Statistical significance in materials science is a challenge that has been trying to overcome by miniaturization. However, this process is still limited to 4-5 tests per parameter variance, i.e. Size, orientation, grain size, composition, etc. as the process of fabricating pillars and testing has to be done one by one. With this project, we aim to fabricate arrays of well-defined and located particles that can be tested in an automated manner. With a statistically significant amount of samples tested per parameter variance, we expect to apply more complex statistical models and implement machine learning techniques to analyze this complex problem.