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

20 September 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

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.

Keywords

Auxetic
Machine Learning
Anomaly Detection
Deep Learning
Autoencoder
Semi-Supervised
Supervised
Regression
Elastic
Material Design
Poisson's Ratio
Material Screening
exceptional properties
Modulus
Reconstruction loss
Neural Network
True Positive
F1 Score
Classification
NPR materials
cross validation
ReLu
Sigmoid
hyperparameters
DFT
materials project
ADAM
Elate
IQR
Interquartile
latent dimension
α-cristobalite
Pearson Correlation
Random Forest
Gradient Boosting

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.