Texas A&M researchers use AI to forecast pollution

Concern over pollution and its impact on weather patterns continues to increase — but what if severe weather events are also impacting pollution?

Researchers from Texas A&M University are using artificial intelligence to track pollution caused by accidental chemical emissions following natural hazards. An increased understanding of the relationship between natural hazards and unplanned chemical emissions may help researchers and policymakers predict, and hopefully prevent, future pollution. The research findings are outlined in a recently published paper.

“In this study, we pursued a data-driven understanding of how climate extremes elevate the likelihood of excessive industrial emissions,” said Dr. Qingsheng Wang, a professor of chemical engineering at Texas A&M. “This understanding is laying the groundwork for predictive tools allowing regulators and operators to anticipate natural hazard-triggered technological accidents.”

An unplanned emissions event or unscheduled maintenance that results in unauthorized emissions of air pollutants is known as a chemical emissions incident. Severe weather events frequently cause chemical emissions incidents, with some weather conditions causing more incidents than others.

For example, a chemical emissions incident occurred in August of 2017, after Hurricane Harvey’s floodwaters disabled the refrigeration trailers at a processing facility. As a result, more than 350,000 pounds of chemicals decomposed and burned, leading to unexpected pollution.

Researchers used artificial intelligence to analyze chemical emissions incident reports and weather data collected from the Houston area over the past 20 years.

The results indicate that precipitation and lightning are the two dominant predictors of chemical emissions incidents, and therefore of increased pollution. Flooding associated with heavy rain or hurricanes drives equipment failure, while lightning-induced power loss forces emergency flaring.

“Lightning and rainfall aren’t just weather forecast items; they’re leading indicators of pollution spikes,” said Haoyu Yang, a chemical engineering Ph.D. student at Texas A&M. 

Equipped with the knowledge that lightning and precipitation are the most likely weather variables to lead to a chemical emissions incident, researchers and local officials can be more prepared for these conditions and even find ways to prevent them.

This could lead to cleaner air and increased health protection for citizens. Forecasting “high-risk” days allows agencies to issue early warnings and reduce public exposure to carcinogens and smog precursors released during chemical emissions incidents.

Identifying trends can also support the implementation of evidence–based policies. The quantification of lightning and precipitation-driven risks supports targeted upgrades, like backup power and flood-proofing at facilities located near neighborhoods. 

This can bolster emergency preparedness and community resilience, which may already be occurring according to researchers’ observations.  

“We discovered that the strength of climate-incident correlations drifts over time, hinting at improving industrial resilience, potentially due to post-Harvey upgrades,” said Yang. “This weakens previously strong climate signals in the later years of the study. Identifying changes in the data over time is now a priority for future research.”

This research is the product of a collaboration between the Artie McFerrin Department of Chemical Engineering and the Texas A&M University Department of Geography. Yang is the first author and the corresponding author is Dr. Qingsheng Wang. The co-authors include assistant professor of geography Dr. Lei Zou, and chemical engineering Ph.D. student Chi-Yang Li.

This work is one aspect of the Climate-LEAD initiative (“Climate effects on Localized Environmental health disparities in overburdened Texas communities along the Gulf Coast”), funded by the Gulf Research Program of the U.S. National Academies of Sciences, Engineering, and Medicine. Dr. Wang’s process-safety group teamed up with Dr. Zou’s climate-geospatial lab to merge industrial incident data with high-resolution weather records. Graduate researchers Yang and Li joined through their research on natural-hazard-triggered-technological risk analytics.

By Alyssa Schaechinger, Texas A&M University College of Engineering