A University of Houston team looked into what areas in Houston had the highest impact on emissions and how certain meteorological factors play into ozone formation. Photo via UH.edu

A team of researchers at the University of Houston are using machine learning to help guide pollution fighting strategies.

As reported in the journal Environmental Pollution last month, the team used the SHAP algorithm of machine learning (a game theory approach) and the Positive Matrix Factorization to pinpoint what areas in Houston had the highest impact on emissions and how certain meteorological factors play into ozone formation.

The paper was authored by Delaney Nelson, a doctoral student at the Department of Earth and Atmospheric Sciences of UH, and Yunsoo Choi, corresponding author and professor of atmospheric chemistry, AI deep learning, air quality modeling and satellite remote sensing.

The team's research closely tracked nitrogen-based compound and volatile organic compound measurements from Texas Commission on Environmental Quality's monitoring stations in the Houston area. After importing measurements from The Lynchburg Ferry station in Houston's ship channel and the urban Milby Park station, the machine learning and SHAP analysis showed a chemically definitive difference between the two areas.

For example, at the industrial station, the most impactful sources of pollution were from oil and gas flaring/production. At the urban site n_decane and industrial emissions/evaporation had the most impact on ozone.

According to Nelson and Choi, this shows that the machine learning and SHAP analysis approach can be used to tailor more precise air quality management strategies in different areas based on the site's unique characteristics.

“Once we know the specific emission sources and factors, we can develop targeted strategies to reduce emissions, which will in turn reduce ozone in the air and make it healthier for everyone," Choi said in a statement.

“Pollution is a critical issue in Houston, where you have extreme high heat and high concentration of ozone in the summers. The types of insights we got are very useful information for the local community to develop effective policies. That’s why we put our time, effort and technological expertise into this project," he continued.

Next the team envisions applying their approach in different cities and across the country.

“Austin, San Antonio and Dallas all have different characteristics, so I expect (volatile organic compound) sources will also be different,” Choi said. “Identifying VOC sources in different cities is very important because each city should have its own unique pollution fighting strategy.”

This summer, the City of Houston released an updated report on its major strategies to combat climate change and build a more resilient future for its residents.

Ad Placement 300x100
Ad Placement 300x600

CultureMap Emails are Awesome

Gold H2 harvests clean hydrogen from depleted California reservoirs in first field trial

breakthrough trial

Houston climatech company Gold H2 completed its first field trial that demonstrates subsurface bio-stimulated hydrogen production, which leverages microbiology and existing infrastructure to produce clean hydrogen.

Gold H2 is a spinoff of another Houston biotech company, Cemvita.

“When we compare our tech to the rest of the stack, I think we blow the competition out of the water," Prabhdeep Singh Sekhon, CEO of Gold H2 Sekhon previously told Energy Capital.

The project represented the first-of-its-kind application of Gold H2’s proprietary biotechnology, which generates hydrogen from depleted oil reservoirs, eliminating the need for new drilling, electrolysis or energy-intensive surface facilities. The Woodlands-based ChampionX LLC served as the oilfield services provider, and the trial was conducted in an oilfield in California’s San Joaquin Basin.

According to the company, Gold H2’s technology could yield up to 250 billion kilograms of low-carbon hydrogen, which is estimated to provide enough clean power to Los Angeles for over 50 years and avoid roughly 1 billion metric tons of CO2 equivalent.

“This field trial is tangible proof. We’ve taken a climate liability and turned it into a scalable, low-cost hydrogen solution,” Sekhon said in a news release. “It’s a new blueprint for decarbonization, built for speed, affordability, and global impact.”

Highlights of the trial include:

  • First-ever demonstration of biologically stimulated hydrogen generation at commercial field scale with unprecedented results of 40 percent H2 in the gas stream.
  • Demonstrated how end-of-life oilfield liabilities can be repurposed into hydrogen-producing assets.
  • The trial achieved 400,000 ppm of hydrogen in produced gases, which, according to the company,y is an “unprecedented concentration for a huff-and-puff style operation and a strong indicator of just how robust the process can perform under real-world conditions.”
  • The field trial marked readiness for commercial deployment with targeted hydrogen production costs below $0.50/kg.

“This breakthrough isn’t just a step forward, it’s a leap toward climate impact at scale,” Jillian Evanko, CEO and president at Chart Industries Inc., Gold H2 investor and advisor, added in the release. “By turning depleted oil fields into clean hydrogen generators, Gold H2 has provided a roadmap to produce low-cost, low-carbon energy using the very infrastructure that powered the last century. This changes the game for how the world can decarbonize heavy industry, power grids, and economies, faster and more affordably than we ever thought possible.”

Rice University spinout lands $500K NSF grant to boost chip sustainability

cooler computing

HEXAspec, a spinout from Rice University's Liu Idea Lab for Innovation and Entrepreneurship, was recently awarded a $500,000 National Science Foundation Partnership for Innovation grant.

The team says it will use the funding to continue enhancing semiconductor chips’ thermal conductivity to boost computing power. According to a release from Rice, HEXAspec has developed breakthrough inorganic fillers that allow graphic processing units (GPUs) to use less water and electricity and generate less heat.

The technology has major implications for the future of computing with AI sustainably.

“With the huge scale of investment in new computing infrastructure, the problem of managing the heat produced by these GPUs and semiconductors has grown exponentially. We’re excited to use this award to further our material to meet the needs of existing and emerging industry partners and unlock a new era of computing,” HEXAspec co-founder Tianshu Zhai said in the release.

HEXAspec was founded by Zhai and Chen-Yang Lin, who both participated in the Rice Innovation Fellows program. A third co-founder, Jing Zhang, also worked as a postdoctoral researcher and a research scientist at Rice, according to HEXAspec's website.

The HEXASpec team won the Liu Idea Lab for Innovation and Entrepreneurship's H. Albert Napier Rice Launch Challenge in 2024. More recently, it also won this year's Energy Venture Day and Pitch Competition during CERAWeek in the TEX-E student track, taking home $25,000.

"The grant from the NSF is a game-changer, accelerating the path to market for this transformative technology," Kyle Judah, executive director of Lilie, added in the release.

---

This article originally ran on InnovationMap.