Fig. 3: Performance evaluation of machine learning (ML) models for spectral data classification. | npj Computational Materials

Fig. 3: Performance evaluation of machine learning (ML) models for spectral data classification.

From: Interpretable X-ray diffraction spectra analysis using confidence evaluated deep learning enhanced by template element replacement

Fig. 3

a The classification accuracy across various ML models verified in real structure spectral data (RSS), with color intensity representing accuracy levels. The vertical coordinate is the training set and the horizontal coordinate is the model. b The variation in accuracy when applying different proportions of RSS to synthetic data. c The classification accuracy before and after the application of the template element replacement (TER).

Back to article page