Researchers improve water filter systems using AI

Now a research team from the University of California Santa Barbara in the US has replicated different patterns of hydrophilic and hydrophobic materials lining a filter’s porous membrane and found ideal configurations that would allow water to pass through more easily. They also discovered filters that would slow down some contaminants when testing the porous membrane.

A bottle of boric acid in a laboratory

Sort connections by size and charge

The difficulty with filtering stems from the fact that synthetic porous materials are usually limited to sorting and separating compounds by either size or charge. However, biological membranes have pores made of proteins such as aquaporin (AQP).

Aquaporins are integral membrane proteins — a protein permanently attached to the biological membrane — that act as channels in the transfer of water and, in some cases, small solutes across the membrane.

Aquaporin can separate water from other molecules both by size and by charge because several different types of functional groups, or assemblies of atoms, line the channels. M. Scott Shell, a professor in the Myers Founders Chair and vice chair in chemical engineering at the University of California, Santa Barbara, decided to develop the same design using synthetic porous material.

Shell and his team wanted to use artificial intelligence and computers to design the inside of a pore made of carbon nanotubes to filter water containing boric acid.

Researchers improve water filtration systems using AI

3D rendering of a carbon nanotube pore.

The researchers mimicked a channel of carbon nanotubes with hydroxyl (hydrophilic) and/or methyl (water-repellent) groups attached to each atom on the inner wall. Next, they designed and tested thousands of functional group patterns using AI, optimization algorithms, and machine learning to evaluate how fast water and boric acid would flow through the pore.

You might also like

Comments are closed.