首页|Recent Research from University of California Los Angeles (UCLA) Highlight Findings in Machine Learning (Machine Learning Interpretability of Outer Radiation Belt Enhancement and Depletion Events)
Recent Research from University of California Los Angeles (UCLA) Highlight Findings in Machine Learning (Machine Learning Interpretability of Outer Radiation Belt Enhancement and Depletion Events)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Amer Geophysical Union
Data detailed on Machine Learning have been presented. According to news reporting out of Los Angeles, California, by NewsRx editors, research stated, “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 the feature attribution analysis called SHAP (SHapley Additive exPlanations) on the superposed epoch results for the first time.” Financial supporters for this research include National Aeronautics & Space Administration (NASA), NASA CCMC, University of Colorado Boulder under NASA, Defense Advanced Research Projects Agency under Department of the Interior award. Our news journalists obtained a quote from the research from the University of California Los Angeles (UCLA), “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 data set 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 offer insight in various physical systems. This study examines the responses of relativistic electrons in Earth’s radiation belt to various solar wind and geomagnetic disturbances, identifying key influencing factors. We first adopt an explainable machine learning method to understand the importance of different features during 19 enhancement and 7 depletion events. Our results directly reveal that an increase in solar wind dynamic pressure contributes to a sudden decrease in electron fluxes. Additionally, we find that the strength and duration of subsequent substorms determine whether the electron flux increases or decreases. Guided by the importance of these features as determined by our machine learning model, we carry out a statistical analysis, showing a significant correlation between the flux level and the average AL index. Our method offers advantages over traditional superposed epoch analysis since it directly shows the determining factors.”
Los AngelesCaliforniaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningUniversity of California Los Angeles (UCLA)
NETL
NSTL
Amer Geophysical Union
