The article "Machine Learning for Fluid Mechanics" by Steven L. Brunton, Bernd R. Noack, and Petros Koumoutsakos provides an overview of the application of machine learning (ML) techniques in fluid mechanics. The authors highlight the rapid advancement of fluid mechanics driven by large datasets from field measurements, experiments, and simulations. ML offers powerful tools for extracting information from these data, enhancing domain knowledge, and automating tasks related to flow control and optimization. The article discusses the historical development of ML in fluid dynamics, the current state of ML applications, and emerging opportunities. It outlines fundamental ML methodologies, including supervised, unsupervised, and semi-supervised learning, and their uses in understanding, modeling, optimizing, and controlling fluid flows. The strengths and limitations of these methods are addressed, emphasizing the importance of incorporating domain knowledge into ML algorithms. The authors also discuss the challenges and opportunities for ML in fluid dynamics, such as the need for interpretable and explainable models, and the potential for hybrid methods combining ML with first-principles models. The review concludes with a summary and outlook on the field, emphasizing the transformative potential of ML in fluid mechanics.The article "Machine Learning for Fluid Mechanics" by Steven L. Brunton, Bernd R. Noack, and Petros Koumoutsakos provides an overview of the application of machine learning (ML) techniques in fluid mechanics. The authors highlight the rapid advancement of fluid mechanics driven by large datasets from field measurements, experiments, and simulations. ML offers powerful tools for extracting information from these data, enhancing domain knowledge, and automating tasks related to flow control and optimization. The article discusses the historical development of ML in fluid dynamics, the current state of ML applications, and emerging opportunities. It outlines fundamental ML methodologies, including supervised, unsupervised, and semi-supervised learning, and their uses in understanding, modeling, optimizing, and controlling fluid flows. The strengths and limitations of these methods are addressed, emphasizing the importance of incorporating domain knowledge into ML algorithms. The authors also discuss the challenges and opportunities for ML in fluid dynamics, such as the need for interpretable and explainable models, and the potential for hybrid methods combining ML with first-principles models. The review concludes with a summary and outlook on the field, emphasizing the transformative potential of ML in fluid mechanics.