New method makes better predictions of material properties using low quality data

By combining large amounts of low-fidelity data with smaller quantities of high-fidelity data, nanoengineers have developed a new machine learning method to predict the properties of materials with more accuracy than existing models. Crucially, their approach is also the first to predict the properties of disordered materials — those with atomic sites that can be occupied by more than one element, or can be vacant.