Materials design follows an experimentally-guided trial-and-error process which limits the search for untapped regions of the solution space and introduces difficulties in adapting designs to new circumstances. This talk discusses how machine learning and optimization can help in the discovery and design process of a lightweight, recoverable and super-compressible metamaterial achieving more than 90% compressive strain without damage. Within minutes, the machine learning model can be used to optimize designs for different choices of base material, length-scales and manufacturing process.
