Rapid identification of ore minerals using multi-scale dilated convolutional attention network associated with portable Raman spectroscopy.

Electron portable Raman spectroscopy tools for ore mineral identification are widely used in raw ore analysis and mineral process engineering. This paper demonstrates an extremely fast and accurate method for identifying unknown ore mineral samples by portable Raman spectroscopy from the RRUFF database. Resampling and background subtraction procedures are used to eliminate the influence of the Raman spectrometer and fluorescence scattering. For the complex mineral spectral classification task, a multi-scale dilated convolutional attention network is designed. In addition, to investigate the identification performance of our method, several machine learning and two basic deep learning models, including k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), cosine similarity, extreme gradient boosting machine (XGBoost), Alexnet and ResNet 18, are also developed on the mineral spectra database and applied for mineral identification. Comparative studies show that our CNN network outperforms other models with state-of-the-art results, achieving a top-1 accuracy of 89.51% and a top-3 accuracy of 96.54%. The function of each module and the explanations of the feature extraction in our CNN network were analyzed by ablation experiments and the Grad-CAM algorithm. The identification of ore mineral samples also proves the outstanding performance of our method. In conclusion, the proposed novel approach that exploits the advantages of portable Raman spectroscopy and a deep learning method is promising for rapidly identifying ore mineral samples.