Earth Observation provides essential insights into volcanic processes, supporting the detection and interpretation of unrest, the monitoring of eruptive activity, and volcanic hazard assessment. Integrating these observations with ground-based measurements and advanced computational methods offers new opportunities to improve our understanding of volcanic systems and strengthen forecasting capabilities.
This session brings together contributions at the interface of Earth Observation (EO), volcanology, and computational innovation. We welcome studies using radar, optical, thermal, and multispectral or hyperspectral observations, particularly those integrating complementary datasets to investigate surface deformation, thermal anomalies, gas emissions, and volcanic deposits. Contributions may address the full range from methodological developments to operational monitoring and forecasting applications.
A central focus is the role of Artificial Intelligence (AI) and Machine Learning (ML) in extracting information from complex datasets, identifying patterns and anomalies, and supporting predictive modeling. We encourage approaches that combine data-driven methods with physical understanding, including physics-informed learning, data assimilation, and statistical and probabilistic frameworks, with attention to uncertainty, interpretability, and robustness.
The session also welcomes emerging quantum and quantum-inspired approaches, including Quantum-AI and Quantum-ML, that seek to complement established methods in EO and volcanology. Topics of interest include hybrid classical–quantum workflows and the exploration of computational challenges associated with high-dimensional data, nonlinear processes, and complex optimization problems.