Predicting thermodynamical stability for 2D materials using machine learning
This competition is part of the course
[10316 Materials design with machine learning and artificial intelligence](https://kurser.dtu.dk/course/10316)
at DTU January 2023. During the first two weeks you have learned the basics of programming and machine learning, and now it's time to apply these skills in a real world problem.
The objective of the competition is to build a machine learning model that predicts the heat of formation (hform) of 2D materials. Heat of formation is the energy of the material with respect to the standard states of its constituent element
The dataset for the competition consists of 12,000 2D materials along with their DFT-calculated heat of formation. The structures are provided as
[Atoms](https://wiki.fysik.dtu.dk/ase/ase/atoms.html)
objects containing the atomic numbers and positions for the structure. The dataset is divided into two sets (66.6% for training and 33.3% for testing). For the test set, only the structures  are provided (and not the heat of formation).