Machine learning models for predicting the hydrogenic impurity nonlinear optical rectification in GaAs/AlGaAs Tetrapod core/shell quantum dots under the effect of temperature

In this study, we investigate the nonlinear optical rectification (NOR) between the first and excited states in GaAs/AlGaAs Tetrapod Core/Shell Quantum Dots (TCSQDs) under the effect of temperature, using the compact density matrix formalism. The energy levels and wave functions are computed by solving the Schrödinger equation with the Finite Element Method (FEM) within the framework of the effective mass approximation (EMA). The objective of the present study is to develop an accurate and efficient method for modelling and predicting the NOR coefficient related to E₂₃ transition, taking into account the influence of temperature variations on the quantum dot system. To achieve this, we apply a range of machine learning (ML) algorithms, including Artificial Neural Networks (ANN), Decision Tree (DT), and Random Forest Regression (RFR). Among these, Random Forest Regression yields the best performance, achieving R² = 0.99940, MSE = 1.10 × 10⁻⁴, and MAE = 0.00510 at room temperature. The importance of this work lies in its potential to provide valuable insights for neither designing advanced quantum dot-based optoelectronic devices, such as infrared detectors and photonic components, where temperature-dependent NOR are properties crucial for performance optimization. Furthermore, the application of ML techniques in this context offers a promising approach for efficient and accurate modelling of complex quantum systems, facilitating the development of future quantum technologies.