Accelerated design and characterization of nonuniformed cellular architected materials with tunable mechanical properties

Cellular materials, widely found in engineered and natural systems, are highly dependent on their geometric arrangement. A nonuniform arrangement could lead to a significant variation of mechanical properties while bringing challenges to material design. Here, this proof-of-concept study demonstrates a machine-learning-based framework with the capability of accelerated characterization and pattern generation, which also opens new avenues for the programmability of function at the system level.