arXiv subjects

Ioanna Bouri

Publications and source records attributed to Ioanna Bouri.

5 recordsLinked to original sources

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↗

arXiv2026

SuNeRF-CME: Physics-Informed Neural Radiance Fields for Tomographic Reconstruction of Coronal Mass Ejections

Coronagraphic observations enable direct monitoring of coronal mass ejections (CMEs) through scattered light from free electrons, but determining the 3D plasma distribution from 2D imaging data is challenging due to the optically-thin plasma and the complex image formation processes. We introduce SuNeRF-CME, a framework for 3D tomographic reconstructions of the heliosphere using multi-viewpoint coronagraphic observations. The method leverages Neural Radiance Fields (NeRFs) to estimate the electron density in the heliosphere through a ray-tracing approach, while accounting for the underlying Thomson scattering of image formation. The model is optimized by iteratively fitting the time-dependent observational data. In addition, we apply physical constraints in terms of continuity, propagation direction, and speed of the heliospheric plasma to overcome limitations imposed by the sparse number of viewpoints. We utilize synthetic observations of a CME simulation to fully quantify the model's performance for different viewpoint configurations. The results demonstrate that our method can reliably estimate the CME parameters from only two viewpoints, with a mean velocity error of $3.01\pm1.94\%$ and propagation direction errors of $3.39\pm1.94^\circ$ in latitude and $1.76\pm0.79^\circ$ in longitude. We further show that our approach can achieve a full 3D reconstruction of the simulated CME from two viewpoints, where we correctly model the three-part structure, deformed CME front, and internal plasma variations. Additional viewpoints can be seamlessly integrated, directly enhancing the reconstruction of the plasma distribution in the heliosphere. This study underscores the value of physics-informed methods for reconstructing the heliospheric plasma distribution, paving the way for unraveling the dynamic 3D structure of CMEs and enabling advanced space weather monitoring.

astro-ph.SR↗

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↗

arXiv2022

ML framework for global river flood predictions based on the Caravan dataset

Reliable prediction of river floods in the first 72 hours can reduce harm because emergency agencies have sufficient time to prepare and deploy for help at the scene. Such river flood prediction models already exist and perform relatively well in most high-income countries. But, due to the limited availability of data, these models are lacking in low-income countries. Here, we offer the first global river flood prediction framework based on the newly published Caravan dataset. Our framework aims to serve as a benchmark for future global river flood prediction research. To support generalizability claims we include custom data evaluation splits. Further, we propose and evaluate a novel two-path LSTM architecture (2P-LSTM) against three baseline models. Finally, we evaluate the generated models on different locations in Africa and Asia that were not part of the Caravan dataset.

physics.geo-ph↗