Search

This study investigates the application of machine learning techniques for predicting volcanic vent locations based on aeromagnetic geophysical data. Magnetic data, known to reflect subsurface geological structures, presents a valuable source of information for understanding volcanic activity. Leveraging this data, we aim to develop and validate predictive models capable of discerning the presence of volcanic vents. Through a comprehensive data analysis, feature engineering, and model training, we explore the intricate relationships between magnetic variations and volcanic vent locations. Various machine learning algorithms were evaluated for their efficacy in binary classification, with a focus on identifying areas with a high likelihood of volcanic vent presence. The Random Forest model (RFM) was adopted given its high performance metrics, achieving a prediction accuracy of 92%. Our results demonstrate the successful prediction of volcanic vent locations, with a significant correlation of 86% between the actual and predicted vent locations and a high Degree of Certainty (DC) at 97%. This research contributes to the advancement of geospatial data analysis within the field of geoscience, showcasing the potential of machine learning in interpreting and utilizing magnetic data for volcanic hazard assessment and early warning systems. The findings represent a significant step towards enhancing our understanding of volcanic dynamics and improving the predictive tools available for volcanic hazard assessment.

Vent opening hazard models are routinely used as inputs for assessing distal volcanic hazards (lava flows, tephra fallout) in distributed volcanic fields. These vent opening hazard models have traditionally relied on the location of mapped vents; seldom have they taken into account how vents are linked in space and time. We show that inputs needed to appropriately model distal hazards are fundamentally different than thoses required to model near-vent hazards (ground deformation). We provide a computational model to obtain more appropriate eruptive source parameters (ESPs) for distal volcanic hazard sources and show the utility of our code through three examples. The code's strength is that it links events based on the spatio-temporal relationships of vents through heirarchical clustering. The development of the code and its strenghts and weaknesses are discussed. This work challenges previous ideas about ESPs and we hope this work leads to further improvement in hazard assessment methods.