Nature Machine Intelligence
14 November 2024
Fast and generalizable micromagnetic simulation with deep neural nets
Yunqi Cai1, Jiangnan Li2,4✉ & Dong Wang3,4
1 Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China.
2 Faculty of Materials Science and Engineering, Kunming University of Science and Technology, Kunming, China.
3 Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China.
4 These authors contributed equally: Jiangnan Li, Dong Wang
doi.org/10.1038/s42256-024-00914-7
Simulation has a crucial role in micromagnetic research. Traditional numerical methods face high computational demands, primarily due to long-range interactions. By leveraging the learning capabilities of a U-shaped neural network, computational complexity can be reduced from O(Nlog(N)) to O(N), facilitating scalable simulations for large sample sizes. The image depicts the simulated topological structure in a magnetic sample.
Anhui Province Academy of Science and Technology, No. 128,Wanshui Road, Hi-Tech Zone, Hefei City, Anhui Province, China
+86 17354022649
service@sondii.com
IPv6 network supported
Our hours
Beijing time: 9:00-18:00
