Tutorials

Jupyter notebook tutorials demonstrating AmorphGen workflows.

Start here:

Tutorial	Description	Backend	System
Tutorial 1: Quick-start tutorial	Orientation: what AmorphGen does, the three workflows, decision tree, one live demo	CHGNet	a-SiO₂

Workflow tutorials — each tutorial reports its own measured wall time on the CPU it was validated on:

Tutorial	Description	Backend	System
Tutorial 2: Zero-config random gen	Composition is the only input; auto minsep / density / target CN / oxidation state; CHGNet relax + save each structure	CHGNet	Si, SiO₂, In₂O₃, CdTe, AlN, LiCl, TiO₂, Cu
Tutorial 3: Explicit control + ensemble analysis	The opposite end of T2: explicit minsep (from crystal-phase bond lengths) + explicit target density (from cited amorphous-thin-film references). 5-structure ensembles per system; quantitative RDF / energy / CN / bond-angle analysis vs the crystalline reference	MACE	In₂O₃, TiO₂, Al₂O₃, Ga₂O₃
Tutorial 4: Melt-and-quench	Full 7-stage pipeline	CHGNet (CPU) / MACE (GPU)	SiO₂
Tutorial 5: Hybrid batch quench	Random gen → equilibrate → batch quench	CHGNet	TiO₂
Tutorial 6: Classical potentials	Buckingham+Coulomb relaxation, hybrid workflow	Classical	SiO₂, Al₂O₃, TiO₂

Application case studies (assume familiarity with the workflow tutorials):

Tutorial	Description	Backend	System
Tutorial 7: Dimer dissociation kinetics	O–O peroxide-defect dissociation in amorphous oxide; Arrhenius temperature scan	MACE	In₂O₃