Keke Tang

About

Keke Tang is a leading researcher in the intersection of mechanical metamaterials and machine learning, with a primary focus on the inverse design and property prediction of advanced cellular structures. Her most impactful work introduces a novel, prior knowledge-free machine learning framework that enables both the prediction and inverse design of two-dimensional metamaterials exhibiting tunable, deformation-dependent Poisson’s ratios—including the rare and highly sought-after negative Poisson’s ratio. This contribution, published in 2022 and already garnering 57 citations, is notable for eliminating the need for extensive pre-existing physical models, thereby significantly accelerating the discovery of metamaterials with extraordinary mechanical properties. By bridging the gap between data-driven algorithms and structural mechanics, Tang’s research offers a powerful, efficient pathway for customizing material behaviors, with profound implications for aerospace, biomedical devices, and soft robotics. Her work stands as a key reference for researchers seeking to harness machine learning for the rational design of next-generation mechanical metamaterials.

Research Focus

Key Achievements

Top Papers

1. 1
   Machine learning-based prediction and inverse design of 2D metamaterial structures with tunable deformation-dependent Poisson's ratio

   57 citations · 2022

Key Collaborators

Contact & Links