Search Results

Search Constraints

Start Over
Filtering by: Creator Zou, Shasha Remove constraint Creator: Zou, Shasha Discipline Science Remove constraint Discipline: Science

Search Results

  • Data and Analysis for Global Probabilistic Geomagnetic Perturbation Forecasting Using the Data-Driven Model GeoDGP

    work
    Creator:
    Chen, Hongfan, Chen, Yang, Huang, Zhenguang, Zou, Shasha, Huan, Xun, and Toth, Gabor
    Description:
    Accurately predicting the horizontal component of the ground magnetic field perturbation (dBH), which can be used to calculate the Geomagnetically Induced Currents (GICs), is crucial for estimating the space weather impact of geomagnetic disturbances. In this work, we develop a new data-driven model GeoDGP using deep Gaussian process (DGP), which is a Bayesian non-parametric approach. The model provides global probabilistic forecasts of dBH at 1-minute time cadence and with arbitrary spatial resolutions. We evaluate the model comprehensively on a wide range of geomagnetic storms, including the 2024 Gannon extreme storm. The results show that GeoDGP significantly outperforms the state-of-the-art physics-based first-principles Space Weather Modeling Framework (SWMF) Michigan Geospace model and the data-driven DAGGER model.
    Keyword:
    Space Weather, Uncertainty Quantification, Machine Learning, and Bayesian Inference
    Citation to related publication:
    Chen, H., et al. (2024). GeoDGP: One-Hour Ahead Global Probabilistic Geomagnetic Perturbation Forecasting using Deep Gaussian Process.
    Discipline:
    Science and Engineering

  • VISTA TEC Database (ver 2.0)

    work
    Creator:
    Sun, Hu, Ren, Jiaen, Chen, Yang, Zou, Shasha, Chang, Yurui, Wang, Zihan, and Coster, Anthea
    Description:
    Our research focuses on providing a fully-imputed map of the worldwide total electron content with high resolution and spatial-temporal smoothness. We fill in the missing values of the original Madrigal TEC maps via estimating the latent feature of each latitude and local time along the 2-D grid and give initial guess of the missing regions based on pre-computed spherical harmonics map. The resulting TEC map has high imputation accuracy and the ease of reproducing. All data are in HDF5 format and are easy to read using the h5py package in Python. The TEC map is grouped in folders based on years and each file contains a single-day data of 5-min cadence. Each individual TEC map is of size 181*361. and WARNING: 2023-12-01 the data file for 2019-Jan-03 has badly fitted values. Please avoid using it. All other days' files are ready to use.
    Keyword:
    Total Electron Content, Matrix Completion, VISTA, Spherical Harmonics, and Spatial-Temporal Smoothing
    Citation to related publication:
    Sun, H., Hua, Z., Ren, J., Zou, S., Sun, Y., & Chen, Y. (2022). Matrix completion methods for the total electron content video reconstruction. The Annals of Applied Statistics, 16(3), 1333-1358., Sun, H., Chen, Y., Zou, S., Ren, J., Chang, Y., Wang, Z., & Coster, A. (2023). Complete Global Total Electron Content Map Dataset based on a Video Imputation Algorithm VISTA. Scientific Data, in press., and Zou, S., Ren, J., Wang, Z., Sun, H., & Chen, Y. (2021). Impact of storm-enhanced density (SED) on ion upflow fluxes during geomagnetic storm. Frontiers in Astronomy and Space Sciences, 8, 746429.
    Discipline:
    Science and Engineering

  • VISTA TEC database

    work
    Creator:
    Sun, Hu, Ren, Jiaen, Chen, Yang, and Zou, Shasha
    Description:
    Our research focuses on providing a fully-imputed map of the worldwide total electron content with high resolution and spatial-temporal smoothness. We fill in the missing values of the original Madrigal TEC maps via estimating the latent feature of each latitude and local time along the 2-D grid and give initial guess of the missing regions based on pre-computed spherical harmonics map. The resulting TEC map has high imputation accuracy and the ease of reproducing. and All data are in HDF5 format and are easy to read using the h5py package in Python. The TEC map is grouped in folders based on years and each file contains a single-day data of 5-min cadence. Each individual TEC map is of size 181*361.
    Keyword:
    Total Electron Content, Matrix Completion, VISTA, Spherical Harmonics, and Spatial-Temporal Smoothing
    Citation to related publication:
    Sun, H., Hua, Z., Ren, J., Zou, S., Sun, Y., & Chen, Y. (2020). Matrix Completion Methods for the Total Electron Content Video Reconstruction. arXiv preprint arXiv:2012.01618. and Zou, S., Ren, J., Wang, Z., Sun, H., & Chen, Y. (2021). Impact of Storm-Enhanced Density (SED) on Ion Upflow Fluxes During Geomagnetic Storm. Frontiers in Astronomy and Space Sciences, 162.
    Discipline:
    Science

  • Results for "New Findings from Explainable SYM-H Forecasting using Gradient Boosting Machines"

    work
    Creator:
    Iong, Daniel, Chen, Yang, Toth, Gabor, Zou, Shasha, Pulkkinen, Tuija I., Ren, Jiaen, Camporeale, Enrico, and Gombosi, Tamas I. I.
    Description:
    In this work, we trained gradient boosted trees using XGBoost to predict the SYM-H forecasting using different combinations of solar wind and interplanetary magnetic field (IMF) parameters. Data are in csv and Python pickle formats.
    Keyword:
    SYM-H forecasting
    Citation to related publication:
    Iong, D., Y. Chen, G. Toth, S. Zou, T. I. Pulkkinen, J. Ren, E. Camporeale, and T. I. Gombosi, New Findings from Explainable SYM-H Forecasting using Gradient Boosting Machines, Space Weather,11, accepted, 2022.  https://doi.org/10.1002/essoar.10508063.3
    Discipline:
    Science