Physics-aware machine learning revolutionizes scientific paradigm for machine learning and process-based hydrology

Q Xu, Y Shi, J Bamber, Y Tuo, R Ludwig… - arxiv preprint arxiv …, 2023 - arxiv.org
Accurate hydrological understanding and water cycle prediction are crucial for addressing
scientific and societal challenges associated with the management of water resources …

Generalized teacher forcing for learning chaotic dynamics

F Hess, Z Monfared, M Brenner… - arxiv preprint arxiv …, 2023 - arxiv.org
Chaotic dynamical systems (DS) are ubiquitous in nature and society. Often we are
interested in reconstructing such systems from observed time series for prediction or …

Curiosity-driven search for novel nonequilibrium behaviors

MJ Falk, FD Roach, W Gilpin, A Murugan - Physical Review Research, 2024 - APS
Exploring the full spectrum of novel behaviors that a system can produce can be an
intensive task. Sampling techniques developed in response to this exploration challenge …

Bayesian Meta-Learning for Probabilistic Modeling and Optimization

M Volpp - 2025 - publikationen.bibliothek.kit.edu
Trotz ihres erwiesenen Potenzials sind moderne Methoden des maschinellen Lernens in
der Praxis oft nicht ohne Weiteres anwendbar, zB für viele Modellierungs-oder …

Let's do the time-warp-attend: Learning topological invariants of dynamical systems

N Moriel, M Ricci, M Nitzan - arxiv preprint arxiv:2312.09234, 2023 - arxiv.org
Dynamical systems across the sciences, from electrical circuits to ecological networks,
undergo qualitative and often catastrophic changes in behavior, called bifurcations, when …