Using artificial intelligence (AI) and machine learning (ML) techniques, NETL researchers are exploring a way to treat water that seeps through coal combustion waste using a sorbent synthesized from fly ash, itself a coal combustion waste ─ a development with implications for improving the costs of managing future waste sites.

According to the University of Kentucky Geological Survey, the United States produces 100 to 130 million tons of combustion wastes annually at coal-fired power plants and in many cases, those materials are disposed of in impoundment ponds.

Leachate is liquid pollution that can escape from impoundments, and it often contains chemicals that are bad for the environment. Sorbents are materials used to recover substances through adsorption. Sorbents can adsorb harmful substances in leachate. New sorbents can be expensive and time-consuming to design and create.

Based on the pore size and composition of the sorbent, zeolites are among the most important sorbents and are frequently used in industrial applications for water and wastewater treatment. Certain zeolites can be readily synthesized from coal combustion residuals.

While investigating the problem of wastewater leaching from coal ash impoundments, NETL researchers realized that AI/ML methods could be used to design sorbents to treat leachates.

AI uses computers to perform functions that traditionally require human intelligence because AI can process large amounts of data in ways that humans cannot. AI can recognize patterns, make decisions, and make judgments like humans. ML is a branch of AI and computer science that focuses on using data and algorithms to imitate the way that humans learn, which gradually improves accuracy. In ML, an algorithm is a procedure that runs on data to create an ML learning model that performs pattern recognition functions. Essentially, the algorithms learn from the data.

In this project, researchers used physics-based simulations to predict the adsorption of a pollutant in several distinct conditions in zeolites which could be synthesized from fly ash. Using these results, the researchers created a database to use for ML. In this step, the researchers fit a model to the data. Using the model in combination with a genetic algorithm, researchers were able to tailor a sorbent to specific impoundment sites to optimize the uptake of the pollutant.    

According to NETL’s John Findley, the Lab’s research allows for the rapid design of tailor-made sorbents.

“Interestingly, the zeolite sorbents identified by the NETL model could be synthesized from fly ash, which could then be deployed to treat leachate from legacy coal ash impoundments,” Findley said. “If that were to happen, you would be using coal combustion residuals to treat environmental liabilities from coal combustion residuals.”

NETL researcher Jan Steckel added that the work demonstrates that AI/ML methodologies can be used for rapid, customized sorbent development, greatly reducing the time and expense usually required to develop sorbents for treating impoundment leachates.

“The methods developed at NETL have the possibility to be applied to many applications in materials design” Steckel said. “Innovative projects like this connect physics-informed simulations to the speed of ML and AI to have a real impact on materials design.”

NETL is a DOE national laboratory that drives innovation and delivers technological solutions for an environmentally sustainable and prosperous energy future. By using its world-class talent and research facilities, NETL is ensuring affordable, abundant and reliable energy that drives a robust economy and national security, while developing technologies to manage carbon across the full life cycle, enabling environmental sustainability for all Americans.