Within the Directorate for Science at its Headquarters in Garching, near Munich, Germany, ESO is inviting university students to apply to our ESO Summer Research Programme. The ESO Summer Research Programme is an opportunity for university students from science, technology, engineering, and mathematics (STEM) fields who have not yet started a PhD programme and have completed at least two years of their degree.

Within the scope of this programme, there are seven exciting individual projects topics to choose from. Please visit https://eso.org/sci/meetings/2026/SummerResearch2026.html to review all seven project topics, as you can only apply to one.

Applications for the ESO Summer Research Programme will be considered from students taking any astronomy, physical science, computer science or mathematical degree subjects. However, it is expected that students have some knowledge of physics, programming, data analysis techniques and, preferably, astronomy.

Students will be selected for the programme based on their academic achievements, research potential and likelihood to significantly benefit from the experience. Particular attention will be given to the motivation of the students to join the programme and specific motivation for Project G:

Project G: From Molecular Lines to Physical Conditions: Teaching Neural Networks to Read the Interstellar Medium

Supervisors: Lukas Neumann, Caterina Bracci, Francesco Belfiore

A major challenge in understanding star formation is determining the physical conditions of the interstellar medium, particularly the dense molecular gas closely associated with active star-forming regions. The most direct method relies on far-infrared dust emission, which is well mixed with the gas and can be modeled to infer temperature and column density. However, far-infrared observations require space-based facilities across infrared wavelengths that are currently not available and typically offer much lower angular resolution compared to modern radio and optical telescopes.

An alternative approach uses molecular line emission in the radio/millimeter regime, accessible with high-resolution observatories such as the IRAM 30m telescope and ALMA. Molecular lines are sensitive to a wide range of physical parameters -- including density, temperature, chemistry, and radiative transfer --- but this sensitivity creates significant complexity, making traditional forward modeling extremely challenging.

The growing availability of machine-learning techniques presents a powerful new way to tackle this problem. In this project, the student will explore a neural network-based framework -- using the tensorflow package in python -- to infer physical conditions of molecular gas from multi-line observational data. The model will be trained using a suite of molecular line data from an IRAM 30m large program (LEGO), combined with Herschel dust observations that provide benchmark physical parameters. Once developed and validated, this approach can be applied across Galactic star-forming regions and extended to high-resolution extragalactic observations from facilities such as ALMA.