Cargando…
Text-mined fossil biodiversity dynamics using machine learning
Documented occurrences of fossil taxa are the empirical foundation for understanding large-scale biodiversity changes and evolutionary dynamics in deep time. The fossil record contains vast amounts of understudied taxa. Yet the compilation of huge volumes of data remains a labour-intensive impedimen...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Royal Society
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6501925/ https://www.ncbi.nlm.nih.gov/pubmed/31014224 http://dx.doi.org/10.1098/rspb.2019.0022 |
_version_ | 1783416168592179200 |
---|---|
author | Kopperud, Bjørn Tore Lidgard, Scott Liow, Lee Hsiang |
author_facet | Kopperud, Bjørn Tore Lidgard, Scott Liow, Lee Hsiang |
author_sort | Kopperud, Bjørn Tore |
collection | PubMed |
description | Documented occurrences of fossil taxa are the empirical foundation for understanding large-scale biodiversity changes and evolutionary dynamics in deep time. The fossil record contains vast amounts of understudied taxa. Yet the compilation of huge volumes of data remains a labour-intensive impediment to a more complete understanding of Earth's biodiversity history. Even so, many occurrence records of species and genera in these taxa can be uncovered in the palaeontological literature. Here, we extract observations of fossils and their inferred ages from unstructured text in books and scientific articles using machine-learning approaches. We use Bryozoa, a group of marine invertebrates with a rich fossil record, as a case study. Building on recent advances in computational linguistics, we develop a pipeline to recognize taxonomic names and geologic time intervals in published literature and use supervised learning to machine-read whether the species in question occurred in a given age interval. Intermediate machine error rates appear comparable to human error rates in a simple trial, and resulting genus richness curves capture the main features of published fossil diversity studies of bryozoans. We believe our automated pipeline, that greatly reduced the time required to compile our dataset, can help others compile similar data for other taxa. |
format | Online Article Text |
id | pubmed-6501925 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | The Royal Society |
record_format | MEDLINE/PubMed |
spelling | pubmed-65019252019-05-15 Text-mined fossil biodiversity dynamics using machine learning Kopperud, Bjørn Tore Lidgard, Scott Liow, Lee Hsiang Proc Biol Sci Palaeobiology Documented occurrences of fossil taxa are the empirical foundation for understanding large-scale biodiversity changes and evolutionary dynamics in deep time. The fossil record contains vast amounts of understudied taxa. Yet the compilation of huge volumes of data remains a labour-intensive impediment to a more complete understanding of Earth's biodiversity history. Even so, many occurrence records of species and genera in these taxa can be uncovered in the palaeontological literature. Here, we extract observations of fossils and their inferred ages from unstructured text in books and scientific articles using machine-learning approaches. We use Bryozoa, a group of marine invertebrates with a rich fossil record, as a case study. Building on recent advances in computational linguistics, we develop a pipeline to recognize taxonomic names and geologic time intervals in published literature and use supervised learning to machine-read whether the species in question occurred in a given age interval. Intermediate machine error rates appear comparable to human error rates in a simple trial, and resulting genus richness curves capture the main features of published fossil diversity studies of bryozoans. We believe our automated pipeline, that greatly reduced the time required to compile our dataset, can help others compile similar data for other taxa. The Royal Society 2019-04-24 2019-04-24 /pmc/articles/PMC6501925/ /pubmed/31014224 http://dx.doi.org/10.1098/rspb.2019.0022 Text en © 2019 The Authors. http://creativecommons.org/licenses/by/4.0/ Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited. |
spellingShingle | Palaeobiology Kopperud, Bjørn Tore Lidgard, Scott Liow, Lee Hsiang Text-mined fossil biodiversity dynamics using machine learning |
title | Text-mined fossil biodiversity dynamics using machine learning |
title_full | Text-mined fossil biodiversity dynamics using machine learning |
title_fullStr | Text-mined fossil biodiversity dynamics using machine learning |
title_full_unstemmed | Text-mined fossil biodiversity dynamics using machine learning |
title_short | Text-mined fossil biodiversity dynamics using machine learning |
title_sort | text-mined fossil biodiversity dynamics using machine learning |
topic | Palaeobiology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6501925/ https://www.ncbi.nlm.nih.gov/pubmed/31014224 http://dx.doi.org/10.1098/rspb.2019.0022 |
work_keys_str_mv | AT kopperudbjørntore textminedfossilbiodiversitydynamicsusingmachinelearning AT lidgardscott textminedfossilbiodiversitydynamicsusingmachinelearning AT liowleehsiang textminedfossilbiodiversitydynamicsusingmachinelearning |