
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
- A. Yan, T. Sokolinski, W. Lane, J. Tan, K. Ferris, E.M. Ryan. Applying transfer learning with convolutional neural networks to identify novel electrolytes for metal air batteries. Computational and Theoretical Chemistry.
- E.M. Ryan, Z. Pollard, A. Roshandelpoor, Q. Ha, P. Vakili, J. Goldfarb. Designing Heterogeneous Hierarchical Material Systems: A Holistic Approach to Structural and Materials Design. MRS Communications, 9, 2, 628-636.
- K. R. Dupre, A. Vyas, J.L. Goldfard, E.M. Ryan Investigation of Computational Upscaling of Adsorption of SO2 and CO2 in Fixed Bed Columns. Adsorption, 25, 4: 773-782.
- W. A. Lane, E.M. Ryan. Verification, validation, and uncertainty quantification of a sub-grid model for heat transfer in gas-particle flows with immersed horizontal cylinders. Chemical Engineering Science.
- W. A. Lane, S. Sundaresan, E.M. Ryan Sub-Grid Filtering Model for Multiphase Heat Transfer With Immersed Tubes. Chemical Engineering Science.
- C. Storlie, W.A. Lane, E.M. Ryan, J.R. Gattiker, D.M. Higdon. Calibration of Computational Models with Categorical Parameters and Correlated Outputs via Bayesian Smoothing Spline ANOVA. Journal of the American Statistical Association.
- W.A. Lane, A. Sarkar, S. Sundaresan, E.M. Ryan. Sub-grid models for heat transfer in gas-particle flows with immersed horizontal cylinders. Chemical Engineering Science.
- D.C. Miller, M. Syamlal, D. Mebane, C. Storlie, D. Bhattacharyya, N. V. Sahinidis, D. Agarwal, C. Tong, S. E. Zitney, A. Sarkar, X. Sun, S. Sundaresan, E.M. Ryan, D. Engel, C. Dale. (2014). Carbon Capture Simulation Initiative: A Case Study in Multi-Scale Modeling and New Challenges. Annual Review of Chemical and Biomolecular Engineering.
- W.A. Lane, C.B. Storlie, C.J. Montgomery, E.M. Ryan. (2014). Numerical modeling and Bayesian calibration of a bubbling fluidized bed with immersed horizontal tubes. Powder Technology, 253: 733-743.