arXiv subjects

Xiangning Chu

Publications and source records attributed to Xiangning Chu.

11 recordsLinked to original sources

arXiv2026

Electron Temperature Gradients Regulate the Duration of Two-Stage Plasmasphere Refilling

After geomagnetic storms erode the plasmasphere, cold ionospheric plasma flows along magnetic field lines to refill the depleted flux tubes. Previous studies have suggested that refilling undergoes two stages characterized by their distinct refilling rates; however, not all observations or models exhibit this feature, and a recent analysis indicates that only a subset of refilling events display two clear stages. In this study, we show that the magnitude of the field-aligned electron temperature gradient and initial/boundary temperature regulate the durations of both the early and late stages. Performing multivariate regressions from the results of simulating early and late-time refilling demonstrated that the length of each stage uniquely depends on the temperature gradient and initial/boundary temperature. These results suggest that variations in the temperature profile may explain why some refilling events appear single-staged in observations.

physics.space-ph↗

arXiv2026

CLARE: Classification-based Regression for Electron Temperature Prediction

Electron temperature (Te) is an important parameter governing space weather in the upper atmosphere, but has historically been underexplored in the space weather machine learning literature. We present CLARE, a machine learning model for predicting electron temperature in the Earth's plasmasphere trained on AKEBONO (EXOS-D) satellite measurements as well as solar and geomagnetic indices. CLARE uses a classification-based regression architecture that transforms the continuous Te output space into 150 discrete classification intervals. Training the model on a classification task improves prediction accuracy by 6.46% relative compared to a traditional regression model while also outputting uncertainty estimation information on its predictions. On a held out test set from the AKEBONO data, the model's Te predictions achieve 69.67% accuracy within 10% of the ground truth and 46.17% on a known geomagnetic storm period from January 30th to February 7th, 1991. We show that machine learning can be used to produce high-accuracy Te models on publicly available data.

physics.space-ph↗

arXiv2025

Automatic Identification of Magnetospheric Regions using Supervised Machine Learning Models

We present an automated approach for identifying magnetospheric regions using supervised machine learning techniques applied to Magnetospheric MultiScale mission data. Our method utilizes ion energy spectra, total magnetic field, total ion temperature, ion velocity component, ion density and spacecraft position data to classify five distinct plasma environments: solar wind, magnetosheath, inner magnetosphere, plasma sheet, and lobe regions. The approach combines a convolutional neural network (CNN) for analyzing ion energy spectrogram data with a Random Forest classifier for scalar plasma parameters. The CNN method employs 2D convolution to identify spatial and temporal patterns in the ion energy spectrogram treated as image-like data, while the Random Forest model processes averaged magnetic field, temperature, velocity, density and position parameters. Our hybrid model achieves 99% accuracy on test dataset with an F1 score of 0.99, providing reliable automated region identification at 3-minute temporal resolution. This lightweight approach requires minimal manual data labeling and can be readily applied to other magnetospheric missions with similar data products.

physics.space-ph↗

arXiv2024

A Global Analysis of Pre-Earthquake Ionospheric Anomalies

Local ionospheric density anomalies have been reported in the days prior to major earthquakes. This global study statistically investigates whether consistent ionospheric anomalies occur in the 24 hours prior to earthquakes across different regions, magnitudes, temporal and spatial scales. We match earthquake data to Total Electron Content (TEC) data from 2000-2020 at a higher resolution and cadence than previous assessed. Globally, no significant, consistent anomaly is found. Regionally, statistically significant ionospheric anomalies arise in the 12 hours prior to earthquakes with $p \leq 0.01$ following Wilcoxon tests. For the Japanese region we find a median negative ionospheric anomaly of around 0.5 TECU between 3 and 8 hours before earthquakes. For the South American region, the median TEC is enhanced by up to ~ 2 TECU, between 7 and 10 hours before an event. We show that the results are robust to different definitions of the ''local'' region and earthquake magnitude. This demonstrates the promise of monitoring the ionosphere as part of a multimodal earthquake forecasting system.

physics.geo-ph↗

arXiv2023

Machine Learning Interpretability of Outer Radiation Belt Enhancement \& Depletion Events

We investigate the response of outer radiation belt electron fluxes to different solar wind and geomagnetic indices using an interpretable machine learning method. We reconstruct the electron flux variation during 19 enhancement and 7 depletion events and demonstrate a feature attribution analysis on the superposed epoch results for the first time. We find that the intensity and duration of the substorm sequence following an initial dropout determine the overall enhancement or depletion of electron fluxes, while the solar wind pressure drives the initial dropout in both types of events. Further statistical results from a dataset with 71 events confirm this and show a significant correlation between the resulting flux levels and the average AL index, indicating that the observed "depletion" event can be more accurately described as a "non-enhancement" event. Our novel SHAP-Enhanced Superposed Epoch Analysis (SHESEA) method can be used as an insight discovery tool in various physical systems.

physics.space-ph↗

arXiv2023

Opening the Black Box of the Radiation Belt Machine Learning Model

Many Machine Learning (ML) systems, especially neural networks, are fundamentally regarded as black boxes since it is difficult to grasp how they function once they have been trained. Here, we tackle the issue of the interpretability of a high-accuracy ML model created to model the flux of Earth's radiation belt electrons. The Outer RadIation belt Electron Neural net model (ORIENT) uses only solar wind conditions and geomagnetic indices as input. Using the Deep SHAPley additive explanations (DeepSHAP) method, we show that the `black box' ORIENT model can be successfully explained. Two significant electron flux enhancement events observed by Van Allen Probes during the storm interval of 17 to 18 March 2013 and non storm interval of 19 to 20 September 2013 are investigated using the DeepSHAP method. The results show that the feature importances calculated from the purely data driven ORIENT model identify physically meaningful behavior consistent with current physical understanding.

physics.space-ph↗

arXiv2022

Modeling the dynamic variability of sub-relativistic outer radiation belt electron fluxes using machine learning

We present a set of neural network models that reproduce the dynamics of electron fluxes in the range of 50 keV $\sim$ 1 MeV in the outer radiation belt. The Outer Radiation belt Electron Neural net model for Medium energy electrons(ORIENT-M) uses only solar wind conditions and geomagnetic indices as input. The models are trained on electron flux data from the Magnetic Electron Ion Spectrometer (MagEIS) instrument onboard Van Allen Probes, and they can reproduce the dynamic variations of electron fluxes in different energy channels. The model results show high coefficient of determination $R^2 \sim $ 0.78-0.92 on the test dataset, an out-of-sample 30-day period from February 25 to March 25 in 2017, when a geomagnetic storm took place, as well as an out-of-sample one year period after March 2018. In addition, the models are able to capture electron dynamics such as intensifications, decays, dropouts, and the Magnetic Local Time (MLT) dependence of the lower energy ($\sim <$ 100 keV )electron fluxes during storms. The models have reliable prediction capability and can be used for a wide range of space weather applications. The general framework of building our model is not limited to radiation belt fluxes and could be used to build machine learning models for a variety of other plasma parameters in the Earth's magnetosphere.

physics.space-ph↗

arXiv2021

Relativistic electron flux model in the outer radiation belt using a neural network approach

We present a machine-learning-based model of relativistic electron fluxes >1.8 MeV using a neural network approach in the Earth's outer radiation belt. The Outer RadIation belt Electron Neural net model for Relativistic electrons (ORIENT-R) uses only solar wind conditions and geomagnetic indices as input. For the first time, we show that the state of the outer radiation belt can be determined using only solar wind conditions and geomagnetic indices, without any initial and boundary conditions. The most important features for determining outer radiation belt dynamics are found to be AL, solar wind flow speed and density, and SYM-H indices. ORIENT-R reproduces out-of-sample relativistic electron fluxes with a correlation coefficient of 0.95 and an uncertainty factor of ~2. ORIENT-R reproduces radiation belt dynamics during an out-of-sample geomagnetic storm with good agreement to the observations. In addition, ORIENT-R was run for a completely out-of-sample period between March 2018 and October 2019 when the AL index ended and was replaced with the predicted AL index (lasp.colorado.edu/~lix). It reproduces electron fluxes with a correlation coefficient of 0.92 and an out-of-sample uncertainty factor of ~3. Furthermore, ORIENT-R captured the trend in the electron fluxes from low-earth-orbit (LEO) SAMPEX, which is a completely out-of-sample dataset both temporally and spatially. In sum, the ORIENT-R model can reproduce transport, acceleration, decay, and dropouts of the outer radiation belt anywhere from short timescales (i.e., geomagnetic storms) and very long timescales (i.e., solar cycle) variations.

physics.space-ph↗

arXiv2020

The Temperature Anisotropy and Helium Abundance Features of Alfv\'enic Slow Solar Wind Observed by Parker Solar Probe, Helios, and Wind Missions

Slow solar wind is typically characterized as having low Alfv\'enicity, but the occasional occurrence of highly Alfv\'enic slow solar wind (HASSW) raises questions about its source regions and evolution. In this work, we conduct a statistical analysis of temperature anisotropy and helium abundance in HASSW using data from PSP within 0.25 AU, Helios between 0.3 AU and 1 AU, and Wind near 1 AU. Our findings reveal that HASSW is prevalent close to the Sun, with PSP observations displaying a distinct ``U-shaped" Alfv\'enicity distribution with respect to increasing solar wind speed, unlike the monotonic increase trend seen in Helios and Wind data. This highlights a previously unreported population of unusually low speed HASSW, which is found in both sub-Alfv\'enic and super-Alfv\'enic regimes. The observed decreasing overlap in temperature anisotropy between HASSW and fast solar wind (FSW) with increasing heliocentric distance suggests different underlying heating processes. Additionally, HASSW exhibits two distinct helium abundance populations, particularly evident in PSP data, with generally higher helium abundance compared to less Alfv\'enic slow solar wind. Moreover, the decreasing overlap in temperature anisotropy versus helium abundance distributions between HASSW and FSW with decreasing radial distance implies that not all HASSW originates from the same source region as FSW.

physics.space-ph↗

arXiv2019

Identifying the magnetospheric driver of STEVE

For the first time, we identify the magnetospheric driver of STEVE, east-west aligned narrow emissions in the subauroral region. In the ionosphere, STEVE is associated with subauroral ion drift (SAID) features of high electron temperature peak, density gradient, and strong westward ion flow. In this study, we present STEVE's magnetospheric driver region at a sharp plasmapause containing: strong tailward quasi-static electric field, kinetic Alfven waves, parallel electron acceleration, perpendicular ion drift. The observed continuous emissions of STEVE are possibly caused by ionospheric electron heating due to heat conduction and/or auroral acceleration process powered by Alfven waves, both driven by the observed equatorial magnetospheric processes. The observed green emissions are likely optical manifestations of electron precipitations associated with wave structures traveling along the plasmapause. The observed SAR arc at lower latitudes likely corresponds to the formation of low-energy plasma inside the plasmapause by Coulomb collisions between ring current ions and plasmaspheric plasma.

physics.space-ph↗

arXiv2018

On the generation of probabilistic forecasts from deterministic models

Most of the methods that produce space weather forecasts are based on deterministic models. In order to generate a probabilistic forecast, a model needs to be run several times sampling the input parameter space, in order to generate an ensemble from which the distribution of outputs can be inferred. However, ensemble simulations are costly and often preclude the possibility of real-time forecasting. We introduce a simple and robust method to generate uncertainties from deterministic models, that does not require ensemble simulations. The method is based on the simple consideration that a probabilistic forecast needs to be both accurate and well-calibrated (reliable). We argue that these two requirements are equally important, and we introduce the Accuracy-Reliability cost function that quantitatively measures the trade-off between accuracy and reliability. We then define the optimal uncertainties as the standard deviation of the Gaussian distribution that minimizes the cost function. We demonstrate that this simple strategy, implemented here by means of a regularized deep neural network, produces accurate and well-calibrated forecasts, showing examples both on synthetic and real-world space weather data.

physics.space-ph↗