Solar energetic particle (SEP) events have attracted increasing attention due to their significant radiation hazards for aviation, spacecraft electronics, and human missions beyond Earth's magnetosphere. From a scientific perspective, SEP events are intriguing because they arise from a set of physical processes extending from the solar surface and corona through the heliosphere, offering insight into particle acceleration and transport mechanisms that are widely applicable across astrophysics. Therefore, advancing our ability to understand and predict SEP events is essential both for deepening our knowledge of such mechanisms and for safeguarding space technologies and exploration. Traditionally, researchers have modeled SEPs using physics-based simulations and empirical methods. More recently, machine learning (ML) has emerged as a new tool for understanding and predicting SEP events. The purpose of this manuscript is to review the currently available ML models for SEP prediction, identify the datasets used for training, compare their architectures, inputs, and outputs, and, based on these insights, outline good practices and recommendations for future research.

Abstract The CLEAR Space Weather Center of Excellence's solar energetic particle (SEP) model, SOlar wind with FIeld lines and Energetic particles (SOFIE), was run and evaluated on‐site during the Space Weather Prediction Testbed (SWPT) exercise at the National Oceanic and Atmospheric Administration's Space Weather Prediction Center (NOAA/SWPC) in May 2025. As a physics‐based SEP model, SOFIE simulates the acceleration and transport of energetic particles by the coronal mass ejection (CME)‐driven shock in the solar corona and inner heliosphere, and has been validated against historical events. However, questions remain regarding whether a physics‐based model, traditionally considered computationally expensive, could meet operational needs. The SWPT exercise offered a valuable opportunity to evaluate SOFIE under simulated operational conditions. On‐site interactive feedback from SWPC forecasters, Space Radiation Analysis Group (SRAG) console operators, Community Coordinated Modeling Center (CCMC) personnel, and Moon‐to‐Mars Space Weather Analysis Office (M2M SWAO) analysts led to significant strategic improvements in the model configuration. The simulation grid was optimized by combining a coarser background grid with higher‐resolution regions along the CME path and toward Earth, reducing computational cost without compromising accuracy. In this work, we present the simulated operational performance of SOFIE and its capability to predict SEP fluxes significantly faster than real time. During the SWPT exercise, SOFIE completed a 4‐day SEP simulation within 5 hr using 1,000 central processing unit cores, although the earliest SEP forecast was obtained a few hours after CME onset. This marks a milestone in demonstrating SOFIE's operational usefulness and robustness to support future human space exploration.

Solar energetic particles (SEPs) can pose hazardous radiation risks to both humans and spacecraft electronics in space. Numerical modeling based on first principles offers valuable insights into the underlying physics of SEPs and provides synthetic observables for SEPs at any time and location in the inner heliosphere. In this work, we present a numerical scheme, which conserves the number of particles based on integral relations for Poisson brackets, to solve the kinetic equation for particle acceleration and transport processes. We implement this scheme within the Space Weather Modeling Framework, developed at the University of Michigan. In addition, we develop a new shock-capturing tool to study the coronal mass ejection-driven shock originating from the low solar corona. These methodological advancements are applied to conduct a comprehensive study of a historical SEP event on 2013 April 11. Observations from multiple spacecraft, including the Solar and Heliospheric Observatory, Solar Dynamics Observatory, Geostationary Operational Environmental Satellite, Advanced Composition Explorer near Earth, and STEREO-A/B, are used for model–data comparison and validation. We show synthetic observables, including extreme ultraviolet and white-light images, proton time–intensity profiles, and energy spectra, and discuss their differences and probable explanations compared to observations. Our simulation results demonstrate the application of the Poisson bracket scheme with a particle solver to simulating a historical SEP event. We also show the capability of extracting the complex shock surface using our shock-capturing tool and understand how the complex shock surface affects the particle acceleration process.

Space weather is a multidisciplinary research area connecting scientists from across heliophysics domains seeking a coherent understanding of our space environment that can also serve modern life and society's needs. COSPAR's ISWAT (International Space Weather Action Teams) 'clusters' focus attention on different areas of space weather study while ensuring the coupled system is broadly addressed via regular communications and interactions. The ISWAT cluster "H3: Radiation Environment in the Heliosphere" (https://www.iswat-cospar.org/h3) has been working to provide a scientific platform to understand, characterize and predict the energetic particle radiation in the heliosphere with the practical goal of mitigating radiation risks associated with areospace activities, satellite industry and human space explorations. In particular, present approaches help us understand the physical phenomena at large, optimizing the output of multi-viewpoint observations and pushing current models to their limits. In this paper, we review the scientific aspects of the radiation environment in the heliosphere covering four different radiation types: Solar Energetic Particles (SEPs), Ground Level Enhancement (GLE, a type of SEP events with energies high enough to trigger the enhancement of ground-level detectors), Galactic Cosmic Rays (GCRs) and Anomalous Cosmic Rays (ACRs). We focus on related advances in the research community in the past 10-20 years and what we still lack in terms of understanding and predictive capabilities. Finally we also consider some recommendations related to the improvement of both observational and modeling capabilities in the field of space radiation environment.

Abstract The Sun continuously affects the interplanetary environment through a host of interconnected and dynamic physical processes. Solar flares, Coronal Mass Ejections (CMEs), and Solar Energetic Particles (SEPs) are among the key drivers of space weather in the near‐Earth environment and beyond. While some CMEs and flares are associated with intense SEPs, some show little to no SEP association. To date, robust long‐term (hours‐days) forecasting of SEP occurrence and associated properties (e.g., onset, peak intensities) does not effectively exist and the search for such development continues. Through an Operations‐2‐Research support, we developed a self‐contained model that utilizes a comprehensive data set and provides a probabilistic forecast for SEP event occurrence and its properties. The model is named Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP). MEMPSEP workhorse is an ensemble of Convolutional Neural Networks that ingests a comprehensive data set (MEMPSEP‐III by Moreland et al. (2024, https://doi.org/10.1029/2023SW003765)) of full‐disc magnetogram‐sequences and in situ data from different sources to forecast the occurrence (MEMPSEP‐I—this work) and properties (MEMPSEP‐II by Dayeh et al. (2024, https://doi.org/10.1029/2023SW003697)) of a SEP event. This work focuses on estimating true SEP occurrence probabilities achieving a 2.5% improvement in reliability and a Brier score of 0.14. The outcome provides flexibility for the end‐users to determine their own acceptable level of risk, rather than imposing a detection threshold that optimizes an arbitrary binary classification metric. Furthermore, the model‐ensemble, trained to utilize the large class‐imbalance between events and non‐events, provides a clear measure of uncertainty in our forecast.

Solar energetic particles (SEPs) can pose hazardous radiation risks to both humans in space and spacecraft electronics. Numerical modeling based on first principles offers valuable insights into SEPs, providing synthetic observables for SEPs at any time and location in space. In this work, we present a high-resolution scheme based on integral relations for Poisson brackets to solve the kinetic equation for particle acceleration and transport processes. We implement this scheme within the Space Weather Modeling Framework (SWMF), developed at the University of Michigan, to conduct a comprehensive study of solar energetic protons during the 2013 April 11 SEP event. In addition, a shock capturing tool is developed to study the coronal-mass-ejection-driven shock starting from the low solar corona. Multi-point spacecraft observations, including SOHO/ERNE, SDO/AIA, GOES and ACE at Earth, and STEREO-A/B, are used for model-data comparison and validation. New synthetic observables such as white-light images, shock geometry and properties, as well as SEP intensity-time profiles and spectra provide insights for SEP studies. The influences of the mean free path on SEP intensity-time profiles and spectra are also discussed. The results demonstrate: (1) the successful implementation of the Poisson bracket scheme with a self-consistent particle tracker within the SWMF, (2) the capability of capturing the time-evolving shock surface in the SWMF, and (3) the complexity of the mean free path impacts on SEPs. Overall, this study contributes to both scientific research and operational objectives by advancing our understanding of particle behaviors and showing the readiness for more accurate SEP predictions.

We introduce a new multivariate data set that utilizes multiple spacecraft collecting in-situ and remote sensing heliospheric measurements shown to be linked to physical processes responsible for generating solar energetic particles (SEPs). Using the Geostationary Operational Environmental Satellites (GOES) flare event list from Solar Cycle (SC) 23 and part of SC 24 (1998-2013), we identify 252 solar events (flares) that produce SEPs and 17,542 events that do not. For each identified event, we acquire the local plasma properties at 1 au, such as energetic proton and electron data, upstream solar wind conditions, and the interplanetary magnetic field vector quantities using various instruments onboard GOES and the Advanced Composition Explorer (ACE) spacecraft. We also collect remote sensing data from instruments onboard the Solar Dynamic Observatory (SDO), Solar and Heliospheric Observatory (SoHO), and the Wind solar radio instrument WAVES. The data set is designed to allow for variations of the inputs and feature sets for machine learning (ML) in heliophysics and has a specific purpose for forecasting the occurrence of SEP events and their subsequent properties. This paper describes a dataset created from multiple publicly available observation sources that is validated, cleaned, and carefully curated for our machine-learning pipeline. The dataset has been used to drive the newly-developed Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP; see MEMPSEP I (Chatterjee et al., 2023) and MEMPSEP II (Dayeh et al., 2023) for associated papers).

With growing interest from the aviation and satellite industries, and for NASA's upcoming Artemis lunar missions, the need for improved scientific understanding and accurate forecasting of solar energetic particle events has never been stronger.In this paper we discuss the observational, validation and model transition support required to achieve these goals.Well-calibrated, high-quality energetic electron, proton, and ion measurements are essential.Expansions to the fields of view offered by current X-ray, extreme ultraviolet and coronagraph instruments, to obtain increased coverage of the solar corona and heliosphere, from vantage points off the Sun-Earth line, are desired for model input.New observations of suprathermal particles are needed to characterize seed particle distributions and low latency space-based observations of solar radio emissions are also desired.Together, this observational suite should offer high cadence, low latency, reliable and accurate space weather data streams.SEP models are a critical part of both understanding and predicting SEP radiation hazards.Consistent, extensive and quantitative validation is required to assess scientific understanding of SEP sources and pave the way for models transitioning to real-time forecast operations.Model performance and skill should be compared to observations and to current operational forecasting baselines.Finally, resources are required to support the significant effort of transitioning mature models into forecast operations.Visualization of CME and SEPs.

In recent years there has been a growing interest from the aviation community for space weather radiation forecasts tailored to the needs of the aviation industry. In 2019 several space weather centers began issuing advisories for the International Civil Aviation Organization alerting users to enhancements in the radiation environment at aviation flight levels. Due to a lack of routine observations, radiation modeling is required to specify the dose rates experienced by flight crew and passengers. While mature models exist, support for key observational inputs and further modeling advancements are needed. Observational inputs required from the ground-based neutron monitor network must be financially supported for research studies and operations to ensure real-time data is available for forecast operations and actionable end user decision making. An improved understanding of the geomagnetic field is required to reduce dose rate uncertainties in regions close to the open/closed geomagnetic field boundary, important for flights such as those between the continental US and Europe which operate in this region. Airborne radiation measurements, which are crucial for model validation and improvement, are lacking, particularly during solar energetic particle events. New measurement campaigns must be carried out to ensure progress and in situ atmospheric radiation measurements made available for real-time situational awareness. Furthermore, solar energetic particle forecasting must be improved to move aviation radiation nowcasts to forecasts in order to meet customer requirements for longer lead times for planning and mitigation.

Ground-based synoptic solar observations provide critical contextual data used to model the large-scale state of the heliosphere. The next decade will see a combination of ground-based telescopes and space missions that will study our Sun's atmosphere microscopic processes with unprecedented detail. This white paper describes contextual observations from a ground-based network needed to fully exploit this new knowledge of the underlying physics that leads to the magnetic linkages between the heliosphere and the Sun. This combination of a better understanding of small-scale processes and the appropriate global context will enable a physics-based approach to Space Weather comparable to Terrestrial Weather forecasting.

In recent years there has been a growing interest from the aviation community for space weather radiation forecasts tailored to the needs of the aviation industry.In 2019 several space weather centers began issuing advisories for the International Civil Aviation Organization alerting users to enhancements in the radiation environment at aviation flight levels.Due to a lack of routine observations, radiation modeling is required to specify the dose rates experienced by flight crew and passengers.While mature models exist, support for key observational inputs and further modeling advancements are needed.Observational inputs required from the ground-based neutron monitor network must be financially supported for research studies, and operationally supported to ensure real-time data is available for forecast operations and actionable end user decision making.An improved understanding of the geomagnetic field is required to reduce dose rate uncertainties in regions close to the open/closed geomagnetic field boundary, important for flights such as those between the continental US and Europe which operate in this region.Airborne radiation measurements, which are crucial for model validation and improvement, are lacking, particularly during solar energetic particle events.New measurement campaigns must be carried out to ensure progress.Furthermore, solar energetic particle forecasting must be improved to move aviation radiation nowcasts to forecasts in order to meet customer requirements for longer lead times for planning and mitigation.

Solar Energetic Particle (SEP) events are interesting from a scientific perspective as they are the product of a broad set of physical processes from the corona out through the extent of the heliosphere, and provide insight into processes of particle acceleration and transport that are widely applicable in astrophysics. From the operations perspective, SEP events pose a radiation hazard for aviation, electronics in space, and human space exploration, in particular for missions outside of the Earth's protective magnetosphere including to the Moon and Mars. Thus, it is critical to improve the scientific understanding of SEP events and use this understanding to develop and improve SEP forecasting capabilities to support operations. Many SEP models exist or are in development using a wide variety of approaches and with differing goals. These include computationally intensive physics-based models, fast and light empirical models, machine learning-based models, and mixed-model approaches. The aim of this paper is to summarize all of the SEP models currently developed in the scientific community, including a description of model approach, inputs and outputs, free parameters, and any published validations or comparisons with data.

Abstract The National Oceanic and Atmospheric Administration's Space Weather Prediction Center (NOAA/SWPC) issues several solar radiation storm products: the long standing proton Warnings and Alerts that are based on particle intensity levels observed by the Geostationary Operational Environmental Satellites; and the more recent International Civil Aviation Organization (ICAO) radiation advisories which specify effective dose rates at aviation flight levels. SWPC ICAO advisories are supported by the U.S. Federal Aviation Administration (FAA) CARI‐7A model. In this paper we use CARI‐7A modeling results for the Ground Level Enhancement 69 (GLE69) solar radiation storm which occurred on the 20th of January 2005 to demonstrate the ICAO advisory format. For the onset and peak of GLE69, we find that a severe (SEV) radiation advisory would have been issued for altitudes above 32,000 ft, for polar and mid latitude regions of the northern and southern hemisphere. At lower altitudes, down to 25,000 ft, the moderate (MOD) radiation threshold would have been exceeded. In total, 10 ICAO radiation advisories would have been issued over 6.5 hr. From the retrospective modeling of GLE69, and feedback from users, we identify ways in which the ICAO advisories should be improved.

Extreme Ultraviolet images of the Sun are becoming an integral part of space weather prediction tasks. However, having different surveys requires the development of instrument-specific prediction algorithms. As an alternative, it is possible to combine multiple surveys to create a homogeneous dataset. In this study, we utilize the temporal overlap of SoHO/EIT and SDO/AIA 171 Å surveys to train an ensemble of deep learning models for creating a single homogeneous survey of EUV images for 2 solar cycles. Prior applications of deep learning have focused on validating the homogeneity of the output while overlooking the systematic estimation of uncertainty. We use an approach called `Approximate Bayesian Ensembling' to generate an ensemble of models whose uncertainty mimics that of a fully Bayesian neural network at a fraction of the cost. We find that ensemble uncertainty goes down as the training set size increases. Additionally, we show that the model ensemble adds immense value to the prediction by showing higher uncertainty in test data that are not well represented in the training data.

Three main points: 1. Data Science (DS) will be increasingly important to heliophysics; 2. Methods of heliophysics science discovery will continually evolve, requiring the use of learning technologies [e.g., machine learning (ML)] that are applied rigorously and that are capable of supporting discovery; and 3. To grow with the pace of data, technology, and workforce changes, heliophysics requires a new approach to the representation of knowledge.

Abstract The effects of solar radiation storms at Earth are felt across a number of technology‐based industries. Energetic particles present during these storms impact electrical components on spacecraft, disrupt high frequency radio communications, and pose a radiation risk for passengers and crew on polar flight routes, as well as for astronauts. An essential aspect of space weather forecasting is therefore to predict the occurrence and properties of a solar proton event before it occurs. In this study, we review radiation storm products issued by the National Oceanic and Atmospheric Administration's Space Weather Prediction Center (SWPC) during Solar Cycles 23 and 24. These include three‐day probabilistic proton event forecasts and short‐term Warning and Alert hazard products. We present performance metrics and forecast skill scores for SWPC probabilistic forecasts and Warning products, which can be used as a benchmark for assessing the performance of radiation storm forecast models.