Machine Learning and Data Science

Machine learning, a versatile set of algorithms, has revolutionized various fields. In CEL, we harness the power of machine learning to enhance material science and engineering research. Machine learning enables us to extract valuable insights and perform tasks such as regression and optimization by automatically learning from datasets.

In CEL, machine learning finds diverse applications. For instance, we utilize machine learning as a regression tool, employing techniques like Kernel ridge regression (KRR). KRR enables us to learn from computational fluid dynamics (CFD) simulations and make predictions with accuracy comparable to CFD, but reduces the computational cost by 5 orders of magnitude. Additionally, as an optimization tool, we leverage Bayesian optimization to identify optimized parameters for diagnosing lithium-ion batteries. We can find the most suitable parameter configuration with just a few iterations, enabling efficient and accurate battery diagnostics.

CEL aims to advance material science and engineering research by leveraging appropriate machine learning algorithms. Through the interdisciplinary integration of machine learning, we enhance our understanding, design, and optimization of materials and processes. This continuous exploration of machine learning holds immense potential in driving groundbreaking advancements within the field, further propelling the progress of material science and engineering in our lab.

Relevant Publications