In our universe, galaxies typically have neighboring galaxies and close companions. A galaxy’s local environment plays a key role in shaping both its history and its future evolution. However, measuring a galaxy’s environment is often challenging and requires advanced astronomical observations. This project is part of a new phase of research based on large-scale observational efforts, such as the NSF/DOE Rubin Legacy Survey of Space and Time (LSST). By combining large amounts of data from different telescopes, this project will identify key relationships between galaxies and their environments. For example, whether galaxies are located in dense clusters, filaments, or empty regions of space. Given the large volume of data involved, this project will also develop a new set of machine learning tools to analyze these datasets. In particular, it will develop a deep learning model using a three-dimensional (3D) convolutional neural network (CNN), a method commonly used in biomedical imaging, to analyze large datasets obtained from the Rubin/LSST survey and other telescopes. In addition, this project will provide foundational research training, with activities open to all undergraduate astronomy majors at the University of Wisconsin - Madison. These training opportunities will include, among other offerings, an introduction to scientific programming with Python and data visualization techniques. By providing both research experience and foundational skill development, the project will help prepare students for future careers both within and beyond academia. This program will integrate data obtained with the 4MOST spectrograph (4HS Survey), Rubin/LSST, and Euclid. In particular, the 4MOST/4HS Survey will observe a nearly complete sample of 5.8 million nearby galaxies in the southern hemisphere. By combining a sophisticated machine learning model, trained on state-of-the-art cosmological hydrodynamical simulations and verified using weak gravitational lensing, with nove