Skip to content

Model for superconducting Tc using chemical formula

  • Description: This is a benchmark to evaluate how accurately an AI model can predict the transition temperature (Tc) of a superconductor from chemical formula using the supercon dataset, which only contains Tc and chemical formula. Here we use mean absolute error (MAE) to compare models with respect to experimental accuracy.


Reference(s): https://doi.org/10.1103/PhysRevMaterials.2.083801, https://epubs.siam.org/doi/abs/10.1137/1.9781611977172.39, https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://www.nature.com/articles/s41598-018-35934-y, https://dl.acm.org/doi/abs/10.1145/3292500.3330703, https://hackingmaterials.lbl.gov/matminer/, https://doi.org/10.1038/s41524-018-0085-8

Model benchmarks

Model name Dataset MAE Team name Dataset size Date submitted Notes
BRNetsupercon_chem5.437NorthWestern_University1641401-14-2023CSV, JSON, run.sh, Info
matminer_rfsupercon_chem4.8511UofT1641405-22-2023CSV, JSON, run.sh, Info
matminer_lgbmsupercon_chem5.1519Matminer1641401-14-2023CSV, JSON, run.sh, Info
ElemNet1supercon_chem5.5901NorthWestern_University1641401-14-2023CSV, JSON, run.sh, Info
IRNet_EFsupercon_chem5.835NorthWestern_University1641401-14-2023CSV, JSON, run.sh, Info
ElemNet2_SCsupercon_chem5.114NorthWestern_University1641401-14-2023CSV, JSON, run.sh, Info
ElemNet2_TLsupercon_chem5.4937NorthWestern_University1641401-14-2023CSV, JSON, run.sh, Info
BNetsupercon_chem5.3076NorthWestern_University1641401-14-2023CSV, JSON, run.sh, Info
matminer_xgboostsupercon_chem4.9295UofT1641405-22-2023CSV, JSON, run.sh, Info
element_fraction_descsupercon_chem5.2921JARVIS1641401-14-2023CSV, JSON, run.sh, Info
cfid_chemsupercon_chem5.0326JARVIS1641401-14-2023CSV, JSON, run.sh, Info