![\"Spiral](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/10\/d41586-026-03316-4_53868694.jpg\"\/)
<\/p>\n <\/p>\n
Ammonite fossils preserved in limestone. Such fossil deposits help scientists to understand biodiversity over Earth\u2019s history.Credit: Herve Conge\/Science Photo Library<\/p>\n
Large language models (LLMs) such as OpenAI\u2019s ChatGPT are trained to recognize patterns in written texts, helping them to choose a statistically probable word to complete a sentence. Palaeontologists have now trained a similar model on fossil records instead of words, then used it to reconstruct a timeline of changes in Earth\u2019s biodiversity over hundreds of millions of years in unprecedented detail.<\/p>\n
This big-data approach to interpreting the rock record \u2014 the field known as stratigraphy \u2014 could spur a rethink of major upheavals in the history of life, the model\u2019s developers say. For instance, the model suggests that three of the \u201cBig Five\u201d mass-extinction events were gradual declines in biodiversity, rather than the sudden cataclysms described by other reconstructions.<\/p>\n
Supercomputer scours fossil record for Earth\u2019s hidden extinctions<\/p>\n <\/a><\/p>\n The model is \u201ca real revolution for studying stratigraphy and past diversity change\u201d, says Shuzhong Shen, a palaeontologist at Nanjing University in China, who presented the research<\/a> at a meeting of the Geological Society of America in Denver, Colorado, on 12 October.<\/p>\n Other researchers say that although the model\u2019s reconstruction \u2014 called OneStrata \u2014 seems to be the most detailed global record so far, scientists already have high-resolution reconstructions of changes in biodiversity at specific locations, including many that shed light on mass extinctions.<\/p>\n \u201cWe could do some extra things with it, but I don\u2019t know if it would be Earth shattering,\u201d says Matthew Clapham, a palaeontologist at the University of California, Santa Cruz.<\/p>\n Strata struggles<\/p>\n The history of life is written in the fossil record<\/a>. Researchers can reconstruct the grand story of adaptation and extinction across Earth\u2019s history by marking the depth at which species occur in layers of sedimentary rock, called strata; depth corresponds to when a fossil was deposited in geological time. However, it is a steep computational problem to combine sequences from many different sites involving tens of thousands of species into a single coherent timeline of changing biodiversity.<\/p>\n To simplify this task, stratigraphers divide sequences of fossils for each species into time intervals of millions of years. This makes it easier to assemble many sequences into a unified whole. But it produces a blurry view, obscuring changes in biodiversity that occur over shorter time intervals.<\/p>\n For the past two decades, Shen and his colleagues have worked to get a sharper picture by compiling a huge data set of fossils and other geological data called OneStratigraphy<\/a>. This includes data on the depth of millions of fossil specimens in sequences of rock from tens of thousands of sites around the world.<\/p>\n Large fossil model<\/p>\n In 2020, Shen and his colleagues ran an algorithmic method on a supercomputer to piece together thousands of these sequences<\/a>, enabling them to estimate when a species appeared and went extinct with a resolution of 26,000 years \u2014 much higher than the resolution of previous estimates. They could then reconstruct a high-resolution timeline for 11,000 marine species over about 300 million years1<\/a>. However, including more species at shorter intervals requires an impractical amount of computational resources.<\/p>\n![\"\"](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/10\/d41586-026-03316-4_53863202.jpg\"\/)
<\/p>\n
![\"\"](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/10\/d41586-026-03316-4_17863038.jpg\"\/)
<\/p>\n