Abstract
The prediction of temperature effects from first principles is computationally demanding and typically too approximate for the engineering of high-temperature processes. Here, we introduce a hybrid approach combining zero-Kelvin first-principles calculations with a Gaussian process regression model trained on temperature-dependent reaction free energies. We apply this physics-based machine-learning model to the prediction of metal oxide reduction temperatures in high-temperature smelting processes that are commonly used for the extraction of metals from their ores and from electronics waste and have a significant impact on the global energy economy and greenhouse gas emissions. The hybrid model predicts accurate reduction temperatures of unseen oxides, is computationally efficient, and surpasses in accuracy computationally much more demanding first-principles simulations that explicitly include temperature effects. The approach provides a general paradigm for capturing the temperature dependence of reaction free energies and derived thermodynamic properties when limited experimental reference data is available.
Highlights
The prediction of temperature effects from first principles is computationally demanding and typically too approximate for the engineering of high-temperature processes
We demonstrate how first-principles quantum-mechanics based theory can be supplemented with a machine-learning (ML) model describing temperature dependence to enable the prediction of chemical reactions at high temperatures
Introducing temperature effects increases the computational cost of the simulations by several orders of magnitude, which is not amenable for the screening of large numbers of compositions and thermodynamic conditions required to aid with process optimization[17]
Summary
The prediction of temperature effects from first principles is computationally demanding and typically too approximate for the engineering of high-temperature processes. We introduce a hybrid approach combining zero-Kelvin first-principles calculations with a Gaussian process regression model trained on temperature-dependent reaction free energies. We apply this physics-based machine-learning model to the prediction of metal oxide reduction temperatures in high-temperature smelting processes that are commonly used for the extraction of metals from their ores and from electronics waste and have a significant impact on the global energy economy and greenhouse gas emissions. The approach provides a general paradigm for capturing the temperature dependence of reaction free energies and derived thermodynamic properties when limited experimental reference data is available. In the case of such data limitations, it is crucial for the construction of accurate models to make use of prior knowledge, for example, in the form of known laws of physics or thermodynamics
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have