Machine learning (ML) is increasingly being integrated with two-dimensional (2D) materials research to enable efficient and accurate prediction, discovery, and characterization of these materials. The unique properties of 2D materials, combined with the ability to tailor heterostructures layer by layer, offer a promising platform for materials by design. However, the complexity and vastness of the multi-dimensional parameter space pose significant challenges for traditional computational methods. ML, as a data-driven approach, provides a more efficient and cost-effective alternative, enabling autonomous experimentation and accelerating the discovery of functional 2D materials. This review summarizes recent advancements in ML applications to 2D materials, highlighting key areas such as property prediction, material discovery, preparation, and characterization. ML algorithms, including supervised and unsupervised learning, have been successfully applied to various tasks, such as predicting bandgaps, thermal properties, mechanical properties, and magnetic behaviors of 2D materials. The integration of ML with first-principles calculations and experimental data has enhanced the accuracy and efficiency of material discovery and design. Key ML techniques include supervised learning algorithms like regression and classification, which are used for property prediction, and unsupervised learning algorithms like clustering and dimensionality reduction, which help in data analysis and feature selection. Feature engineering plays a crucial role in improving model performance by selecting relevant features and reducing noise. ML models are trained using large datasets, often derived from open-source databases, and validated through cross-validation and performance metrics such as mean squared error (MSE), R-squared, and area under the curve (AUC). The review also discusses the challenges and future prospects of ML in 2D materials research, emphasizing the need for further integration of ML with experimental and computational methods to advance the field. Overall, ML is transforming the study of 2D materials, enabling more efficient and accurate exploration of their properties and applications.Machine learning (ML) is increasingly being integrated with two-dimensional (2D) materials research to enable efficient and accurate prediction, discovery, and characterization of these materials. The unique properties of 2D materials, combined with the ability to tailor heterostructures layer by layer, offer a promising platform for materials by design. However, the complexity and vastness of the multi-dimensional parameter space pose significant challenges for traditional computational methods. ML, as a data-driven approach, provides a more efficient and cost-effective alternative, enabling autonomous experimentation and accelerating the discovery of functional 2D materials. This review summarizes recent advancements in ML applications to 2D materials, highlighting key areas such as property prediction, material discovery, preparation, and characterization. ML algorithms, including supervised and unsupervised learning, have been successfully applied to various tasks, such as predicting bandgaps, thermal properties, mechanical properties, and magnetic behaviors of 2D materials. The integration of ML with first-principles calculations and experimental data has enhanced the accuracy and efficiency of material discovery and design. Key ML techniques include supervised learning algorithms like regression and classification, which are used for property prediction, and unsupervised learning algorithms like clustering and dimensionality reduction, which help in data analysis and feature selection. Feature engineering plays a crucial role in improving model performance by selecting relevant features and reducing noise. ML models are trained using large datasets, often derived from open-source databases, and validated through cross-validation and performance metrics such as mean squared error (MSE), R-squared, and area under the curve (AUC). The review also discusses the challenges and future prospects of ML in 2D materials research, emphasizing the need for further integration of ML with experimental and computational methods to advance the field. Overall, ML is transforming the study of 2D materials, enabling more efficient and accurate exploration of their properties and applications.