Giuseppe Romano

Giuseppe Romano is a research scientist at MIT’s Institute for Soldier Nanotechnology. His research focuses on computation-driven materials discovery, with application to renewable energy. He is the lead developer of OpenBTE, an open-source software for simulating nanoscale thermal transport in nanostructured materials. With the MIT Quest for Intelligence, he is working on the inverse design of nanostructures using machine learning. During the summer of 2018, Romano was a visiting scientist at NASA Jet Propulsion Lab (JPL), investigating next-generation Radioisotope Thermoelectric Generators (RTGs). Romano earned a BS in telecommunications engineering, and a PhD in microelectronics engineering, from the Università di Roma Tor Vergata.

Selected Publications

• Romano, G., Johnson, S. G. (2022). Inverse design in nanoscale heat transport via interpolating interfacial phonon transmission. Journal of Structural and Multidisciplinary Optimization.
• Nguyen, T. V., Mroueh, Y., Hoffman, S. C., Das, P., Dognin, P., Romano, G., Hegde, C. (2020). Nano-Material Configuration Design with Deep Surrogate Langevin Dynamics. International Conference on Learning Representations (ICLR).
• Romano, G., Kolpak, A. M., Carrete, J., Broido, D. (2019). Parameter-free model to estimate thermal conductivity in nanostructured materials. Physical Review B, Vol. 100, Iss. 4.
• Kurchin, R., Romano, G., Buonassisi, T. (2019). Bayesim: A tool for adaptive grid model fitting with Bayesian inference. Computer Physics Communications 239, 161-165.
• Oviedo, F., Ren, Z., Sun, S., Settens, C., Liu, Z., Hartono, N. T. P., Ramasamy, S., DeCost, B. L., Tian, S. I. P., Romano, G., Kusne, A. G., Buonassisi, T. (2019). Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks. Nature Computational Materials 5 (1), 1-9.