Ice plays a crucial role on Earth, from its presence in the polar regions to its impact on global climate and sea levels. First principle calculations, which use fundamental principles of physics to model the behavior of atoms and molecules, are commonly used to study ice. However, these calculations do not accurately predict the temperatures and pressures at which ice melts. In this talk, PI Sigbjørn Bore will talk about how the project group is working towards truly capturing ice from first principles by combining machine learning and first principles.