Using artificial intelligence (AI) and machine learning (ML) techniques, NETL researchers permeate coal-burning waste using sorbents synthesized from fly ash, which is the coal-burning waste itself. I’m looking for a way to treat water. Management costs of future landfills.
According to the University of Kentucky Geological Survey, coal-fired power plants in the United States generate 100 to 130 million tons of combustion waste annually, and these materials are often dumped into reservoirs.
Leachate is liquid pollution that can escape from reservoirs and often contains chemicals that are harmful to the environment. Sorbents are materials used to recover substances by adsorption. Adsorbents can adsorb harmful substances in the leachate. New sorbents can be expensive and time consuming to design and create.
Based on the pore size and composition of the adsorbent, zeolites are one of the most important adsorbents and are frequently used in industrial applications for water and wastewater treatment. Certain zeolites can be readily synthesized from coal combustion residues.
While investigating the problem of wastewater leaching from coal ash reservoirs, researchers at NETL realized that AI/ML techniques could be used to design sorbents to treat the leachate.
Using AI Computers perform functions that traditionally required human intelligence because AI can process large amounts of data in ways humans cannot. AI can recognize patterns, make decisions, and make judgments just like humans. ML is a branch of AI and computer science that focuses on using data and algorithms to mimic how humans learn, with incremental accuracy. Algorithms in ML are the steps performed on data to create an ML learning model that performs pattern recognition functions. Basically, algorithms learn from data.
In this project, researchers used physics-based simulations to predict the adsorption of contaminants under several different conditions on zeolites that can be synthesized from fly ash. Using these results, researchers created a database to use for ML. In this step, the researcher fits the model to the data. Using this model in combination with genetic algorithms allowed researchers to tailor sorbents to specific storage sites to optimize contaminant uptake.
According to NETL’s John Findley, lab research will enable the rapid design of tailor-made sorbents.
“Interestingly, the zeolite sorbents identified by the NETL model can be synthesized from fly ash and then deployed to treat leachate from conventional coal ash storage,” says Findley. “If that happens, we will be using coal combustion residues to deal with the environmental debt from coal combustion residues.”
NETL researcher Jan Steckel said AI/ML techniques allow for rapid and customized sorbent development, saving the time and He added that the study demonstrates that costs can be significantly reduced.
“The methods developed at NETL have potential for many applications in materials design,” says Steckel. “Innovative projects like this combine physics-based simulation with 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. Leveraging world-class talent and research facilities, NETL secures affordable, abundant and reliable energy that advances the economy and national security while developing technologies that manage carbon throughout its lifecycle and making environmental sustainability a reality for all Americans.
