Fig. 8

Artificial intelligence-enhanced sensor design and VOC detection. a Machine learning-enabled forward design of sensors (Li, D. et al. 2021b). i: 3D view of the sensor. ii: Design process. b Inverse design of sensors using a semi-supervised deep learning algorithm (Ma et al. 2019). i: A schematic of inverse design. ii: The desired spectra (upper panel), the results of inverse design (lower panel). Insets are the design pattern through algorithms. iii: Visualization of the latent space. c Machine learning-enabled VOC detection (Ren et al. 2022). i: A diagram illustrating the VOC sensor. ii: The measured spectra of analytes, show spectral overlapping, which is difficult to distinguish clearly with the classic data processing methods. iii: The measured raw spectral data. iv: Data preprocessing using PCA. v: The weight of scores of each spectrum in 3D space. vi: The confusion map for analyte classification results