Machine Learning and Computer Vision for the Solar-Terrestrial Environment: Space Weather, Atmospheric Science, and Next-Generation Instrumentation

The rapid growth of artificial intelligence (AI), machine learning (ML), and computer vision (CV) is transforming how scientific data are acquired, processed, and interpreted across the solar-terrestrial system. These techniques are opening new possibilities for extracting physical information from increasingly complex observations, improving forecasting capabilities, and optimizing scientific instrumentation for current and future missions.This Research Topic is organized in conjunction with two international meetings hosted by the Brazilian National Institute for Space Research (INPE) in São José dos Campos, Brazil: the GSST/CBERS-5 International Symposium on Machine Learning in Heliophysics and Space Weather (SolarAI), 17–21 August 2026, which includes a mini-ISWAT working session of the COSPAR International Space Weather Action Teams, and the 4th International Workshop on Equatorial Plasma Bubbles (EPB-4), 14–18 September 2026. These meetings bring together researchers, engineers, and data scientists working at the intersection of artificial intelligence and solar-terrestrial physics, spanning the solar atmosphere, the heliosphere, and the ionosphere-thermosphere system.The symposium highlights scientific and technological opportunities associated with the Galileo Solar Space Telescope (GSST) and the China-Brazil Earth Resources Satellite-5 (CBERS-5) missions, while EPB-4 addresses one of the most consequential space-weather effects at low latitudes, ionospheric plasma bubbles and their impact on trans-ionospheric radio propagation and GNSS positioning, an area where AI-based forecasting is becoming a decisive tool. This Research Topic extends those discussions into a lasting, peer-reviewed scientific collection open to the broader research community.We invite original research, reviews, methods papers, perspectives, and technology reports addressing the development and application of AI across the solar-terrestrial chain: from solar magnetism and eruptive activity, through the heliosphere and magnetosphere, to the ionosphere and operational space weather forecasting. We particularly encourage work that combines machine learning with physical knowledge for example, physics-informed neural networks and neural operators, and that explicitly addresses interpretability, uncertainty quantification, and validation against independent data.We also welcome contributions on the instrumentation and enabling technologies that make this science possible: onboard and autonomous AI systems, optical engineering and photonics, sensors, and the high-performance computing infrastructure needed to process next-generation observatory and satellite data. Submissions extending these methods to closely related areas, such as Earth observation or atmospheric science, are welcome where they are directly relevant to the solar-terrestrial environment, though this is not the primary focus of the collection.Contributions may address, but are not limited to, the following topics:• Machine learning and computer vision for solar magnetism, eruptive activity, and heliospheric structures.• Space physics: solar wind–magnetosphere coupling, particle acceleration, and the ionosphere-thermosphere system, including equatorial plasma bubbles.• Physics-informed machine learning, neural operators, surrogate models, and uncertainty quantification.• Space weather forecasting, data assimilation, digital twins, and research-to-operations.• Next-generation instrumentation: onboard AI, photonics and optical systems, sensors, and high-performance computing.Frontiers sponsored the conference from which the authors for this collection were selected. This does not influence the editorial decisions and peer review process, which maintain high standards of rigor and impartiality. The Topic Editors report no competing interests related to this Research Topic. Topic editors: Luis Eduardo Antunes Vieira, Hui Li, David Gary Sibeck, Franciele Carlesso, Jose Paulo Marchezi, Ligia Alves Da Silva, Marcos Silveira, Cristiano Wrasse, Jiaben Lin, David B. Jess Source: https://www.frontiersin.org/research-topics/83541/machine-learning-and-computer-vision-for-the-solar-terrestrial-environment-space-weather-atmospheric-science-and-next-generation-instrumentation