Report | First Machine Learning Hackathon at GFZ Potsdam

Assessing mineral concentrations of soil and predicting „earthquakes" in laboratory experiments were the focus of the first Machine Learning Hackathon at GFZ.

At the first Machine Learning Hackathon of the GFZ on March 5, 2020, more than 40 researchers worked on the assessment of mineral concentrations of soil from infrared data and on the prediction of "earthquakes" in laboratory experiments. Machine Learning (ML) is a branch of data science in which algorithms "learn" patterns and trends from training data and then use them to process unknown data sets. In recent years, Machine Learning has seen successful applications in automatic speech, text and image recognition. Now, these techniques are becoming increasingly popular in Geoscience.

Researchers from all four GFZ departments and external guests from the Geo.X network in Berlin and Brandenburg took part in the first GFZ Machine Learning Hackathon. When estimating the mineral content of soil from infrared data, researchers were able to predict the concentration of certain minerals with up to 95 percent accuracy. When predicting artificial "earthquakes" in laboratory experiments, the participants managed to identify a sequence of laboratory earthquakes in the seismic data.

The hackathon was organized by the group "ML@GFZ", which was founded in August 2019 and usually organizes a jour fixe every first Tuesday of the month. "We are building a close cooperation between natural and data science in order to better understand processes in the Earth system," says Werner Köckeritz, Chief Information Officer of GFZ. "This creates a cross-sectional network for the application of artificial intelligence (AI). The use of AI methods, such as Machine Learning is, in my view, the future of Earth sciences".

The aim of the group is to further increase machine learning competences at GFZ and an expansion into a "Competence Centre Telegrafenberg" where an exchange of experience and joint activities with PIK, AWI and AIP take place. The exchange of experience with other people interested in Machine Learning within the Helmholtz Association is also important for "ML@GFZ": "The Helmholtz-AI platforms are now starting up", explains Frederik Tilmann, head of the GFZ section "Seismology". He represents the GFZ on the steering committee of the Helmholtz Artificial Intelligence Cooperation Unit (Helmholtz AI). "The Helmholtz AI platforms will also help to give more scientists access to AI methods to support their research". (ph)

GFZ Sections involved in the first GFZ Machine Learning Hackathon:

  • Space Geodetic Techniques
  • Remote Sensing and Geoinformatics
  • Physics of Earthquakes and Volcanoes
  • Seismology
  • Geodynamical modelling
  • Seismic Hazard and Risk Dynamics
  • Geomicrobiology
  • Lithosphere Dynamics
  • Geomechanics and Scientific Drilling
  • Hydrology
  • Basin Modelling
  • Geomorphology
  • Earth Surface Process Modelling
  • eScience Centre

Further information:

Additional News

Portrait Lars Bernard, green background

The Board of Trustees appoints Prof. Lars Bernard to the Scientific Advisory Board of the…

Portrait photo of Harald Schuh, background: green

AGU Award for Harald Schuh

The glass building with flagging "IASS" at Helmholtzstraße 5.

An ideal addition to the Helmholtz Association

SLR Station, Laser

New DFG Research Unit “Clock Metrology: A Novel Approach to TIME in Geodesy” with GFZ…

Niels Hovius portrait

Niels Hovius appointed to the renowned "National Academy of Science and Engineering –…

[Translate to English:] GFZ-Logo

GFZ's position on the Leopoldina paper “Earth System Science”

Kimberella fossile

Feeding strategies of the oldest known animals (Ediacara)

Portraits of the five young researchers

EGU OSPP Awards 2022 to five GFZ researchers

[Translate to English:] Lila Flagge wehend über einem Dachgiebel

Interviews on the occasion of the Purple Light Up 2022

Obituary picture of Dr. Kemâl Erbas.

Obituary Dr. Kemâl Erbas

Two profile photos and in between the logo of BMWK and a symbol image for a text document.

Important signal for the expansion of deep geothermal energy

German map with quality-checked data points, shown as columns

A new heat-flow analysis shows higher values for Germany

P. Martinez-Garzon in a forest next to a giant split rock

Dr. Patricia Martinez-Garzon wins ERC Starting Grant for her project QUAKE-HUNTER

Map of Türkiye with the marked epicentre of the earthquake in the northwestern part of the country

Background on today's earthquake in northwest Türkiye

Topography map of the alps.

What is driving the Alps upwards?

Groupp picture ICDP/IODP Kolloquiums

Joint IODP/ICDP-Colloquium at GFZ

Teachers in lecture hall during lecture

"Extreme Events in the Earth System" - 20th "System Earth" Autumn School

Two young researchers stand in front of trees holding their certificates, next to them stands Ludwig Stroink, who awarded the certificates.

“GFZ Friends” honours Theresa Hennig and Lei Wang with the “Friedrich-Robert-Helmert Prize…

Satellite image of a desert area: Colorful spots show different minerals.

German environmental satellite EnMAP: start into regular operation

On the left, a measuring tower in a low overgrown tundra landscape.

More methane from Siberia in summer

[Translate to English:] Profilfoto mit schwarzem Rahmen von Henning Francke

Obituary: Henning Francke

Group photo with projekt responsible

Making geodata interoperable and suited for curiosity driven research: GEO-INQUIRE project…

Schema Energiebereitstellung durch Geothermie

European Geothermal Congress from 17 to 21 October 2022 in Berlin

Gruppenfoto PAM

International Conference on Polar and Alpine Microbiology

Leni Scheck Wenderoth

“AWG Professional Excellence Award” for Magdalena Scheck-Wenderoth

Ausbildung am GFZ

Berufsausbildung und duales Studium am GFZ

Dr. Ute Weckmann during the opening speech of the workshop

Dr. Ute Weckmann takes over the chairmanship of IAGA Division VI

Anke Neumann aon a boat during a research trip

Dr Anke Neumann is a Senior Humboldt Research Fellow

Earth Model

New DFG priority programme on deep Earth evolution over geologic time

Logo of the Helmholtz Innovation Labs: written words only

Successful interim evaluation of the two Helmholtz Innovation Labs at the GFZ

back to top of main content