DOE OSTI · 3002739
Synthetic-domain computing and neural networks using lithium niobate integrated nonlinear phononics
Abstract
Analogue computing uses the physical behaviours of devices to provide energy-efficient arithmetic operations. However, scaling up analogue computing platforms by simply increasing the number of devices leads to challenges such as device-to-device variation. Here, in this study, we report scalable analogue computing and neural networks in the synthetic frequency domain using an integrated nonlinear phononic platform on lithium niobate. This synthetic-domain computing is robust to device variations, as vectors and matrices are concurrently encoded at different frequencies within a single device, achieving a high throughput per area. Leveraging inherent nonlinearities, our device-aware neural network can perform a four-class classification task with an accuracy of 98.2%. The nonlinear phononic computing hardware also maintains consistent performance over a wide operational temperature range (characterized up to 192 °C). Our synthetic-domain computing combines single-device parallelism, inherent nonlinearity and environmental stability, and could be of use in edge computing applications in which power efficiency and environmental resilience are crucial.
Keep this discovery
Explore connections, maps & timelines
Ji, Jun [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)] (ORCID:0000000269945358), Xi, Zichen [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)], Thomas, Joseph G. [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)] (ORCID:0000000236825931), Srijanto, Bernadeta R. [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Sciences (CNMS)] (ORCID:0000000211881267), Kravchenko, Ivan I. [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Sciences (CNMS)] (ORCID:0000000349995822), Baikadi, Pranay [Univ. of Texas at Dallas, Richardson, TX (United States)], Sun, Minglei [Univ. of Texas at Dallas, Richardson, TX (United States)], Vandenberghe, William G. [Univ. of Texas at Dallas, Richardson, TX (United States)] (ORCID:0000000267175046), Jin, Ming [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)], Zhu, Yizheng [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)] (ORCID:0000000180990371), Xiong, Wenjie [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)] (ORCID:0000000276262651), Shao, Linbo [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)] (ORCID:0000000206157848). 2025-08-25. Synthetic-domain computing and neural networks using lithium niobate integrated nonlinear phononics. https://doi.org/10.1038/s41928-025-01436-9
Cite the original work for its findings. Save a collection to share your selection of sources.