Thesis supervisor: Róbert Erdélyi
Location of studies (in Hungarian): Dept of Astronomy, Eotvos University Abbreviation of location of studies: ELTE
Description of the research topic:
"Coronal Mass Ejections (CMEs) are one of the two major eruptive phenomena (the other ones are flares) occurring within the solar atmosphere with determining effects on the heliosphere.
This project will systematically combine Machine Learning, Artificial Intelligence and Computer Vision techniques, which are underpinning and supporting e.g. the world-famous Google Alpha Go, with the intricate physics behind these events. Based on the vast amount of data available from the Sun and inter-planetary space, this interdisciplinary study will have significant advantage over traditional methods, including the CPU-expensive numerical simulations and the over-simplified empirical methods. This project, ultimately, will offer fast, accurate and reliable prediction on CME arrival times and provide a fast and reliable warning of to what extent our Earth will be affected by a specific eruption. All the above will enable more than enough practical warning time for the government, military and related industries to take necessary mitigating actions to minimize the corresponding socio-economic losses.
Unlike traditional methods, the AI-ML techniques take a bulk of direct observations as input, use no presumed physics and find underlying “hidden” relationships. This different and highly innovative approach will not only help us to avoid the limit of the current relevant maths/physics, but also enables us to unveil new physics within the bounds of laws describing these solar eruptive events. The research of this project will therefore benefit in both opening new avenues in the understanding of our proxy plasma laboratory – the Sun, and contributing to the development of the associated maths, physics and instrumental engineering."
Required language skills: English Further requirements: This project requires interest in taking observations by either ground- or space-based telescope. Therefore it is expected that the student may undertake such work at ground-based solar observatories. Further, the project also likely requires collabo
Number of students who can be accepted: 1
Deadline for application: 2024-05-31
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
