Understanding galaxy evolution and its interplay with physical and cosmological parameters is fundamental to extragalactic astronomy and cosmology. Building upon the foundations of galaxy classification and environmental effects explored in the previous edition of this workshop, we now adopt a more holistic approach that leverages subtle observational features often overlooked in traditional analyses.

Modern astronomy provides an unprecedented wealth of data spanning multiple observational regimes—from standard photometry and spectroscopy to integral field spectroscopy and deep imaging sensitive to low surface brightness structures. Machine learning methodologies have emerged as powerful tools to extract meaningful patterns from these diverse datasets, enabling new insights into galaxy formation, evolution, and characterization across cosmic time.

The combination of data from established facilities (HST, JWST, ALMA, VLT) with upcoming surveys from next-generation observatories (Euclid, Vera C. Rubin Observatory, ARRAKIHS) presents both extraordinary opportunities and significant challenges. While advanced machine learning approaches can process and analyze data at unprecedented scales, their results require rigorous validation and physical interpretation to ensure robust scientific conclusions.

This workshop will bring together ML and galaxy experts to review the current state of the field, discuss recent breakthroughs, and explore new avenues opened by ongoing and future surveys from ground-based and space-borne facilities. Beyond showcasing technical advances, we aim to reflect critically on machine learning's impact: distinguishing between its capacity to accelerate and scale traditional methodologies, and its potential to fundamentally transform our questions and approaches to understanding galaxy evolution.