I
I. S. Knyazeva
Researcher at Saint Petersburg State University
Publications - 33
Citations - 154
I. S. Knyazeva is an academic researcher from Saint Petersburg State University. The author has contributed to research in topics: Computational topology & Flare. The author has an hindex of 7, co-authored 32 publications receiving 146 citations. Previous affiliations of I. S. Knyazeva include Pulkovo Observatory & Russian Academy of Sciences.
Papers
More filters
Stokes inversion techniques with neural networks: analysis of uncertainty in parameter estimation
Lukiya A. Mistryukova,A. Plotnikov,Aleksandr Khizhik,I. S. Knyazeva,Mikhail Hushchyn,Denis Derkach +5 more
TL;DR: This paper provides end-to-end inversion codes based on the simple Milne-Eddington model of the stellar atmosphere and deep neural networks to both parameter estimation and their uncertainty intervals and demonstrates that the proposed architecture provides high accuracy of results, including a reliable uncertainty estimation, even in the multidimensional case.
Journal ArticleDOI
Comparison of Predictive Efficiency of Topological Descriptors and SHARP in Solar Flares Forecasting
TL;DR: The classification results turned out practically identical to those obtained by the Stanford Solar Observatory group, which means that using LOS magnetograms retains enough complexity for magnetic field description.
Journal ArticleDOI
Topological diagnostics of the cyclic component of the time series associated with helium
I. S. Knyazeva,I. S. Knyazeva,Yu. A. Nagovitsyn,Yu. A. Nagovitsyn,F. A. Urt’ev,N. G. Makarenko +5 more
TL;DR: A method based on the combination of time-series topological embedding in Euclidean space and the identification of a persistent cycle by homology theory methods is proposed and demonstrated based on actual data.
Journal ArticleDOI
Features of Spatiotemporal Clustering in a Maunder Butterfly Diagram
TL;DR: In this article, the Fisher-Rao metric was used to calculate the distances between the butterfly wings of the Maunder butterfly pattern and found that the similarities or differences in the patterns of individual butterfly wings in this metric are approximately the same for each hemisphere.