Jun Wei Zhang, Jun Yan Dai, Geng‐Bo Wu, Ying Juan Lu, Wan Wan Cao, Jing Cheng Liang, Jun Wei Wu, Manting Wang, Zhen Zhang, Jia Nan Zhang, Qiang Cheng, Chi Hou Chan, Tie Jun Cui
{"title":"用于快速获取可重构元表面数据的低成本代用模型","authors":"Jun Wei Zhang, Jun Yan Dai, Geng‐Bo Wu, Ying Juan Lu, Wan Wan Cao, Jing Cheng Liang, Jun Wei Wu, Manting Wang, Zhen Zhang, Jia Nan Zhang, Qiang Cheng, Chi Hou Chan, Tie Jun Cui","doi":"10.1002/admt.202400850","DOIUrl":null,"url":null,"abstract":"In recent years, machine learning (ML) and deep learning (DL) have been widely used to break the metasurface’s performance ceiling. However, the existing data‐driven ML and DL methods usually require the availability of vast amounts of training data to ensure their stable and accurate performance. The process of acquiring these data is high‐cost due to the need for numerous full‐wave electromagnetic (EM) simulations. Here, we propose a low‐cost surrogate model to generate these data efficiently. The proposed model employs microwave network theory to separate meta‐elements into four independent components. Through integration with transmission line theory, we derive the EM responses of meta‐elements using analytical representation with the active device equivalent impedance and dielectric as design variables. Two typical phase‐modulation active meta‐elements are employed to verify the accuracy of our macromodel in comparison with full‐wave EM simulations. Based on the developed macromodel, the superior prediction ability is further presented to illustrate the performance of meta‐elements with various active devices and dielectric substrates. The proposed macromodel is a feasible and general method to rapidly obtain the necessary training data of active meta‐elements, which holds a great potential to significantly reduce the designing time of ML and DL models for the active metasurfaces.","PeriodicalId":7200,"journal":{"name":"Advanced Materials & Technologies","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Low‐Cost Surrogate Modeling for Expedited Data Acquisition of Reconfigurable Metasurfaces\",\"authors\":\"Jun Wei Zhang, Jun Yan Dai, Geng‐Bo Wu, Ying Juan Lu, Wan Wan Cao, Jing Cheng Liang, Jun Wei Wu, Manting Wang, Zhen Zhang, Jia Nan Zhang, Qiang Cheng, Chi Hou Chan, Tie Jun Cui\",\"doi\":\"10.1002/admt.202400850\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, machine learning (ML) and deep learning (DL) have been widely used to break the metasurface’s performance ceiling. However, the existing data‐driven ML and DL methods usually require the availability of vast amounts of training data to ensure their stable and accurate performance. The process of acquiring these data is high‐cost due to the need for numerous full‐wave electromagnetic (EM) simulations. Here, we propose a low‐cost surrogate model to generate these data efficiently. The proposed model employs microwave network theory to separate meta‐elements into four independent components. Through integration with transmission line theory, we derive the EM responses of meta‐elements using analytical representation with the active device equivalent impedance and dielectric as design variables. Two typical phase‐modulation active meta‐elements are employed to verify the accuracy of our macromodel in comparison with full‐wave EM simulations. Based on the developed macromodel, the superior prediction ability is further presented to illustrate the performance of meta‐elements with various active devices and dielectric substrates. The proposed macromodel is a feasible and general method to rapidly obtain the necessary training data of active meta‐elements, which holds a great potential to significantly reduce the designing time of ML and DL models for the active metasurfaces.\",\"PeriodicalId\":7200,\"journal\":{\"name\":\"Advanced Materials & Technologies\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advanced Materials & Technologies\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1002/admt.202400850\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced Materials & Technologies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1002/admt.202400850","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
近年来,机器学习(ML)和深度学习(DL)被广泛用于打破元表面的性能上限。然而,现有的数据驱动型 ML 和 DL 方法通常需要大量的训练数据才能确保其性能的稳定性和准确性。由于需要进行大量的全波电磁(EM)模拟,获取这些数据的过程成本很高。在此,我们提出了一种低成本代用模型来高效生成这些数据。该模型采用微波网络理论,将元元件分成四个独立的部分。通过与传输线理论的整合,我们利用有源器件等效阻抗和介电质作为设计变量,通过分析表示法推导出元元件的电磁响应。我们采用了两个典型的相位调制有源元元件,通过与全波电磁模拟的比较,验证了我们宏模型的准确性。在开发的宏模型基础上,进一步展示了卓越的预测能力,以说明具有各种有源器件和介质基底的元元件的性能。所提出的宏模型是一种可行的通用方法,可快速获得有源元元件所需的训练数据,在大幅缩短有源元表面的 ML 和 DL 模型设计时间方面具有巨大潜力。
Low‐Cost Surrogate Modeling for Expedited Data Acquisition of Reconfigurable Metasurfaces
In recent years, machine learning (ML) and deep learning (DL) have been widely used to break the metasurface’s performance ceiling. However, the existing data‐driven ML and DL methods usually require the availability of vast amounts of training data to ensure their stable and accurate performance. The process of acquiring these data is high‐cost due to the need for numerous full‐wave electromagnetic (EM) simulations. Here, we propose a low‐cost surrogate model to generate these data efficiently. The proposed model employs microwave network theory to separate meta‐elements into four independent components. Through integration with transmission line theory, we derive the EM responses of meta‐elements using analytical representation with the active device equivalent impedance and dielectric as design variables. Two typical phase‐modulation active meta‐elements are employed to verify the accuracy of our macromodel in comparison with full‐wave EM simulations. Based on the developed macromodel, the superior prediction ability is further presented to illustrate the performance of meta‐elements with various active devices and dielectric substrates. The proposed macromodel is a feasible and general method to rapidly obtain the necessary training data of active meta‐elements, which holds a great potential to significantly reduce the designing time of ML and DL models for the active metasurfaces.