In response to the requirements for high-precision detection and diverse data scenarios in the field of intelligent optical sensing, this research combines whispering gallery mode (WGM) microcavity sensing with machine learning to solve the problems of low spectral information utilization, large random errors, and poor adaptability to data scales in the traditional microcavity sensing. Firstly, the WGM microcavity sensing system is used to collect transmission spectral datasets of different scales. Secondly, a multi-layer perceptron (MLP) deep learning algorithm based on full-spectrum feature mapping is adopted to train and test the datasets through hierarchical feature extraction and nonlinear fitting. The results show that the MLP achieves the test accuracy of 99.95% on large datasets. However, it exhibits poor performance on small datasets. Subsequently, the generalized regression neural network (GRNN) is introduced, leveraging its non-iterative training and strong local feature fitting advantages to optimize the small sample scenarios. The results indicate that the GRNN can achieve a test accuracy of 98.85% on small data sample datasets, improving by 10.29% compared to MLP. Finally, this study quantitatively compares and analyzes the test performance of MLP and GRNN models for five datasets of different scales, clarifying the performance advantages of the two models under different data conditions. This study fully utilizes the characteristics of MLP and GRNN models to achieve high-precision detection under different data scales, providing strong technical support for the application of intelligent optical microcavity sensing technology in various scenarios.

High-precision detection of microwave field information is important in the fields of space wireless communication, space microwave remote sensing, and satellite navigation. In this paper, the high-precision detection of broadband microwave is realized. High-precision detection of microwave fields has been realized for the first time based on the spin-mixing model of nitrogen-vacancy color centers and the continuous wave optically detected magnetic resonance (ODMR) process. By changing the power ratio between the signal and reference microwave fields, the validity of high-precision detection of microwaves is verified, and the microwave magnetic field detection resolution is less than 100 nW and the Pearson correlation coefficient of the system’s response to microwave intensity is 0.9974. Then, by optimizing the data acquisition time, the megahertz-level frequency resolution of the signal microwave is achieved. In addition, the gigahertz bandwidth and megahertz resolution were also verified by tuning the resonance frequency of the spin energy level to an external static magnetic field. These results provide an important technological basis for solid-state microwave receivers based on nitrogen-vacancy color centers, high-precision spectral resolution detection, and microwave sensing.

Owing to their strong nonlinearity, cadmium sulfide (CdS) nanostructures are promising platforms for investigating the fundamental physics of light–matter interactions. However, observing the strong exciton–photon interactions in CdS microstructures at room temperature continues to present significant challenges, primarily because of the limited exciton binding energy. This study reports the direct observation of the interaction between excitons and microcavity photons in Sn-doped CdS microsheets without extreme fabrication conditions. Using angle-resolved photoluminescence (ARPL) spectroscopy, Rabi splitting of polaritons up to 163 meV was obtained at room temperature. Additionally, the temporal lasing dynamics of the Sn-doped CdS microsheets were investigated using a streak camera system. Most importantly, exciton–polariton condensation and coherent exciton–polariton lasing in the Sn-doped CdS microsheet was observed at room temperature. These results advance the fundamental understanding of exciton–polaritons in Sn-doped CdS microsheets and their applications in miniaturized microlaser devices.