Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userForecasting Megaelectron-Volt Electrons inside Earths Outer Radiation Belt: PreMevE 2.0 Based on Supervised Machine Learning Algorithms
231
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Here we present the recent progress in upgrading a predictive model for Megaelectron-Volt (MeV) electrons inside the Earths outer Van Allen belt. This updated model, called PreMevE 2.0, is demonstrated to make much improved forecasts, particularly at outer Lshells, by including upstream solar wind speeds to the models input parameter list. Furthermore, based on several kinds of linear and artificial machine learning algorithms, a list of models were constructed, trained, validated and tested with 42-month MeV electron observations from Van Allen Probes. Out-of-sample test results from these models show that, with optimized model hyperparameters and input parameter combinations, the top performer from each category of models has the similar capability of making reliable 1-day (2-day) forecasts with Lshell-averaged performance efficiency values ~ 0.87 (~0.82). Interestingly, the linear regression model is often the most successful one when compared to other models, which indicates the relationship between 1 MeV electron dynamics and precipitating electrons is dominated by linear components. It is also shown that PreMevE 2.0 can reasonably predict the onsets of MeV electron events in 2-day forecasts. This improved PreMevE model is driven by observations from longstanding space infrastructure (a NOAA satellite in low-Earth-orbit, the solar wind monitor at the L1 point, and one LANL satellite in geosynchronous orbit) to make high-fidelity forecasts for MeV electrons, and thus can be an invaluable space weather forecasting tool for the future.
rate research
Read More
Energetic electrons inside Earths outer Van Allen belt pose a major radiation threat to space-borne electronics that often play vital roles in our modern society. Ultra-relativistic electrons with energies greater than or equal to two Megaelectron-volt (MeV) are of particular interest due to their high penetrating ability, and thus forecasting these >=2 MeV electron levels has significant meaning to all space sectors. Here we update the latest development of the predictive model for MeV electrons inside the Earths outer radiation belt. The new version, called PreMevE-2E, focuses on forecasting ultra-relativistic electron flux distributions across the outer radiation belt, with no need of in-situ measurements except for at the geosynchronous (GEO) orbit. Model inputs include precipitating electrons observed in low-Earth-orbits by NOAA satellites, upstream solar wind conditions (speeds and densities) from solar wind monitors, as well as ultra-relativistic electrons measured by one Los Alamos GEO satellite. We evaluated a total of 32 supervised machine learning models that fall into four different classes of linear and neural network architectures, and also successfully tested ensemble forecasting by using groups of top-performing models. All models are individually trained, validated, and tested by in-situ electron data from NASAs Van Allen Probes mission. It is shown that the final ensemble model generally outperforms individual models overs L-shells, and this PreMevE-2E model provides reliable and high-fidelity 25-hr (~1-day) and 50-hr (~2-day) forecasts with high mean performance efficiency values. Our results also suggest this new model is dominated by non-linear components at low L-shells (< ~4) for ultra-relativistic electrons, which is different from the dominance of linear components at all L-shells for 1 MeV electrons as previously discovered.
Real-time prediction of the dynamics of energetic electrons in Earths radiation belts incorporating incomplete observation data is important to protect valuable artificial satellites and to understand their physical processes. Traditionally, reduced models have employed a diffusion equation based on the quasilinear approximation. Using a Physics-Informed Neutral Network (PINN) framework, we train and test a model based on four years of Van Allen Probe data. We present a recipe for gleaning physical insight from solving the ill-posed inverse problem of inferring model coefficients from data using PINNs. With this, it is discovered that the dynamics of killer electrons is described more accurately instead by a drift-diffusion equation. A parameterization for the diffusion and drift coefficients, which is both simpler and more accurate than existing models, is presented.
Energetic particle fluxes in the outer magnetosphere present a significant challenge to modelling efforts as they can vary by orders of magnitude in response to solar wind driving conditions. In this article, we demonstrate the ability to propagate test particles through global MHD simulations to a high level of precision and use this to map the cross-field radial transport associated with relativistic electrons undergoing drift orbit bifurcations (DOBs). The simulations predict DOBs primarily occur within an Earth radius of the magnetopause loss cone and appears significantly different for southward and northward interplanetary magnetic field orientations. The changes to the second invariant are shown to manifest as a dropout in particle fluxes with pitch angles close to 90$^circ$ and indicate DOBs are a cause of butterfly pitch angle distributions within the night-time sector. The convective electric field, not included in previous DOB studies, is found to have a significant effect on the resultant long term transport, and losses to the magnetopause and atmosphere are identified as a potential method for incorporating DOBs within Fokker-Planck transport models.
The Cluster mission, launched in 2000, has produced a large database of electron flux intensity measurements in the Earths magnetosphere by the Research with Adaptive Particle Imaging Detector (RAPID)/ Imaging Electron Spectrometer (IES) instrument. However, due to background contamination of the data with high-energy electrons (>400 keV) and inner- zone protons (230-630 keV) in the radiation belts and ring current, the data have been rarely used for inner-magnetospheric science. The current paper presents two algorithms for background correction. The first algorithm is based on the empirical contamination percentages by both protons and electrons. The second algorithm uses simultaneous proton observations. The efficiencies of these algorithms are demonstrated by comparison of the corrected Cluster/RAPID/IES data with Van Allen Probes/Magnetic Electron Ion Spectrometer (MagEIS) measurements for 2012-2015. Both techniques improved the IES electron data in the radiation belts and ring current.Yearly averaged flux intensities of the two missions show the ratio of measurements close to 1. IES corrected measurements were also compared with Arase Medium-Energy Particle Experiments-Electron Analyzer (MEP-e) electron data during two conjunction periods in 2017 and also exhibited ratio close to 1. We demonstrate a scientific application of the corrected IES electron data analyzing its evolution during solar cycle. Spin-averaged yearly mean IES electron intensities in the outer belt for energies 40-400 keV at L-shell between 4 and 6 showed high positive correlation with AE index and solar wind dynamic pressure during 2001- 2016. Relationship between solar wind dynamic pressure and IES electron measurements in the outer radiation belt was derived as a uniform linear-logarithmic equation.
The numerous recent breakthroughs in machine learning (ML) make imperative to carefully ponder how the scientific community can benefit from a technology that, although not necessarily new, is today living its golden age. This Grand Challenge review paper is focused on the present and future role of machine learning in space weather. The purpose is twofold. On one hand, we will discuss previous works that use ML for space weather forecasting, focusing in particular on the few areas that have seen most activity: the forecasting of geomagnetic indices, of relativistic electrons at geosynchronous orbits, of solar flares occurrence, of coronal mass ejection propagation time, and of solar wind speed. On the other hand, this paper serves as a gentle introduction to the field of machine learning tailored to the space weather community and as a pointer to a number of open challenges that we believe the community should undertake in the next decade. The recurring themes throughout the review are the need to shift our forecasting paradigm to a probabilistic approach focused on the reliable assessment of uncertainties, and the combination of physics-based and machine learning approaches, known as gray-box.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
