Abstract: A method for selecting a final model for detecting cells of interest in image datasets includes dividing a curated image dataset into a training set, a validation set, and a testing set where each image in the curated image dataset has been labeled as positive or negative for a cell of interest. The method trains each model of an ensemble of neural networks using the training and validation sets. Next, each model of the ensemble is tested using the testing set and the predictions of the ensemble are combined. The combined prediction is compared to the label and the method determines whether the combined prediction satisfies a pre-determined level of detection (LOD). If so, the method outputs the ensemble as a final ensemble. If not, the method modifies a hyperparameter of at least one of the models of the ensemble until the combined prediction satisfies the pre-determined LOD.

Abstract: A method of recovering boric acid from a subterranean deposit of colemanite ore by solution mining, comprises:supplying a leach solution comprising hydrochloric acid to the subterranean deposit via an injection well in communication therewith, whereby colemanite ore is dissolved and an aqueous pregnant solution of boric acid and calcium chloride is formed in the deposit;withdrawing the pregnant solution of boric acid and calcium chloride from said deposit via a production well in communication therewith;separating boric acid from the withdrawn solution;adding sulfuric acid to the resultant concentrated solution from which boric acid has been separated, whereby hydrochloric acid is regenerated therein and CaSO.sub.4.2H.sub.2 O is formed;separating CaSO.sub.4.2H.sub.2 O from the resultant solution containing regenerated hydrochloric acid thereby forming a regenerated leach solution; andrecycling the regenerated leach solution to the subterranean deposit of colemanite via an injection well.