Bayesian Hyperparametric Optimization Based Random Forest Algorithm for Bathymetric Inversion of Inland Water Bodies

With the rapid development of remote sensing technology and computer technology, machine learning algorithms are widely used in optical remote sensing bathymetry inversion. However, due to the many parameters of machine learning algorithm, the parameter selection has a large impact on the accuracy of model inversion. To address this problem, this paper adopts Bayesian optimization algorithm to select the parameters of the clerk forest model. The experimental results show that the Bayesian hyperparameter-based optimization random forest algorithm has the highest accuracy, and the average relative error is only 10.60% which is better than the research results of many scholars at present.