Abstract: Missing value processing is an important foundation for the analysis of dam safety monitoring data. Traditional methods for handling missing values in dams often use a single type of machine learning model for prediction interpolation, without effectively integrating the advantages of multiple types of machine learning models. This article integrates multiple classic machine learning and deep learning algorithms into a strong learner within the framework of ensemble learning. To address the issue of weight allocation for each model, a new critic stacking (CS) weight allocation method is proposed to establish a dam monitoring data interpolation hybrid model based on CS ensemble learning. The research results show that compared to single base learners and traditional Stacking ensemble models, the RMSE index of ensemble learning has reduced by an average of 72.7% and 58%, indicating that ensemble learning can fully leverage the predictive advantages of various machine learning models, and the improvement of weight allocation methods can also improve the predictive accuracy of ensemble learning models, providing a new solution for handling missing values in dam monitoring data and constructing prediction models.