arXiv subjects

Ivan Zaitsev

Publications and source records attributed to Ivan Zaitsev.

8 recordsLinked to original sources

arXiv2026

Geoelectric Field Caused by Flux Transfer Events in an Ionosphere-Coupled Vlasiator Simulation

We report on the relationship between flux transfer events (FTEs) at Earth's magnetopause and the geoelectric field that is induced near the FTEs' magnetic footpoints. We study this system using the global hybrid-Vlasov code Vlasiator, which has recently been extended to model ionospheric physics. We also highlight the significance of 3D magnetic null points, which in our simulation can separate the FTEs into multiple flux ropes. Near the null points, the coiled FTE magnetic field lines are rerouted towards Earth, so that the magnetic footpoints are planted near the Region 1 ionospheric current system. The helicities of the flux ropes are organized by the y-component (GSE) of the magnetic field at the Earth's magnetopause. This occurs in our simulation due to the absence of a y-component of the interplanetary magnetic field, which would normally supply the FTE guide field that determines the helicity. We observe Alfvenic, Earthward-flowing field-aligned currents generated near the magnetopause that correlate with the passage of FTEs nearby. These pulses of current coincide with the formation of rotational geoelectric field structures, that appear near the noon meridian and propagate around the auroral oval towards the nightside.

physics.space-ph↗

arXiv2026

Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations

Hybrid-Vlasov simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are computationally expensive. We show that graph-based machine learning emulators can learn the spatiotemporal evolution of electromagnetic fields and lower-order moments of the ion velocity distribution function in near-Earth space from four 5D Vlasiator runs, each driven by steady solar wind conditions. The upstream ion number density is systematically varied between the runs, while the grid spacing is held constant, to scan the ratio of ion inertial length to grid size. Using a graph neural network (GNN) operating on the 2D spatial simulation grid comprising 670k cells, we demonstrate that both a deterministic forecasting model (Graph-FM) and a probabilistic ensemble forecasting model (Graph-EFM) based on a latent variable formulation produce accurate predictions of future plasma states. A divergence penalty is incorporated to encourage divergence-freeness in the magnetic fields. For the probabilistic model, a continuous ranked probability score objective is added to improve the calibration of the ensemble forecasts. In terms of wall time per output step, the trained emulators run over two orders of magnitude faster on a single GPU than the Vlasiator simulations on 100 CPUs. Most forecasted fields have Pearson correlations above 0.95 at 50 seconds lead time. Fields that exhibit degenerate (near-zero) distributions in the 5D setting are more challenging for the emulator to keep well correlated. The ensemble forecasts remain underdispersive, with spread-skill ratios of approximately 0.2-0.3, and thus provide spatially structured relative uncertainty estimates. Overall, these results demonstrate that GNNs provide a viable framework for rapid ensemble generation in hybrid-Vlasov modeling and highlight promising directions for future work.

physics.space-ph↗

arXiv2025

Graph-based Neural Space Weather Forecasting

Accurate space weather forecasting is crucial for protecting our increasingly digital infrastructure. Hybrid-Vlasov models, like Vlasiator, offer physical realism beyond that of current operational systems, but are too computationally expensive for real-time use. We introduce a graph-based neural emulator trained on Vlasiator data to autoregressively predict near-Earth space conditions driven by an upstream solar wind. We show how to achieve both fast deterministic forecasts and, by using a generative model, produce ensembles to capture forecast uncertainty. This work demonstrates that machine learning offers a way to add uncertainty quantification capability to existing space weather prediction systems, and make hybrid-Vlasov simulation tractable for operational use.

physics.space-ph↗

arXiv2023

Graph Representation of the Magnetic Field Topology in High-Fidelity Plasma Simulations for Machine Learning Applications

Topological analysis of the magnetic field in simulated plasmas allows the study of various physical phenomena in a wide range of settings. One such application is magnetic reconnection, a phenomenon related to the dynamics of the magnetic field topology, which is difficult to detect and characterize in three dimensions. We propose a scalable pipeline for topological data analysis and spatiotemporal graph representation of three-dimensional magnetic vector fields. We demonstrate our methods on simulations of the Earth's magnetosphere produced by Vlasiator, a supercomputer-scale Vlasov theory-based simulation for near-Earth space. The purpose of this work is to challenge the machine learning community to explore graph-based machine learning approaches to address a largely open scientific problem with wide-ranging potential impact.

physics.plasm-ph↗

arXiv2020

In situ evidence of firehose instability in multiple reconnection

Energy conversion via reconnecting current sheets is common in space and astrophysical plasmas. Frequently, current sheets disrupt at multiple reconnection sites, leading to the formation of plasmoid structures between sites, which might affect energy conversion. We present in situ evidence of the firehose instability in multiple reconnection in the Earth's magnetotail. The observed proton beams accelerated in the direction parallel to magnetic field and ion-scale fluctuations of whistler type imply the development of firehose instability between two active reconnection sites. The linear wave dispersion relation, estimated for the measured plasma parameters, indicates a positive growth rate of firehose-related electromagnetic fluctuations. Simulations of temporal evolution of the observed multiple reconnection by using a 2.5D implicit particle-in-cell code show that, as the plasmoid formed between two reconnection sites evolves, the plasma at its edge becomes anisotropic and overcomes the firehose marginal stability threshold, leading to the generation of magnetic field fluctuations. The combined results of observations and simulations suggest that the firehose instability, operating between reconnection sites, converts plasma kinetic energy into energy of magnetic field fluctuations, counteracting the conversion of magnetic energy into plasma energy occurring at reconnection sites. This suggests that magnetic energy conversion in multiple reconnection can be less efficient than in the case of the single-site reconnection.

physics.space-ph↗

arXiv2019

A General Framework for Counterfactual Learning-to-Rank

Implicit feedback (e.g., click, dwell time) is an attractive source of training data for Learning-to-Rank, but its naive use leads to learning results that are distorted by presentation bias. For the special case of optimizing average rank for linear ranking functions, however, the recently developed SVM-PropRank method has shown that counterfactual inference techniques can be used to provably overcome the distorting effect of presentation bias. Going beyond this special case, this paper provides a general and theoretically rigorous framework for counterfactual learning-to-rank that enables unbiased training for a broad class of additive ranking metrics (e.g., Discounted Cumulative Gain (DCG)) as well as a broad class of models (e.g., deep networks). Specifically, we derive a relaxation for propensity-weighted rank-based metrics which is subdifferentiable and thus suitable for gradient-based optimization. We demonstrate the effectiveness of this general approach by instantiating two new learning methods. One is a new type of unbiased SVM that optimizes DCG -- called SVM PropDCG --, and we show how the resulting optimization problem can be solved via the Convex Concave Procedure (CCP). The other is Deep PropDCG, where the ranking function can be an arbitrary deep network. In addition to the theoretical support, we empirically find that SVM PropDCG significantly outperforms existing linear rankers in terms of DCG. Moreover, the ability to train non-linear ranking functions via Deep PropDCG further improves performance.

cs.IR↗

arXiv2018

Estimating Position Bias without Intrusive Interventions

Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal. While it was recently shown how counterfactual learning-to-rank (LTR) approaches \cite{Joachims/etal/17a} can provably overcome presentation bias when observation propensities are known, it remains to show how to effectively estimate these propensities. In this paper, we propose the first method for producing consistent propensity estimates without manual relevance judgments, disruptive interventions, or restrictive relevance modeling assumptions. First, we show how to harvest a specific type of intervention data from historic feedback logs of multiple different ranking functions, and show that this data is sufficient for consistent propensity estimation in the position-based model. Second, we propose a new extremum estimator that makes effective use of this data. In an empirical evaluation, we find that the new estimator provides superior propensity estimates in two real-world systems -- Arxiv Full-text Search and Google Drive Search. Beyond these two points, we find that the method is robust to a wide range of settings in simulation studies.

cs.IR↗

arXiv2018

Consistent Position Bias Estimation without Online Interventions for Learning-to-Rank

Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal with uninformative signals due to position in the ranking, saliency, and other presentation factors. While it was recently shown how counterfactual learning-to-rank (LTR) approaches \cite{Joachims/etal/17a} can provably overcome presentation bias if observation propensities are known, it remains to show how to accurately estimate these propensities. In this paper, we propose the first method for producing consistent propensity estimates without manual relevance judgments, disruptive interventions, or restrictive relevance modeling assumptions. We merely require that we have implicit feedback data from multiple different ranking functions. Furthermore, we argue that our estimation technique applies to an extended class of Contextual Position-Based Propensity Models, where propensities not only depend on position but also on observable features of the query and document. Initial simulation studies confirm that the approach is scalable, accurate, and robust.

cs.LG↗