Methods for selecting metrics for substrate classification, and apparatus to perform such methods. The methods include determining a value of a metric from an image of a substrate sample for each substrate sample of a plurality of substrate samples, wherein the metric is indicative of a surface texture of each substrate sample and iteratively assigning substrate samples of the plurality of substrate samples to an aggregate of a particular number of aggregates in response to a value of the metric for each substrate sample until a convergence of clustering is deemed achieved, then determining an indication of cluster tightness of the particular number of aggregates. The methods further include selecting or ignoring the metric for substrate classification in response to the indication of cluster tightness of the particular number of aggregates.