Seismic Sleuthing with MACREE: A Refined Approach to Earthquake and Explosion Detection

Abstract

The accurate and timely detection of seismic events, including both natural earthquakes and anthropogenic explosions, remains a critical concern for geophysical research, public safety, and international security. Traditional seismic detection systems often struggle to differentiate between these two classes of events due to overlapping wave characteristics and background noise. In response to this challenge, this paper introduces MACREE (Modular Analysis for Classification and Refined Event Evaluation), a novel seismic analysis framework designed to enhance event classification accuracy through an integrated approach combining signal preprocessing, spectral decomposition, and machine learning-based decision algorithms. MACREE improves the resolution of waveform features by applying adaptive filtering and event-specific transformation layers before classification, thus distinguishing subtle differences in wave patterns. Preliminary testing using both historical and real-time seismic data has demonstrated MACREE’s potential in achieving higher detection accuracy and reducing false positives. This work outlines the architectural design of MACREE, its algorithmic foundation, and its implications for seismic monitoring systems, particularly in contexts where discriminating between earthquakes and explosions is of high importance.