Date of Award
Open Access Thesis
Materials with extreme mechanical properties leads to future technological advancements. However, discovery of these materials is non-trivial. The use of machine learning (ML) techniques and density functional theory (DFT) calculation for structure properties prediction has helped to the discovery of novel materials over the past decade. ML techniques are highly efficient, but less accurate and density functional theory (DFT) calculation is highly accurate, but less efficient. We proposed a technique to combine ML methods and DFT calculations in discovering new materials with desired properties. This combination improves the search for materials because it combines the efficiency of ML and the accuracy of DFT. Here, we train a ML algorithm, the algorithm is used to make prediction. We use stein novelty (SN) score which recommends potential candidates from the ML prediction. We then verify the potential candidates using DFT calculation. In our demonstration, we use three property space for our search: Bulk Modulus vs Shear Modulus, Shear Modulus vs Hardness and Pugh’s ratio vs Poisson’s ratio. In exploring our property space, we found 30 crystal structures with high bulk and shear moduli, 21 crystal structures with ultrahigh hardness, and 11 crystal structures with negative Poisson’s ratio from original 85,707 crystal structures taking from material project database. The method deployed herein can be extended to push other material properties to the limit.
Ojih, J.(2021). Searching Extreme Mechanical Properties Using Active Machine Learning and Density Functional Theory. (Master's thesis). Retrieved from https://scholarcommons.sc.edu/etd/6789