This talk focuses on the acoustic characterization of boiling noise to identify boiling regimes using machine learning methods. The data set is generated by conducting the pool boiling experiment of water on a wire heater at saturated conditions. The data set is divided into three classes: no boiling, nucleate boiling, and critical heat flux to identify the boiling incipience and critical heat flux. Focus is laid on identifying critical heat flux as it is significant in the safety of cooling systems. Data set size optimization is performed to find the lowest number of records required for each method. Three machine-learning methods are employed to predict the boiling regime: the binary decision tree method, the decision tree ensemble method, and the naive Bayes method. Out of these, the decision tree ensemble outperformed the binary decision tree and naive Bayes classifiers. The decision tree ensemble classified the regimes in the given data with the lowest classification error and inference time. The accurate classification of boiling regimes strengthens the safety measures in the real-time monitoring of cooling systems.