Transforming Scientific Inquiry: How AI and Machine Learning Aid OU Researchers in Innovative Breakthroughs

Next-Generation Weather Research

Groundbreaking strides in weather prediction and research are being achieved through artificial intelligence applications at the University of Oklahoma. The OU-led National Science Foundation AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography, or AI2ES, aims to revolutionize understanding and prediction of high-impact atmospheric and ocean science phenomena. By fostering trustworthy AI methods, AI2ES ensures that the actionable intelligence generated by AI technologies is reliable and useful in real-world applications. Additionally, the program is educating and retraining today’s workers to leverage the power of artificial intelligence and machine learning to improve their careers and the planet.

“Understanding what it means to create trustworthy artificial intelligence is critical as AI applications are expanding rapidly in society,” said Amy McGovern, principal investigator for the AI2ES, the Lloyd G. and Joyce Austin Presidential Professor in the Gallogly College of Engineering and professor in the OU School of Meteorology. “AI2ES is taking the lead in understanding how professional end-users can work side-by-side with AI methods to improve decision-making for high-risk tasks.”

OU researchers are also addressing the challenges posed by extreme weather, climate change, and natural hazards on aging reservoir systems with the help of novel artificial intelligence and data mining tools. By utilizing deep learning models, these researchers hope to correct errors in current precipitation forecasts, conduct large-scale validation experiments and simulations across the U.S., and ultimately prevent reservoir failures.

The Advanced Radar Research Center’s all-digital polarimetric phased array radar, “Horus,” provides unparalleled atmospheric data quality and temporal resolution. It also offers unprecedented clarity and insights into the genesis of severe weather events. With its highly robust weather-processing algorithms, Horus can capture and analyze terabytes of data each minute and produce actionable information to help scientists understand and predict severe weather formation. As artificial intelligence continues to advance, expect to see even more impressive outcomes from OU’s radar program.

These efforts contribute to the safety and well-being of communities impacted by severe weather. They are paving the way for a future where rapid analysis and response to atmospheric changes can save lives and resources around the globe.

Ambitious Green Energy Research

A team of OU researchers is advancing methane monitoring technology with funding from the U.S. Department of Energy. This project harnesses innovative technologies to develop a network to predict, sense, and reduce methane emissions in the Anadarko Basin. By deploying autonomous-capable mobile sensing tools using a self-driving Tesla and unmanned robot, the team will be better able to identify and quantify methane emission sources.

Similarly, OU’s Data Institute for Societal Challenges is designing a fully integrated platform for continuous methane emission monitoring, potentially covering scales from individual facilities to entire continents. By adopting and employing machine learning advancements, these initiatives could lead to a robust solution for real-time, large-scale methane emission tracking, significantly enhancing natural gas production safety and environmental compliance.

“Creating a leak-tight energy system is key to sustainability and a great example of the combination of cutting-edge science, policy and data science innovation here at the University of Oklahoma,” said David Ebert, the Gallogly Chair Professor of electrical and computer engineering and director of the Data Institute for Societal Challenges.

Researchers in the OU Mewbourne School of Petroleum and Geological Engineering are also using advanced 3D modeling technology to study the area around geothermal wells in eastern California. After extensive observation, modeling and computer simulation, they will create and monitor controlled fracture networks around the wells and hope to improve well output cost-effectively.

Cutting-Edge Medical Research

Researchers at the University of Oklahoma are pioneering medical research, particularly in studying human genetics and disease. The recent discovery of 135 new genes responsible for pigmentation showcases the university's innovative use of AI and machine learning in health-related research. This work has significant implications for understanding the genetic factors that determine skin, hair, and eye color and could lead to breakthroughs in future genetic research and personalized medicine.

By combining machine learning and artificial intelligence, OU researchers are also developing novel endoscopic optical imaging techniques to provide real-time visualizations to help clinicians successfully administer needle-based medical interventions. This research will have broad applications for brain and tumor-related or laparoscopic surgeries.

By integrating machine learning algorithms with biological data and artificial intelligence, OU researchers are on the front lines of creating predictive models that can lead to more effective treatments and preventive strategies. 

Big Data, Big Opportunities

The University of Oklahoma is harnessing the power of big data to unlock solutions to some of society’s most persistent challenges. Through its Data Institute for Societal Challenges, OU is pioneering data analysis techniques incorporating artificial intelligence and machine learning to transform massive amounts of data—from cell phones, sensors, videos, automation, and simulation—into actionable insights.

This effort includes a federally funded project that addresses false claims and attacks on infrastructure. By analyzing data patterns and enhancing information reliability through machine learning, researchers at OU seek to minimize the disinformation that can be weaponized to disrupt underlying cyber-physical systems, human lives, and economic productivity.

Additionally, OU researchers are creating an extensive computational and visual analytic environment using state-of-the-art modeling and predictive techniques to identify vulnerabilities and patterns that can help decision-makers better understand the different types of risks associated with the global supply chain networks. These enhanced efforts will help the nation better withstand and recover from any supply chain disruptions as quickly as possible.

“The 448 Supply Chain Management Wing at Tinker Air Force Base is the global supply chain manager for the entire U.S. Air Force,” said Lt Gen (ret) Don Wetekam, chief strategist for OU’s Oklahoma Aerospace and Defense Innovation Institute. “Working with the 448 is an opportunity for the University of Oklahoma and our research capabilities to contribute to our national defense.”

Other relevant research includes exploring how machine learning and artificial intelligence can be used with traditional statistical data analysis for social and natural sciences, an enhanced understanding and predictability of landslides, identifying faults and seismic characteristics, innovative collaborations with the OU emerging technologies program, and more.

“All fields are creating digital data today, and close collaboration between domain researchers, data scientists, and the public drives use-inspired innovation, creating the evolution of technology that can transform lives, our society, and our world,” Ebert said. “This culture of convergent research is powering important innovations at OU and creating beneficial societal impact.”

These data analysis initiatives and integration of artificial intelligence, machine learning, and advanced computing are integral to research success at the University of Oklahoma. By embracing the technological advancements these processes provide, OU research is changing lives.