arXiv AI
Discovering Dual-Origin Slow Wind from Solar Orbiter with Self-Supervised Contrastive Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 21
Preserving Clusters in Error-Bounded Lossy Compression of Scientific Particle Data
arXiv:2604. 18801v2 Announce Type: replace Abstract: Scientific particle simulations in cosmology, molecular dynamics, and fluid dynamics produce large-scale datasets whose storage, movement, and analysis increasingly rely on lossy compression.
arXiv Machine Learning
Jun 17
Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere
arXiv:2606. 17603v1 Announce Type: new Abstract: In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective.
arXiv AI
Jun 30
Domain-Informed Multi-View Self-Distillation for Astronomical Light-Curve Representation Learning with JEPA
arXiv:2606. 28446v1 Announce Type: cross Abstract: Light curves describe temporal variations in the brightness of celestial objects.
arXiv Machine Learning
Aug 24
Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations
arXiv:2601. 12614v4 Announce Type: replace-cross Abstract: Hybrid-Vlasov simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are computationally expensive.
arXiv Machine Learning
Jun 5
Central Description Length (CDL) Clustering Validation Index
arXiv:2606. 05230v1 Announce Type: cross Abstract: Selecting a clustering algorithm and its hyperparameters without labels is a common difficulty in engineering machine learning pipelines that work with unsupervised analysis of sensor, image, or process data.
arXiv Machine Learning
Sep 22
SolarFlowRefiner: Refinement-Aware Flow Matching for Surface Solar Radiation Downscaling
SolarFlowRefiner is a refinement‑aware flow‑matching framework designed to downscale high‑resolution surface solar radiation (SSR) fields from coarse ERA5 radiative variables and satellite channels. It first uses a conditional FlowMatch generator to predict a normalized correction to an upsampled ERA5 baseline, then trains a refiner on prediction‑conditioned states between the generator’s output and the target residual, exposing the refiner to the generator’s structured errors. The refinement objective is backpropagated through the FlowMatch sampler, enabling joint optimization of generation and correction, and experiments on an ERA5–SolarCube benchmark demonstrate consistent improvements over standalone generation and post‑hoc refinement.