Assistant Professor
Mechanical Engineering-Engineering Mechanics
Faculty member of Center for Data Sciences at the Institute of Computing and Cybersystems
Scientific Machine Learning; Bayesian Neural Networks, Uncertainty Quantification; Computational Mechanics; Inverse Problems; High Performance Computing
We draw ideas from diverse disciplines such as computational mechanics, applied mathematics, and machine learning to model complex deformation of two-dimensional materials, model failure of materials, couple atomistic and continuum methods, solve inverse problems, accelerate material design, and quantify uncertainty.
R Mattey, S Ghosh, Gradient Flow Based Phase-Field Modeling Using Separable Neural Networks. Computer Methods in Applied Mechanics and Engineering (Accepted). arXiv preprint arXiv:2405.06119 https://authors.elsevier.com/a/1klxOAQEJ8x-Q
S. Pathrudkar, S. Taylor, A. Keripale, A. S. Gangan, P. Thiagarajan, S. Agarwal, J. Marian, S. Ghosh, and A.S. Banerjee, Electronic structure prediction of medium and high-entropy alloys across composition space, arXiv preprint PDF
S. Pathrudkar, P. Thiagarajan, S. Agarwal, A. S. Banerjee, & S. Ghosh. Electronic Structure Prediction of Multi-million Atom Systems Through Uncertainty Quantification Enabled Transfer Learning. npj Computational Materials, Vol. 10, Article No. 175, 2024.
P Thiagarajan, S Ghosh, "A Jensen-Shannon Divergence Based Loss Function for Bayesian Neural Networks", arXiv preprint arXiv:2209.11366
P. Thiagarajan, P. Khairnar and S. Ghosh, "Explanation and Use of Uncertainty Quantified by Bayesian Neural Network Classifiers for Breast Histopathology Images," in IEEE Transactions on Medical Imaging, pp. 815 - 825, Volume: 41, Issue: 4, April 2022. PDF
R. Mattey and S. Ghosh, "A Novel Sequential Method to Train Physics Informed Neural Networks for Allen Cahn and Cahn Hilliard Equations", Computer Methods in Applied Mechanics and Engineering, Volume 390, 15 February 2022, 114474, PDF
S. Pathrudkar, H. M. Yu, Susanta Ghosh and A.S. Banerjee, Machine learning based prediction of the electronic structure of quasi-one-dimensional materials under strain; Physical Review B; Volume 105 (No. 19), 195141, 2022. PDF
U. Yadav, S. Pathrudkar, S. Ghosh, "Interpretable machine learning model for the deformation of multiwalled carbon nanotubes", Physical Review B 103 (3), 035407, 2021 PDF
S. Ghosh et. al., "Modified error in constitutive equations (MECE) approach for ultrasound elastography", The Journal of the Acoustical Society of America (Vol.142, No.4), 2017. PDF
S. Ghosh and M. Arroyo, “An atomistic-based 3D foliation model for multilayer graphene materials and nanotubes", Journal of the Mechanics and Physics of Solids. 61, 2013, pp. 235-253. PDF
Recent Funding:
"CAREER: Bayesian Symmetry-Respecting Machine Learning Framework for Predicting Electronic Structures in Materials Design". National Science Foundation, Office of Advanced Cyberinfrastructure (OAC). Amount: $669,490.00, Project Period: 2025-2030, Award number: 2442313
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2442313&HistoricalAwards=false
"Prediction and Tuning of Spin Selectivity Properties of Chiral Nanomaterials via an integrated Machine Learning - First Principles Approach". DOE (Theoretical Condensed Matter Physics). PI Ghosh's Share: $321,941. Project Period: 2022-2025, Award number: DE-SC0023432
"EAGER: An Atomistic-Continuum Formulation for the Mechanics of Monolayer Transition Metal Dichalcogenides", National Science Foundation, CMMI, MoMS, PI: Susanta Ghosh,
Total Awarded Amount: $170,604, Project Period: 2019-2022, https://nsf.gov/awardsearch/showAward?AWD_ID=1937983
Contact:
Susanta Ghosh
Email: susantag[AT]mtu.edu, Phone: 906-487-2689, Office: MEEM 829