Andres Pena Castro, University of New Mexico The seismicity detected in the Antarctic continent is low compared with other continental intraplate regions of similar size. The low seismicity may be explained by (i) insufficient strain rates to generate earthquakes, (ii) scarcity of seismic instrumentation for detecting relatively small earthquakes, (iii) lack of comprehensive data mining for tectonic seismicity, or a combination of all the aforementioned. There have been ∼ 200 earthquakes in the interior of the Antarctic continent in the past two decades according to the International Seismological Centre (ISC) and other global catalogs. Previous studies in Antarctica have used seismometers installed for relatively short periods of time (∼days to months) to detect icequakes and/or tectonic earthquakes but a thorough integration of temporary and permanent network data is needed. Additionally, most of the reported seismicity was detected using classic earthquake detection techniques such as short-term-average/long-term-average or other energy detectors. State-of-the-art detection techniques, including machine learning, have proven to outperform classic detection techniques in different seismic sequences around the world and enable automated re-analysis of large volumes of data. Here I will present a new seismic catalog for the southernmost continent. We use a Machine Learning phase picker technique on over 21 years of seismic data from on-continent temporary and permanent networks to obtain the most complete catalog of seismicity in Antarctica to date. The new catalog contains 60,006 seismic events within the Antarctic continent between January 1, 2000 to January 1, 2021, with event magnitudes between −1.0 to 4.5. Most of the detected seismicity occurs near Ross Island, large ice shelves, ice streams, ice-covered volcanoes, or in distinct and isolated areas within the continental interior. Their locations and waveform characteristics indicate volcanic, tectonic, or cryospheric sources. The catalog shows that Antarctica is more seismically active than prior catalogs would indicate. This catalogue provides a resources for more specific targeting with other detection and analysis methods such as template-matching or transfer learning, to further discriminate event types and investigate diverse seismogenic processes across the continent.