Skip to content

Model for AGRA CO dataset

  • Description: This is a benchmark to evaluate how accurately an AI model can predict the energy of adsorption of CO using the Automatic graph representation algorithm (AGRA) dataset. The dataset contains different types of heterogeneous catalysts. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://pubs.aip.org/aip/aml/article/1/3/036103/2900763/Automatic-graph-representation-algorithm-for


Reference(s): https://doi.org/10.1063/5.0140487, https://www.nature.com/articles/s41524-021-00650-1, https://pubs.rsc.org/en/content/articlehtml/2023/dd/d2dd00096b

Model benchmarks

Model nameDataset MAE Team name Dataset size Date submitted Notes
alignnff_pretrained_wt0.1AGRA_CO20.2772JARVIS19301-14-2023CSV, JSON, run.sh, Info
MACE_pretrainedAGRA_CO26.6027ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-AGRA_OH-test-mae.csv.zipAGRA_CO2.4536ALIGNN19301-14-2023CSV, JSON, run.sh, Info
MATGL_pretrainedAGRA_CO19.7591ALIGNN19301-14-2023CSV, JSON, run.sh, Info
alignn_modelAGRA_CO0.1349ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-tinnet_O-test-mae.csv.zipAGRA_CO2.4926ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-tinnet_N-test-mae.csv.zipAGRA_CO4.2395ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-AGRA_COOH-test-mae.csv.zipAGRA_CO1.2564ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-AGRA_CHO-test-mae.csv.zipAGRA_CO0.4694ALIGNN19301-14-2023CSV, JSON, run.sh, Info
CHGNet_pretrainedAGRA_CO28.7804ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-AGRA_CO-test-mae.csv.zipAGRA_CO0.1082ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-tinnet_OH-test-mae.csv.zipAGRA_CO0.8095ALIGNN19301-14-2023CSV, JSON, run.sh, Info
Out-AI-SinglePropertyPrediction-ead-AGRA_O-test-mae.csv.zipAGRA_CO2.4271ALIGNN19301-14-2023CSV, JSON, run.sh, Info