Distributed Machine Learning-based Digital Twins Modelling

This project delves into the integration of two distinct digital twin (DT) use cases: the DT for Drought Early Warning in the Alps (EURAC) and the Noise Simulation for Gravitational Waves Detector DT (VIRGO), utilizing the itwinai1 library designed for distributed machine learning modelling within high-performance computing (HPC) environments. A key focus is on measuring the performance overhead of itwinai in distributed machine learning across various resource configurations, facilitated by scaling tests incorporated within these DT use cases. Additionally, the project explores Hyperparameter Optimization (HPO) to fine-tune the machine learning models used in these scenarios.