The paper "Physics-Informed Machine Learning for Metal Additive Manufacturing" by Abdelrahman Farrag, Yuxin Yang, Nieqing Cao, Daehan Won, and Yu Jin discusses the advancements in additive manufacturing (AM) technologies and their applications in creating complex structures. The authors highlight the importance of advanced modeling techniques to ensure quality and process control in metal AM. While existing physics-based and data-driven methods have shown effectiveness, they have limitations in generalizability, interpretability, and accuracy. The paper introduces Physics-Informed Machine Learning (PIML) as a significant development, which integrates physical knowledge into Machine Learning (ML) models to enhance reliability, interpretability, and predictive accuracy. PIML is categorized into three types: Physics-Informed Domain Knowledge, Simulation-Based Input Data, and Physics-Guided Model Training. The Physics-Informed Neural Network (PINN) is highlighted as a notable example of Physics-Guided Model Training, known for its ability to provide more explainable and reliable results even with noisy data. The paper also discusses the limitations and potential solutions of PINN, emphasizing the need for more robust and resource-efficient modeling methods in AM.The paper "Physics-Informed Machine Learning for Metal Additive Manufacturing" by Abdelrahman Farrag, Yuxin Yang, Nieqing Cao, Daehan Won, and Yu Jin discusses the advancements in additive manufacturing (AM) technologies and their applications in creating complex structures. The authors highlight the importance of advanced modeling techniques to ensure quality and process control in metal AM. While existing physics-based and data-driven methods have shown effectiveness, they have limitations in generalizability, interpretability, and accuracy. The paper introduces Physics-Informed Machine Learning (PIML) as a significant development, which integrates physical knowledge into Machine Learning (ML) models to enhance reliability, interpretability, and predictive accuracy. PIML is categorized into three types: Physics-Informed Domain Knowledge, Simulation-Based Input Data, and Physics-Guided Model Training. The Physics-Informed Neural Network (PINN) is highlighted as a notable example of Physics-Guided Model Training, known for its ability to provide more explainable and reliable results even with noisy data. The paper also discusses the limitations and potential solutions of PINN, emphasizing the need for more robust and resource-efficient modeling methods in AM.