Special Issue on Data Driven Science Applied to Magmatic and Volcanic Systems

Pre-eruptive and eruptive processes are often investigated by synthesizing limited data and observations with laboratory and numerical experiments. However, increasing data quality and quantity combined with advances in data science and machine learning methods allow models for various processes to be derived directly from data-driven approaches. The application of these methods extends across diverse datasets, including geochemical, petrological, seismic, geodetic, and imagery data in volcanic settings. They can be used to detect, characterize, and possibly forecast volcanic activity, and model pre- and syn-eruptive processes.

While the potential of data science and machine learning in volcanological applications is evident, there is a need to acknowledge and overcome the limitations and precautions associated with these approaches, often perceived as "black boxes".

This special issue welcomes experimental, analytical, numerical, geophysical, and field-based studies addressing volcanic systems that develop, combine, and discuss volcanic processes from a data-driven perspective.

Topics covered:

• Data-driven investigation in the study of pre- and syn- eruptive volcanic processes
• Data-driven studies of geochemical, seismic, geodetic, and imagery data in volcanic setting
• Machine Learning investigations in experimental, analytical, geophysical, and field-based studies
• Machine Learning assisted numerical simulations of volcanic processes
• Deep-learning applications in the study of volcanic systems
• Machine Learning in Volcano Monitoring
• Generative AI in Volcanology

Important Deadlines:

• Submission deadline: 1 Sep 2024

Submission Instructions:

Please read the Guide for Authors before submitting. All articles should be submitted online, please select SI: Magmatic and Volcanic Systems on submission. All submissions will undergo a normal peer-review process. To all papers submitted before 31 December 2024, the Article Processing Charge (APC) will be fully waived.

Guest Editors:

Maurizio Petrelli, University of Perugia, Italy. Email: maurizio.petrelli@unipg.it

Gabriele Morra, University of Louisiana at Lafayette, USA. Email: Gabriele.morra@louisiana.edu