Predicting Poisson's Ratio: A Study of Semi-supervised Anomaly Detection and Supervised Approaches

Auxetics are a rare class of materials that exhibit a negative Poisson's ratio. The existence of these auxetic materials is rare but has a large number of applications in designing exotic materials. We build a complete machine learning framework to detect Auxetic materials as well as Poisson’s ratio of non-auxetic materials. A semi-supervised anomaly detection model is presented which is capable of separating out the auxetics materials (treated as an anomaly) from an unknown database with an average accuracy of 0.63. Another regression model (supervised) is also created to predict the Poisson’s ratio of non-auxetic materials with an R² ≈ 0.82. Additionally, this regression model helps in finding the optimal features for the anomaly detection model. This methodology can be generalized and used to discover materials with rare physical properties.