DOE OSTI · 3022489
Gradient-based optimization of complex nanoparticle heterostructures enabled by deep learning on heterogeneous graphs
Abstract
Applications of deep learning (DL) to design nanomaterials are hampered by a lack of suitable data representations and training data. Here, in this study, we report efforts to overcome these limitations and leverage DL to optimize the nonlinear optical properties of core–shell upconverting nanoparticles (UCNPs). UCNPs, which have applications in fields such as biosensing, super-resolution microscopy and three-dimensional printing, can emit visible and ultraviolet light from near-infrared excitations. We report a large-scale dataset of UCNP emission spectra based on accurate but expensive kinetic Monte Carlo simulations (N > 6,000) and use these data to train a heterogeneous graph neural network using a physically motivated representation of UCNP nanostructure. Applying gradient-based optimization on the trained graph neural network, we identify structures with 6.5× higher predicted emission under 800-nm illumination than any UCNP in our training set. Our work reveals design principles for UCNP heterostructures and presents a roadmap for DL-based inverse design of nanomaterials.
Keep this discovery
Explore connections, maps & timelines
Sivonxay, Eric [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Attia, Lucas [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)] (ORCID:0000000299413846), Spotte-Smith, Evan Walter Clark [Carnegie Mellon Univ., Pittsburgh, PA (United States)] (ORCID:000000031554197X), Sanchez-Lengeling, Benjamin [Univ. of Toronto, ON (Canada); Vector Inst. for Artificial Intelligence, Toronto, ON (Canada); Google DeepMind, Cambridge, MA (United States)], Xia, Xiaojing [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). Molecular Foundry], Barter, Daniel [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)], Chan, Emory M. [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). Molecular Foundry] (ORCID:0000000256550146), Blau, Samuel M. [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (ORCID:0000000331323032). 2025-12-08. Gradient-based optimization of complex nanoparticle heterostructures enabled by deep learning on heterogeneous graphs. https://doi.org/10.1038/s43588-025-00917-3
Cite the original work for its findings. Save a collection to share your selection of sources.