Search

Customization of silicon photodiodes (SiPDs) for specific target wavelengths has become increasingly important in the rapidly evolving domains of optical communication, medical devices, and autonomous driving technologies. This study pioneers the use of machine learning (ML) for the structural optimization of SiPDs, leveraging simulation data from Synopsys technology computer-aided design (TCAD) to identify optimal configurations without the need for extensive physical prototyping. We aim to predict photodiode performance across a range of design parameters by employing XGBoost (XGB) and light gradient-boosting machine (LGBM) algorithms, thus streamlining the design and development process for high-performance, cost-effective devices. Our findings indicate that the LGBM algorithm provides a more accurate prediction of photodiode responsivity than XGB, as evidenced by lower root mean square error (RMSE) values. Specifically, the LGBM model achieved an RMSE of $0.282\times 10^{\mathbf {-{4}}}$ for datasets comprising 50% of the data, markedly outperforming the XGB model, which posted an RMSE of $0.754\times 10^{\mathbf {-{3}}}$ under comparable conditions. This work highlights the potential of employing ML in the optimization process of SiPDs, offering a path toward reducing the resources required for device design and optimization. The approach demonstrates the effectiveness of ML in accelerating the development of photonic devices, enabling more efficient and targeted optimization of photodiode structures for specific applications.

Conventional metallic electromagnetic interference (EMI) shields, as well as the emerging 2D material-based shields, meet the shielding effectiveness (SE) needs of most applications. However, their shielding performance is dominated by the reflection of incoming radiation due to their high electrical conductivity, which leads to secondary pollution. This problem is getting exacerbated with the proliferation of electronics and communication networks in modern society. Thus, EMI shields that function dominantly by the absorption of incoming radiation are highly desirable. Such shields would be characterized by a green index, which is the ratio of absorbance over reflectance, close to or greater than one. For nonmagnetic materials, the best way to reduce the undesirable large impedance mismatch is to reduce the effective permittivity of the shield material. Here, we present a new EMI shield with a semiconductor Bi2S3filler in a conducting PEDOT:PSS polymer matrix, instead of the conventional conductive fillers, to reduce the effective permittivity and demonstrate that even a light loading of only 10% Bi2S3provides high SE of over 40 dB with a green index value of 0.75. Increasing the filler content to 15 wt% increases the green index close to unity while dropping the SE to 30 dB. The shielding mechanism is explained through electromagnetic parameter measurements and supplemented by density functional theory calculations. This work lays the foundation for the advancement of lightweight and ultrathin green EMI shields with minimum secondary pollution.