{"id":3249,"date":"2025-09-29T12:25:51","date_gmt":"2025-09-29T10:25:51","guid":{"rendered":"https:\/\/speinshart.ai\/pulse\/p\/"},"modified":"2025-11-07T12:16:10","modified_gmt":"2025-11-07T11:16:10","slug":"machine-learning-in-geophysical-modeling","status":"publish","type":"post","link":"https:\/\/speinshart.ai\/de\/pulse\/p\/machine-learning-in-geophysical-modeling","title":{"rendered":"Machine Learning in Geophysical Modeling"},"content":{"rendered":"
\"\"<\/figure>\n\n\n\n

From September 24\u201326, 2025<\/strong>, the Speinshart Scientific Centre for AI and SuperTech (SSC)<\/em> hosted a workshop dedicated to the intersection of Machine Learning (ML)<\/strong> und Geosciences<\/strong>. Organized by Tijana Janjic, Marcel Oliver, and Nadja Ray<\/strong>, the event brought together researchers from across Europe to discuss the latest developments, challenges, and perspectives in this exciting field.<\/p>\n\n\n\n

A Wide Range of Topics<\/strong><\/h2>\n\n\n\n

Participants explored a broad spectrum of questions, including:<\/p>\n\n\n\n

    \n
  • the use of\u00a0ML in geophysical modeling<\/strong>,<\/li>\n\n\n\n
  • methods of\u00a0uncertainty quantification<\/strong>,<\/li>\n\n\n\n
  • data assimilation<\/strong>\u00a0and bias analysis,<\/li>\n\n\n\n
  • as well as\u00a0explainable AI<\/strong>\u00a0in geoscientific contexts.<\/li>\n<\/ul>\n\n\n\n

    One theme became immediately clear: progress in this domain depends on close collaboration between ML experts and geoscientists.<\/p>\n\n\n\n

    Day 1 \u2013 Arrival and First Impulses<\/strong><\/h2>\n\n\n\n

    The workshop began on Wednesday with an informal get-together and the first talks. Thomas Mortier (Ghent University)<\/strong> presented methods to improve weather forecasts using conformal prediction intervals, while Maryam Ramezani Ziarani (KU Eichst\u00e4tt-Ingolstadt)<\/strong> discussed the role of ML in simplified shallow water models. A subsequent discussion focused on the prerequisites for successfully applying ML in geosciences .<\/p>\n\n\n\n

    Day 2 \u2013 Applications and Case Studies<\/strong><\/h2>\n\n\n\n

    Thursday highlighted a variety of applications:<\/p>\n\n\n\n

      \n
    • Karoline Rummel (IOW Warnem\u00fcnde)<\/strong>\u00a0demonstrated how LSTM networks can be used for real-time estimation of salt intrusion.<\/li>\n\n\n\n
    • Katharina Holube (University of Hamburg)<\/strong>\u00a0introduced data-driven approaches to quantify energy transfers in the atmosphere.<\/li>\n\n\n\n
    • Additional talks covered\u00a0ergodic theory for ocean drifter data<\/strong>,\u00a0origin identification of raw materials<\/strong>, and\u00a0graph-based deep learning for geomorphological mapping<\/strong>.<\/li>\n<\/ul>\n\n\n\n

      After a day of intensive discussions, participants continued their conversations on a communal hike<\/strong> \u2013 a refreshing way to extend the scientific exchange beyond the lecture hall .<\/p>\n\n\n\n

      Day 3 \u2013 Outlook and Networking<\/strong><\/h2>\n\n\n\n

      Friday began with a guided tour of Speinshart Monastery<\/strong> before moving on to the final sessions:<\/p>\n\n\n\n

        \n
      • Sergiy Vasylkevych (University of Hamburg)<\/strong>\u00a0spoke on error growth in forecasting models.<\/li>\n\n\n\n
      • Sarah Eberle-Blick (KU Eichst\u00e4tt-Ingolstadt)<\/strong>\u00a0presented new ML-based approaches to solving inverse problems.<\/li>\n\n\n\n
      • Other contributions addressed the\u00a0assimilation of radar data<\/strong>\u00a0and the\u00a0recovery of energy spectra from incomplete observations<\/strong>.<\/li>\n<\/ul>\n\n\n\n

        The workshop concluded with a lively discussion on the future of ML in geosciences<\/strong>, underscoring a clear message: building robust, explainable, and broadly applicable models will only be possible through genuine interdisciplinary collaboration .<\/p>\n\n\n\n

        Conclusion<\/strong><\/h2>\n\n\n\n

        The workshop impressively demonstrated just how dynamic and multifaceted<\/strong> the field of geophysical modeling with ML has become. The combination of talks, discussions, and personal exchange provided valuable impulses and strengthened collaboration across disciplines.<\/p>\n\n\n\n

        We look back with gratitude on three inspiring days \u2013 and forward with excitement to the next steps in this joint research endeavor.<\/p>\n\n\n\n

        <\/p>","protected":false},"excerpt":{"rendered":"

        From September 24\u201326, 2025, the Speinshart Scientific Centre for AI and SuperTech (SSC) hosted a workshop dedicated to the intersection of Machine Learning (ML) and Geosciences. Organized by Tijana Janjic, Marcel Oliver, and Nadja Ray, the event brought together researchers from across Europe to discuss the latest developments, challenges, and perspectives in this exciting field. A Wide Range of Topics Participants explored […]<\/p>","protected":false},"author":2,"featured_media":3250,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[3],"tags":[10,11,12,24],"class_list":["post-3249","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research-retreats","tag-ai","tag-convention","tag-event","tag-ssc"],"acf":[],"_links":{"self":[{"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/posts\/3249","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/comments?post=3249"}],"version-history":[{"count":1,"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/posts\/3249\/revisions"}],"predecessor-version":[{"id":3251,"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/posts\/3249\/revisions\/3251"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/media\/3250"}],"wp:attachment":[{"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/media?parent=3249"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/categories?post=3249"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/speinshart.ai\/de\/wp-json\/wp\/v2\/tags?post=3249"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}