Posted in | News | Machining Robotics

Exploring the Possibilities of Artificial Intelligence in Materials Science

Dierk Raabe and collaborators are considering artificial intelligence in materials science and the untapped spaces it opens if integrated with physics-based simulations. Comparing the conventional simulation techniques, AI consists of numerous benefits and will play a vital role in material sciences ahead.

Merging physics-based simulations with artificial intelligence gains increasing importance in materials science. Image Credit: T. You, Max-Planck-Institut für Eisenforschung GmbH

For daily human life, advanced materials are of pressing need, be it in high technology, infrastructure, mobility, medicine, or green energy. But conventional methods of finding and exploring new materials experience limitations as a result of the complications of chemical structures, compositions, and targeted properties.

Furthermore, new materials must allow not only novel applications but also include viable methods of using, producing, and recycling them. At the Max-Planck-Institut für Eisenforschung (MPIE), scientists examine the status of physics-based modeling and discuss how integrating such a method with artificial intelligence can open so far untapped spaces for the design of complicated materials.

The study has been reported in the Nature Computational Science journal.

Combining Physics-Based Approaches with Artificial Intelligence

For the demands of environmental and technological difficulties to be fulfilled, multifold material properties and progressive demands have to be taken into account, thus making alloys highly complicated in relation to synthesis, composition, processing, and recycling. Variations in such parameters involve changes in their microstructure, which causes a direct impact on the materials’ properties.

This complexity requires understanding in order to allow the forecasting of structures and properties of materials. In this context, computational materials design methods play a vital role.

Our means of designing new materials rely today exclusively on physics-based simulations and experiments. This approach can experience certain limits when it comes to the quantitative prediction of high-dimensional phase equilibria and particularly to the resulting non-equilibrium microstructures and properties.

Dierk Raabe, Study First Author, Professor and Director, Max-Planck-Institut für Eisenforschung

Raabe added, “Moreover, many microstructure- and property-related models use simplified approximations and rely on a large number of variables. However, the question remains if and how these degrees of freedom are still capable of covering the material’s complexity.”

The study makes a comparison of physics-based simulations, like ab initio simulations and molecular dynamics, with advanced artificial intelligence and descriptor-based modeling approaches. While physics-based simulations are often too expensive to forecast materials having complicated compositions, the use of artificial intelligence (AI) consists of numerous benefits.

AI is capable of automatically extracting thermodynamic and microstructural features from large data sets obtained from electronic, atomistic, and continuum simulations with high predictive power.

Jörg Neugebauer, Study Co-Author, Professor and Director, Max-Planck-Institut für Eisenforschung

Enhancing Machine Learning with Large Data Sets

Since the predictive power of artificial intelligence relies on the availability of huge data sets, methods of defeating this hindrance are required. One opportunity is to make use of active learning cycles, where machine learning models have been trained with initially small subsets of labeled data.

Furthermore, the predictions of the model are screened by a labeling unit that feeds high-quality data back into the pool of labeled records, and the machine learning model is made to run again. This stepwise method results in a final high-quality data set that has been usable for precise predictions.

Yet, there are still several open questions for the use of artificial intelligence in materials science: how to control sparse and noisy data? How to take interesting outliers or “misfits” into account? How to implement undesirable elemental intrusion from recycling or synthesis?

But when designing compositionally complex alloys is concerned, artificial intelligence will play a more significant role shortly, particularly with the development of algorithms and the handiness of high-performance computing resources and high-quality material datasets.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.