Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress)

  title={Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress)},
  author={Ryan Mcgranaghan and Jack L. Ziegler and T{\'e}o Bloch and Spencer Mark Hatch and Enrico Camporeale and Kristina A. Lynch and Mathew J. Owens and Jesper W. Gjerloev and Binzheng Zhang and Susan Skone},
  journal={Space Weather},
We advance the modeling capability of electron particle precipitation from the magnetosphere to the ionosphere through a new database and use of machine learning (ML) tools to gain utility from those data. We have compiled, curated, analyzed, and made available a new and more capable database of particle precipitation data that includes 51 satellite years of Defense Meteorological Satellite Program (DMSP) observations temporally aligned with solar wind and geomagnetic activity data. The new… 

Harnessing expressive capacity of Machine Learning modeling to represent complex coupling of Earth’s auroral space weather regimes

Multiple Deep Learning models are developed that improve prediction of the extreme events, historically obstinate to accurate specification and indicate that increased expressive capacity provided by ML innovation can address grand challenges in the science of space weather.

Towards an AI-based understanding of the solar wind: A critical data analysis of ACE data

This work contains guidelines and highlights issues in the ACE data that are likely to be found in other space weather datasets: missing values, inconsistency in distributions, hidden information in statistics, etc.

Testing the mirror symmetry of Birkeland and ionospheric currents with respect to magnetic latitude, dipole tilt angle, and IMF B y

It is often assumed that on average, polar ionospheric electrodynamics in the Northern and Southern Hemispheres are mirror symmetric or antisymmetric with respect to the interplanetary magnetic field

The evolution of heliophysics: Complexity, community, and open science

Responding to the grand challenges that confront the Earth and Space Sciences requires an embrace of methods from the field of complexity and systems science that can adapt our thinking and our

Application of Recurrent Neural Network to Modeling Earth's Global Electron Density

The total electron density is a fundamental quantity in the Earth's magnetosphere and plays an important role in a number of physical processes, but its dynamic global evolution is not fully

Auroral Drivers of Large dB∕dt During Geomagnetic Storms

Forecasting geomagnetically induced currents (GICs) remains a difficult challenge, and open questions hindering our understanding include when and where GICs become large and what magnetospheric and

Improving Electron Density Predictions in the Topside of the Ionosphere Using Machine Learning on In Situ Satellite Data

Modeling the Earth's ionosphere is a critical component of forecasting space weather, which in turn impacts radio wave propagation, navigation and communication. This research focuses on predicting

Machine Learning Methods Applied to the Global Modeling of Event-Driven Pitch Angle Diffusion Coefficients During High Speed Streams

A global mean event-driven model in which both the Kp-index and time kept as in an epoch analysis following the storm evolution is achieved, with a poor performance of any mean models compared with individual events, with mean diffusion coefficients computing the general trend at best, due to their large variability.

Assimilative Mapping of Auroral Electron Energy Flux Using SSUSI Lyman‐Birge‐Hopfield (LBH) Emissions

Far ultraviolet (FUV) imaging of the aurora from space provides great insight into the dynamic coupling of the atmosphere, ionosphere, and magnetosphere on global scales. To gain a quantitative

Transfer Learning Aurora Image Classification and Magnetic Disturbance Evaluation

An open source algorithm to apply Transfer learning to Aurora image classification and Magnetic disturbance Evaluation (TAME) and it is demonstrated that the classifier can be used as a filter to remove cloudy images from datasets and that the extracted features allow to predict magnetometer measurements.



A nearly universal solar wind-magnetosphere coupling function inferred from 10 magnetospheric state variables

[1] We investigated whether one or a few coupling functions can represent best the interaction between the solar wind and the magnetosphere over a wide variety of magnetospheric activity. Ten

Probability distributions of electron precipitation at high magnetic latitudes

[1] We have integrated more than 600 million energetic electron spectra measured by the Special Sensor for Precipitating Particles, version 4 (SSJ4) sensor on nine Defense Meteorological Satellite

Model Evaluation Guidelines for Geomagnetic Index Predictions

Geomagnetic indices are convenient quantities that distill the complicated physics of some region or aspect of near‐Earth space into a single parameter. Most of the best‐known indices are calculated

Evaluation of OVATION Prime as a forecast model for visible aurorae

This study evaluates the ability of the OVATION Prime auroral precipitation model to provide operational forecasts of the visible aurora. An operational implementation would primarily provide the

Principal component analysis: a review and recent developments

  • I. JolliffeJ. Cadima
  • Computer Science
    Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
  • 2016
The basic ideas of PCA are introduced, discussing what it can and cannot do, and some variants of the technique have been developed that are tailored to various different data types and structures.

New DMSP database of precipitating auroral electrons and ions

A new public database of precipitating electrons and ions from the Special Sensor J (SSJ) instrument is described, complete with original counts, calibrated differential fluxes adjusted for penetrating radiation, estimates of the total kinetic energy flux and characteristic energy, uncertainty estimates, and accurate ephemerides.

Evaluation of SuperMAG auroral electrojet indices as indicators of substorms and auroral power

[1] We use magnetometer chains collaborating with SuperMAG to derive SME, a generalization of the auroral electrojet indices calculated from 100 or more sites instead of the 12 used in the official

Substorm and magnetosphere characteristic scales inferred from the SuperMAG auroral electrojet indices

[1] A generalization of the traditional 12-station auroral electrojet (AE) index to include more than 100 magnetometer stations, SME, is an excellent predictor of global auroral power (AP), even at

A statistical model of auroral electron precipitation

A statistical study has been completed using data from the Defense Meteorological Satellite Program F2 and F4 and the Satellite Test Program P78-1 satellites to determine the average characteristics

A coupled thermosphere/ionosphere general circulation model

The NCAR thermospheric general circulation model (TGCM) is extended to include a self-consistent aeronomic scheme of the thermosphere and ionosphere. The model now calculates total temperature,