Monitoring Earth's atmosphere with Sentinel-5 TROPOMI and Artificial Intelligence: Quantifying volcanic SO2 emissions

Abstract

Identifying changes in volcanic unrest and tracking eruptive activity are fundamental for volcanic surveillance and monitoring. Magmatic gases, particularly sulphur dioxide (SO 2 ), play a crucial role in influencing eruptive styles, making the monitoring of SO 2 emissions essential. Recent advancements in satellite remote sensing technology, including higher spatial resolution and sensitivity, have enhanced our ability to detect SO 2 emissions from volcanoes worldwide. However, traditional fixed-threshold algorithms struggle to automatically distinguish volcanic SO 2 emissions from non-volcanic sources. Additionally, accurately quantifying SO 2 emissions is challenging due to their dependence on plume height, particularly when reaching high altitudes. To address these challenges, we developed an Artificial Intelligence (AI) algorithm that detects and quantifies volcanic SO 2 emissions in near real-time. Our approach utilizes a Random Forest (RF) model, a supervised Machine Learning (ML) algorithm, to identify volcanic SO 2 emissions and integrates Cloud Top Height (CTH) data to enhance the accuracy of SO 2 mass quantification during intense volcanic eruptions. This AI algorithm, fully implemented in Google Earth Engine (GEE), leverages data from the TROPOspheric Monitoring Instrument (TROPOMI) aboard the Copernicus Sentinel-5 Precursor (S5P) satellite to automatically retrieve daily volcanic SO 2 plumes and CTH. We validated the model's performance against the Radius classifier, a state-of-the-art tool, and generalized its application across various volcanoes (Etna, Villarrica, Fuego, Pacaya, and Cumbre Vieja) with differing degassing activities, SO 2 emission rates, and plume geometries. Our findings demonstrate that the proposed AI approach effectively identifies and quantifies SO 2 plumes emitted by different volcanoes, enabling the investigation of SO 2 emission time series that reflect magma dynamics. • ⁠We present a new AI based approach for automatic detection and quantification of volcanic SO 2 emissions. • The AI algorithm is fully implemented in GEE and uses ESA Sentinel-5P TROPOMI dataset. • The proposed approach allows to investigate volcanic SO 2 emission time series reflecting volcanic degassing activity.

Topics & Concepts