search

CederGroupHub / chgnet

Pretrained universal neural network potential for charge-informed atomistic modeling https://chgnet.lbl.gov
https://doi.org/10.1038/s42256-023-00716-3
Other
220 stars 60 forks source link

Energy error #92

Closed Yong-Q closed 10 months ago

Yong-Q commented 10 months ago

Email (Optional)

3244608729@qq.com

Version

0.3.0

Which OS(es) are you using?

What happened?

The result of the test was" CHGNet predicted energy (eV/atom):-4.5642852783203125" but ture is "-1.119ev/atom"

Code snippet

prediction = chgnet.predict_structure(structure)

for key, unit in [
    ("energy", "eV/atom"),
    ("forces", "eV/A"),
    ("stress", "GPa"),
    ("magmom", "mu_B"),
]:
    print(f"CHGNet-predicted {key} ({unit}):\n{prediction[key[0]]}\n")

Log output

No response

Code of Conduct

Yong-Q commented 10 months ago

The predicted structure is mp-696138

BowenD-UCB commented 10 months ago

If you're get the -1.119 eV/atom from Materials Project This value from MP is formation energy, not the energy that CHGNet is predicting.

Please read carefully the terminologies from MP and CHGNet paper before reporting the bug in the github. if you're not sure, please raise these questions to Discussion.