T245 Machine Learning for Advancing Data Analysis Toolkit in Geoscience

Wednesday, 13 October 2021
1:30 PM - 5:30 PM
B113/B114 (Hybrid Room)

THE DEEP-TIME DIGITAL EARTH (DDE) PROGRAM: DATA-DRIVEN DISCOVERY IN GEOSCIENCE

Paper number: T245-5
Program: Technical Sessions
Time: 2:20 PM – 2:35 PM

Authors

Abstract

The evolution of materials, life, and climate during 4.5-billion-year Earth history are some of the most fascinating yet challenging research topics. This results partly from our lack of a systematic and effective way to integrate and analyze the enormous volumes of deep-time Earth data. A significant proportion of the deep-time Earth data either exists in unstructured formats or has not been digitized. The various deep-time Earth databases hosted by individuals and organizations have been crucial for deep-time research. However, they are geographically heterogeneous and do not always adhere to the FAIR (findable, accessible, interoperable, and reusable) principles. We also need a well-structured geoscience knowledge graph to harness the power of DE data and artificial intelligence.

To address these challenges, the International Union of Geological Sciences initiated the Deep-Time Digital Earth (DDE) program in cooperation with national geological surveys, professional associations, academic institutions, and scientists worldwide. DDE aims to harmonize DE data, share global geoscience knowledge and facilitate data-driven discoveries about Earth's evolution. To this end, DDE will build on previous research to develop a systematic deep-time geoscience knowledge graph, a FAIR data infrastructure that links existing databases and makes dark data visible, and tailored tools for data analysis and visualizations.

A first and crucial step of the program is to unleash the power of existing databases and let them "talk" to each other through a data alliance initiative. This will allow scientists to discover, access, and utilize deep-time Earth data in an effective and productive way that was unimaginable in the past. However, challenges such as database schema heterogeneity and data security concerns require collective efforts and collaboration across borders and disciplines. We are actively testing existing and developing new methods for data integration across diverse databases. Internal testing of the data search portal for a few well-curated databases is scheduled to be finished by the end of this year.

Ultimately, by creating an open-access data resource that for the first time integrates all aspects of Earth's narrated past, DDE holds the promise of understanding our planet's past, present, and future in new and vivid detail.

Geological Society of America Abstracts with Programs. Vol. 53, No. 6

doi: 10.1130/abs/2021AM-369211

© Copyright 2021 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.