Abstract
Viscosity is of great importance in governing the dynamics of volcanoes,
including their eruptive style. The viscosity of a volcanic melt is
dominated by temperature and chemical composition, both oxides and water
content. The changes in melt structure resulting from the interactions
between the various chemical components are complex, and the
construction of a physical viscosity model that depends on composition
has not yet been achieved. We therefore train an Artificial Neural
Networks (ANN) on a large database of measured compositions, including
water, and viscosities that spans virtually the entire chemical space of
terrestrial magmas, as well as some technical and extraterrestrial
silicate melts. The ANN uses composition, temperature, a structural
parameter reflecting melt polymerisation and the alkaline ratio as input
parameters. It successfully reproduces and predicts measurements in the
database with significantly higher accuracy than previous global models
for volcanic melt viscosities. A calculator based on our ANN model is
available at
https://share.streamlit.io/domlang/visc_calc/main/final_script.py.
Viscosity measurements are restricted to low and high viscosity range,
which exclude typical eruptive temperatures. Without training data at
such conditions, the ANN cannot reliably predict viscosities for this
important temperature range. To overcome this limitation, we use the ANN
to create a synthetic viscosity data in the high and low viscosity
regime and fit these points using a physically motivated,
temperature-dependent viscosity model. An Excel file to calculate
viscosities using these parameters and the MYEGA equation is supplied in
the Supporting Information.