DeepAngle: Fast calculation of contact angles in tomography images using deep learning

TL;DR

DeepAngle introduces a deep learning method for fast, accurate contact angle measurement in tomography images of porous materials, significantly reducing computational costs compared to traditional techniques.

Contribution

The paper presents a novel deep learning approach that enables rapid and low-cost estimation of interfacial contact angles directly from 3D tomography images.

Findings

Improves R-squared by 5-16% over direct measurement.

Reduces computational cost by 20 times.

Applicable to large and time-resolved tomography datasets.

Abstract

DeepAngle is a machine learning-based method to determine the contact angles of different phases in the tomography images of porous materials. Measurement of angles in 3--D needs to be done within the surface perpendicular to the angle planes, and it could become inaccurate when dealing with the discretized space of the image voxels. A computationally intensive solution is to correlate and vectorize all surfaces using an adaptable grid, and then measure the angles within the desired planes. On the contrary, the present study provides a rapid and low-cost technique powered by deep learning to estimate the interfacial angles directly from images. DeepAngle is tested on both synthetic and realistic images against the direct measurement technique and found to improve the r-squared by 5 to 16% while lowering the computational cost 20 times. This rapid method is especially applicable for processing large tomography data and time-resolved images, which is computationally intensive. The developed code and the dataset are available at an open repository on GitHub (https://www.github.com/ArashRabbani/DeepAngle).