Lectures & Exercises
Lectures
Day 1
-
NanoSpace and AI in Astrochemistry TS Overview – Aníbal García-Hernández and Edward Goldwyn
-
Fundamentals of ML
– Miguel Caro
- Basics of Neural Networks – Xabier Pérez Couto
Day 2
-
Gaussian Processes and Regressors
– Mads-Peter V. Christiansen
-
ML for Interatomic Potentials
– Rina Ibragimova
-
Atomistic Modelling for Radiation Damage in Space
– Andrea Sand
- ML for Chemical Intuition – Brett McGuire
Day 3
- ML for Radio Interferometry – Ryan Loomis
- ML Binding Energies of Astrochemical Molecules – Johannes Heyl
- Neural Networks for Astrochemistry – Lorenzo Branca
Day 4
- Interpretable ML Techniques for Astrochemistry – Johannes Heyl
- Intelligent Crystal and Molecular Structure Search Algorithms – Isabelle Braems
Exercises
This git repository contains the instructions and files required for the practical hands-on sessions of the COST NanoSpace – AI in Astrochemistry Training School 2025 . We have the following four hands-on tutorials or exercises (see ' Documentation ' ):
1) Basics of neural networks (NN) (AI_basics_ann) – Xabier Pérez Couto
2) Machine learning (ML) for Interatomic Potentials (ML_for_interatomic_potentials) – Rina Ibragimova
3) Machine learning (ML) in astrochemistry (Surrogate-notebook) – Lorenzo Branca
4) Bayesian Optimization with Gaussian Processes (Bayesian_and_gps) – Mads-Peter V. Christiansen