Towards reliable assessment of pyroclastic density current hazards

In a world where the human population keeps growing and is pushed to living in hazardous volcanic areas, volcanoes are increasingly becoming a larger threat to life. Volcanoes that erupt explosively have had devastating societal impacts, including covering countries in ash, changing the climate, and the extensive loss of human life. The most serious class of volcanic hazards is caused by volcanic flows, which include landslides, debris flows and the most dangerous of all, pyroclastic flows. Pyroclastic flows, made of scorching ash and gas, can burn and bury entire cities within minutes. These hot currents are typically composed of a basal dense avalanche and overriding dilute turbulent ash-cloud surge. Pyroclastic flows do not solely affect the ground, as they can also form large plumes of fine ash particles that rise to the altitude of cruising flights and can disrupt aviation paths. Predicting the propagation of these flows has been one of the largest challenges in geosciences because we lack a fundamental understanding of how complex granular media flow, i.e. our understanding of their rheology is very incomplete. This gap in our knowledge makes the impacts from pyroclastic flows very difficult to predict. The ability to forecast future pyroclastic flow velocity and inundation areas would help to limit the loss of human life and reduce economic impacts by informing mitigation strategies such as evacuations. Unfortunately, this goal cannot be achieved until we capture the physics of these currents and implement it in numerical models. The dense avalanche layer is a highly complex granular flow made of particles spanning a wide range of sizes (from microns to meters). The gas-particle coupling leads to elevated gas pressure and enables the transformation of the highly frictional granular avalanche into a mixture analogous to a liquid. While our understanding of granular flows has grown significantly in the past decade, previous studies have focused on steady configurations and simplified mixtures of grains. In nature, pyroclastic flows evolve over time as particles fragment and abrade by colliding with each other, and flows propagate across a variety of topographic obstacles such as valleys that control their behaviour, making their behaviour transient. Without a physical description of unsteady rheology of natural volcanic mixtures, we may never capture their behaviour accurately. Another major challenge we face is the time that current models require to run simulations of pyroclastic flows on highly resolved digital-elevation models. At the moment, all models use Central Processing Unit (CPU) computing to simulate volcanic flows, and require supercomputers to solve hundreds of scenarios taking days to weeks to complete. This project will take advantage of recent advances in computing abilities and analytical techniques available in physics and engineering and apply these to geosciences. These techniques will be used to study the dissipation energy from unsteady pyroclastic mixtures, enabling physical descriptions of the processes to be implemented in a new generation of volcanic flow model based on graphic cards. This new model will use Graphic Processing Unit (GPU) computing that can be undertaken on any laptop. This new model will allow highly resolved calculations and will radically transform our ability to forecast pyroclastic flow hazards and their interaction with topography, and enable volcanologists to undertake rapid hazard assessment when most needed: during volcanic unrest. Combining the findings and development from this study with other fields in geosciences will lead to important advances in how volcanic hazard assessment is undertaken and help limit loss of life.