Search

Solar Energetic Particles (SEPs) form a critical component of Space Weather. The complex, intertwined dynamics of SEP sources, acceleration, and transport make their forecasting very challenging. Yet, information about SEP arrival and their properties (e.g., peak flux) is crucial for space exploration on many fronts. We have recently introduced a novel probabilistic ensemble model called the Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP). Its primary aim is to forecast the occurrence and physical properties of SEPs. The occurrence forecasting, thoroughly discussed in a preceding paper (MEMPSEP‐I by Chatterjee et al., 2024a, https://doi.org/10.1029/2023sw003568), is complemented by the work presented here, which focuses on forecasting the physical properties of SEPs. The MEMPSEP model relies on an ensemble of Convolutional Neural Networks, which leverage a multi‐variate data set comprising full‐disc magnetogram sequences and numerous derived and in‐situ data from various sources (MEMPSEP‐III by Moreland et al., 2024, https://doi.org/10.1029/2023SW003765). Skill scores demonstrate that MEMPSEP exhibits improved predictions on SEP properties for the test set data with SEP occurrence probability above 50%, compared to those with a probability below 50%. Results present a promising approach to address the challenging task of forecasting SEP physical properties, thus improving our forecasting capabilities and advancing our understanding of the dominant parameters and processes that govern SEP production. Plain Language Summary: Solar Energetic Particles (SEPs) are important for understanding space weather. SEPs are hard to predict because they come from various sources and go through complicated processes. However, knowing when and how intense SEPs are in space is crucial for things like space exploration. In this work, we created a new model called MEMPSEP to help predict when and what the properties of these SEPs will be when they are detected. We used data from different sources to train the model on how to make these predictions. The results show that MEMPSEP is better at predicting the properties of SEPs when the chances of them happening are more than 50%. This is a significant step forward in improving our ability to forecast SEPs and understanding the factors that influence them in space. Key Points: An end‐to‐end deep neural network model ensemble, trained on remote sensing and in situ data sets, is used to forecast SEP propertiesModel ensemble maximizes the utilization of an imbalanced data set and enhances forecasting confidence with uncertainty estimatesSolar energetic particle occurrence probabilities are utilized as weights in the loss function to enhance regression performance for events [ABSTRACT FROM AUTHOR]

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 (>C‐class 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 spacecraft. We also collect remote sensing data from instruments onboard the Solar Dynamic Observatory, Solar and Heliospheric Observatory, 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 data set created from multiple publicly available observation sources that is validated, cleaned, and carefully curated for our ML pipeline. The data set has been used to drive the newly‐developed Multivariate Ensemble of Models for Probabilistic Forecast of SEPs (MEMPSEP; see MEMPSEP‐I (Chatterjee et al., 2024, https://doi.org/10.1029/2023SW003568) and MEMPSEP‐II (Dayeh et al., 2024, https://doi.org/10.1029/2023SW003697) for accompanying papers). Plain Language Summary: We present a new data set that uses observations from multiple spacecraft observing the Sun and the interplanetary space around it. This data is connected to the processes that create solar energetic particles (SEPs). SEP events pose threats to both astronauts and assets in space. The data set contains 252 solar flare events that caused SEPs and 17,542 that do not. For each event, we gather information about the local space environment around the sun, such as energetic protons and electrons, the conditions of the solar wind, the magnetic field, and remote solar imaging data. We use instruments from NOAA's Geostationary Operational Environmental Satellites (GOES) and the Advanced Composition Explorer spacecraft, as well as data from the Solar Dynamic Observatory, the Solar and Heliospheric Observatory, and the Wind solar radio instrument WAVES. This data set is designed to be used in machine learning (ML), with a focus on predicting the occurrence and properties of SEP events. We detail each observation obtained from publicly available sources, and the data treatment processes used to validate the reliability and usefulness for ML applications. Key Points: Machine learning oriented data set for predicting the occurance and properties of solar energetic particle eventsMultivariate remote sensing and in‐situ observationsContinuous data set spanning several decades [ABSTRACT FROM AUTHOR]

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. Plain Language Summary: Solar Energetic Particles (SEPs) play an important role in modulating near‐Earth space weather environments affecting communication satellites and posing radiation hazards to astronauts. Because of the complex processes involved reliable early forecast of SEP events still remains a challenge. In this paper, we present an ensemble of models that ingest both solar images and parameters measured by in situ instruments to reliably forecast the chance of SEP event occurrence. Our approach transforms a "yes"/"no" forecast to the probability of event occurrence and provides the users additional flexibility in prioritizing their forecasting goals. Our ensemble of models utilizes the fact that SEP events are much rarer than non‐events and generate uncertainties on predicted probabilities. These uncertainties add value in providing a measure of trust to users in forecasting outcomes. Key Points: End‐to‐End Deep Neural Network model‐ensemble trained on remote sensing + in situ data set for forecast of SEP occurrenceUsage of model ensemble maximizes the use of an imbalanced data set and brings forecasting confidence with uncertainty estimatesCalibration of model outcome to true probability optimizes the forecast reliability acting as a means to step away from the binary forecast [ABSTRACT FROM AUTHOR]

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 FROM AUTHOR]