On Artificial Intelligence-based emulators of physical models to forecast the evolution of lava flows

Timely forecasting of the evolution of lava flows is one of the key elements for assessing volcanic hazards. Lava flows are among the main hazardous phenomena during an effusive eruption, due to the possibility to reach urban areas and cause damage to infrastructure. Physical-mathematical models can be used to estimate the dynamics of a fluid or the fluid-solid interactions, in particular for the case of lava flows. However, high fidelity models require long execution times and large computational resources. Recently, artificial intelligence (AI) has been adopted to emulate physics-based models and deliver similar results, speeding up the simulations. We will discuss the possibility to use AI-based approaches to emulate highly complex numerical models used to simulate the spatio-temporal evolution of lava flows. Analyzing and treating the formal mathematical aspects of the models under analysis, we will verify and validate the models using test cases associated with the main features of lavas, discussing the accuracy and the performance offered by the two approaches.