Citrination Plays Key Role in Creating 3d-Printable Aluminum Alloys

With the help of Citrine Informatics’ Citrination platform, scientists at University of California Santa Barbara and HRL Laboratories, a joint venture of General Motors and Boeing, have solved a long-standing challenge hindering the wide use of aluminum alloys in 3d printing. In particular, the high-strength aluminum alloys of relevance to the aerospace and automotive industries have notoriously remained impossible to 3d print due to a stubborn problem called hot cracking. In a study published in Nature, one of the world’s most prestigious scientific journals, the researchers employ a combination of metallurgical expertise and Citrination to design a robust solution to hot cracking.

Describing the breakthrough, John Martin, a scientist at HRL Laboratories, says, “We took an unweldable old metal and made it weldable.” How? The team started with a strong scientific hypothesis grounded in well-established metallurgical principles. They reasoned that the introduction of highly tailored grain refiners, a tried-and-true route to improve processability and properties of alloys, could make existing commercial aluminum alloys amenable to 3d printing.

However, testing this hypothesis presented an enormous challenge. The team would have to sift through millions of combinations of candidate grain refiners and target aluminum alloys to find ideal matches. This crucial step, for which no other software solution existed, is where Citrination came in. Brennan Yahata, another scientist on the study, notes, “Using informatics was key. The point of using [Citrination] was to do a selective approach to … find the materials with the exact properties we needed. Once we told them what to look for, their big data analysis narrowed the field of available materials from hundreds of thousands to a select few. We went from a haystack to a handful of possible needles.” Specifically, the authors of the study used Citrination to search millions of candidate materials combinations to find optimal sets of four key properties for which they were screening. When they tested these optimal combinations in the laboratory, the scientists found that the resulting parts had dramatically higher strength than had been demonstrated previously in 3d printed aluminum.

Martin calls this work a “true optimization from the atomic scale up to the component scale,” which has long been a dream of materials design. The study opens new frontiers in the use of aluminum alloys in 3d printing, and demonstrates the great potential of informatics in helping to unlock previously-intractable materials design problems.

  • B Meredig, Chief Science Officer 


Further reading:

·       Engineers 3-D print high-strength aluminum, solve ages-old welding problem using nanoparticles []

·       JH Martin et al., 3D printing of high-strength aluminium alloys, Nature (2017)

Deep Learning on Microstructural Images

It’s well known that microstructure plays a key role in determining material properties.  One common way of assessing material microstructure is via Scanning Electron Microscopy (SEM) images.  On Citrination, we have the capability to use these microstructural images as inputs to our data-driven models.  


We have developed customized deep learning techniques to automatically detect which textures are present in the images.  Those textures can then be used as inputs to machine learning models to label the microstructure and predict material properties.  This framework is shown schematically in the figure below.  

This schematic illustrates the deep learning framework for featurizing SEM images.  The SEM image on the left shows steel with pearlite microstructure.  That image is transformed through deep learning into a vector of textures.  A machine learning model is then able to correctly label the microstructure of this image with high confidence.


A tutorial video of how SEM images can be ingested onto the platform and used to build models is available here.  This tutorial used data from the Ultra High Carbon Steel Database, which is accessible here on the public Citrination platform, complete with deep learning texture vectors.  


This capability is an example of how Citrine’s platform provides cutting edge artificial intelligence solutions specialized for materials science use cases.

-Julia Ling

Cutting Edge Uncertainty Quantification for Data-Driven Materials Models

In many applications of machine learning, the machine learning model accuracy is the most important consideration, and knowing the uncertainty of those predictions is not critical.  For example, for a clothing recommendation engine, it is important that on average it suggests clothes that a customer would like to buy.  It is acceptable for it to occasionally recommend an article of clothing that a customer dislikes, as long as its average performance is high.  

At Citrine, we recognize that building accurate models for materials properties is not enough.

In order for data-driven models to be useful in materials science applications, it is critical to have a reliable estimate of model uncertainty reported with every prediction.  

For example, say that we have trained a model to predict band gap based on the Strehlow and Cook experimental dataset.  We want to make predictions for the band gaps of a couple new compounds, tin monoxide (SnO) and nickel oxide (NiO).  Our model predicts values of 2.4 eV and 2.8 eV respectively. The key question is, “How confident is our model in these predictions?”  

There are many different sources of uncertainty in data-driven models.  If the model was fit to noisy training data, then that noise will cause uncertainty in the model.  If the model is fit to only a small number of data points, it will also have higher uncertainty.  Another important source of uncertainty is extrapolation.  For example, if we trained a model on the blue dots in the figure to the right, then tried to make a prediction at the red X, our prediction would have high uncertainty.  Similarly, data-driven models are unreliable at making predictions on materials that are significantly different from any of the materials in the training set.


At Citrine, all our predictions come with uncertainty estimates.  We have developed, implemented, and validated cutting edge uncertainty quantification methods for data-driven materials models.  For more details on our uncertainty quantification techniques and how they can be used to accelerate materials design, please see our recent paper.1 


In the cases of SnO and NiO, our predictions are shown below.

These plots show the probability distribution function for our prediction.  For example, in the case of SnO, the mean value of the distribution is 2.45 eV and the uncertainty of 0.78 eV is based on the spread of the distribution at one standard deviation. Since the uncertainty estimates are based on the standard deviation of the distribution, they are a 68% confidence interval, i.e. the probability that the true value is within 0.75 eV of the prediction (2.45 eV) is 68%.

The model uncertainty for NiO (1.41 eV) is much higher than for SnO (0.78 eV), in part because the training set included far fewer compounds containing nickel than tin.  The higher uncertainty in the NiO predictions reflects the fact that the model is extrapolating at this point.  The true band gap for SnO is approximately 2.5 eV and for NiO is approximately 3.8 eV.2  

At Citrine, we know that uncertainty estimates are critical for assessing model confidence when using data-driven models for real engineering applications.  We are proud to be leading the field by providing well-calibrated uncertainty estimates for all our predictions.3 

  1.  Ling, Julia, et al. “High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates.” Integrating Materials and Manufacturing Innovation (2017).
  2. Wong, Terence KS, et al. “Current status and future prospects of copper oxide heterojunction solar cells.” Materials 9.4 (2016): 271.
  3. This work was funded in part by Argonne National Laboratories through contract 6F-31341, associated with the R2R Manufacturing Consortium funded by the Department of Energy Advanced Manufacturing Office.



Learn Citrination to generate a useful data analysis

In this Learn Citrination tutorial, we’re going to learn to use Citrination to generate a useful data analysis called t-SNE. This data visualization technique enables you to represent a high dimensional set of data in fewer dimensions in a way that preserves the local structure of the data. In materials informatics, this allows you to create a two-dimensional plot of a set of materials where points corresponding to similar materials are grouped together in two-dimensional space. More information on t-SNE here.

This tutorial will teach you to create and export a two-dimensional t-SNE plot for any data on Citrination. The first step is to create a data view on the Citrination. Instructions for creating a data view can be found in this tutorial.

We’ll be using this data view: (view id 787) for this tutorial, which includes a model predicting experimental band gaps based on data compiled by W.H. Strehlow and E.L. Cook, which can be viewed in this dataset.

See the full tutorial notebook with step-by-step instructions here.

– E Antono, Citrine


The dawn of the Moneyball era in materials and manufacturing

Moneyball movie poster
Moneyball Movie Poster

This is a special time of year for me: the beginning of a new baseball season, and the hope against hope that the Chicago Cubs can finally win a World Series after a 107-year championship drought (here’s a realistic view of what that would look like).

While my research career and work at Citrine focus on materials informatics, I also do sports analytics as a hobby. Baseball stands out among American professional sports for being particularly data-obsessed, and the book and movie Moneyball have elevated baseball analytics to a pop culture phenomenon. Billy Beane, general manager of the Oakland Athletics, famously used advanced data analytics to gain a competitive edge against perennial titans such as the New York Yankees, despite having one of the smallest payrolls in baseball.

We founded Citrine because we want to help customers unlock a Moneyball edge in materials and manufacturing. Just as the Oakland Athletics became four times more efficient (in terms of payroll dollars per win) than the Boston Red Sox by harnessing the power of data, materials and manufacturing companies can make R&D and production dramatically more efficient by analyzing large-scale data about the materials and chemicals they use.

Continue reading…

My Internship Experience at Citrine

For a materials science student with a background in computer science, finding somewhere to combine work in these two fields is already an uncommon opportunity. Applying machine learning and data mining techniques to answer questions in materials science has been an opportunity that is really unique to Citrine. The projects that I’ve worked on have paired materials intuition with an understanding of data science and machine learning to build models for various material properties. This goes hand in hand with learning how to visualize and communicate machine learning results to people in the materials science field who can be unfamiliar with machine learning concepts. In addition to various modeling projects, I’ve also been able to contribute to the continued development of our in-house machine learning infrastructure. Working as an intern in a small, fast-moving team has been especially rewarding as projects I’ve worked on actually see the light of day. Work that I’ve done has been delivered to customers, and demo’d to investors and potential customers. It has been an honor and a rush to be able to work at Citrine as we try to fundamentally change how data is used in the field of materials science.

Analytics Platform: Build or Buy?

As more materials and manufacturing companies consider acquiring data analytics capabilities, a question we often hear from customers is, “How is Citrine’s analytics platform better than what we could build in-house?” We believe that partnering with Citrine enables our customers to focus intensively on their core competencies (e.g., metallurgy, chemistry, process engineering, manufacturing, etc) without trying to simultaneously develop advanced data infrastructure and analytics software systems that lie outside their traditional areas of strength. These areas are precisely Citrine’s core competencies, so we think that customers will find they are best served by leveraging our tremendous strength in the software domain to amplify their own in the physical domain. To help further clarify the advantages of adopting the Citrine materials analytics solution over building a custom in-house solution from the ground up, we will walk through a condensed version of our data analytics pipeline.

Continue reading…

Connect Heroku to a VPC with stunnel

Heroku offers many features that make writing & deploying web applications extremely painless. However, their networking options make it moderately difficult to connect securely to resources in EC2. Thankfully, with a little bit of elbow grease you can use stunnel to create a secure network tunnel directly to a machine inside your VPC. This blog post will walk you through all of the necessary steps. 

Continue reading…