Decoding the Earth’s Rumbles: MACREE for Smart Classification of Earthquakes and Explosions

Abstract

The detection and classification of seismic events, particularly distinguishing between natural earthquakes and anthropogenic explosions, is a crucial challenge in the field of seismology. Traditional seismic monitoring systems often struggle to accurately differentiate between these event types due to their similar seismic wave characteristics, especially at regional distances or for low-magnitude events. This paper introduces MACREE (Modular Analysis for Classification and Refined Event Evaluation), a cutting-edge seismic analysis framework designed to improve the classification accuracy of seismic events using advanced signal processing and machine learning techniques. MACREE integrates adaptive signal preprocessing, time-frequency analysis, and feature extraction to enhance event discrimination. Subsequently, it applies a hybrid machine learning classification model, trained on a diverse set of labeled seismic data, to provide reliable and precise event classification. Preliminary results demonstrate MACREE’s capability to outperform traditional systems, reducing false positives and improving the differentiation between earthquakes and explosions. This work outlines the architecture of MACREE, discusses its algorithmic foundations, and evaluates its performance, providing a new tool for seismic monitoring systems worldwide.