Inferring solar-wind plasma structures from sparse probe trajectories using recurrent reduced-order learning

Farbod Faraji; Maryam Reza

A recurrent reduced-order model reconstructs solar-wind plasma fields from sparse probe time series.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-29 01:06 UTC pith:KUQEVUAA

load-bearing objection Recurrent reduced-order model reconstructs 2D solar-wind fields from sparse virtual probes inside WSA-ENLIL runs, but stays simulation-only with no quantitative metrics shown. the 2 major comments →

arxiv 2606.27620 v1 pith:KUQEVUAA submitted 2026-06-26 physics.plasm-ph physics.space-ph

Inferring solar-wind plasma structures from sparse probe trajectories using recurrent reduced-order learning

Maryam Reza , Farbod Faraji This is my paper

classification physics.plasm-ph physics.space-ph

keywords solar windplasma reconstructionreduced-order modelingrecurrent learningspacecraft measurementsheliospheric structuresmeridional planeequatorial solar wind

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a recurrent reduced-order learning framework that takes time histories from a small number of virtual probes as input and produces reconstructed two-dimensional fields of radial velocity and plasma density. Trained on WSA-ENLIL simulation data, the approach recovers the main radial and latitudinal patterns in the meridional plane together with the spiral organization in the equatorial plane. It also infers spatial distributions of plasma quantities that are dynamically coupled but not directly measured by the probes. Sensitivity tests examine how accuracy changes with modal rank, number of probes, and length of input history. The method is positioned as a way to obtain needed spatial context from the limited local sampling that spacecraft provide.

Core claim

From sparse temporal probe signals as inputs, the recurrent reduced-order model recovers the dominant radial and latitudinal variations in the meridional plane and the spiral-shaped organization of the equatorial solar wind, while also reconstructing spatial distributions of dynamically coupled plasma fields not directly sensed.

What carries the argument

The recurrent reduced-order learning framework, which learns a low-rank spatial representation from simulation data and uses recurrent mapping to convert probe time histories into the coefficients of that representation.

Load-bearing premise

The solar-wind plasma structures in the target quantities are sufficiently captured by a low-rank reduced-order representation learned from the WSA-ENLIL simulation data, allowing recurrent mapping from sparse time histories to spatial fields.

What would settle it

A test in which reconstructed fields from the learned low-rank model show large pointwise or structural deviations from independent high-resolution simulation snapshots or from real spacecraft observations when the same sparse probe inputs are supplied.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

The model reconstructs spatial distributions of dynamically coupled plasma fields not directly sensed by the probes.
Reconstruction accuracy depends on modal rank, number of probes, and input-history length, as quantified in the sensitivity studies.
The framework supplies a practical route for extracting spatial plasma-state information from spacecraft measurements.
It supports studies on the underlying physics of space and solar-wind plasmas by providing the needed spatial context.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same low-rank recurrent mapping could be retrained or fine-tuned on actual multi-spacecraft observations to test performance on real rather than simulated data.
Success in recovering unsensed coupled fields suggests the approach may allow inference of additional plasma parameters from the same limited probe set.
The reported dependence of accuracy on probe count and history length supplies concrete guidance for choosing sampling strategies in future heliospheric missions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Desk Editor's Note

Recurrent reduced-order model reconstructs 2D solar-wind fields from sparse virtual probes inside WSA-ENLIL runs, but stays simulation-only with no quantitative metrics shown.

read the letter

The paper introduces a recurrent reduced-order learning framework that takes time histories from a small number of virtual probes and outputs 2D maps of radial velocity and density, recovering the main radial and latitudinal structure in the meridional plane plus the spiral pattern in the equatorial plane.

The combination of recurrent networks with reduced-order modeling for this specific solar-wind task is new, and the work shows the model can also fill in coupled fields that were not directly measured. The sensitivity checks on modal rank, probe count, and input history length are useful for understanding behavior inside the training data.

Everything is trained and tested on WSA-ENLIL simulation outputs. No real spacecraft measurements appear, so the method has not been checked against instrument noise, data gaps, or differences between the simulation's steady-state assumptions and actual observations. The abstract gives no error numbers or validation scores, which makes it difficult to assess how accurate the reconstructions actually are.

The low-rank assumption works for the simulation fields, but it is unclear how well it survives when the input statistics change. This limits how far the claims about practical use with spacecraft data can be taken right now.

The paper is aimed at heliophysics researchers who need ways to infer spatial plasma structure from limited probe time series. A reader working on data-driven methods for space plasmas would see a concrete demonstration, but the simulation-only scope keeps the impact contained.

It deserves peer review so that referees can ask for quantitative metrics and at least one test against real observations.

Referee Report

2 major / 0 minor

Summary. The paper presents a recurrent reduced-order learning framework trained on WSA-ENLIL solar-wind simulations to reconstruct 2D meridional and equatorial plasma fields (radial velocity and density) from sparse temporal signals of a small number of virtual probes. It claims recovery of dominant radial/latitudinal variations and equatorial spiral organization, reconstruction of dynamically coupled fields, and sensitivity of accuracy to modal rank, probe count, and input history length, positioning the method as a route to infer spatial structures from spacecraft measurements.

Significance. If the reconstruction accuracy holds under broader testing, the approach could offer a practical data-driven tool for interpreting limited in-situ measurements in heliophysics by leveraging reduced-order representations and recurrent mapping. The demonstration on coupled fields and parameter sensitivities is a positive step, but the exclusive reliance on simulation data limits immediate applicability to observations.

major comments (2)

[Abstract] Abstract and results (sensitivity studies paragraph): The central claim that the model 'recovers the dominant radial and latitudinal variations' and 'spiral-shaped organization' is stated without any reported quantitative metrics (e.g., RMSE, correlation, or normalized error) or error analysis for the reconstructions, despite explicit sensitivity studies on modal rank, probe count, and history length. This absence prevents assessment of whether the low-rank recurrent mapping actually achieves the claimed recovery.
[Abstract] Abstract (final sentence) and discussion of spacecraft application: The assertion that the methodology provides 'a practical route for extracting spatial plasma-state information from spacecraft measurements' is load-bearing for the paper's motivation but rests entirely on virtual probes inside the WSA-ENLIL domain. No domain-shift tests, instrument noise injection, or real spacecraft data validation are described, leaving open whether the learned mapping generalizes when input statistics deviate from the steady-state simulation assumptions.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major point below and indicate where revisions will be made.

read point-by-point responses

Referee: [Abstract] Abstract and results (sensitivity studies paragraph): The central claim that the model 'recovers the dominant radial and latitudinal variations' and 'spiral-shaped organization' is stated without any reported quantitative metrics (e.g., RMSE, correlation, or normalized error) or error analysis for the reconstructions, despite explicit sensitivity studies on modal rank, probe count, and history length. This absence prevents assessment of whether the low-rank recurrent mapping actually achieves the claimed recovery.

Authors: The sensitivity studies section quantifies reconstruction performance via error metrics (including RMSE) as functions of modal rank, probe count, and history length, with results shown in the associated figures. However, these quantitative values are not summarized in the abstract. We will revise the abstract to include explicit metrics (e.g., typical RMSE ranges) supporting the recovery claims. revision: yes
Referee: [Abstract] Abstract (final sentence) and discussion of spacecraft application: The assertion that the methodology provides 'a practical route for extracting spatial plasma-state information from spacecraft measurements' is load-bearing for the paper's motivation but rests entirely on virtual probes inside the WSA-ENLIL domain. No domain-shift tests, instrument noise injection, or real spacecraft data validation are described, leaving open whether the learned mapping generalizes when input statistics deviate from the steady-state simulation assumptions.

Authors: We agree that the demonstration uses only virtual probes from the steady-state WSA-ENLIL simulations and does not include domain-shift, noise, or real-data tests. This is an inherent limitation of the present proof-of-concept study. We will revise the abstract's final sentence and the discussion to clarify that the work establishes the method on simulation data as a foundation, while noting the need for future observational validation. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation self-contained

full rationale

The paper describes a recurrent reduced-order learning framework trained on external WSA-ENLIL simulation data to map sparse temporal probe signals to reconstructed spatial fields for radial velocity and density. No load-bearing steps reduce to self-definition, fitted parameters renamed as predictions, or self-citation chains; the model learns mappings from simulation inputs to outputs with sensitivity studies on modal rank, probe count, and history length performed on held-out simulation cases. The approach remains independent of its target results by construction and does not invoke uniqueness theorems or ansatzes from prior author work that would collapse the claim.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

Abstract-only review limits visibility into parameters and assumptions; modal rank is highlighted as a tunable element in sensitivity studies.

free parameters (1)

modal rank
Number of modes retained in the reduced-order representation; tested for effect on reconstruction accuracy.

axioms (1)

domain assumption Solar-wind plasma fields admit a useful low-rank reduced-order representation derived from WSA-ENLIL simulation data.
This underpins the ability to reconstruct spatial fields from sparse temporal inputs.

pith-pipeline@v0.9.1-grok · 5752 in / 1220 out tokens · 65078 ms · 2026-06-29T01:06:45.719659+00:00 · methodology

0 comments

read the original abstract

In space plasma studies, spacecraft measurements often provide time histories of the solar-wind plasma. However, many heliospheric plasma processes are organized over spatial scales that cannot be directly resolved by limited local sampling. This creates a persistent challenge: how to use limited probe measurements to recover the spatial plasma distributions needed to interpret evolving solar-wind structures. In this work, we present a recurrent reduced-order learning framework to address this challenge. The method is demonstrated using WSA-ENLIL solar-wind simulation data to reconstruct two-dimensional meridional and equatorial fields from a small number of virtual probes, with radial velocity and plasma density considered as target quantities on both planes. From sparse temporal probe signals as inputs, the model recovers the dominant radial and latitudinal variations in the meridional plane and the spiral-shaped organization of the equatorial solar wind. It is also able to reconstruct spatial distributions of dynamically coupled plasma fields not directly sensed. Sensitivity studies are performed to assess the dependence of reconstruction accuracy on key parameters of the machine-learning framework: modal rank, number of probes, and input-history length. The outcomes underline the methodology's promise as a practical route for extracting spatial plasma-state information from spacecraft measurements in support of studies on the underlying physics of space and solar-wind plasmas.

discussion (0)

Reference graph

Works this paper leans on

48 extracted references · 1 canonical work pages

[1]

The solar wind as a turbulence laboratory,

R. Bruno and V. Carbone, “The solar wind as a turbulence laboratory,” Living Reviews in Solar Physics 10, 2 (2013)

2013
[2]

The multi-scale nature of the solar wind,

D. Verscharen, K. G. Klein, and B. A. Maruca, “The multi-scale nature of the solar wind,” Living Reviews in Solar Physics 16, 5 (2019)

2019
[3]

Solar wind turbulence and the role of ion instabilities,

O. Alexandrova, C. H. K. Chen, L. Sorriso -Valvo, T. S. Horbury, and S. D. Bale, “Solar wind turbulence and the role of ion instabilities,” Space Science Reviews 178, 101–139 (2013)

2013
[4]

Kinetic physics of the solar corona and solar wind,

E. Marsch, “Kinetic physics of the solar corona and solar wind,” Living Reviews in Solar Physics 3, 1 (2006)

2006
[5]

The spectrum of turbulence,

G. I. Taylor, “The spectrum of turbulence,” Proceedings of the Royal Society of London. Series A, Mathematical and Physical Sciences 164, 476–490 (1938)

1938
[6]

Validity of the Taylor hypothesis for linear kinetic waves in the weakly collisional solar wind,

G. G. Howes, K. G. Klein, and J. M. TenBarge, “Validity of the Taylor hypothesis for linear kinetic waves in the weakly collisional solar wind,” The Astrophysical Journal 789, 106 (2014)

2014
[7]

The violation of the Taylor hypothesis in measurements of solar wind turbulence,

K. G. Klein, G. G. Howes, and J. M. TenBarge, “The violation of the Taylor hypothesis in measurements of solar wind turbulence,” The Astrophysical Journal Letters 790, L20 (2014). [8] A. R. Macneil, M. J. Owens, A. J. Finley, and S. P. Matt, “A statistical evaluation of ballistic backmapping for the slow solar wind: The interplay of solar wind acceleratio...

2014
[8]

Interplanetary coronal mass ejections observed in the heliosphere: 1. Review of theory,

T. A. Howard and S. J. Tappin, “Interplanetary coronal mass ejections observed in the heliosphere: 1. Review of theory,” Space Science Reviews 147, 31–54 (2009)

2009
[9]

Accuracy and limitations of fitting and stereoscopic methods to determine the direction of coronal mass ejections from heliospheric imagers observations,

N. Lugaz, “Accuracy and limitations of fitting and stereoscopic methods to determine the direction of coronal mass ejections from heliospheric imagers observations,” Solar Physics 267, 411–429 (2010)

2010
[10]

The application of heliospheric imaging to space weather operations: Lessons learned from published studies,

R. A. Harrison, J. A. Davies, D. A. Biesecker, and M. Gibbs, “The application of heliospheric imaging to space weather operations: Lessons learned from published studies,” Space Weather 15, 985–1003 (2017)

2017
[11]

Improvement in the prediction of solar wind conditions using near -real time solar magnetic field updates,

C. N. Arge and V. J. Pizzo, “Improvement in the prediction of solar wind conditions using near -real time solar magnetic field updates,” Journal of Geophysical Research: Space Physics 105, 10465–10479 (2000)

2000
[12]

Improved method for specifying solar wind speed near the Sun,

C. N. Arge, D. Odstrčil, V. J. Pizzo, and L. R. Mayer, “Improved method for specifying solar wind speed near the Sun,” AIP Conference Proceedings 679, 190–193 (2003)

2003
[13]

Modeling 3-D solar wind structure,

D. Odstrčil, “Modeling 3-D solar wind structure,” Advances in Space Research 32, 497–506 (2003)

2003
[14]

Three-dimensional propagation of coronal mass ejections in a structured solar wind flow: 1. CME launched within the streamer belt,

D. Odstrčil and V. J. Pizzo, “Three-dimensional propagation of coronal mass ejections in a structured solar wind flow: 1. CME launched within the streamer belt,” Journal of Geophysical Research: Space Physics 104, 483–492 (1999). [18] A. M. Wold, M. L. Mays, A. Taktakishvili, L. K. Jian, D. Odstrčil, and P. MacNeice, “Verification of real -time WSA– ENLIL...

1999
[15]

Global MHD modeling of the solar corona and inner heliosphere for the Whole Heliosphere Interval,

P. Riley, R. Lionello, J. A. Linker, Z. Mikić, J. G. Luhmann, and J. Wijaya, “Global MHD modeling of the solar corona and inner heliosphere for the Whole Heliosphere Interval,” Solar Physics 274, 361–377 (2011)

2011
[16]

Magnetohydrodynamic simulation of interplanetary propagation of multiple coronal mass ejections with internal magnetic flux rope,

D. Shiota and R. Kataoka, “Magnetohydrodynamic simulation of interplanetary propagation of multiple coronal mass ejections with internal magnetic flux rope,” Space Weather 14, 56–75 (2016). [21] G. Tóth, I. V. Sokolov, T. I. Gombosi, D. R. Chesney, C. R. Clauer, D. L. De Zeeuw, et al., “Space Weather Modeling Framework: A new tool for the space science co...

2016
[17]

A solution -adaptive upwind scheme for ideal magnetohydrodynamics,

K. G. Powell, P. L. Roe, T. J. Linde, T. I. Gombosi, and D. L. De Zeeuw, “A solution -adaptive upwind scheme for ideal magnetohydrodynamics,” Journal of Computational Physics 154, 284–309 (1999). 18

1999
[18]

Adaptive numerical algorithms in space weather modeling,

G. Tóth, B. van der Holst, I. V. Sokolov, D. L. De Zeeuw, T. I. Gombosi, F. Fang, et al., “Adaptive numerical algorithms in space weather modeling,” Journal of Computational Physics 231, 870–903 (2012)

2012
[19]

What sustained multi-disciplinary research can achieve: The Space Weather Modeling Framework,

T. I. Gombosi, Y. Chen, A. Glocer, Z. Huang, X. Jia, M. W. Liemohn, et al., “What sustained multi-disciplinary research can achieve: The Space Weather Modeling Framework,” Journal of Space Weather and Space Climate 11, 42 (2021)

2021
[20]

Adapting ensemble-calibration techniques to probabilistic solar-wind forecasting,

N. O. Edward -Inatimi, M. J. Owens, L. A. Barnard, H. Turner, M. Marsh, S. Gonzi, M. Lang, and P. Riley, “Adapting ensemble-calibration techniques to probabilistic solar-wind forecasting,” Space Weather 22, e2024SW004164 (2024)

2024
[21]

Vlasov methods in space physics and astrophysics,

M. Palmroth, U. Ganse, Y. Pfau -Kempf, M. Battarbee, L. Turc, T. Brito, et al., “Vlasov methods in space physics and astrophysics,” Living Reviews in Computational Astrophysics 4, 1 (2018). [27] L. K. Jian, P. J. MacNeice, A. Taktakishvili, D. Odstrčil, B. Jackson, H.-S. Yu, P. Riley, I. V. Sokolov, and R. M. Evans, “Validation for solar wind prediction a...

2018
[22]

Assessing the quality of models of the ambient solar wind,

P. MacNeice, L. K. Jian, S. K. Antiochos, C. N. Arge, C. D. Bussy-Virat, M. L. DeRosa, et al., “Assessing the quality of models of the ambient solar wind,” Space Weather 16, 1644–1667 (2018)

2018
[23]

Unifying the validation of ambient solar wind models,

M. A. Reiss, K. Muglach, R. Mullinix, M. M. Kuznetsova, C. Wiegand, M. Temmer, et al., “Unifying the validation of ambient solar wind models,” Advances in Space Research 72, 5275–5286 (2023)

2023
[24]

Machine learning applications to computational plasma physics and reduced -order plasma modeling: A perspective,

F. Faraji and M. Reza, “Machine learning applications to computational plasma physics and reduced -order plasma modeling: A perspective,” Journal of Physics D: Applied Physics 58, 102002 (2025)

2025
[25]

Dynamic mode decomposition of numerical and experimental data,

P. J. Schmid, “Dynamic mode decomposition of numerical and experimental data,” Journal of Fluid Mechanics 656, 5– 28 (2010)

2010
[26]

Spectral properties of dynamical systems, model reduction and decompositions,

I. Mezić, “Spectral properties of dynamical systems, model reduction and decompositions,” Nonlinear Dynamics 41, 309– 325 (2005)

2005
[27]

Discovering governing equations from data by sparse identification of nonlinear dynamical systems,

S. L. Brunton, J. L. Proctor, and J. N. Kutz, “Discovering governing equations from data by sparse identification of nonlinear dynamical systems,” Proceedings of the National Academy of Sciences 113, 3932–3937 (2016)

2016
[28]

Data-driven discovery of coordinates and governing equations,

K. Champion, B. Lusch, J. N. Kutz, and S. L. Brunton, “Data-driven discovery of coordinates and governing equations,” Proceedings of the National Academy of Sciences 116, 22445–22451 (2019)

2019
[29]

S. L. Brunton and J. N. Kutz, Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control, Cambridge University Press, Cambridge (2019)

2019
[30]

Data -driven discovery of reduced plasma physics models from fully kinetic simulations,

E. P. Alves and F. Fiuza, “Data -driven discovery of reduced plasma physics models from fully kinetic simulations,” Physical Review Research 4, 033192 (2022). [37] F. Faraji, M. Reza, A. Knoll, and J. N. Kutz, “Dynamic mode decomposition for data -driven analysis and reduced-order modelling of E × B plasmas: I. Extraction of spatiotemporally coherent patt...

2022
[31]

Dynamic mode decomposition for data -driven analysis and reduced-order modelling of E × B plasmas: II. Dynamics forecasting,

F. Faraji, M. Reza, A. Knoll, and J. N. Kutz, “Dynamic mode decomposition for data -driven analysis and reduced-order modelling of E × B plasmas: II. Dynamics forecasting,” Journal of Physics D: Applied Physics 57, 065202 (2024)

2024
[32]

Turbulence model reduction by deep learning,

R.A. Heinonen and P. H. Diamond, “Turbulence model reduction by deep learning,” Physical Review E, 101(6), 061201 (2020)

2020
[33]

Compressed sensing,

D. L. Donoho, “Compressed sensing,” IEEE Transactions on Information Theory 52, 1289–1306 (2006)

2006
[34]

Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information,

E. J. Candès, J. Romberg, and T. Tao, “Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information,” IEEE Transactions on Information Theory 52, 489–509 (2006)

2006
[35]

An introduction to compressive sampling,

E. J. Candès and M. B. Wakin, “An introduction to compressive sampling,” IEEE Signal Processing Magazine 25, 21–30 (2008)

2008
[36]

Evensen, Data Assimilation: The Ensemble Kalman Filter, 2nd ed., Springer, Berlin (2009)

G. Evensen, Data Assimilation: The Ensemble Kalman Filter, 2nd ed., Springer, Berlin (2009)

2009
[37]

C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning, MIT Press, Cambridge, MA (2006)

2006
[38]

Karhunen –Loève procedure for gappy data,

R. Everson and L. Sirovich, “Karhunen –Loève procedure for gappy data,” Journal of the Optical Society of America A 12, 1657–1664 (1995)

1995
[39]

Sparse sensor placement optimization for classification,

B. W. Brunton, S. L. Brunton, J. L. Proctor, and J. N. Kutz, “Sparse sensor placement optimization for classification,” SIAM Journal on Applied Mathematics 76, 2099–2122 (2016)

2099
[40]

Data -driven sparse sensor placement for reconstruction,

K. Manohar, B. W. Brunton, J. N. Kutz, and S. L. Brunton, “Data -driven sparse sensor placement for reconstruction,” IEEE Control Systems Magazine 38, 63–86 (2018)

2018
[41]

The challenge of machine learning in space weather: Nowcasting and forecasting,

E. Camporeale, “The challenge of machine learning in space weather: Nowcasting and forecasting,” Space Weather 17, 1166–1207 (2019)

2019
[42]

Solar wind prediction using deep learning,

V. Upendran, A. Cheung, R. Hanasoge, and I. R. Manchester, “Solar wind prediction using deep learning,” Space Weather 18, e2020SW002478 (2020)

2020
[43]

Machine-learning research in the Space Weather journal: Prospects, scope, and limitations,

N. Lugaz, H. Liu, M. Hapgood, S. Morley , “Machine-learning research in the Space Weather journal: Prospects, scope, and limitations,” Space Weather 19, e2021SW002862 (2021). 19

2021
[44]

Sensing with shallow recurrent decoder networks,

J. P. Williams, O. Zahn, and J. N. Kutz, “Sensing with shallow recurrent decoder networks,” Proceedings of the Royal Society A 480, 20240054 (2024)

2024
[45]

Data -driven inference of high-dimensional spatiotemporal state of plasma systems,

M. Reza, F. Faraji, and J. N. Kutz, “Data -driven inference of high-dimensional spatiotemporal state of plasma systems,” Journal of Applied Physics 136, 183301 (2024)

2024
[46]

Shallow recurrent decoder for reduced order modeling of E × B plasma dynamics,

F. Faraji, M. Reza, and J. N. Kutz, “Shallow recurrent decoder for reduced order modeling of E × B plasma dynamics,” Machine Learning: Science and Technology 6, 025024 (2025)

2025
[47]

Wang–Sheeley–Arge (WSA)–Enlil Solar Wind Prediction,

Space Weather Prediction Center (SWPC), “Wang–Sheeley–Arge (WSA)–Enlil Solar Wind Prediction,” NOAA National Centers for Environmental Information, doi:10.7289/V5445JGH

work page doi:10.7289/v5445jgh
[48]

A randomized algorithm for a tensor -based generalization of the singular value decomposition,

P. Drineas and M. W. Mahoney, “A randomized algorithm for a tensor -based generalization of the singular value decomposition,” Linear Algebra Appl. 420 553–71 (2007)

2007

[1] [1]

The solar wind as a turbulence laboratory,

R. Bruno and V. Carbone, “The solar wind as a turbulence laboratory,” Living Reviews in Solar Physics 10, 2 (2013)

2013

[2] [2]

The multi-scale nature of the solar wind,

D. Verscharen, K. G. Klein, and B. A. Maruca, “The multi-scale nature of the solar wind,” Living Reviews in Solar Physics 16, 5 (2019)

2019

[3] [3]

Solar wind turbulence and the role of ion instabilities,

O. Alexandrova, C. H. K. Chen, L. Sorriso -Valvo, T. S. Horbury, and S. D. Bale, “Solar wind turbulence and the role of ion instabilities,” Space Science Reviews 178, 101–139 (2013)

2013

[4] [4]

Kinetic physics of the solar corona and solar wind,

E. Marsch, “Kinetic physics of the solar corona and solar wind,” Living Reviews in Solar Physics 3, 1 (2006)

2006

[5] [5]

The spectrum of turbulence,

G. I. Taylor, “The spectrum of turbulence,” Proceedings of the Royal Society of London. Series A, Mathematical and Physical Sciences 164, 476–490 (1938)

1938

[6] [6]

Validity of the Taylor hypothesis for linear kinetic waves in the weakly collisional solar wind,

G. G. Howes, K. G. Klein, and J. M. TenBarge, “Validity of the Taylor hypothesis for linear kinetic waves in the weakly collisional solar wind,” The Astrophysical Journal 789, 106 (2014)

2014

[7] [7]

The violation of the Taylor hypothesis in measurements of solar wind turbulence,

K. G. Klein, G. G. Howes, and J. M. TenBarge, “The violation of the Taylor hypothesis in measurements of solar wind turbulence,” The Astrophysical Journal Letters 790, L20 (2014). [8] A. R. Macneil, M. J. Owens, A. J. Finley, and S. P. Matt, “A statistical evaluation of ballistic backmapping for the slow solar wind: The interplay of solar wind acceleratio...

2014

[8] [8]

Interplanetary coronal mass ejections observed in the heliosphere: 1. Review of theory,

T. A. Howard and S. J. Tappin, “Interplanetary coronal mass ejections observed in the heliosphere: 1. Review of theory,” Space Science Reviews 147, 31–54 (2009)

2009

[9] [9]

Accuracy and limitations of fitting and stereoscopic methods to determine the direction of coronal mass ejections from heliospheric imagers observations,

N. Lugaz, “Accuracy and limitations of fitting and stereoscopic methods to determine the direction of coronal mass ejections from heliospheric imagers observations,” Solar Physics 267, 411–429 (2010)

2010

[10] [10]

The application of heliospheric imaging to space weather operations: Lessons learned from published studies,

R. A. Harrison, J. A. Davies, D. A. Biesecker, and M. Gibbs, “The application of heliospheric imaging to space weather operations: Lessons learned from published studies,” Space Weather 15, 985–1003 (2017)

2017

[11] [11]

Improvement in the prediction of solar wind conditions using near -real time solar magnetic field updates,

C. N. Arge and V. J. Pizzo, “Improvement in the prediction of solar wind conditions using near -real time solar magnetic field updates,” Journal of Geophysical Research: Space Physics 105, 10465–10479 (2000)

2000

[12] [12]

Improved method for specifying solar wind speed near the Sun,

C. N. Arge, D. Odstrčil, V. J. Pizzo, and L. R. Mayer, “Improved method for specifying solar wind speed near the Sun,” AIP Conference Proceedings 679, 190–193 (2003)

2003

[13] [13]

Modeling 3-D solar wind structure,

D. Odstrčil, “Modeling 3-D solar wind structure,” Advances in Space Research 32, 497–506 (2003)

2003

[14] [14]

Three-dimensional propagation of coronal mass ejections in a structured solar wind flow: 1. CME launched within the streamer belt,

D. Odstrčil and V. J. Pizzo, “Three-dimensional propagation of coronal mass ejections in a structured solar wind flow: 1. CME launched within the streamer belt,” Journal of Geophysical Research: Space Physics 104, 483–492 (1999). [18] A. M. Wold, M. L. Mays, A. Taktakishvili, L. K. Jian, D. Odstrčil, and P. MacNeice, “Verification of real -time WSA– ENLIL...

1999

[15] [15]

Global MHD modeling of the solar corona and inner heliosphere for the Whole Heliosphere Interval,

P. Riley, R. Lionello, J. A. Linker, Z. Mikić, J. G. Luhmann, and J. Wijaya, “Global MHD modeling of the solar corona and inner heliosphere for the Whole Heliosphere Interval,” Solar Physics 274, 361–377 (2011)

2011

[16] [16]

Magnetohydrodynamic simulation of interplanetary propagation of multiple coronal mass ejections with internal magnetic flux rope,

D. Shiota and R. Kataoka, “Magnetohydrodynamic simulation of interplanetary propagation of multiple coronal mass ejections with internal magnetic flux rope,” Space Weather 14, 56–75 (2016). [21] G. Tóth, I. V. Sokolov, T. I. Gombosi, D. R. Chesney, C. R. Clauer, D. L. De Zeeuw, et al., “Space Weather Modeling Framework: A new tool for the space science co...

2016

[17] [17]

A solution -adaptive upwind scheme for ideal magnetohydrodynamics,

K. G. Powell, P. L. Roe, T. J. Linde, T. I. Gombosi, and D. L. De Zeeuw, “A solution -adaptive upwind scheme for ideal magnetohydrodynamics,” Journal of Computational Physics 154, 284–309 (1999). 18

1999

[18] [18]

Adaptive numerical algorithms in space weather modeling,

G. Tóth, B. van der Holst, I. V. Sokolov, D. L. De Zeeuw, T. I. Gombosi, F. Fang, et al., “Adaptive numerical algorithms in space weather modeling,” Journal of Computational Physics 231, 870–903 (2012)

2012

[19] [19]

What sustained multi-disciplinary research can achieve: The Space Weather Modeling Framework,

T. I. Gombosi, Y. Chen, A. Glocer, Z. Huang, X. Jia, M. W. Liemohn, et al., “What sustained multi-disciplinary research can achieve: The Space Weather Modeling Framework,” Journal of Space Weather and Space Climate 11, 42 (2021)

2021

[20] [20]

Adapting ensemble-calibration techniques to probabilistic solar-wind forecasting,

N. O. Edward -Inatimi, M. J. Owens, L. A. Barnard, H. Turner, M. Marsh, S. Gonzi, M. Lang, and P. Riley, “Adapting ensemble-calibration techniques to probabilistic solar-wind forecasting,” Space Weather 22, e2024SW004164 (2024)

2024

[21] [21]

Vlasov methods in space physics and astrophysics,

M. Palmroth, U. Ganse, Y. Pfau -Kempf, M. Battarbee, L. Turc, T. Brito, et al., “Vlasov methods in space physics and astrophysics,” Living Reviews in Computational Astrophysics 4, 1 (2018). [27] L. K. Jian, P. J. MacNeice, A. Taktakishvili, D. Odstrčil, B. Jackson, H.-S. Yu, P. Riley, I. V. Sokolov, and R. M. Evans, “Validation for solar wind prediction a...

2018

[22] [22]

Assessing the quality of models of the ambient solar wind,

P. MacNeice, L. K. Jian, S. K. Antiochos, C. N. Arge, C. D. Bussy-Virat, M. L. DeRosa, et al., “Assessing the quality of models of the ambient solar wind,” Space Weather 16, 1644–1667 (2018)

2018

[23] [23]

Unifying the validation of ambient solar wind models,

M. A. Reiss, K. Muglach, R. Mullinix, M. M. Kuznetsova, C. Wiegand, M. Temmer, et al., “Unifying the validation of ambient solar wind models,” Advances in Space Research 72, 5275–5286 (2023)

2023

[24] [24]

Machine learning applications to computational plasma physics and reduced -order plasma modeling: A perspective,

F. Faraji and M. Reza, “Machine learning applications to computational plasma physics and reduced -order plasma modeling: A perspective,” Journal of Physics D: Applied Physics 58, 102002 (2025)

2025

[25] [25]

Dynamic mode decomposition of numerical and experimental data,

P. J. Schmid, “Dynamic mode decomposition of numerical and experimental data,” Journal of Fluid Mechanics 656, 5– 28 (2010)

2010

[26] [26]

Spectral properties of dynamical systems, model reduction and decompositions,

I. Mezić, “Spectral properties of dynamical systems, model reduction and decompositions,” Nonlinear Dynamics 41, 309– 325 (2005)

2005

[27] [27]

Discovering governing equations from data by sparse identification of nonlinear dynamical systems,

S. L. Brunton, J. L. Proctor, and J. N. Kutz, “Discovering governing equations from data by sparse identification of nonlinear dynamical systems,” Proceedings of the National Academy of Sciences 113, 3932–3937 (2016)

2016

[28] [28]

Data-driven discovery of coordinates and governing equations,

K. Champion, B. Lusch, J. N. Kutz, and S. L. Brunton, “Data-driven discovery of coordinates and governing equations,” Proceedings of the National Academy of Sciences 116, 22445–22451 (2019)

2019

[29] [29]

S. L. Brunton and J. N. Kutz, Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control, Cambridge University Press, Cambridge (2019)

2019

[30] [30]

Data -driven discovery of reduced plasma physics models from fully kinetic simulations,

E. P. Alves and F. Fiuza, “Data -driven discovery of reduced plasma physics models from fully kinetic simulations,” Physical Review Research 4, 033192 (2022). [37] F. Faraji, M. Reza, A. Knoll, and J. N. Kutz, “Dynamic mode decomposition for data -driven analysis and reduced-order modelling of E × B plasmas: I. Extraction of spatiotemporally coherent patt...

2022

[31] [31]

Dynamic mode decomposition for data -driven analysis and reduced-order modelling of E × B plasmas: II. Dynamics forecasting,

F. Faraji, M. Reza, A. Knoll, and J. N. Kutz, “Dynamic mode decomposition for data -driven analysis and reduced-order modelling of E × B plasmas: II. Dynamics forecasting,” Journal of Physics D: Applied Physics 57, 065202 (2024)

2024

[32] [32]

Turbulence model reduction by deep learning,

R.A. Heinonen and P. H. Diamond, “Turbulence model reduction by deep learning,” Physical Review E, 101(6), 061201 (2020)

2020

[33] [33]

Compressed sensing,

D. L. Donoho, “Compressed sensing,” IEEE Transactions on Information Theory 52, 1289–1306 (2006)

2006

[34] [34]

Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information,

E. J. Candès, J. Romberg, and T. Tao, “Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information,” IEEE Transactions on Information Theory 52, 489–509 (2006)

2006

[35] [35]

An introduction to compressive sampling,

E. J. Candès and M. B. Wakin, “An introduction to compressive sampling,” IEEE Signal Processing Magazine 25, 21–30 (2008)

2008

[36] [36]

Evensen, Data Assimilation: The Ensemble Kalman Filter, 2nd ed., Springer, Berlin (2009)

G. Evensen, Data Assimilation: The Ensemble Kalman Filter, 2nd ed., Springer, Berlin (2009)

2009

[37] [37]

C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning, MIT Press, Cambridge, MA (2006)

2006

[38] [38]

Karhunen –Loève procedure for gappy data,

R. Everson and L. Sirovich, “Karhunen –Loève procedure for gappy data,” Journal of the Optical Society of America A 12, 1657–1664 (1995)

1995

[39] [39]

Sparse sensor placement optimization for classification,

B. W. Brunton, S. L. Brunton, J. L. Proctor, and J. N. Kutz, “Sparse sensor placement optimization for classification,” SIAM Journal on Applied Mathematics 76, 2099–2122 (2016)

2099

[40] [40]

Data -driven sparse sensor placement for reconstruction,

K. Manohar, B. W. Brunton, J. N. Kutz, and S. L. Brunton, “Data -driven sparse sensor placement for reconstruction,” IEEE Control Systems Magazine 38, 63–86 (2018)

2018

[41] [41]

The challenge of machine learning in space weather: Nowcasting and forecasting,

E. Camporeale, “The challenge of machine learning in space weather: Nowcasting and forecasting,” Space Weather 17, 1166–1207 (2019)

2019

[42] [42]

Solar wind prediction using deep learning,

V. Upendran, A. Cheung, R. Hanasoge, and I. R. Manchester, “Solar wind prediction using deep learning,” Space Weather 18, e2020SW002478 (2020)

2020

[43] [43]

Machine-learning research in the Space Weather journal: Prospects, scope, and limitations,

N. Lugaz, H. Liu, M. Hapgood, S. Morley , “Machine-learning research in the Space Weather journal: Prospects, scope, and limitations,” Space Weather 19, e2021SW002862 (2021). 19

2021

[44] [44]

Sensing with shallow recurrent decoder networks,

J. P. Williams, O. Zahn, and J. N. Kutz, “Sensing with shallow recurrent decoder networks,” Proceedings of the Royal Society A 480, 20240054 (2024)

2024

[45] [45]

Data -driven inference of high-dimensional spatiotemporal state of plasma systems,

M. Reza, F. Faraji, and J. N. Kutz, “Data -driven inference of high-dimensional spatiotemporal state of plasma systems,” Journal of Applied Physics 136, 183301 (2024)

2024

[46] [46]

Shallow recurrent decoder for reduced order modeling of E × B plasma dynamics,

F. Faraji, M. Reza, and J. N. Kutz, “Shallow recurrent decoder for reduced order modeling of E × B plasma dynamics,” Machine Learning: Science and Technology 6, 025024 (2025)

2025

[47] [47]

Wang–Sheeley–Arge (WSA)–Enlil Solar Wind Prediction,

Space Weather Prediction Center (SWPC), “Wang–Sheeley–Arge (WSA)–Enlil Solar Wind Prediction,” NOAA National Centers for Environmental Information, doi:10.7289/V5445JGH

work page doi:10.7289/v5445jgh

[48] [48]

A randomized algorithm for a tensor -based generalization of the singular value decomposition,

P. Drineas and M. W. Mahoney, “A randomized algorithm for a tensor -based generalization of the singular value decomposition,” Linear Algebra Appl. 420 553–71 (2007)

2007