diff --git a/docs/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride.md b/docs/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride.md new file mode 100644 index 000000000..83d8745df --- /dev/null +++ b/docs/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride.md @@ -0,0 +1,20 @@ +# Model for Superconducting Tc of High Pressure Hydrides + - Description: This is a benchmark to evaluate how accurately an AI model can predict the superconducting transition temperature of hydride materials under pressure. The dataset contains the structures and DFT calculated Tc of the hydride materials under various amounts of pressure. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94

Reference(s): [https://www.nature.com/articles/s41524-020-00440-1](https://www.nature.com/articles/s41524-020-00440-1), [https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94](https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94), [https://doi.org/10.48550/arXiv.2305.11842](https://doi.org/10.48550/arXiv.2305.11842)
+ + +

Model benchmarks

+ + + + + + + + + + + + + + +
Model nameDatasetMAETeam nameDataset sizeDate submittedNotes
alignn_hydride_supercondft_3d12.3099ALIGNN95305-16-2024CSV, JSON, run.sh, Info
\ No newline at end of file diff --git a/docs/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride_plus_bulk.md b/docs/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride_plus_bulk.md new file mode 100644 index 000000000..ff5fd7d84 --- /dev/null +++ b/docs/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride_plus_bulk.md @@ -0,0 +1,20 @@ +# Model for Superconducting Tc of High Pressure Hydrides + - Description: This is a benchmark to evaluate how accurately an AI model can predict the superconducting transition temperature of hydride materials under pressure. The dataset contains the structures and DFT calculated Tc of the hydride materials under various amounts of pressure plus the DFT dataset of bulk hydride materials. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://iopscience.iop.org/article/10.1088/2752-5724/ad4a95, https://www.nature.com/articles/s41524-022-00933-1

Reference(s): [https://www.nature.com/articles/s41524-020-00440-1](https://www.nature.com/articles/s41524-020-00440-1), [https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94](https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94), [https://doi.org/10.48550/arXiv.2305.11842](https://doi.org/10.48550/arXiv.2305.11842)
+ + +

Model benchmarks

+ + + + + + + + + + + + + + +
Model nameDatasetMAETeam nameDataset sizeDate submittedNotes
alignn_hydride_supercon_plusbulkdft_3d7.9619ALIGNN199305-16-2024CSV, JSON, run.sh, Info
\ No newline at end of file diff --git a/jarvis_leaderboard/benchmarks/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride.json.zip b/jarvis_leaderboard/benchmarks/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride.json.zip new file mode 100644 index 000000000..0f88c1902 Binary files /dev/null and b/jarvis_leaderboard/benchmarks/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride.json.zip differ diff --git a/jarvis_leaderboard/benchmarks/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride_plus_bulk.json.zip b/jarvis_leaderboard/benchmarks/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride_plus_bulk.json.zip new file mode 100644 index 000000000..f0e2c5596 Binary files /dev/null and b/jarvis_leaderboard/benchmarks/AI/SinglePropertyPrediction/dft_3d_Tc_supercon_hydride_plus_bulk.json.zip differ diff --git a/jarvis_leaderboard/benchmarks/benchmark_dois.json b/jarvis_leaderboard/benchmarks/benchmark_dois.json index 44ca02c68..30489a82c 100644 --- a/jarvis_leaderboard/benchmarks/benchmark_dois.json +++ b/jarvis_leaderboard/benchmarks/benchmark_dois.json @@ -203,6 +203,16 @@ "https://www.nature.com/articles/s41524-020-00440-1", "https://doi.org/10.48550/arXiv.2305.11842" ], + "dft_3d_Tc_supercon_hydride.json.zip": [ + "https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94", + "https://www.nature.com/articles/s41524-020-00440-1", + "https://doi.org/10.48550/arXiv.2305.11842" + ], + "dft_3d_Tc_supercon_hydride_plus_bulk.json.zip": [ + "https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94", + "https://www.nature.com/articles/s41524-020-00440-1", + "https://doi.org/10.48550/arXiv.2305.11842" + ], "dft_3d_ph_heat_capacity.json.zip": [ "https://www.nature.com/articles/s41524-020-00440-1", "https://doi.org/10.48550/arXiv.2305.11842" diff --git a/jarvis_leaderboard/benchmarks/descriptions.csv b/jarvis_leaderboard/benchmarks/descriptions.csv index 28628e174..3b6bb8662 100644 --- a/jarvis_leaderboard/benchmarks/descriptions.csv +++ b/jarvis_leaderboard/benchmarks/descriptions.csv @@ -46,6 +46,8 @@ AI,SinglePropertyPrediction,qm9_std_jctc_U,This is a benchmark to evaluate how a AI,SinglePropertyPrediction,qm9_std_jctc_U0,This is a benchmark to evaluate how accurately an AI model can predict the internal energy (U0) at 0 K using the QM9 dataset. The dataset contains the structures and properties of molecules. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://www.nature.com/articles/sdata201422, AI,SinglePropertyPrediction,qm9_std_jctc_ZPVE,This is a benchmark to evaluate how accurately an AI model can predict the zero-point vibrational energy (ZPVE) using the QM9 dataset. The dataset contains the structures and properties of molecules. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://www.nature.com/articles/sdata201422, AI,SinglePropertyPrediction,qm9_std_jctc_alpha,This is a benchmark to evaluate how accurately an AI model can predict the isotropic polarizability using the QM9 dataset. The dataset contains the structures and properties of molecules. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://www.nature.com/articles/sdata201422, +AI,SinglePropertyPrediction,dft_3d_Tc_supercon_hydride,This is a benchmark to evaluate how accurately an AI model can predict the superconducting transition temperature of hydride materials under pressure. The dataset contains the structures and DFT calculated Tc of the hydride materials under various amounts of pressure. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94, +AI,SinglePropertyPrediction,dft_3d_Tc_supercon_hydride_plus_bulk,"This is a benchmark to evaluate how accurately an AI model can predict the superconducting transition temperature of hydride materials under pressure. The dataset contains the structures and DFT calculated Tc of the hydride materials under various amounts of pressure plus the DFT dataset of bulk hydride materials. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://iopscience.iop.org/article/10.1088/2752-5724/ad4a95, https://www.nature.com/articles/s41524-022-00933-1", AI,SinglePropertyPrediction,dft_3d_avg_elec_mass,This is a benchmark to evaluate how accurately an AI model can predict the average electron mass using the JARVIS-DFT (dft_3d) dataset. The dataset contains different types of chemical formula and atomic structures. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy., AI,SinglePropertyPrediction,dft_3d_avg_hole_mass,This is a benchmark to evaluate how accurately an AI model can predict the average hole mass using the JARVIS-DFT (dft_3d) dataset. The dataset contains different types of chemical formula and atomic structures. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy., AI,SinglePropertyPrediction,qmof_bandgap,This is a benchmark to evaluate how accurately an AI model can predict the bandgap using the QMOF dataset. The dataset contains different types of metal organic frameworks. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://github.com/Andrew-S-Rosen/QMOF, @@ -295,4 +297,4 @@ FF,SinglePropertyPrediction,biobench_deltaF,This is a benchmark to evaluate how FF,SinglePropertyPrediction,biobench_left_handed_population,This is a benchmark to evaluate how accurately an FF model can predict bulk free energy difference of peptides., FF,SinglePropertyPrediction,biobench_right_handed_population,This is a benchmark to evaluate how accurately an FF model can predict bulk free energy difference of peptides., FF,SinglePropertyPrediction,lj_2d_liquid_viscosity,This is a benchmark to evaluate how accurately an FF model can predict viscosity of Lennard-Jones liquid., -QC,EigenSolver,dft_3d_electron_bands_JVASP_816_Al_WTBH,This is a benchmark to evaluate how accurately an QC model can predict electronic bands of aluminum (JVASP-816) produced using Wannier tight binding Hamiltonian approach., +QC,EigenSolver,dft_3d_electron_bands_JVASP_816_Al_WTBH,This is a benchmark to evaluate how accurately an QC model can predict electronic bands of aluminum (JVASP-816) produced using Wannier tight binding Hamiltonian approach., \ No newline at end of file diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon/.DS_Store b/jarvis_leaderboard/contributions/alignn_hydride_supercon/.DS_Store new file mode 100644 index 000000000..7b954559d Binary files /dev/null and b/jarvis_leaderboard/contributions/alignn_hydride_supercon/.DS_Store differ diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon/AI-SinglePropertyPrediction-Tc_supercon_hydride-dft_3d-test-mae.csv.zip b/jarvis_leaderboard/contributions/alignn_hydride_supercon/AI-SinglePropertyPrediction-Tc_supercon_hydride-dft_3d-test-mae.csv.zip new file mode 100644 index 000000000..61f3607e8 Binary files /dev/null and b/jarvis_leaderboard/contributions/alignn_hydride_supercon/AI-SinglePropertyPrediction-Tc_supercon_hydride-dft_3d-test-mae.csv.zip differ diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon/config.json b/jarvis_leaderboard/contributions/alignn_hydride_supercon/config.json new file mode 100644 index 000000000..d1263b17c --- /dev/null +++ b/jarvis_leaderboard/contributions/alignn_hydride_supercon/config.json @@ -0,0 +1,53 @@ +{ + "version": "112bbedebdaecf59fb18e11c929080fb2f358246", + "dataset": "user_data", + "target": "target", + "atom_features": "cgcnn", + "neighbor_strategy": "k-nearest", + "id_tag": "jid", + "random_seed": 123, + "classification_threshold": null, + "n_val": null, + "n_test": null, + "n_train": null, + "train_ratio": 0.8, + "val_ratio": 0.1, + "test_ratio": 0.1, + "target_multiplication_factor": null, + "epochs": 300, + "batch_size": 16, + "weight_decay": 1e-05, + "learning_rate": 0.001, + "filename": "sample", + "warmup_steps": 2000, + "criterion": "mse", + "optimizer": "adamw", + "scheduler": "onecycle", + "pin_memory": false, + "save_dataloader": false, + "write_checkpoint": true, + "write_predictions": true, + "store_outputs": true, + "progress": true, + "log_tensorboard": false, + "standard_scalar_and_pca": false, + "use_canonize": true, + "num_workers": 0, + "cutoff": 8.0, + "max_neighbors": 12, + "keep_data_order": false, + "model": { + "name": "alignn", + "alignn_layers": 4, + "gcn_layers": 4, + "atom_input_features": 92, + "edge_input_features": 80, + "triplet_input_features": 40, + "embedding_features": 64, + "hidden_features": 256, + "output_features": 1, + "link": "identity", + "zero_inflated": false, + "classification": false + } +} diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon/metadata.json b/jarvis_leaderboard/contributions/alignn_hydride_supercon/metadata.json new file mode 100644 index 000000000..7cc8501fd --- /dev/null +++ b/jarvis_leaderboard/contributions/alignn_hydride_supercon/metadata.json @@ -0,0 +1,17 @@ +{ + "model_name": "ALIGNN", + "project_url": "https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94", + "date_submitted": "05-16-2024", + "author_email": "daniel.wines@nist.gov", + "team_name": "ALIGNN", + "time_taken_seconds": { + "AI-SinglePropertyPrediction-Tc_supercon_hydride-dft_3d-test-mae.csv.zip": "15327" + }, + "language": "python", + "os": "linux", + "software_used": "jarvis-tools,numpy,scipy,torch,alignn", + "hardware_used": "nisaba-cluster at NIST, V100 Tesla GPU", + "git_url": [ + "https://github.com/usnistgov/alignn" + ] +} \ No newline at end of file diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon/run.sh b/jarvis_leaderboard/contributions/alignn_hydride_supercon/run.sh new file mode 100644 index 000000000..472b06c9e --- /dev/null +++ b/jarvis_leaderboard/contributions/alignn_hydride_supercon/run.sh @@ -0,0 +1,11 @@ +#!/bin/bash +#SBATCH --nodes=1 +#SBATCH --ntasks-per-node=16 +#SBATCH --time=100:00:00 +#SBATCH --partition=mml +#SBATCH --error=job3.err +#SBATCH --output=job3.out + + +conda activate alignn +train_folder.py --root_dir "data/" --config "config.json" --output_dir=temp-3 diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/.DS_Store b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/.DS_Store new file mode 100644 index 000000000..7b954559d Binary files /dev/null and b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/.DS_Store differ diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/AI-SinglePropertyPrediction-Tc_supercon_hydride_plus_bulk-dft_3d-test-mae.csv.zip b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/AI-SinglePropertyPrediction-Tc_supercon_hydride_plus_bulk-dft_3d-test-mae.csv.zip new file mode 100644 index 000000000..3a1d47d02 Binary files /dev/null and b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/AI-SinglePropertyPrediction-Tc_supercon_hydride_plus_bulk-dft_3d-test-mae.csv.zip differ diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/config.json b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/config.json new file mode 100644 index 000000000..d1263b17c --- /dev/null +++ b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/config.json @@ -0,0 +1,53 @@ +{ + "version": "112bbedebdaecf59fb18e11c929080fb2f358246", + "dataset": "user_data", + "target": "target", + "atom_features": "cgcnn", + "neighbor_strategy": "k-nearest", + "id_tag": "jid", + "random_seed": 123, + "classification_threshold": null, + "n_val": null, + "n_test": null, + "n_train": null, + "train_ratio": 0.8, + "val_ratio": 0.1, + "test_ratio": 0.1, + "target_multiplication_factor": null, + "epochs": 300, + "batch_size": 16, + "weight_decay": 1e-05, + "learning_rate": 0.001, + "filename": "sample", + "warmup_steps": 2000, + "criterion": "mse", + "optimizer": "adamw", + "scheduler": "onecycle", + "pin_memory": false, + "save_dataloader": false, + "write_checkpoint": true, + "write_predictions": true, + "store_outputs": true, + "progress": true, + "log_tensorboard": false, + "standard_scalar_and_pca": false, + "use_canonize": true, + "num_workers": 0, + "cutoff": 8.0, + "max_neighbors": 12, + "keep_data_order": false, + "model": { + "name": "alignn", + "alignn_layers": 4, + "gcn_layers": 4, + "atom_input_features": 92, + "edge_input_features": 80, + "triplet_input_features": 40, + "embedding_features": 64, + "hidden_features": 256, + "output_features": 1, + "link": "identity", + "zero_inflated": false, + "classification": false + } +} diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/metadata.json b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/metadata.json new file mode 100644 index 000000000..c78fd04e1 --- /dev/null +++ b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/metadata.json @@ -0,0 +1,17 @@ +{ + "model_name": "ALIGNN", + "project_url": "https://iopscience.iop.org/article/10.1088/2752-5724/ad4a94", + "date_submitted": "05-16-2024", + "author_email": "daniel.wines@nist.gov", + "team_name": "ALIGNN", + "time_taken_seconds": { + "AI-SinglePropertyPrediction-Tc_supercon_hydride_plus_bulk-dft_3d-test-mae.csv.zip": "24672" + }, + "language": "python", + "os": "linux", + "software_used": "jarvis-tools,numpy,scipy,torch,alignn", + "hardware_used": "nisaba-cluster at NIST, V100 Tesla GPU", + "git_url": [ + "https://github.com/usnistgov/alignn" + ] +} \ No newline at end of file diff --git a/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/run.sh b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/run.sh new file mode 100644 index 000000000..392396cbb --- /dev/null +++ b/jarvis_leaderboard/contributions/alignn_hydride_supercon_plusbulk/run.sh @@ -0,0 +1,11 @@ +#!/bin/bash +#SBATCH --nodes=1 +#SBATCH --ntasks-per-node=16 +#SBATCH --time=100:00:00 +#SBATCH --partition=mml +#SBATCH --error=jobfull.err +#SBATCH --output=jobfull.out + + +conda activate alignn +train_folder.py --root_dir "data/" --config "config.json" --output_dir=temp-full