter for wind transport but full complexity for aerosol formation, enabling a more realistic representation of particulate pollution in air quality forecasts for Europe.<\/p>\n

This summer as a Sonosky Fellow, I am continuing to study air pollution with data-driven techniques. Given only data on pollutant concentrations, can we use AI to infer the complex network of chemical reactions behind the scenes? This knowledge is essential for accurate air quality models and is usually obtained in a lab one reaction at a time. I am hoping to develop a complementary approach by building on an existing technique called a chemical reaction neural network and applying it first to a simple smog model. So far, the technique is able to rediscover one known reaction: that ozone reacts with nitric oxide, a primary pollutant from car exhaust. However, this is just one of 10 reactions in the reaction network, and one of many more in the actual atmosphere, so we have a long way to go. Chemistry can be hard to learn, even for AI!<\/p>\n

Many atmospheric models, like the smog model I\u2019m trying to teach to AI, are not data-driven but rather based on our understanding of how the universe works. Such models often obey fundamental physical laws, for example mass conservation: \u201cmatter cannot be created nor destroyed.\u201d A second part of my summer fellowship research, in collaboration with researchers at the Tegmark group at MIT, tested a data-driven tool that is designed to discover invariants from data, such as mass conservation during chemical reactions.<\/p>\n

We analyzed simulated concentrations from the smog model with the hypothesis that this data-driven technique would find the built-in carbon and nitrogen conservation. However, we not only rediscovered both conservation laws, but also a third unexpected constant. This third conserved quantity is a combination of several pollutant concentrations that stays constant over a wide variety of atmospheric conditions, even when the chemistry is changing rapidly. Earlier this summer, we submitted some of this work to a journal for peer-review (arXiv preprint<\/a>), and it also got some attention on Twitter (see below).<\/p>\n

\n

With our new #AI<\/a> algorithm, we finally managed to discover new conservation laws that domain experts didn’t know about, in both fluid mechanics and atmospheric chemistry: https:\/\/t.co\/yWjNtkE2O3<\/a> pic.twitter.com\/0vtEcp7Kx1<\/a><\/p>\n

\u2014 Max Tegmark (@tegmark) June 1, 2023<\/a><\/p><\/blockquote>\n