The solar wind includes charged particles and magnetic fields emanating from the Sun’s outer layers. Space weather results from interactions between the solar wind and the Earth’s geomagnetic field. Therefore, it is important to understand the detailed processes that occur within the solar wind. This project explores the physics of the solar wind through analysis of satellite observations and development of machine learning models. Undergraduate and graduate students will be trained in interdisciplinary research including space plasma physics and machine learning techniques. Also, an early career post-doctoral researcher will be supported. This project is co-funded by the Directorate for Geosciences to support AI/ML advancement in the geosciences.<br/><br/>Motivated by new observations with NASA’s Parker Solar Probe (PSP) mission, the science objective of this project is to investigate the heating and acceleration of the solar wind plasma associated with proton and alpha particle temperature anisotropy evolution, their relative drift and beaming velocities, and the associated ion kinetic instabilities. The work will focus on the effects of proton beams, detected by PSP/SPAN-I on the nonlinear evolution of the magnetosonic instability. The magnetic wave spectra and energy partition between the ions and the electromagnetic fields will be determined focusing on ion kinetic scales. The team will analyze the PSP/SPAN-I data of the proton and alpha particle velocity distribution functions (VDFs) with beams during perihelia encounters, as well as plasma moments such as density, anisotropic temperature, and alpha relative abundance data. The FIELDS instrument will provide the corresponding kinetic wave activity magnitude, spectra, and polarizations. Guided by the observations, the team will use 2.5D and 3D hybrid-particle-in-cell (hybrid-PIC) models of kinetic protons and alpha particles with background electron fluid in an expanding box model to study the kinetic instabilities driven by initially unstable non- Maxwellian VDFs such as super-Alfvénic beams and ion relative drifts in the inner solar wind. The models will be used to calculate the physical properties and nonlinear evolution of the proton and alpha particle populations in the expanding solar wind, such as the ion drift speeds, anisotropic temperatures, magnetic energy and spectra, and the associated plasma heating processes. They will develop Artificial Intelligence Machine Learning (AI/ML) methods to automate the detection of unstable VDFs and classification of the kinetic instabilities using semi-supervised (i.e., labeled, and unlabeled data) and supervised (i.e., labeled data) ML methods such as multi-layered (i.e., deep) neural networks (DNNs).<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.