No abstract

No abstract

An automated data analysis pipeline is developed to preprocess electroluminescence (EL) module images, and parse the images into individual cells to be used as an input for machine learning algorithms. The dataset used in the study includes EL images of three 60 cell modules from each of five commercial brands at six steps of damp heat exposure, from 500 to 3000 h. Preprocessing of the original raw EL images includes lens distortion correction, filtering, thresholding, convex hull, regression fitting, and perspective transformation to produce planar indexed module and single cell images. Parsing of PV cells from each of the preprocessed 90 EL module images gives us 5400 cell images, which are function of module brand and damp heat exposure step. From the dataset, two unique degradation categories ("cracked" and "corroded") were observed, while cells that did not degrade were classified as "good." For supervised machine learning modeling, cell images were sorted into these three classes yielding 3550 images. A training and testing framework with 80:20 sampling ratio was generated using stratified sampling. Three machine learning algorithms (support vector machine, Random Forest, and convolutional neural network) were trained and tuned independently on the training set and then given the test set to predict the scores for each of the three models. Five-fold cross validation was done on training set to tune hyper-parameters of the models. Model prediction scores showed that convolutional neural network outperforms support vector machine and Random Forest for supervised PV cell classification.

Polarized Raman spectra were measured for single crystals and polycrystalline ZnGeN 2 grown by a vaporliquid-solid method. A group-theoretical analysis of the selection rules governing the predicted dependence of the spectra on incoming and outgoing wave polarizations and propagation direction is presented. First-order Raman spectra corresponding to the zone center phonons are calculated from first principles using density functional perturbation theory. The Brillouin zone integrated density of phonon states is also calculated. Comparison of theory and experiment allows us to identify the a 1t symmetry modes. However, vibrational density of states features deviating from the pure a 1t spectrum are also visible in the experimental spectra and indicate some relaxation of momentum conservation rules. Differences in the experimental spectra under different polarization conditions are compared to the calculations. These differences allow us to identify different a 1t Raman tensor components as well as to obtain at least partial information on the b 2t modes. The much weaker polarization dependence in experiment than in theory, however, can at least in part be explained by using wurtzite-type selection rules. The observation of features explainable with wurtzite together with orthorhombic selection rules suggest that there is only partial ordering of the cations on their sublattice.

No abstract