Exploring System Dynamics in the Natural World with AI
William Gilpin & Nikola Kovachki
Interdisciplinary scientific machine learning symposium exploring neural operators, chaotic dynamical systems forecasting, climate modeling, and physics-informed AI in the natural sciences.
Syllabus
7Model Scale Versus Domain Knowledge in Long-Term Forecasting of Chaos
William Gilpin explores the interplay between model complexity and foundational domain understanding for robust long-term prediction in chaotic natural systems.
Operator Learning in Theory and Practice
Nikola Kovachi details the theoretical underpinnings and practical applications of operator learning for solving complex scientific and engineering problems.
Science Education for AI: Beyond AI in Science Education
Danny Caballero argues for a fundamental shift: prioritizing scientific literacy for an AI-driven world over merely integrating AI tools into existing science curricula.
From Polar Ice to Rising Seas: Advancing Climate Science with Machine Learning
Karianne Bergen explores how advanced machine learning techniques are accelerating discovery and improving predictive capabilities in critical climate science research.
From Scheduled to Predictive Maintenance in Hydropower using AI
Pia Zacharias from Statkraft details the transition from traditional scheduled maintenance to AI-driven predictive approaches within hydropower operations.
Data-Driven Approaches to Mitigate Chalk Influxes
Felix Kohler discusses applying data-driven methodologies to forecast and mitigate challenging chalk influx events in geological and industrial contexts.
Physical Insights from Discriminative and Generative Models for Frictional Surface Design
Anders Malthe-Sørenssen delves into how machine learning models can yield physical insights for designing novel frictional surfaces at a fundamental level.