{"id":1037749,"date":"2026-09-01T23:51:22","date_gmt":"2026-09-01T23:51:22","guid":{"rendered":"https:\/\/www.europesays.com\/us\/1037749\/"},"modified":"2026-09-01T23:51:22","modified_gmt":"2026-09-01T23:51:22","slug":"ai-scanned-2-million-earthquake-records-and-found-six-hidden-zones-near-earths-core","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/us\/1037749\/","title":{"rendered":"AI Scanned 2 Million Earthquake Records and Found Six Hidden Zones Near Earth\u2019s Core"},"content":{"rendered":"

Nearly 35 years<\/strong> of seismic data. Over two million waveforms<\/strong><\/a> from roughly 5,000<\/strong> magnitude-6-plus earthquakes. Manual analysis had picked through this archive for decades and kept missing something. A deep-learning system developed by researchers at the Chinese Academy of Sciences<\/a> didn’t. It identified approximately 174,929<\/a> faint seismic signals \u2014 more than ten times every previous catalogue combined \u2014 and mapped six zones at Earth’s core-mantle boundary<\/strong><\/a> that nobody<\/strong> had documented before. The study appeared in the Journal of Geophysical Research: Solid Earth in late August 2026.<\/p>\n

\"A<\/p>\n

A schematic showing how different seismic waves travel through Earth, from the source of an earthquake (star) to a seismic station at the surface (triangle). Waves get deflected near the core-mantle boundary (CMB). PKP precursors pass through the outer liquid core, but not the solid inner core, and arrive at detectors before PKIKP waves. (Guan et al., J. Geophys. Res. Solid Earth, 2026)<\/p>\n

Training a Classifier on Earth’s Heartbeat<\/p>\n

The AI method is as significant as the discovery itself.<\/p>\n

The signals in question are called PKP precursors<\/strong><\/a>: faint echoes that scatter off irregularities where solid mantle rock meets the liquid iron-nickel outer core, roughly 2,900 km<\/strong> down. They arrive just before the main seismic wave, weak enough to drown in noise. Finding them manually was slow, subjective, and geographically patchy.<\/p>\n

The team trained a deep-learning classifier on human-labeled precursor examples, ran it across decades of archived recordings, then used iterative human-in-the-loop validation to sharpen accuracy \u2014 the same methodology behind content moderation systems, except the training data is earthquake noise instead of flagged posts. Think of it as training Shazam on every song ever recorded, then running it on silence, listening for the ghost of a melody.<\/p>\n

What the system found was six previously undocumented strong-scattering regions<\/a>, labeled B1 through B6<\/strong>, beneath high-latitude Eurasia, Central Asia, the South Atlantic, and other undersampled zones. Earlier studies had seen isolated, seemingly random anomalies. The new dataset reveals something more striking: larger, belt-like zones extending across parts of the globe.<\/p>\n

As the paper states<\/a>: “We also discovered six areas that likely host significant heterogeneities that had never been documented before, providing clear priority targets for future exploration of Earth’s deep interior.”<\/p>\n

\"Earthquakes<\/p>\n

Earthquakes with identified PKP precursors that traveled from the source (pink stars) to seismic array detectors (blue triangles). (Guan et al., J. Geophys. Res. Solid Earth, 2026)<\/p>\n

What’s Actually Down There<\/p>\n

Ancient subducted slabs, partial melting \u2014 and one very speculative cosmic collision.<\/p>\n

The <\/a>core-mantle boundary<\/strong><\/a> is already strange territory. Solid but malleable mantle rock meets liquid iron-nickel at roughly 5,500\u00b0C<\/strong>, with a temperature jump of around 1,000\u00b0C<\/strong> across the interface. Known features here \u2014 massive low-shear-velocity provinces beneath Africa and the Pacific \u2014 already fuel competing geodynamic models<\/a>. Heat flow at this boundary drives Earth’s geodynamo, the mechanism behind the magnetic field protecting you from solar radiation.<\/p>\n

The six new zones are regions where temperature and composition likely differ sharply from surrounding mantle material \u2014 what researchers cautiously describe as deep heterogeneities<\/strong> rather than fully mapped structures. Possible origins include:<\/p>\n