Skip to main content
Join the official 2020 Python Developers SurveyStart the survey!

Materials Morphology Python Package

Project description

# m2py: Materials Morphology Python Package

## Contributors

  • Wesley Tatum, PhD Student at University of Washington MSE Department
  • Diego Torrejon, Staff Machine Learning Engineer at BlackSky
  • Patrick O’Neil, Director of Machine Learning and Artificial Intelligence at BlackSky

## Installation

### Through github: Clone or download this repository

pip install -r requirements.txt

### Through pip: pip install m2py

## Usage At the moment, we are offering two tutorials found under the Tutorials directory. There is an introductory tutorial showing the basic processing capabilities of m2py. The other tutorial is more advanced, showing how users can use current m2py capabilities to make them suitable for their own applications.

## Background

Thin films of semiconducting materials will enable stretchable and flexible electronic devices, but these thin films are currently stochastic and inconsistent in their properties and morphologies because processing and chemical conditions influence the mixing and domain size of the different components. By using atomic force microscopy (AFM), a cheap and quick technique, it is possible to spatially resolve and quantify these different domains based on differences in their mechanical properties, which are strongly correlated to their electronic performance. For this project, a library of AFM images has been curated, which includes poly(3- hexylthiophene) that has been processed in different ways (e.g. annealing time and temperature, thin film vs nanowire), as well as thin film mixtures of PTB7-th and PC 71 BM. To analyze these samples, several semantic segmentation methods from the fields of machine learning and topological data analysis are employed. Among these, a Gaussian mixture model utilizing machine learned local geometric features proved effective. From the segmentation, probability distributions describing the mechanical properties of each semantic segment can be obtained, allowing the accurate classification of the various phase domains present in each sample.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for m2py, version 0.0.1
Filename, size File type Python version Upload date Hashes
Filename, size m2py-0.0.1-py3-none-any.whl (23.5 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size m2py-0.0.1.tar.gz (2.1 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page