EAGER: Federating HPC and cloud resources for sea-level rise modeling and adaptation

Accurate and robust sea-level rise modeling requires concurrently using both large-scale, high-fidelity simulations that run on high-performance computing platforms (supercomputers) and rapid computations using machine learning-trained simulation emulators that can run on commercial clouds and smaller computing resources. These complicated, multi-part simulations, along with the growing size and distribution of the data sets, require integrating commercial cloud and high-performance computing (HPC) platforms to carry out the computations. Enabling this seamless federation of cloud and HPC platforms for diverse and heterogeneous workloads requires advanced distributed resource management. The investigators propose an information architecture that will be used to investigate problems and test solutions that will address these requirements. The project will prototype middleware to address the resource management challenges in distributed cloud and HPC resources federation and investigate task mapping and execution decisions. This project will enable the coupling of data-driven methods with computational simulations and deepen the integration of national cyberinfrastructure capabilities with high-performance platforms. Prototypes and software systems developed by this project will be integrated into curricula, exposing non-computing students and researchers to advanced tools and stimulating innovation in environmental and climate sciences. The capability to utilize federated resources will allow the processing of large datasets with higher resolution. By enhancing sea-level rise modeling, the project will improve the accuracy and reliability of predictions vital for coastal communities globally. This will aid governments and organizations in developing timely and informed strategies for coastal adaptation, thereby safeguarding large populations from the detrimental impacts of sea-level rise, such as flooding and erosion. This project will partner with the Megalopolitan Coastal Transformation Hub to organize workshops and training programs for underrepresented groups and broaden participation in STEM fields. This award by the NSF Office of Advanced Cyberinfrastructure is jointly supported by the Division of Computer and Network Systems within the NSF Directorate for Computer and Information Science and Engineering. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.