PINN ME: A Physics-Informed Neural Network Framework for Accurate Milne–Eddington Inversions of Solar Magnetic Fields
Robert Jarolim et al 2025 ApJL 985 L7 A new framework successfully mitigates observational noise, inverts even large fields of view in a memory-efficient way, and can resolve small-scale features in…
Read the full articleYou might also wanna read
Machine Learning Validates Unrecognized Transient Astronomical Phenomena in Historical Observatory Images
Transient, star-like point sources that appear and vanish over short timescales are described in astronomical images prior to launch of Sput
arxiv.org·2mo ago
ICESEE v1.0.0: An Open-Source Python Framework for Ensemble Kalman Filtering in Ice Sheet Modeling
ICESEE (ICE Sheet statE and parameter Estimator) is a Python-based, open-source data assimilation framework designed for seamless integratio
doi.org·21d ago
General Physics Transformer Achieves Foundation Model Capabilities for Multiple Physical Systems
Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-tra
arxiv.org·9mo ago
Scientists develop mathematical tool to measure solar wind using spacecraft radio signals
A newly developed mathematical framework allows scientists to use any spacecraft's radio signal to consistently measure the speed and densit
researchmatters.in·15d ago
NJIT Physicists Pinpoint Sun's Magnetic Dynamo 200,000 km Below Surface Using 30 Years of Acoustic Data
In an analysis of nearly three decades of solar acoustic data, NJIT physicists report evidence that the solar dynamo — the magnetic engine p
news.njit.edu·3mo ago
SOLAR: An Automated Framework for Speed-of-Light Performance Analysis of Deep Learning Models
How fast could a deep-learning model run on target hardware, and how far is today's implementation from that limit? These questions are cent
arxiv.org·12d agoSOLAR: An Automated Framework for Speed-of-Light Performance Analysis of Deep Learning Models
How fast could a deep-learning model run on target hardware, and how far is today's implementation from that limit? These questions are cent
arxiv.org·12d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.