Classification of thermoluminescence features of CaCO3 with long short-term memory model

Abstract

Calcium carbonate (CaCO3 ), a mineral commonly found in the Earth's crust, is mainly in the forms of calcite and aragonite. Calcite has the most stable type of thermodynamics at room temperature and ambient pressure. It has wide band gap structure and is of great interest for a wide-range technical and industrial applications due to its physical properties and suitability. In this study, a new method based on the long short-term memory (LSTM) model of deep learning is proposed to classify the thermoluminescence properties such as fading, cycle of measurement, heating rate, and dose-response of CaCO3 . Therefore the thermoluminescence properties of calcite was investigated as a suitable band structure and its coherent data were used to classify the features using a deep learning LSTM model. Experiments were carried out on a dataset consisting of four classes. The accuracy, precision, and sensitivity values of the proposed model obtained were 98.34, 97.90, and 98.56%, respectively. The classification process of the results obtained from the designed model showed good performance.