Researchers use AI to develop speed of specialized nanoparticles, according to a study published on June 1, 2018.
This study was conducted by the researchers at the Massachusetts Institute of Technology. This newly developed method, in future, is expected to be used in custom-designing of multilayered nanoparticles with desired properties. Researchers have used a type of artificial intelligence known as computational neural networks to understand how the behavior of nanoparticle such as scattering of light is affected by its structure. Then, using a process called as inverse design, particle with the suitable set of light-scattering properties can be designed.
The neural network was used on the system for nanophotonics. The nanoparticles are layered like an onion and each layer is made of a different material and has a different thickness. The size of the nanoparticles are comparable to the wavelengths of visible light and the way light of different colors scatters off of these particles depends on the details of these layers and on the wavelength of the incoming beam.
The neural network could exactly predict the pattern of a graph of light scattering versus wavelength. Furthermore, they reversed the program to check if the neural network works in the same way like before. When this was compared with the conventional inverse designs, this was found to be quicker. Shen, co-author said, “the initial motivation we had to do this was to set up a general toolbox that any generally well-educated person who isn’t an expert in photonics can use. That was our original motivation, and it clearly works pretty well for this particular case.”