相关论文: Autoencoder-Based Detection of Anomalous Stokes V …

The complex structure and extensive details of solar spectral data, combined with a recent surge in volume, present significant processing challenges. To address this, we propose a deep learning-based compression technique using deep…

We analyze a set of full Stokes profile observations of the flaring active region NOAA 10808 recorded with the Vector-Spectromagnetograph (VSM) of the SOLIS facility. We aim to quantify transient and permanent changes in the magnetic field…

The tens of millions of spectra being captured by the Dark Energy Spectroscopic Instrument (DESI) provide tremendous discovery potential. In this work we show how Machine Learning, in particular Variational Autoencoders (VAE), can detect…

Predicting the severity of the solar eruptive phenomena like flares and Coronal Mass Ejections (CMEs) remains a great challenge despite concerted efforts for several decades. The advent of high quality vector magnetograms obtained from…

This is a follow-up investigation of a magnetic-flux cancellation event at a polarity inversion line (PIL) on the Sun observed with the spectropolarimeter on board Hinode. Anomalous circular polarization (Stokes V) profiles are observed in…

The formation of unusually shaped Stokes V profiles of the Fe I 630.2 nm line in the solar photosphere are investigated. The results of numerical 2-D MHD simulation of solar magnetogranulation are used for this. In their properties, the…

The application of machine learning techniques for anomaly detection in particle accelerators has gained popularity in recent years. These efforts have ranged from the analysis of quenches in radio frequency cavities and superconducting…

Climate anomalies significantly impact terrestrial carbon cycle dynamics, necessitating robust methods for detecting and analyzing anomalous behavior in plant productivity. This study presents a novel application of variational autoencoders…

We used multi-wavelength high-resolution data from ARIES, THEMIS, and SDO instruments, to analyze a non-standard, C3.3 class flare produced within the active region NOAA 11589 on 2012 October 16. Magnetic flux emergence and cancellation…

This work demonstrates the possibility of magnetic field topology investigations using microwave polarimetric observations. We study a solar flare of GOES M1.7 class that occurred on 11 February, 2014. This flare revealed a clear signature…

We study the structure of the magnetic elements in network-cell interiors. A quiet Sun area close to the disc centre was observed with the spectro-polarimeter of the Solar Optical Telescope on board the Hinode space mission, which yielded…

We introduce an anomaly detection method for multivariate time series data with the aim of identifying critical periods and features influencing extreme climate events like snowmelt in the Arctic. This method leverages the Variational…

The first significant sunquake event of Solar Cycle 25 was observed during the X1.5 flare of May 10, 2022, by the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory. We perform a detailed spectro-polarimetric…

We analyse spectropolarimetric observations of the penumbra of the NOAA AR 10953 at high spatial resolution (0.3"). The full Stokes profiles of the Fe I lines at 630.1 nm and 630.2 nm have been obtained with the Solar Optical Telescope…

We analyze spectropolarimetric data taken with the Hinode spacecraft in quiet solar regions at the disk center. Distorted redshifted Stokes $V$ profiles are found showing a characteristic evolution that always follows the same sequence of…

We report seven examples of a long-ignored type of confined solar flare eruption that does not fit the standard model for confined flare eruptions. Because they are confined eruptions, do not fit the standard model, and unexpectedly erupt…

Anomaly detection is a prominent data preprocessing step in learning applications for correction and/or removal of faulty data. Automating this data type with the use of autoencoders could increase the quality of the dataset by isolating…

It has been previously observed that narrow lanes of transverse and longitudinal magnetic field with opposite polarity are the site of large solar flares. We performed a comprehensive examination of the stokes asymmetries of active region…

The extreme ultraviolet portion of the solar spectrum contains a wealth of diagnostic tools for probing the lower solar atmosphere in response to an injection of energy, particularly during the impulsive phase of solar flares. These include…

A machine-learning-based method is developed to identify objects with unusual stellar spectra. The method employs an autoencoder, a neural network trained to compress spectral data into a low-dimensional representation and subsequently…