Enthought at the 2020 Materials Research Society Conference

Machine learning classification model learns complex printability window for inkjet printed polymer films using data from automated formulation and printing system.

Authors: Michael Heiber, Ph.D., Manager, Materials Informatics and Frank Longford, Ph.D., Scientific Software Developer

The Materials Research Society (MRS) is a global community of materials researchers, built to promote the advancement of interdisciplinary materials research and technology. Enthought is presenting in two symposiums in the 2020 Materials Research Society Fall Meeting and Exhibit

Frank Longford will be presenting a paper in the symposium titled ‘Using Machine Learning and Multiscale Modeling to Study Soft Materials and Interfaces’. The symposium will discuss the use of machine learning and computational modelling for the design and characterization of structural and dynamical properties in soft materials. A limiting factor in the development of new – or improved – soft materials is the difficulty of predicting final macroscopic structure from knowledge of nanoscopic units. Critical tools to overcoming this limitation are machine learning and advanced multiscale modeling methods. 

In his presentation, Frank will discuss Enthought’s contributions towards the Formulations and Computational Engineering (FORCE) project, implemented within the EU Horizon 2020 program, which aims to bring materials modelling to the heart of business decision making via the creation of Business Decision Support Systems (BDSS). The FORCE BDSS software framework is built using Enthought’s open source software and connects simulation models of varying complexity, experimental data, and commercially relevant key performance indicators (KPIs) together into a workflow object. Workflow objects can then be used with a variety of multi-criteria optimization algorithms that allow business decision making to include both predicted physical properties and business-relevant KPIs. Examples of how this system can work in practice are demonstrated with optimization of micelle-based formulations and polymer foam processing.  

In parallel, Mike Heiber will be presenting a paper in the symposium titled ‘Data Science and Automation to accelerate Materials Development and Discovery’. This is a symposium designed to celebrate achievements and highlight challenges among the MRS community around the complex human-machine partnership we see developing in materials laboratories across the world. In research, reliable knowledge is gained through experimentation. Therefore, the pace of experimentation dictates the pace at which knowledge is gained. Accelerating experimentation through machine learning technologies and autonomous research systems has had the dual effect of increasing knowledge, and unlocking entirely new areas of experimentation, where machine learning models have become major players in choosing experiments. 

In his presentation titled “An Automated Formulation System to Accelerate Development of Printed Thin Film Materials,” Mike will outline part of an ongoing project with one of our specialty chemical materials partners to transform how they develop new polymer thin film products. His presentation will discuss some of the important design decisions made in developing an automated, high-throughput polymer solution formulation and inkjet printing system. As a first use case for the system, he’ll show how the system can rapidly generate data that feeds into a machine learning pipeline to learn the complex printability window for a given formulation type, which allows product development scientists to quickly weed out bad formulations and make final products more processable.  

Related to his presentation, Mike, together with Enthought VP, Materials Science Solutions Chris Farrow also recently authored a white paper on the journey to digital centric chemicals and materials laboratories, setting out five levels through which a laboratory must progress to achieve ever greater levels of automation, and the associated value delivered to the business.  Mike’s presentation is an example of how Enthought is driving laboratory transformation with our industrial partners and making progress towards digital-centric labs in service of broader digital transformation goals.

About the Authors

Michael Heiber, Ph.D., Manager, Materials Informatics, at Enthought holds a Ph.D. in polymer science from The University of Akron and a B.S. in materials science and engineering from the University of Illinois at Urbana-Champaign with expertise in polymers for optoelectronic applications from both a computational and experimental perspective.

Frank Longford, Ph.D., Scientific Software Developer at Enthought holds a Ph.D. in complex systems simulation from the University of Southampton, UK and a M.Chem. from the University of Sussex, UK, providing him with a multidisciplinary background in chemistry, computational modelling, data science and image analysis.

Share this article:

Related Content

3 Trends for Scientists To Watch in 2023

As a company that delivers Digital Transformation for Science, part of our job at Enthought is to understand the trends that will affect how our…

Read More

Retuning the Heavens: Machine Learning and Ancient Astronomy

What can we learn about machine learning from ancient astronomy? When thinking about Machine Learning it is easy to be model-centric and get caught up…

Read More

Extracting Target Labels from Deep Learning Classification Models

In the blog post Configuring a Neural Network Output Layer we highlighted how to correctly set up an output layer for deep learning models. Here,…

Read More

Exploring Python Objects

Introduction When we teach our foundational Python class, one of the things we do is make sure that our students know how to explore Python…

Read More

Choosing the Right Number of Clusters

Introduction When I first started my machine learning journey, K-means clustering was one of the first algorithms I was introduced to – and it is…

Read More

Prospecting for Data on the Web

Introduction At Enthought we teach a lot of scientists and engineers about using Python and the ecosystem of scientific Python packages for processing, analyzing, and…

Read More

Configuring a Neural Network Output Layer

Introduction If you have used TensorFlow before, you know how easy it is to create a simple neural network model using the Keras API. Just…

Read More

No Zero Padding with strftime()

One of the best features of Python is that it is platform independent. You can write code on Linux, Windows, and MacOS and it works…

Read More

Digital Transformation of the Materials Science R&D Lab

“Digital transformation”, “machine learning”, and “artificial intelligence” are buzzwords heard in every industry, from the boardroom to the lab. We asked Dr. Michael Heiber, lead…

Read More

Got Data?

Introduction So, you have data and want to get started with machine learning. You’ve heard that machine learning will help you make sense of that…

Read More

Join Our Mailing List!

Sign up below to receive email updates including the latest news, insights, and case studies from our team.