MeV Electron Research Articles

Towards Better Perovskite Absorber Materials: Cu+ Doping Improves Photostability and Radiation Hardness of Complex Lead Halides

ABSTRACTThe partial Pb2+ substitution with Cu+ ions has been thoroughly applied as an approach to produce new absorber materials with enhanced light and radiation hardness required for potential aerospace applications of perovskite solar cells. X‐ray photoelectron spectroscopy revealed that Cu+ ions are partially integrated into the crystal lattice of MAPbI3 on the surface of perovskite grains and induce p‐doping effect, which is crucial for a range of applications. Importantly, the presence of Cu+ enhances photostability of perovskite films and blocks the formation of metallic lead as a photolysis product. Furthermore, we have carried out one of the first studies on the radiation hardness of complex lead halides exposed to two different stressors: γ‐rays and 8.5 MeV electron beams. The obtained results demonstrate that Cu+ doping alters completely the radiation‐induced degradation pathways of the double cation perovskite. Indeed, while Cs0.12FA0.88PbI3 degrades mostly with segregation of δ‐phase of FAPbI3 forming a Cs‐rich perovskite phase, the Cs0.12FA0.88Pb0.99Cu0.01I2.99 films tend to expel δ‐CsPbI3 and produce FA‐rich perovskite phase, which shows impressive tolerance to both γ‐rays and high energy electrons. The beneficial effect of copper ion incorporation on the stability of lead halide perovskite solar cells under light soaking and γ‐ray irradiation conditions has been shown. The discovered possibility of controlling the electronic properties and major materials degradation pathways through minor modification of their chemical composition (e.g., replacing 1% of Pb2+ with Cu+) opens up tremendous opportunities for engineering new perovskite absorber compositions with significantly improved properties for both terrestrial and aerospace applications. image

Influence of absorbing layers on the average dose and dose uniformity during irradiation with 1–3 MEV electrons

Electron beams with energies up to 3 MeV, widely used in technological and research practice, have a relatively low penetration depth into matter, and the nonuniformity of energy absorption can reach 30% per 1 mm of path. High nonuniformity, as well as the high cost of radiation, requires the researcher to have skills in optimizing the uniformity of irradiation and reducing energy losses. This work presents the dependence of the average absorbed dose and dose nonuniformity when irradiating a liquid with a horizontal beam in test tubes or pipes with different glass wall thicknesses (0.2–2 mm Pyrex). The dependencies are applicable to clarify, predict and analyze the distribution of absorbed dose in materials.

Determination of Photoneutron Production from Different Targets Irradiated by Electron Beam

In the present work, a study has been conducted to estimate the production of photoneutrons from different targets irradiated by a 70 MeV electron beam. The linear electron accelerator at the Yerevan Physics Institute in Armenia was used for the purpose. The reaction rates were determined through detailed off-line analysis of experimental data and subsequently compared to theoretical predictions by using the MCNP (Monte Carlo N-Particle Transport) and Cascade Exciton Physics Model (CEM03.03) codes.

Upward, MeV‐Class Electron Beams Over Jupiter's Main Aurora

AbstractJupiter's poleward (Zone II) main aurora exhibits bi‐directional electron acceleration; upward acceleration dominates but downward acceleration generates strong aurora. During Juno's first perijove (PJ1), the upward acceleration manifested as narrow electron angular beams (within ∼5° of the magnetic field) over the 30–1,200 keV energy range of Juno's Jupiter Energetic Particle Detector Investigation (JEDI). These beams can be simply connected (non‐uniquely) to >10 to perhaps 100's of MeV electrons that penetrated the radiation shielding of the camera head of the Magnetometer Investigation's Advanced Stellar Compass (ASC). The most intense of those multiple MeV populations are shown to have been highly directional and propagating upwards. How auroral processes generate such beams is unknown. With azimuthal symmetry assumed (not demonstrated here), these beams provided >1026 s−1 of >30 keV electrons to Jupiter's vast magnetosphere, a possibly critical and dominating source of energetic electrons to that region and ultimately to Jupiter's radiation belts.

Investigating the Effectiveness of 6Mev Electron and Ultrasound Beams with the Use of Iron Oxide Magnetic Nanoparticles Attached to Cisplatin on B16F10 Cells: In-Vitro Study

Melanoma is considered the deadliest skin cancer that can be treated with surgery, radiotherapy, chemotherapy, etc. The use of magnetic iron oxide nanoparticles (IONPs) in order to increase the effectiveness of electron beams and ultrasound beams by increasing the production of free radicals (ROS) and their ability to deliver chemotherapy drugs is under research. Cisplatin is one of the chemotherapy drugs based on platinum, whose ability to deal with melanoma has recently been clarified. In this study, we studied the synthesis of [Formula: see text], [Formula: see text]@L-Aspartic and [Formula: see text]@L-Aspartic@Cisplatin nanoparticles and we managed to determine the characteristics of each of them using TEM, DLS, FTIR, UV–Vis tests; also, MTT and flow cytometry tests were performed for [Formula: see text] and [Formula: see text]@L-Aspartic with the concentrations of 10, 25, 50, 80 and 100 [Formula: see text] g/mL and for [Formula: see text]@L-Aspartic@Cisplatin and cisplatin with concentrations of 0.6, 1.6, 5, 10 and 20 [Formula: see text] g/mL alone and in combination with electron beam with doses of 1 Gy, 2[Formula: see text]Gy and 3[Formula: see text]Gy and ultrasound beam with the intensities of 1[Formula: see text]W/cm2 and 2[Formula: see text]. The results of the mining TEM test show the size of [Formula: see text], [Formula: see text]@L-Aspartic and [Formula: see text]@L-Aspartic@Cisplatin to be 25[Formula: see text]nm, 35[Formula: see text]nm and 42[Formula: see text]nm, and the FTIR and UV–Vis tests also confirmed the nanoparticle coating and drug loading; also, the results of MTT and flow cytometry test showed the effectiveness of [Formula: see text], [Formula: see text]@L-Aspartic and [Formula: see text]@L-Aspartic@Cisplatin in increasing the effectiveness of electron beam and ultrasound beam. The use of nanotechnology together with other treatment methods can shed light on a new way to overcome cancer.

Study on non-radiative recombination centers in GaInP sub-cell of electron-irradiated triple junction solar cells based on photoluminescence measurements

The radiation damage induced by energetic particles on GaInP sub-cell in GaInP/GaAs/Ge triple junction solar cell (TJSC) has a significant impact on its performance. Thus, in this paper, we measured the photoluminescence (PL) spectra for GaInP sub-cell in TJSC irradiated by 11.5 MeV electron at temperature range 10 –300 K. By analyzing the variation of PL intensity with temperature, the thermal activation energy for nonradiative recombination center was determined as 8.43 meV, and its minority carrier capture cross-section is about 3.63 × 10−13 cm2. Further confirmed that the nonradiative recombination center in GaInP is H2 (EV + 0.55 eV) defect. Furthermore, by using multi-peaks curve-fittings to analyze PL spectra, the carrier recombination processes in electron irradiated GaInP sub-cell are determined, and a phenomenological model was given for explaining carrier recombination processes.

The compact beam energy measurement method of the photocathode RF gun by the solenoid and beam shaping.

Beam energy, normalized emittance, and quantum efficiency are crucial parameters of the RF gun. In this study, we proposed a compact and low-cost method to measure the beam energy at the exit of the 120 MeV electron linac's RF gun. We utilized a solenoid magnetic field to rotate an elliptical beam and measured the rotation angle of the beam to calculate the energy. To generate an elliptical electron beam, we inserted a slit device after the laser beam shaping aperture (BSA) to produce a long strip of driving laser beam for the RF gun photocathode. During the measurement process, we employed the Maximally Stable Extremal Regions (MSER) detection algorithm to measure the beam spot angle, improving the accuracy and stability of the angle measurement. This method does not require any changes to the accelerator lattice, nor does it require additional space. It only requires inserting a slit device to measure the beam's energy. Our results indicated that the energy at the exit of the RF gun was 4-5 MeV, consistent with simulation calculations using ASTRA.

Global prediction of sub-relativistic and relativistic electron fluxes in the geosynchronous orbit using artificial neural networks

High-energy particles in geosynchronous orbit (GEO) present significant hazards to astronauts and artificial satellites, particularly during extreme geomagnetic activity conditions. In the present study, based on observations onboard the GOES-15 (Geostationary Operational Environmental Satellites) spanning from 2011 to 2019 as well as the historical values of solar wind and geomagnetic activity indices, an artificial neural network model was established to predict the temporal evolution of the GEO sub-relativistic and relativistic (>0.8 MeV and >2 MeV) electron fluxes one day in advance. By adding the last-orbital observations of electron flux in each of all 24 different magnetic local times (MLTs) and its two MLT-adjacent values into inputs, the current model can provide accurate predictions with an MLT resolution of one hour for the first time. Moreover, it achieves the best performance in comparison with previous methods, with overall root mean square errors of 0.276 and 0.311, prediction efficiencies of 0.863 and 0.844, and Pearson correlation coefficients of 0.930 and 0.921 for >0.8 MeV and >2 MeV electrons, respectively. More than 99% of the samples exhibit an observation-prediction difference of less than one order of magnitude, while over 90% demonstrate a difference of less than 0.5 order. Further analysis revealed that it can precisely track the global variations of the electron flux during both quiet times and active conditions. The present model would be an important supplement for examining the temporospatial variations of inner magnetospheric particles and helping to establish a warning mechanism for space weather disaster events.

Acceleration of Energetic Electrons in Jovian Middle Magnetosphere by Whistler‐Mode Waves

AbstractAn abundant multi‐MeV electron population beyond the orbit of Io is required to explain the intense inner radiation belt (electrons MeV) at Jupiter and its synchrotron radiation. In order to better understand the synergistic effect of radial transport and local wave‐particle interactions driven by whistler‐mode waves on the formation of Jupiter's radiation belt, we perform 3‐D Fokker‐Planck simulations for Jovian energetic electrons with the Versatile Electron Radiation Belt code. An empirical model of Jovian whistler‐mode waves updated with measurements from the Juno extended mission is used to quantify the local acceleration and pitch angle scattering. Resonant cyclotron acceleration by whistler‐mode waves leads to significant enhancement in the intensity of electrons above 1 MeV in the middle magnetosphere. Radial diffusion is capable of transporting MeV electrons accelerated by outer‐belt whistler‐mode waves into the region, where they are further accelerated adiabatically to energies of about 10 MeV.

Study of modulation in complex refractive indices induced by ultrafast relativistic electrons using infrared and THz probe pulses

Objective.Achieving ultra-precise temporal resolution in ionizing radiation detection is essential, particularly in positron emission tomography, where precise timing enhances signal-to-noise ratios and may enable reconstruction-less imaging. A promising approach involves utilizing ultrafast modulation of the complex refractive index, where sending probe pulses to the detection crystals will result in changes in picoseconds (ps), and thus a sub-10 ps coincidence time resolution can be realized. Towards this goal, here, we aim to first measure the ps changes in probe pulses using an ionizing radiation source with high time resolution. Approach.We used relativistic, ultrafast electrons to induce complex refractive index and use probe pulses in the near-infrared (800 nm) and terahertz (THz, 300µm) regimes to test the hypothesized wavelength-squared increase in absorption coefficient in the Drude free-carrier absorption model. We measured BGO, ZnSe, BaF2, ZnS, PBG, and PWO with 1 mm thickness to control the deposited energy of the 3 MeV electrons, simulating ionization energy of the 511 keV photons.Main results.Both with the 800 nm and THz probe pulses, transmission decreased across most samples, indicating the free carrier absorption, with an induced signal change of 11% in BaF2, but without the predicted Drude modulation increase. To understand this discrepancy, we simulated ionization tracks and examined the geometry of the free carrier distribution, attributing the mismatch in THz modulations to the sub-wavelength diameter of trajectories, despite the lengths reaching 500µm to 1 mm. Additionally, thin samples truncated the final segments of the ionization tracks, and the measured initial segments have larger inter-inelastic collision distances due to lower stopping power (dE/dx) for high-energy electrons, exacerbating diffraction-limited resolution.Significance.Our work offers insights into ultrafast radiation detection using complex refractive index modulation and highlights critical considerations in sample preparation, probe wavelength, and probe-charge carrier coupling scenarios.

High-brightness megahertz-rate beam from a direct-current and superconducting radio-frequency combined photocathode gun

High-brightness megahertz-rate electron beams are highly desired for cutting-edge applications in many areas of science. Photocathode electron guns capable of generating such beams with low dark current remain to be a challenging field. In this paper, we report breakthroughs with a hybrid gun combining a direct-current gap and a superconducting radio-frequency (SRF) cavity. The gun, employing K2CsSb photocathodes driven by a green laser, delivers a few MeV electron beam at 1 and 81.25 MHz rates with an average current up to 3 mA and a dark current several orders lower than current normal conducting continuous-wave guns. Emittance compensation and multipole field corrections have been applied to achieve a high-quality beam. The achievement will inspire the development of high-brightness SRF guns and promote megahertz-rate beam applications including coherent linac light sources and ultrafast electron diffraction/microscopy. Published by the American Physical Society 2024

Ultra-relativistic electron flux enhancement under persistent high speed solar wind stream

The physical mechanisms usually applied to explain the relativistic electron enhancement have been delved into to elucidate non-adiabatic electron acceleration resulting in the ultra-relativistic electron population observed in the outer radiation belt. We considered multisatellite observations of the solar wind parameters, magnetospheric waves, and particle flux to report an unusual local acceleration of ultra-relativistic electrons under a prolonged high-speed solar wind stream (HSS). A corotating interaction region reaches the Earth’s bowshock on August 3, 2016, causing a minor geomagnetic storm. Following this, the magnetosphere was driven for 72 h by a long-term HSS propagating at 600 km/s. During this period, the magnetosphere sustained both ultra-low frequency (ULF) and very-low frequency (VLF) waves in the outer radiation belt region. Besides the waves, the relativistic and ultra-relativistic electron fluxes were enhanced with different time lags regarding the magnetic storm main phase. The efficiency of wave-particle interaction in enhancing ultrarelativistic electrons is evaluated by the diffusion coefficient rates, considering both ULF and VLF waves together with phase space density analyses. Results show that local acceleration by whistler mode chorus waves can occur in a time scale of 2–4 h, whereas ULF waves take around 10’s of hours and magnetosonic waves take a time scale of days. This result is confirmed by the phase space density analysis. Accordingly, it shows that peaks of local acceleration of 1 MeV electrons are consistent with the observation of the highest chorus wave amplitude at the same L-shell and MLT. Thus, we argue that whistler mode chorus waves interacting with relativistic electrons are the main physical mechanisms leading to ultra-relativistic electron enhancement, while ULF and fast magnetosonic waves are found as secondary physical processes. Lastly, our analysis contributes to understanding how whistler and ULF waves can contribute to ultra-relativistic electrons showing up in the inner magnetosphere under the HSS driver.

Performance Evaluation of Electron Multiplier Tubes as a High-Intensity Muon Beam Monitor of Accelerator Neutrino Experiments

Abstract Upgrade work towards increasing the beam intensity of the neutrino beamline at the Japan Proton Accelerator Research Complex (J-PARC) is underway. Monitoring tertiary muon beams is essential for stable operation of the beamline. Accordingly, we plan to replace the present muon monitor sensors with electron multiplier tubes (EMTs). We investigated the radiation tolerance and linearity response of EMTs using a 90 MeV electron beam. EMTs were irradiated with electrons up to 470 nC. EMTs show higher radiation tolerance than the Si sensors which are presently used as one of the muon monitor detectors for the Tokai-to-Kamioka (T2K) long-baseline neutrino experiment at J-PARC. The integrated charge yield decrease is found to be less than 8% after a beam irradiation equivalent to 132 days of operation at the future J-PARC beam power of 1.3 MW. The EMTs show linearity better than $\pm$5% up to the future beam intensity. The observed yield decrease is likely due to dynode deterioration, based on detailed investigation. The studies described here confirm that EMTs can be used as a high-intensity muon beam monitor. Owing to the reported results, we are proceeding with the installation in the J-PARC neutrino beamline.

Spatially Fractionated Radiotherapy with Very High Energy Electron Pencil Beam Scanning.


To evaluate spatially fractionated radiation therapy (SFRT) for very-high-energy electrons (VHEEs) delivered with pencil beam scanning. Radiochromic film was irradiated at the CERN Linear Electron Accelerator for Research (CLEAR) using 194 MeV electrons with a step-and-shoot technique, moving films within a water tank. Peak-to-valley dose ratios (PVDRs), depths of convergence (PVDR≤1.1), peak doses, and valley doses assessed SFRT dose distribution quality. A Monte Carlo (MI) model of the pencil beams was developed using TOPAS and applied to a five-beam VHEE SFRT treatment for a canine glioma patient, compared to a clinical 6 MV VMAT plan. The plans were evaluated based on dose-volume histograms, mean dose, and maximum dose to the planning target volume (PTV) and organs at risk (OARs).
Main Results:
Experimental PVDR values were maximized at 15.5 ± 0.1 at 12 mm depth for 5 mm spot spacing. A depth of convergence of 76.5 mm, 70.7 mm, and 56.6 mm was found for 5 mm, 4 mm, and 3 mm beamlet spacings, respectively. MC simulations and experiments showed good agreement, with maximum relative dose differences of 2% in percentage depth dose curves and less than 3% in beam profiles. Simulated PVDR values reached 180 ± 4, potentially achievable with reduced leakage dose. VHEE SFRT plans for the canine glioma patient showed a decrease in mean dose (>16%) to OARs while increasing the PTV mean dose by up to 15%. Lowering beam energy enhanced PTV dose homogeneity and reduced OAR maximum doses. The presented work demonstrates that pencil beam scanning SFRT with VHEEs could treat deep-seated tumors such as head and neck cancer or lung lesions, though small beam size and leakage dose may limit the achievable PVDR.&#xD.

Study on dosimetric characteristics of polycarbonate films irradiated by electron beam

In this study, the dosimetric characteristics (thickness applicability, dose linear response, signal fading characteristic, in-batch consistency, readout reproducibility, humidity dependence, and electron energy response) of engineering polycarbonate films irradiated by electron beam were studied using spectrophotometry. The results show that polycarbonate films of various thicknesses exhibit good dose linearity within their corresponding wavelength ranges. Specifically, the dose capture range of 0.3 mm polycarbonate film spans from 950 Gy to 1000 kGy. After irradiation, the net absorbance of polycarbonate films showed an exponential decline, which was dose-dependent. The average absolute deviation of net absorbance for polycarbonate films produced within the same batch is 1.49% at 100 kGy. After 15 repeated absorbance measurements, the coefficient of variation in net absorbance for the polycarbonate films is less than 1%. Additionally, the radiation response of the polycarbonate film is affected by the environment relative humidity (during irradiation and post-irradiation storage). At the same dose of 3.5–20 MeV electron beam irradiation, the net absorbance response deviation of polycarbonate films remains below 2.26%. These results provide a comprehensive reference for detecting high doses of electron beams using engineering polycarbonate films.

Simulation Study of High-Precision Characterization of MeV Electron Interactions for Advanced Nano-Imaging of Thick Biological Samples and Microchips.

The resolution of a mega-electron-volt scanning transmission electron microscope (MeV-STEM) is primarily governed by the properties of the incident electron beam and angular broadening effects that occur within thick biological samples and microchips. A precise understanding and mitigation of these constraints require detailed knowledge of beam emittance, aberrations in the STEM column optics, and energy-dependent elastic and inelastic critical angles of the materials being examined. This simulation study proposes a standardized experimental framework for comprehensively assessing beam intensity, divergence, and size at the sample exit. This framework aims to characterize electron-sample interactions, reconcile discrepancies among analytical models, and validate Monte Carlo (MC) simulations for enhanced predictive accuracy. Our numerical findings demonstrate that precise measurements of these parameters, especially angular broadening, are not only feasible but also essential for optimizing imaging resolution in thick biological samples and microchips. By utilizing an electron source with minimal emittance and tailored beam characteristics, along with amorphous ice and silicon samples as biological proxies and microchip materials, this research seeks to optimize electron beam energy by focusing on parameters to improve the resolution in MeV-STEM/TEM. This optimization is particularly crucial for in situ imaging of thick biological samples and for examining microchip defects with nanometer resolutions. Our ultimate goal is to develop a comprehensive mapping of the minimum electron energy required to achieve a nanoscale resolution, taking into account variations in sample thickness, composition, and imaging mode.

Monte Carlo modeling of a commercial machine and experimental setup for FLASH‐minibeam irradiations with electrons

BackgroundUltra‐high dose rate (UHDR/FLASH) irradiations, along with particle minibeam therapy (PMBT) are both emerging as promising alternatives to current radiotherapy techniques thanks to their improved healthy tissue sparing and similar tumor control.PurposeMonte Carlo (MC) modeling of a commercial machine delivering 5–7 MeV electrons at UHDR. This model was used afterward to compare measurements against simulations for an experimental setup combining both FLASH and PMBT modalities.MethodsWe modeled the main accelerator elements with TOPAS3.8/Geant4.10.07.p03, optimized the electron source parameters, and subsequently benchmarked this geometry against measurements. Minibeam experiments were performed by delivering 7 MeV electrons at UHDR on three different 65‐mm thick brass collimators as manufactured for protons with a 400‐µm slit width: single slit, 5 slits with a center‐to‐center (CTC) distance of 4 mm and 9 slits with CTC of 2 mm. Finally, complementary simulations were run by changing critical PMBT collimator parameters to assess their specific impact on peak‐to‐valley dose ratio (PVDR) as well as on the Bremsstrahlung photon contribution to the total dose.ResultsPercentage depth dose (PDD) distributions and lateral dose profiles showed a good agreement between simulations and measurements, with a maximum discrepancy of less than 4%. With the PMBT collimators in place, discrepancies between simulated and measured dose profiles, lateral and in‐depth in peaks and valleys, were within 3%. High PVDR between 5 and 26 were observed until 4 mm in the phantom. During the experiments, a mean dose rate of 167 Gy/s and an instantaneous dose rate of 1.2 × 105 Gy/s were obtained for the FLASH‐minibeam setup. PMBT collimator parameters need to be optimized to maximize PVDR while limiting Bremsstrahlung photon contribution to the total dose.ConclusionsThe validation of the MC model and the configuration of an electron FLASH‐minibeam setup were successfully completed, paving the way for future radiobiological investigations.

Radiation protection of W–Al composite films/coatings for aviation using genetic algorithms

This study evaluated electron shielding capabilities of various materials using Geant4 Monte Carlo software. By analyzing materials with different atomic numbers, we designed and tested composite films and coatings for radiation protection. Under 1.2 MeV electron irradiation, these materials reduced the dose deposited in electronic components by over 70 %. The fabricated composite films (W–Al) reduced the actual total dose by 100 % with a 30.67 % mass increase, closely matching the simulation result of 75.36 %. The composite coatings (W–Al) reduced the dose by 89.2 % with a 33 % mass increase, matching the simulation result of 70 %. Cascade collision simulations revealed that higher PKA energies lead to longer times to reach the thermal peak, more peak defects, and more stable defect pairs. This is due to the displacement threshold energy of the atoms in aluminum and tungsten. These results demonstrate the effectiveness of our composite films and coatings in enhancing electron shielding performance and validate our design methods.

Dose coefficients of mesh-type reference Korean phantoms (MRKPs) for idealized external exposure geometries of photons and electrons

The present study produced Korean-specific dose coefficients for idealized external exposures to photons and electrons by performing Monte Carlo dose calculations with mesh-type reference Korean phantoms (MRKPs). The Korean dose coefficients were then compared with those previously calculated using the mesh-type reference computational phantoms (MRCPs) of the International Commission on Radiological Protection (ICRP). For photons, excellent agreements in the organ/tissue dose coefficients between the Korean and ICRP phantoms were observed for the most energies except for the low energies (<0.1 MeV), in which significant differences were observed. For example, the colon dose coefficient of the female MRKP was ∼1780 times lower at 0.02 MeV for LLAT. For electrons, while excellent agreements were observed at the energies > ∼30 MeV, significant differences were observed in the lower energy region, especially from 0.3 to 20 MeV. For example, the gonad dose coefficient of the male MRKP was ∼57 times lower at 1.5 MeV for PA. When comparing the effective dose coefficients, the differences were generally small, i.e., generally less than 20 %, for both photons and electrons, although some exposure cases showed notable differences (e.g., 32 % at 0.03-MeV photon and 61 % at 10-MeV electron for PA).

Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes

AbstractThe geosynchronous orbit (GEO) is a region filled with energetic electrons and it hosts hundreds of satellites. Electron fluxes at GEO can change sharply within hours, making high‐time‐resolution prediction crucial. In this study, we develop and compare two neural networks for persistent high‐time‐resolution prediction: long short‐term memory with temporal pattern attention (TPA‐LSTM) and Transformer. Unlike most previous models, which only output electron fluxes, our models output the same parameters as the inputs, including magnetic local time, solar wind speed, solar wind dynamic pressure, AE, Kp, Dst, the north‐south component of the interplanetary magnetic field, and electron flux data from GOES‐15. The models are trained on approximately six years of data (2012–2016) and validated using about one year of data (2017–2018). We compare the TPA‐LSTM and Transformer models using 0.8 MeV electron fluxes and find that while the Transformer model performs slightly better, the difference is not statistically significant. Considering the Transformer's higher computational cost, we use the TPA‐LSTM model to develop prediction models for electron fluxes of 275, 475, 0.8 MeV, and 2 MeV with a 5‐min resolution at GEO, up to 3 days. The prediction efficiencies (PE) for 275, 475, 0.8 and 2 MeV electron fluxes based on about one year of test data (2018–2019) are 0.799, 0.831, 0.849, 0.881 (1‐day prediction); and 0.551, 0.618, 0.663 and 0.710 (3‐day prediction), respectively. Our high‐time‐resolution persistent models should be useful for both protecting satellites at GEO and serving as boundary conditions for physics‐based radiation belt models.