Abstract: A precise optical technique for measuring electronic transport properties in semiconductors is disclosed. The sensitivity of the technique to electronic transport properties follows from a simple analytic expression for the Z dependence of a photo-modulated reflectance signal in terms of the (complex) carrier diffusion length. The sensitivity of the technique to electronic transport properties also enables a trained neural network to predict electronic transport properties directly from Z-scan photo-modulated reflectance data. Synthetic data and/or physical constraints may be derived from the analytical expression and incorporated into a machine learning algorithm. Moreover, electronic transport properties as determined or predicted may be used to enable machine learning based control of semiconductor process tools and/or manufacturing processes, including via advanced reinforcement learning algorithms.

Abstract: A precise optical technique for measuring electronic transport properties in semiconductors is disclosed. Using tightly focused laser beams in a photo-modulated reflectance system, the modulated reflectance signal is measured as a function of the longitudinal (Z) displacement of the sample from focus. The modulated component of the reflected probe beam is a Gaussian beam with its profile determined by the focal parameters and the complex diffusion length. The reflected probe beam is collected and input to the detector, thereby integrating over the radial profile of the beam. This results in a simple analytic expression for the Z dependence of the signal in terms of the complex diffusion length. Best fit values for the diffusion length and recombination lifetime are obtained via a nonlinear regression analysis. The output diffusion lengths and recombination lifetimes and their estimated uncertainties may then be used to evaluate various transport properties and their associated uncertainties.