Data driven branch-point identification using Shack–Hartmann wavefront sensor measurements

We leverage wave-optics simulations to explore a machine learning approach for identifying the locations of branch points in Shack–Hartmann wavefront sensor (SHWFS) data. We train a convolutional neural network to receive a single SHWFS sub-aperture irradiance pattern image and estimate whether the pupil of that area of interest (AOI) contains at least one branch point. We test the model alongside a branch-point detection approach that relies on the beam spread (D4σ) of individual SHWFS irradiance patterns. We explore the performance of both the machine-learning-based and D4σ-based branch-point identification approaches across a wide range of optical turbulence conditions, quantified by Rytov numbers (R) ranging from 0 to 2, as well as in the presence of additive noise. To quantify our performance, we use various metrics commonly used for binary classifiers, including the receiver operating characteristic (ROC) area under the curve (AUC). From our analysis, we show that the proposed machine learning model has an ROC AUC of >0.66 and outperforms the D4σ models, which have an ROC AUC of