In this article, we demonstrate a silicon-based carrier-injection optical single-sideband (OSSB) modulator featuring a double-parallel Mach-Zehnder interferometer architecture. This design simultaneously achieves ultra-low driving voltage and high sideband suppression ratio (SSR). By optimizing the p- and n-doping profiles, the device achieves a V ${}_{pi }~cdot $ L of approximately 0.0375 V$cdot $ cm. In OSSB operation, the unwanted sideband is suppressed by around 33 dB, highlighting the modulator’s exceptional sideband suppression. These characteristics—low driving voltage, low loss, and high suppression—make the device highly suitable for homodyne phase-locking, on-chip sensing, and other integrated photonic applications.
在本文中,我们展示了一种基于硅的载流子注入光学单边带(OSSB)调制器,该调制器具有双并行马赫-曾德尔干涉仪结构。该设计同时实现了超低驱动电压和高边带抑制比(SSR)。通过优化p掺杂和n掺杂谱,器件的V ${}_{pi}~cdot $ L约为0.0375 V $cdot $ cm,在OSSB工作中,不需要的边带被抑制约33 dB,突出了调制器出色的边带抑制能力。这些特性-低驱动电压,低损耗和高抑制-使该器件非常适合于零差锁相,片上传感和其他集成光子应用。
{"title":"Compact Single-Sideband Modulator With High Side-Mode Rejection Ratio and Low Power Consumption","authors":"Xiongping Bao;Xiao Chen;Runwei Zhou;Yuheng Wu;Wenjun Li;Wenbing Jiang;Libing Zhou","doi":"10.1109/LPT.2025.3636510","DOIUrl":"https://doi.org/10.1109/LPT.2025.3636510","url":null,"abstract":"In this article, we demonstrate a silicon-based carrier-injection optical single-sideband (OSSB) modulator featuring a double-parallel Mach-Zehnder interferometer architecture. This design simultaneously achieves ultra-low driving voltage and high sideband suppression ratio (SSR). By optimizing the p- and n-doping profiles, the device achieves a V <inline-formula> <tex-math>${}_{pi }~cdot $ </tex-math></inline-formula>L of approximately 0.0375 V<inline-formula> <tex-math>$cdot $ </tex-math></inline-formula>cm. In OSSB operation, the unwanted sideband is suppressed by around 33 dB, highlighting the modulator’s exceptional sideband suppression. These characteristics—low driving voltage, low loss, and high suppression—make the device highly suitable for homodyne phase-locking, on-chip sensing, and other integrated photonic applications.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 6","pages":"386-389"},"PeriodicalIF":2.5,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-25DOI: 10.1109/LPT.2025.3636736
Zhaoyi Liu;Feng Wang;Jitao Cao;Wenzhe Zhao;Pan Dai;Xiangfei Chen;Yanqing Lu
Linear frequency sweep of lasers is essential for high-speed optical communications, frequency-modulated continuous-wave (FMCW) light detection and ranging (LiDAR), and fiber sensing. Existing linearization methods suffer from structural complexity or calibration dependence, limiting chip-scale applicability. This letter presents a Dual Long short-term memory (LSTM)-based inverse system for nonlinear compensation, using two sub-LSTMs to model the distinct dynamics of rising and falling edges. Experiments show the method reduces relative residual nonlinearity by 96% and 60% for falling and rising ramps, respectively, outperforming conventional LSTM by 80%. Its compact, multi-task capability design enables simple, chip-level implementation for optical communications, sensing, and LiDAR.
{"title":"Dual-LSTM-Based Inverse System Control for Laser Nonlinear Compensation","authors":"Zhaoyi Liu;Feng Wang;Jitao Cao;Wenzhe Zhao;Pan Dai;Xiangfei Chen;Yanqing Lu","doi":"10.1109/LPT.2025.3636736","DOIUrl":"https://doi.org/10.1109/LPT.2025.3636736","url":null,"abstract":"Linear frequency sweep of lasers is essential for high-speed optical communications, frequency-modulated continuous-wave (FMCW) light detection and ranging (LiDAR), and fiber sensing. Existing linearization methods suffer from structural complexity or calibration dependence, limiting chip-scale applicability. This letter presents a Dual Long short-term memory (LSTM)-based inverse system for nonlinear compensation, using two sub-LSTMs to model the distinct dynamics of rising and falling edges. Experiments show the method reduces relative residual nonlinearity by 96% and 60% for falling and rising ramps, respectively, outperforming conventional LSTM by 80%. Its compact, multi-task capability design enables simple, chip-level implementation for optical communications, sensing, and LiDAR.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 5","pages":"317-320"},"PeriodicalIF":2.5,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This letter presents a comparative study of phase transition behaviour and near-infrared (NIR) regulation of vanadium dioxide (VO2) thin films (TFs) and nanocolumnar (NC) structures fabricated via glancing angle deposition (GLAD) using electron-beam evaporation. Optical reflectance spectra demonstrate enhanced and reverse NIR modulation and suppressed specular interference in NCs compared to TFs. Raman spectroscopic analysis confirms the formation of monoclinic (M1) VO2 in both morphologies, while in NCs partial stabilization of the rutile (R) phase at room temperature is observed. Reduction in transition temperature, Tc ($sim 4~^{circ }$ C) and hysteresis width ($Delta $ Tc) is confirmed from both temperature dependent optical and electrical studies. These findings offer an alternative approach for the development of smart radiative devices and other optoelectronic and thermochromic applications by nano-architecting of VO2 using GLAD.
{"title":"Enhanced NIR Modulation of GLAD-Deposited VO2 Nanocolumns for Smart Radiative Applications","authors":"Subrata Saha;Iman Biswas;Subhasish Chanda;Nilanjan Halder;Arjun Dey;Aniruddha Mondal","doi":"10.1109/LPT.2025.3637163","DOIUrl":"https://doi.org/10.1109/LPT.2025.3637163","url":null,"abstract":"This letter presents a comparative study of phase transition behaviour and near-infrared (NIR) regulation of vanadium dioxide (VO2) thin films (TFs) and nanocolumnar (NC) structures fabricated via glancing angle deposition (GLAD) using electron-beam evaporation. Optical reflectance spectra demonstrate enhanced and reverse NIR modulation and suppressed specular interference in NCs compared to TFs. Raman spectroscopic analysis confirms the formation of monoclinic (M1) VO2 in both morphologies, while in NCs partial stabilization of the rutile (R) phase at room temperature is observed. Reduction in transition temperature, Tc (<inline-formula> <tex-math>$sim 4~^{circ }$ </tex-math></inline-formula>C) and hysteresis width (<inline-formula> <tex-math>$Delta $ </tex-math></inline-formula> Tc) is confirmed from both temperature dependent optical and electrical studies. These findings offer an alternative approach for the development of smart radiative devices and other optoelectronic and thermochromic applications by nano-architecting of VO2 using GLAD.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 5","pages":"325-328"},"PeriodicalIF":2.5,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-25DOI: 10.1109/LPT.2025.3636567
Guangyu Luan;Chenggen Quan
Here, we report an asymmetric single-channel color image cryptosystem that employs phase retrieval based on an iterative phase-truncation (PT) scheme. For the proposed encryption process, colored plaintext is converted to the corresponding indexed image, and then the two-phase information is iteratively updated to construct one private key mask and one ciphertext mask. The scheme is an asymmetric single-channel encryption method for color image. In contrast to other PT-based techniques, there is no information leakage issue in our scheme. At the same time, with three sensitive additional keys, viz., the two diffraction distances and the illuminating wavelength, the encryption security is significantly strengthened. The scheme is also resistant to several attacks, and simulation results demonstrate its reliability and capability.
{"title":"Asymmetric Single-Channel Color Image Cryptosystem Based on an Iterative Phase-Truncation Scheme","authors":"Guangyu Luan;Chenggen Quan","doi":"10.1109/LPT.2025.3636567","DOIUrl":"https://doi.org/10.1109/LPT.2025.3636567","url":null,"abstract":"Here, we report an asymmetric single-channel color image cryptosystem that employs phase retrieval based on an iterative phase-truncation (PT) scheme. For the proposed encryption process, colored plaintext is converted to the corresponding indexed image, and then the two-phase information is iteratively updated to construct one private key mask and one ciphertext mask. The scheme is an asymmetric single-channel encryption method for color image. In contrast to other PT-based techniques, there is no information leakage issue in our scheme. At the same time, with three sensitive additional keys, viz., the two diffraction distances and the illuminating wavelength, the encryption security is significantly strengthened. The scheme is also resistant to several attacks, and simulation results demonstrate its reliability and capability.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 5","pages":"297-300"},"PeriodicalIF":2.5,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145712564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-25DOI: 10.1109/LPT.2025.3636564
Heeyun Jung;Taewon Jin;Seokhyeon Yoon;Kyungjin Jo;Seokyoung Shin;Seungwoo Park;Younghyun Kim
Realizing high-efficiency grating couplers (GCs) on glass substrates for high-bandwidth Co-packaged Optics (CPO) systems is challenging due to optical leakage into the substrate. In this work, we address this challenge by designing, fabricating, and characterizing a uniform silicon nitride (SiN) GC with an aluminum bottom reflector on a glass substrate. The device achieves a peak coupling efficiency of −5.1 dB and a 1-dB bandwidth of 47 nm, a 4.3 dB improvement over the non-reflector device. Furthermore, we demonstrate 106 Gbps Pulse Amplitude Modulation 4-level (PAM-4) transmission, confirming practical applicability. These results provide a valuable foundation for high-performance SiN GCs on a glass substrate platform, enabling their integration into advanced CPO for glass substrate-based optical interconnects in System-on-Wafer (SoW).
{"title":"Demonstration of a SiN Grating Coupler With a Metal Reflector on a Glass Substrate","authors":"Heeyun Jung;Taewon Jin;Seokhyeon Yoon;Kyungjin Jo;Seokyoung Shin;Seungwoo Park;Younghyun Kim","doi":"10.1109/LPT.2025.3636564","DOIUrl":"https://doi.org/10.1109/LPT.2025.3636564","url":null,"abstract":"Realizing high-efficiency grating couplers (GCs) on glass substrates for high-bandwidth Co-packaged Optics (CPO) systems is challenging due to optical leakage into the substrate. In this work, we address this challenge by designing, fabricating, and characterizing a uniform silicon nitride (SiN) GC with an aluminum bottom reflector on a glass substrate. The device achieves a peak coupling efficiency of −5.1 dB and a 1-dB bandwidth of 47 nm, a 4.3 dB improvement over the non-reflector device. Furthermore, we demonstrate 106 Gbps Pulse Amplitude Modulation 4-level (PAM-4) transmission, confirming practical applicability. These results provide a valuable foundation for high-performance SiN GCs on a glass substrate platform, enabling their integration into advanced CPO for glass substrate-based optical interconnects in System-on-Wafer (SoW).","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 5","pages":"341-344"},"PeriodicalIF":2.5,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145830926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-24DOI: 10.1109/LPT.2025.3636288
Xiangyu Zhang;Zhanhua Huang;Lin Zhang
Waveguide displays are promising for augmented reality or mixed reality, but chromatic dispersion in conventional diffractive elements limits full-color display performance. Although promising, achromatic metagratings’ diffraction efficiency needs to be improved. We propose an inverse design method using a quantum genetic algorithm for achromatic slanted metagratings. Two designs with 20° and 40° fields of view exhibit diffraction efficiencies as high as $29%pm 1%$ for RGB wavelengths at normal incidence and excellent angular and spectral uniformity. The proposed single-layer manufacturable structures offer a promising route to future full-color waveguide displays.
{"title":"Inversely Designed High-Efficiency Achromatic Slanted Metagratings for Augmented Reality Waveguide Displays","authors":"Xiangyu Zhang;Zhanhua Huang;Lin Zhang","doi":"10.1109/LPT.2025.3636288","DOIUrl":"https://doi.org/10.1109/LPT.2025.3636288","url":null,"abstract":"Waveguide displays are promising for augmented reality or mixed reality, but chromatic dispersion in conventional diffractive elements limits full-color display performance. Although promising, achromatic metagratings’ diffraction efficiency needs to be improved. We propose an inverse design method using a quantum genetic algorithm for achromatic slanted metagratings. Two designs with 20° and 40° fields of view exhibit diffraction efficiencies as high as <inline-formula> <tex-math>$29%pm 1%$ </tex-math></inline-formula> for RGB wavelengths at normal incidence and excellent angular and spectral uniformity. The proposed single-layer manufacturable structures offer a promising route to future full-color waveguide displays.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 6","pages":"390-393"},"PeriodicalIF":2.5,"publicationDate":"2025-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145808580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This work presents a novel hardware-efficient FPGA implementation of a real-time parallel loop-unrolled decision feedback equalizer (DFE) for PAM-4 IM/DD optical links. The proposed DSP architecture integrates timing recovery, a 5-tap FFE, and a novel single-tap parallel DFE leveraging an $8times 8$ loop-unrolled structure and a hardware-friendly error-based tap update mechanism thus effectively reduces processing complexity and clock delay. The implementation occupies only 4.2% LUTs, 2.75% FFs, and 6.8% DSP48E2 resources of a Xilinx XCVU13P chip. A successful 29.4912 Gb/s real-time PAM-4 signal transmission over a 10 km SSMF is demonstrated using a cost-effective directly modulated laser (DML) and achieving a BER below the 7% HD-FEC threshold, indicating a scalable and efficient solution for high-speed short reach optical data links.
{"title":"FPGA Implementation of a Real-Time Parallel Loop-Unrolled DFE for PAM-4 IM/DD Optical Links","authors":"Jianyu Wang;Jianwei Tang;Yaguang Hao;Yingying Zhou;Xiuquan Cui;Linsheng Fan;Zhongliang Sun;Junpeng Liang;Zhaopeng Xu;Weisheng Hu;Zhixue He;Yanfu Yang;Jinlong Wei","doi":"10.1109/LPT.2025.3636126","DOIUrl":"https://doi.org/10.1109/LPT.2025.3636126","url":null,"abstract":"This work presents a novel hardware-efficient FPGA implementation of a real-time parallel loop-unrolled decision feedback equalizer (DFE) for PAM-4 IM/DD optical links. The proposed DSP architecture integrates timing recovery, a 5-tap FFE, and a novel single-tap parallel DFE leveraging an <inline-formula> <tex-math>$8times 8$ </tex-math></inline-formula> loop-unrolled structure and a hardware-friendly error-based tap update mechanism thus effectively reduces processing complexity and clock delay. The implementation occupies only 4.2% LUTs, 2.75% FFs, and 6.8% DSP48E2 resources of a Xilinx XCVU13P chip. A successful 29.4912 Gb/s real-time PAM-4 signal transmission over a 10 km SSMF is demonstrated using a cost-effective directly modulated laser (DML) and achieving a BER below the 7% HD-FEC threshold, indicating a scalable and efficient solution for high-speed short reach optical data links.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 5","pages":"321-324"},"PeriodicalIF":2.5,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Neural networks can be employed for chaotic synchronization and decryption at the receiver end of chaotic optical communication systems. Simple training methods and efficient networks are worthy of further exploration in this field. We propose a novel training method for application in electrooptic phase feedback (EOPF) chaotic communication systems. Specifically, it employs a gated recurrent unit neural network (GRU-NN) trained solely on datasets constructed from encrypted and plaintext data. Experimental validation confirms that the trained model achieves high-quality chaotic synchronization and supports decryption. This approach requires only partial plaintext data sharing between communication parties for training, offering a promising reference for remote training scenarios in chaotic optical communication.
{"title":"Chaos Synchronization and Decryption in Electro-Optic Chaotic Systems Using GRU Neural Networks","authors":"Hao Yang;Peng Hou;Xing Li;Jinyang Ye;Yuehua An;Anbang Wang;Yuncai Wang;Yuwen Qin;Zhensen Gao","doi":"10.1109/LPT.2025.3635654","DOIUrl":"https://doi.org/10.1109/LPT.2025.3635654","url":null,"abstract":"Neural networks can be employed for chaotic synchronization and decryption at the receiver end of chaotic optical communication systems. Simple training methods and efficient networks are worthy of further exploration in this field. We propose a novel training method for application in electrooptic phase feedback (EOPF) chaotic communication systems. Specifically, it employs a gated recurrent unit neural network (GRU-NN) trained solely on datasets constructed from encrypted and plaintext data. Experimental validation confirms that the trained model achieves high-quality chaotic synchronization and supports decryption. This approach requires only partial plaintext data sharing between communication parties for training, offering a promising reference for remote training scenarios in chaotic optical communication.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 5","pages":"301-304"},"PeriodicalIF":2.5,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-18DOI: 10.1109/LPT.2025.3634428
Mauro Biagi
This work investigates the impact of high-reflectivity wall coatings on the performance of NLOS VLC channels. We extend conventional models by incorporating measured Bidirectional Reflectance Distribution Function (BRDF) data to better represent real-world surface behaviors. A comprehensive analysis is conducted through simulations that assess key channel parameters, including received signal strength, delay spread, and achievable data rates. The results demonstrate that specialized coatings significantly enhance NLOS performance, improving signal coverage while moderately affecting multipath dispersion. Unlike prior BRDF-based studies focusing on single-surface cases, this letter provides a systematic, material-aware comparison ($rho =0.60$ –0.99) that jointly maps SNR, delay spread, and ISI-aware capacity, yielding quantitative design guidelines for NLOS VLC in real rooms.
{"title":"Impact of High-Reflectivity Wall Coatings on Non-Line-of-Sight Visible Light Communication Channels","authors":"Mauro Biagi","doi":"10.1109/LPT.2025.3634428","DOIUrl":"https://doi.org/10.1109/LPT.2025.3634428","url":null,"abstract":"This work investigates the impact of high-reflectivity wall coatings on the performance of NLOS VLC channels. We extend conventional models by incorporating measured Bidirectional Reflectance Distribution Function (BRDF) data to better represent real-world surface behaviors. A comprehensive analysis is conducted through simulations that assess key channel parameters, including received signal strength, delay spread, and achievable data rates. The results demonstrate that specialized coatings significantly enhance NLOS performance, improving signal coverage while moderately affecting multipath dispersion. Unlike prior BRDF-based studies focusing on single-surface cases, this letter provides a systematic, material-aware comparison (<inline-formula> <tex-math>$rho =0.60$ </tex-math></inline-formula>–0.99) that jointly maps SNR, delay spread, and ISI-aware capacity, yielding quantitative design guidelines for NLOS VLC in real rooms.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 5","pages":"337-340"},"PeriodicalIF":2.5,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145830941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-17DOI: 10.1109/LPT.2025.3633564
Kawsar Ahmed;Md Mamun Ali;Md Aslam Mollah;Francis M. Bui;Li Chen
In this study, we present a deep-learning-assisted design of a photonic crystal fiber (PCF)-based surface plasmon resonance (SPR) biosensor that enables simultaneous, label-free detection of multiple waterborne analytes. Using finite element analysis, a dual-channel PCF is modeled to generate more than 40,000 data points. A lightweight, fully connected regressor predicts the confinement loss (CL) and amplitude sensitivity (AS) from structural variables (hole sizes, gaps, metal/dielectric thicknesses) and operational variables (wavelength, refractive index (RI) of analytes in both channels), achieving $R^{2} approx 0.99$ with low error. The surrogate speeds up the process of exploring designs. Using SHAP analysis, it finds that wavelength and channel RIs are the main factors, while layer thicknesses mainly change channel-specific resonances. Parametric sweeps confirm stable, concurrent redshifts across channels with increasing RI, enabling multiplexed detection of bacterial pathogens and formaldehyde. The proposed model achieves maximum amplitude sensitivity (AS) of $512.87~RIU^{-1}$ , wavelength sensitivity (WS) of 10,$638.30~nm/RIU$ , and sensor resolution (SR) of $9.4times 10^{-5}$ . The resulting architecture combines high accuracy with computational efficiency, offering a compact route to rapid, real-time water quality monitoring and food safety screening, as well as a generalizable workflow for data-driven PCF-SPR design.
{"title":"Deep Learning Optimized SPR Multi-Analyte Biosensor for Simultaneous Detection of Water Pathogens","authors":"Kawsar Ahmed;Md Mamun Ali;Md Aslam Mollah;Francis M. Bui;Li Chen","doi":"10.1109/LPT.2025.3633564","DOIUrl":"https://doi.org/10.1109/LPT.2025.3633564","url":null,"abstract":"In this study, we present a deep-learning-assisted design of a photonic crystal fiber (PCF)-based surface plasmon resonance (SPR) biosensor that enables simultaneous, label-free detection of multiple waterborne analytes. Using finite element analysis, a dual-channel PCF is modeled to generate more than 40,000 data points. A lightweight, fully connected regressor predicts the confinement loss (CL) and amplitude sensitivity (AS) from structural variables (hole sizes, gaps, metal/dielectric thicknesses) and operational variables (wavelength, refractive index (RI) of analytes in both channels), achieving <inline-formula> <tex-math>$R^{2} approx 0.99$ </tex-math></inline-formula> with low error. The surrogate speeds up the process of exploring designs. Using SHAP analysis, it finds that wavelength and channel RIs are the main factors, while layer thicknesses mainly change channel-specific resonances. Parametric sweeps confirm stable, concurrent redshifts across channels with increasing RI, enabling multiplexed detection of bacterial pathogens and formaldehyde. The proposed model achieves maximum amplitude sensitivity (AS) of <inline-formula> <tex-math>$512.87~RIU^{-1}$ </tex-math></inline-formula>, wavelength sensitivity (WS) of 10,<inline-formula> <tex-math>$638.30~nm/RIU$ </tex-math></inline-formula>, and sensor resolution (SR) of <inline-formula> <tex-math>$9.4times 10^{-5}$ </tex-math></inline-formula>. The resulting architecture combines high accuracy with computational efficiency, offering a compact route to rapid, real-time water quality monitoring and food safety screening, as well as a generalizable workflow for data-driven PCF-SPR design.","PeriodicalId":13065,"journal":{"name":"IEEE Photonics Technology Letters","volume":"38 4","pages":"283-286"},"PeriodicalIF":2.5,"publicationDate":"2025-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}