This paper reviews the application of machine learning in water resource modeling, focusing on various aspects such as precipitation, flood, runoff, soil moisture, evapotranspiration, groundwater level, and water quality. Traditional hydrological models, while physically significant, are complex and labor-intensive, often leading to limited accuracy. Machine learning, with its ability to process large datasets and extract valuable information, enhances the efficiency and sustainability of water resource modeling. The review discusses the strengths and weaknesses of various machine learning algorithms, including artificial neural networks (ANN), decision trees (DT), random forests (RF), support vector machines (SVM), and logistic regression (LR). It also explores the selection of appropriate assessment methods for different tasks, such as classification, regression, and clustering. The paper highlights the progress in precipitation prediction, flood forecasting, urban waterlogging prediction, runoff prediction, soil moisture prediction, evapotranspiration prediction, and groundwater level prediction using machine learning. Despite the advancements, challenges such as data noise, overfitting, and the need for more interpretable models remain. The paper concludes by discussing future research directions, emphasizing the integration of machine learning with physical processes and the development of adaptive, transferable models for different climatic conditions.This paper reviews the application of machine learning in water resource modeling, focusing on various aspects such as precipitation, flood, runoff, soil moisture, evapotranspiration, groundwater level, and water quality. Traditional hydrological models, while physically significant, are complex and labor-intensive, often leading to limited accuracy. Machine learning, with its ability to process large datasets and extract valuable information, enhances the efficiency and sustainability of water resource modeling. The review discusses the strengths and weaknesses of various machine learning algorithms, including artificial neural networks (ANN), decision trees (DT), random forests (RF), support vector machines (SVM), and logistic regression (LR). It also explores the selection of appropriate assessment methods for different tasks, such as classification, regression, and clustering. The paper highlights the progress in precipitation prediction, flood forecasting, urban waterlogging prediction, runoff prediction, soil moisture prediction, evapotranspiration prediction, and groundwater level prediction using machine learning. Despite the advancements, challenges such as data noise, overfitting, and the need for more interpretable models remain. The paper concludes by discussing future research directions, emphasizing the integration of machine learning with physical processes and the development of adaptive, transferable models for different climatic conditions.