The UH team is developing ways to use machine learning to ensure that power systems can continue to run efficiently when pulling their energy from wind and solar sources. Photo via Getty Images

An associate professor at the University of Houston received the highly competitive National Science Foundation CAREER Award earlier this month for a proposal focused on integrating renewable resources to improve power grids.

The award grants more than $500,000 to Xingpeng Li, assistant professor of electrical and computer engineering and leader of the Renewable Power Grid Lab at UH, to continue his work on developing ways to use machine learning to ensure that power systems can continue to run efficiently when pulling their energy from wind and solar sources, according to a statement from UH. This work has applications in the events of large disturbances to the grid.

Li explains that currently, power grids run off of converted, stored kinetic energy during grid disturbances.

"For example, when the grid experiences sudden large generation losses or increased electrical loads, the stored kinetic energy immediately converted to electrical energy and addressed the temporary shortfall in generation,” Li said in a statement. “However, as the proportion of wind and solar power increases in the grid, we want to maximize their use since their marginal costs are zero and they provide clean energy. Since we reduce the use of those traditional generators, we also reduce the power system inertia (or stored kinetic energy) substantially.”

Li plans to use machine learning to create more streamlined models that can be implemented into day-ahead scheduling applications that grid operators currently use.

“With the proposed new modeling and computational approaches, we can better manage grids and ensure it can supply continuous quality power to all the consumers," he said.

In addition to supporting Li's research and model creations, the funds will also go toward Li and his team's creation of a free, open-source tool for students from kindergarten up through their graduate studies. They are also developing an “Applied Machine Learning in Power Systems” course. Li says the course will help meet workforce needs.

The CAREER Award recognizes early-career faculty members who “have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization,” according to the NSF. It's given to about 500 researchers each year.

Earlier this year, Rice assistant professor Amanda Marciel was also

granted an NSF CAREER Award to continue her research in designing branch elastomers that return to their original shape after being stretched. The research has applications in stretchable electronics and biomimetic tissues.

------

This article originally ran on EnergyCapital.

Ad Placement 300x100
Ad Placement 300x600

CultureMap Emails are Awesome

Houston researchers create AI model to tap into how brain activity relates to illness

brainiac

Houston researchers are part of a team that has created an AI model intended to understand how brain activity relates to behavior and illness.

Scientists from Baylor College of Medicine worked with peers from Yale University, University of Southern California and Idaho State University to make Brain Language Model, or BrainLM. Their research was published as a conference paper at ICLR 2024, a meeting of some of deep learning’s greatest minds.

“For a long time we’ve known that brain activity is related to a person’s behavior and to a lot of illnesses like seizures or Parkinson’s,” Dr. Chadi Abdallah, associate professor in the Menninger Department of Psychiatry and Behavioral Sciences at Baylor and co-corresponding author of the paper, says in a press release. “Functional brain imaging or functional MRIs allow us to look at brain activity throughout the brain, but we previously couldn’t fully capture the dynamic of these activities in time and space using traditional data analytical tools.

"More recently, people started using machine learning to capture the brain complexity and how it relates it to specific illnesses, but that turned out to require enrolling and fully examining thousands of patients with a particular behavior or illness, a very expensive process,” Abdallah continues.

Using 80,000 brain scans, the team was able to train their model to figure out how brain activities related to one another. Over time, this created the BrainLM brain activity foundational model. BrainLM is now well-trained enough to use to fine-tune a specific task and to ask questions in other studies.

Abdallah said that using BrainLM will cut costs significantly for scientists developing treatments for brain disorders. In clinical trials, it can cost “hundreds of millions of dollars,” he said, to enroll numerous patients and treat them over a significant time period. By using BrainLM, researchers can enroll half the subjects because the AI can select the individuals most likely to benefit.

The team found that BrainLM performed successfully in many different samples. That included predicting depression, anxiety and PTSD severity better than other machine learning tools that do not use generative AI.

“We found that BrainLM is performing very well. It is predicting brain activity in a new sample that was hidden from it during the training as well as doing well with data from new scanners and new population,” Abdallah says. “These impressive results were achieved with scans from 40,000 subjects. We are now working on considerably increasing the training dataset. The stronger the model we can build, the more we can do to assist with patient care, such as developing new treatment for mental illnesses or guiding neurosurgery for seizures or DBS.”

For those suffering from neurological and mental health disorders, BrainLM could be a key to unlocking treatments that will make a life-changing difference.

Houston-based cleantech unicorn named among annual top disruptors

on the rise

Houston-based biotech startup Solugen is making waves among innovative companies.

Solugen appears at No. 36 on CNBC’s annual Disruptor 50 list, which highlights private companies that are “upending the classic definition of disruption.” Privately owned startups founded after January 1, 2009, were eligible for the Disruptor 50 list.

Founded in 2016, Solugen replaces petroleum-based products with plant-derived substitutes through its Bioforge manufacturing platform. For example, it uses engineered enzymes and metal catalysts to convert feedstocks like sugar into chemicals that have traditionally been made from fossil fuels, such as petroleum and natural gas.

Solugen has raised $643 million in funding and now boasts a valuation of $2.2 billion.

“Sparked by a chance medical school poker game conversation in 2016, Solugen evolved from prototype to physical asset in five years, and production hit commercial scale shortly thereafter,” says CNBC.

Solugen co-founders Gaurab Chakrabarti and Sean Hunt received the Entrepreneur of The Year 2023 National Award, presented by professional services giant EY.

“Solugen is a textbook startup launched by two partners with $10,000 in seed money that is revolutionizing the chemical refining industry. The innovation-driven company is tackling impactful, life-changing issues important to the planet,” Entrepreneur of The Year judges wrote.

In April 2024, Solugen broke ground on a Bioforge biomanufacturing plant in Marshall, Minnesota. The 500,000-square-foot, 34-acre facility arose through a Solugen partnership with ADM. Chicago-based ADM produces agricultural products, commodities, and ingredients. The plant is expected to open in the fall of 2025.

“Solugen’s … technology is a transformative force in sustainable chemical manufacturing,” says Hunt. “The new facility will significantly increase our existing capabilities, enabling us to expand the market share of low-carbon chemistries.”

Houston cleantech company tests ​all-electric CO2-to-fuel production technology

RESULTS ARE IN

Houston-based clean energy company Syzygy Plasmonics has successfully tested all-electric CO2-to-fuel production technology at RTI International’s facility at North Carolina’s Research Triangle Park.

Syzygy says the technology can significantly decarbonize transportation by converting two potent greenhouse gases, carbon dioxide and methane, into low-carbon jet fuel, diesel, and gasoline.

Equinor Ventures and Sumitomo Corp. of Americas sponsored the pilot project.

“This project showcases our ability to fight climate change by converting harmful greenhouse gases into fuel,” Trevor Best, CEO of Syzygy, says in a news release.

“At scale,” he adds, “we’re talking about significantly reducing and potentially eliminating the carbon intensity of shipping, trucking, and aviation. This is a major step toward quickly and cost effectively cutting emissions from the heavy-duty transport sector.”

At commercial scale, a typical Syzygy plant will consume nearly 200,000 tons of CO2 per year, the equivalent of taking 45,000 cars off the road.

“The results of this demonstration are encouraging and represent an important milestone in our collaboration with Syzygy,” says Sameer Parvathikar, director of renewable energy and energy storage at RTI.

In addition to the CO2-to-fuel demonstration, Syzygy's Ammonia e-Cracking™ technology has completed over 2,000 hours of performance and optimization testing at its plant in Houston. Syzygy is finalizing a site and partners for a commercial CO2-to-fuel plant.

Syzygy is working to decarbonize the chemical industry, responsible for almost 20 percent of industrial CO2 emissions, by using light instead of combustion to drive chemical reactions.

------

This article originally ran on EnergyCapital.