TY - JOUR

T1 - Reconstructing Magnetotail Reconnection Events Using Data Mining is Feasible and Repeatable

AU - Stephens, G. K.

AU - Weigel, R. S.

AU - Sitnov, M. I.

AU - Tsyganenko, N. A.

PY - 2026/2

Y1 - 2026/2

N2 - Recently, Stephens et al. (2023), https://doi.org/10.1029/2022ja031066 utilized a data mining (DM) algorithm, applied to 26 years of magnetospheric magnetometer observations coupled with a flexible formulation of the magnetospheric magnetic field, to reconstruct the global configuration of the magnetotail when the Magnetospheric MultiScale (MMS) mission observed tail reconnection in situ. Of the 26 DM‐reconstructed MMS reconnection events, 16 had a isocontour within Earth radii of the observed reconnection location. Another eight had a minimum region, identified using nT isocontours, within . This consistency suggests that the structure of tail reconnection is correlated with the substorm/storm state of the magnetosphere, as reflected by geomagnetic indices and solar wind conditions. We verify these results using new validation methods and by comparing in‐sample (including event data) to out‐of‐sample (excluding event data) reconstructions. We first benchmark the architecture of the reconstructed magnetic field using 100 randomly generated magnetic fields containing tail X‐ and O‐lines, resolving 77 of them with three false positives. Next, we quantify the consistency of the reconstructions in resolving the reconnection location using a skill score relative to random chance. 88% of the in‐sample and 75% of the out‐of‐sample scores are positive, confirming that the reconstructions resolve the location of tail reconnection better than random chance. Last, a bootstrapping analysis, which refits the model architecture to 100 random resamples of data, shows standard deviations in of nT, indicating that the DM approach is not overly sensitive to the particular sampling of magnetometer records. The Earth's magnetotail is a region on the nightside of Earth where the interaction between the Earth's intrinsic magnetic field and the solar wind stretches the field. Magnetic reconnection occurs within the electric current sheet at the center of the stretched magnetic field, leading to a reconfiguration of the magnetotail and the energization of charged particles. Tail reconnection is a crucial process in large‐scale space weather events, including geomagnetic storms and substorms. Knowing where and when tail reconnection occurs during these events is necessary to understand how they work. A spacecraft can observe tail reconnection when it flies through the region where it occurs, as the Magnetospheric MultiScale (MMS) mission has done, finding at least 26 tail reconnection events. The magnetic field configuration for these events was reconstructed using a data mining‐based algorithm that searches through decades of space magnetic field observations for data when the tail was in a comparable storm and substorm state. The identified data constrain a mathematical model representing the tail magnetic field. A previous study showed that the reconstructed magnetic field was generally consistent with the observed reconnection locations. This study further supports the prior one by using more advanced methods. The magnetic field architecture used in data mining reconstructions of tail reconnection events is capable of resolving most X‐ and O‐lines Both in‐sample and out‐of‐sample reconstructions possess skill in identifying the location of tail reconnection over random chance A bootstrapping analysis indicates that the reconstructions are not overly sensitive to the particular sample of magnetometer records

AB - Recently, Stephens et al. (2023), https://doi.org/10.1029/2022ja031066 utilized a data mining (DM) algorithm, applied to 26 years of magnetospheric magnetometer observations coupled with a flexible formulation of the magnetospheric magnetic field, to reconstruct the global configuration of the magnetotail when the Magnetospheric MultiScale (MMS) mission observed tail reconnection in situ. Of the 26 DM‐reconstructed MMS reconnection events, 16 had a isocontour within Earth radii of the observed reconnection location. Another eight had a minimum region, identified using nT isocontours, within . This consistency suggests that the structure of tail reconnection is correlated with the substorm/storm state of the magnetosphere, as reflected by geomagnetic indices and solar wind conditions. We verify these results using new validation methods and by comparing in‐sample (including event data) to out‐of‐sample (excluding event data) reconstructions. We first benchmark the architecture of the reconstructed magnetic field using 100 randomly generated magnetic fields containing tail X‐ and O‐lines, resolving 77 of them with three false positives. Next, we quantify the consistency of the reconstructions in resolving the reconnection location using a skill score relative to random chance. 88% of the in‐sample and 75% of the out‐of‐sample scores are positive, confirming that the reconstructions resolve the location of tail reconnection better than random chance. Last, a bootstrapping analysis, which refits the model architecture to 100 random resamples of data, shows standard deviations in of nT, indicating that the DM approach is not overly sensitive to the particular sampling of magnetometer records. The Earth's magnetotail is a region on the nightside of Earth where the interaction between the Earth's intrinsic magnetic field and the solar wind stretches the field. Magnetic reconnection occurs within the electric current sheet at the center of the stretched magnetic field, leading to a reconfiguration of the magnetotail and the energization of charged particles. Tail reconnection is a crucial process in large‐scale space weather events, including geomagnetic storms and substorms. Knowing where and when tail reconnection occurs during these events is necessary to understand how they work. A spacecraft can observe tail reconnection when it flies through the region where it occurs, as the Magnetospheric MultiScale (MMS) mission has done, finding at least 26 tail reconnection events. The magnetic field configuration for these events was reconstructed using a data mining‐based algorithm that searches through decades of space magnetic field observations for data when the tail was in a comparable storm and substorm state. The identified data constrain a mathematical model representing the tail magnetic field. A previous study showed that the reconstructed magnetic field was generally consistent with the observed reconnection locations. This study further supports the prior one by using more advanced methods. The magnetic field architecture used in data mining reconstructions of tail reconnection events is capable of resolving most X‐ and O‐lines Both in‐sample and out‐of‐sample reconstructions possess skill in identifying the location of tail reconnection over random chance A bootstrapping analysis indicates that the reconstructions are not overly sensitive to the particular sample of magnetometer records

KW - magnetosphere

KW - solar wind

KW - reconnection

KW - magnetic storms

KW - data mining

KW - machine learning

UR - https://www.mendeley.com/catalogue/f2e67977-3aa7-3b02-a0ca-437b25a4d2a7/

U2 - 10.1029/2025JH000965

DO - 10.1029/2025JH000965

M3 - Article

VL - 3

JO - Journal of Geophysical Research: Machine Learning and Computation

JF - Journal of Geophysical Research: Machine Learning and Computation

SN - 2993-5210

IS - 1

M1 - e2025JH000965

ER -