Information-theoretic frameworks for Machine Learning on Solar Data

Diplôme Thèse Information-theoretic frameworks for Machine Learning on Solar Data eng 2024 2024 author Ullmann Denis Adrien 0000-0002-7179-005X 881533 director Voloshynovskyy Svyatoslav 514089 Département d'informatique (DINFO) 10.13097/archive-ouverte/unige:177717 urn:nbn:ch:unige-1777176 Sc. 5822 This thesis is at the intersection of Information Theory (IT), solar physics, signal processing and Machine Learning (ML). It discusses the evolution of astronomy, highlighting the influence of technological advancements that, together with statistics, and the rise of Big Data in modern astronomy, enable efficient space exploration. It emphasizes the challenges and opportunities presented by ML in analyzing vast astronomical datasets, particularly focusing on solar data from NASA’s IRIS satellite. The thesis explores IT and ML applications for several detection problems, classification in decentralized systems, and forecasting multivariate data, such as solar activity. It addresses the challenges of astronomical data, with the design of sufficient statistics and information bottleneck formulations. The thesis emphasizes the importance of these formulations to enhance the scientific value learned on large collected datasets that are often multidimensional, sparse, weekly annotated, and processed with limited dedicated hardware as, for instance, in space-based instruments. Information Bottleneck Detection Decentralized classification Multivariate time series forecast Solar data Interface Region Imaging Spectrograph (IRIS) Machine learning Signal processing Information theory Rate-distortion theory Dewey 025.063 Swiss National Science Foundation Machine Learning based Analytics for Big Data in Astronomy 167158 CH Programmes 32 Département d'informatique 18 13 Centre universitaire d'informatique 0D3 false 933 Stochastic Information Processing Group 17fb5496-9ab9-48cd-b620-3a91d601bd2d Thesis Public PhD_Thesis_Publication.pdf 22853273 application/pdf CC BY-NC 2084770040e08b25df284a6a762d36176acbde834a4c2c0a2cc974050de6d7a5 80216da6-ae63-4775-bef8-2d623168508f Imprimatur Public Imprimatur.pdf 38493 application/pdf 5f04434adadaaa2adb0bd71b67ce0360510f7a68d5f5863cdea17c7c5d29a4d3 openAccess Faculté des sciences / Département d'informatique Centres et instituts / Centre universitaire d'informatique

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Information-theoretic frameworks for Machine Learning on Solar Data				2024	358	224

Archive ouverte UNIGE

Ullmann, Denis Adrien

account_balance Affiliation entities

Research groups

Affiliation entities