The method combines quantum mechanics with machine learning to accurately predict reactions of oxides at high temperatures when experimental data are not available. In this way, clean, climate-neutral processes for steel production and metal recycling could be designed.
Extracting metals from oxides at high temperatures is essential not only for making metals such as steel, but also for recycling. Since current extraction processes are very carbon intensive and emit large amounts of greenhouse gases, researchers have explored new approaches to develop this work in the laboratory as it requires expensive reactors. Building and running computer simulations would be an alternative, but there is currently no computer method that can accurately predict oxide reactions at high temperatures in the absence of experimental data.
A team of Columbia engineers reports that they have developed a new computational technique that, through the combination of quantum mechanics and machine learning, can accurately predict the temperature of reduction of metal oxides to their base metals. Their approach is computationally just as efficient as conventional calculations at zero temperature and, when tested, is more accurate than computationally intensive simulations of the temperature effects using quantum chemical methods. The study, led by Alexander Urban, Assistant Professor of Chemical Engineering, was published by Nature Communications on December 1, 2021.
Decarbonising the chemical industry is critical to moving towards a more sustainable future, but developing alternatives to established industrial processes is very costly and time-consuming, said Urban. Bottom-up computer-aided process design that does not require any initial experimental input would be an attractive alternative, but has not yet been done. This new study is, to our knowledge, the first time a hybrid approach combining computation with AI has been tried for this application. And it is the first proof that calculations based on quantum mechanics can be used for the design of high-temperature processes.
The researchers knew that quantum mechanical calculations at very low temperatures can accurately predict the energy that chemical reactions require or release. They added a machine learning model to this zero temperature theory that learned the temperature dependence from publicly available high temperature measurements, focused on extracting metal at high temperatures to also predict the change in “free energy” with temperature, either high or low.
Free energy is a key variable in thermodynamics and other temperature-dependent variables can in principle be derived from it, says José A. Garrido Torres, first author of the article, who was a postdoc in Urban’s laboratory and is now a research scientist at Princeton. So we hope that our approach will also be useful, for example, to predict melting temperatures and solubilities for the design of clean electrolytic metal extraction processes that run on renewable electrical energy.
“The future just got a little closer, “says Nick Birbilis, Vice Dean of the College of Engineering and Computer Science at the Australian National University and an expert in materials design with a focus on corrosion resistance, who was not involved in the study. “Much of the human endeavor and sunken capital of the past century has focused on creating materials that we use every day and that we rely on for our performance, flight and entertainment. Material development is time consuming and expensive, which makes machine learning a crucial development for the material design of the future. In order for machine learning and AI to develop their potential, models must be mechanically relevant and interpretable. This is exactly what the work of Urban and Garrido Torres shows. In addition, the work follows a holistic system approach. For the first time, it combines atomistic simulations on one end and technical applications on the other through advanced algorithms.
The team is now working on extending the approach to other temperature-dependent material properties such as solubility, conductivity and melting, which are necessary to design carbon-free and energy-driven electrolytic metal extraction processes.
Source link
