This track focuses on the latest developments in data-driven approaches to numerical methods, emphasizing their applicability in solving complex mathematical problems. Participants will explore innovative techniques that leverage data to enhance traditional numerical methodologies.

This session will examine the integration of machine learning models into computational mathematics, highlighting their potential to improve accuracy and efficiency. Researchers are invited to present studies that demonstrate the effectiveness of these models in various mathematical contexts.

This track addresses the use of surrogate models to simplify complex simulations, enabling faster computational processes without significant loss of accuracy. Contributions should focus on novel surrogate modeling techniques and their applications in real-world scenarios.

This session will delve into reduced order modeling techniques that aim to tackle high-dimensional problems in numerical simulations. Participants are encouraged to share their findings on the effectiveness and efficiency of reduced order models in various applications.

This track will explore cutting-edge numerical methods for solving partial differential equations (PDEs), with an emphasis on both theoretical and practical advancements. Researchers are invited to discuss their approaches and results in this critical area of applied mathematics.

This session focuses on the application of neural networks in simulation and modeling, particularly in enhancing the accuracy of numerical methods. Contributions should highlight novel architectures and training techniques that improve simulation outcomes.