Engineering and Technologynpj Computational Materials
Electronic structure prediction of multi-million atom systems through uncertainty quantification enabled transfer learning
S. Pathrudkar, P. Thiagarajan, et al.
This research, conducted by Shashank Pathrudkar, Ponkrshnan Thiagarajan, Shivang Agarwal, Amartya S. Banerjee, and Susanta Ghosh, tackles the challenges of Kohn-Sham Density Functional Theory simulations by employing transfer learning and Bayesian neural networks. This innovative approach allows for confident predictions in material properties at multi-million-atom scales with limited computational resources.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Computer Science
Personalized Federated Learning for In-Hospital Mortality Prediction of Multi-Center ICU
H. Hamdan, R. Yaakob, et al.
Engineering and Technology
Machine learning-enabled forward prediction and inverse design of 4D-printed active plates
X. Sun, L. Yue, et al.
Chemistry
Machine learning assisted prediction of organic salt structure properties
E. P. Shapera, D. Bučar, et al.
Biology
Deep learning of a bacterial and archaeal universal language of life enables transfer learning and illuminates microbial dark matter
A. Hoarfrost, A. Aptekmann, et al.
