The article discusses how machine learning can be applied to the Sun’s interior and atmosphere, which are complex, multiscale dynamical systems. It introduces a state-space framework where the Sun’s global state vector is governed by thermodynamic, kinetic, and magnetic properties, and observations provide only partial, projected measurements. The authors propose that machine learning serves as a family of operators—Inference, Emulation, Propagation, and Control—to reconstruct, simulate, and couple this hidden state across different physical layers, thereby bridging observational gaps and accelerating nonlinear simulations to predict the Sun’s global evolution.
arXiv:2608.22782v1 Announce Type: cross Abstract: The Solar wind is a continuous flow of charged particles emanating from the solar surface and governed by complex, interacting magnetohydrodynamic pr...
The paper introduces a neural‑network based local‑box chemical kinetics solver for exoplanet atmospheres, employing a residual flow‑map architecture. It achieves microsecond‑scale inference with percent‑level accuracy across a wide range of temperatures, pressures, time steps, and compositional variations, outperforming other machine‑learning models and handling the extreme stiffness of atmospheric chemistry. The surrogate model offers a flexible, efficient alternative to classical solvers for state‑to‑state flow‑map problems in numerical simulations.
arXiv:2510. 25306v3 Announce Type: replace Abstract: Partial physical knowledge--governing structures known, constitutive relations or their combinations not--pervades spatiotemporal systems.
arXiv:2606. 19539v1 Announce Type: cross Abstract: Solar energetic particle (SEP) events have attracted increasing attention due to their significant radiation hazards for aviation, spacecraft electronics, and human missions beyond Earth's magnetosphere.
arXiv:2607. 18877v1 Announce Type: new Abstract: In the context of global warming, extreme events have become more frequent and intense, making their trustworthy detection and forecasting more important than ever.
arXiv:2608.22065v1 Announce Type: cross Abstract: Whether the slow solar wind originates from one coronal source or two distinct channels remains a central open question in heliophysics. Resolving th...
arXiv:2601.21151v3 Announce Type: replace Abstract: Machine-learning approaches to weather forecasting often employ a monolithic architecture in which distinct physical mechanisms, such as advection,...
arXiv:2610.09770v1 Announce Type: cross Abstract: Deep learning has made rapid advances in weather forecasting: autoregressive models trained on atmospheric reanalyses now rival dynamical models acro...
arXiv:2605.16929v2 Announce Type: replace Abstract: Global climate models are essential tools to simulate past and potential future pathways of climate change, as well as associated climate impacts....
arXiv:2606. 18464v1 Announce Type: cross Abstract: Detecting the tiny Doppler shifts induced by Earth-mass planets in stellar radial-velocity measurements remains extremely challenging due to stellar activity.
The paper presents a two‑stage method that first trains a neural network on N‑body simulations of multi‑planet systems and then distills its knowledge into closed‑form algebraic equations via symbolic regression. These distilled equations predict the onset of dynamical instability across a wide range of mass ratios, spacings, and eccentricities, outperforming existing analytic estimates. The approach yields a small set of interpretable variables that capture the structure of the instability landscape.
arXiv:2607. 27320v1 Announce Type: cross Abstract: Field-level inference of cosmological initial conditions from galaxy surveys requires a forward model that is simultaneously accurate in the non-linear regime, computationally efficient, and fully differentiable.