Supplementary data: Accurate large-scale simulations of siliceous zeolites by neural network potentials
Lists
Only you see this
Abstract
Content\n\n1. Zeolite databases\n\n\n\tDeem database containing 331170 hypothetical zeolite frameworks [Deem09, Pophale11] geometrically optimized at the NNPscan level (note, the first row of the database is alpha-quartz): "DEEM_NNPscan.db"\n\tDatabase of 236 exiting zeolite frameworks of the International Zeolite Association (IZA) optimized at the NNPscan level: "IZA_NNPscan.db"\n\tBoth databases are ASE SQLite database files of the Atomic Simulation Environment containing the ASE Atoms objects with energies and forces (NNPscan level); readable with ASE's I/O module\n\tAdditionally, relevant quantities can be extracted with, e.g., the following queries (further information: ase db --help):\n\n\nase db DEEM_NNPscan.db -c id,formula,natoms,volume,mass,density,energy_per_tsite,n_tsites,relative_energy\n# Output\nid|formula|natoms| volume| mass|density|energy_per_tsite|n_tsites|relative_energy\n 1|O6Si3 | 9|111.161|180.249| 26.988| -31.796| 3| 0.000\n 2|O16Si8 | 24|433.858|480.664| 18.439| -31.638| 8| 15.265\n 3|O16Si8 | 24|421.114|480.664| 18.997| -31.596| 8| 19.359\n 4|O16Si8 | 24|426.557|480.664| 18.755| -31.614| 8| 17.613\n 5|O16Si8 | 24|412.410|480.664| 19.398| -31.613| 8| 17.677\n 6|O16Si8 | 24|393.544|480.664| 20.328| -31.594| 8| 19.546\n 7|O16Si8 | 24|422.400|480.664| 18.939| -31.657| 8| 13.476\n 8|O16Si8 | 24|394.405|480.664| 20.284| -31.581| 8| 20.797\n 9|O12Si6 | 18|265.201|360.498| 22.624| -31.611| 6| 17.868\n10|O16Si8 | 24|357.047|480.664| 22.406| -31.581| 8| 20.785\n11|O16Si8 | 24|434.894|480.664| 18.395| -31.621| 8| 16.911\n12|O16Si8 | 24|384.158|480.664| 20.825| -31.657| 8| 13.448\n13|O12Si6 | 18|258.977|360.498| 23.168| -31.679| 6| 11.278\n14|O16Si8 | 24|466.429|480.664| 17.152| -31.593| 8| 19.588\n15|O16Si8 | 24|423.469|480.664| 18.892| -31.639| 8| 15.179\n16|O16Si8 | 24|450.716|480.664| 17.750| -31.628| 8| 16.219\n17|O16Si8 | 24|331.528|480.664| 24.131| -31.642| 8| 14.857\n18|O16Si8 | 24|458.573|480.664| 17.445| -31.635| 8| 15.572\n19|O16Si8 | 24|359.298|480.664| 22.266| -31.655| 8| 13.636\n20|O16Si8 | 24|464.264|480.664| 17.232| -31.612| 8| 17.750\nRows: 331171 (showing first 20)\nKeys: density, energy_per_tsite, n_tsites, relative_energy\n\nase db IZA_NNPscan.db -c id,formula,natoms,volume,mass,density,energy_per_tsite,n_tsites,relative_energy,iza_code\n# Output\nid|formula |natoms| volume| mass|density|energy_per_tsite|n_tsites|relative_energy|iza_code\n 1|O16Si8 | 24| 435.488| 480.664| 18.370| -31.676| 8| 11.594|ABW\n 2|O32Si16 | 48| 961.419| 961.328| 16.642| -31.645| 16| 14.612|ACO\n 3|O96Si48 | 144|3154.579|2883.984| 15.216| -31.664| 48| 12.810|AEI\n 4|O80Si40 | 120|2102.921|2403.320| 19.021| -31.703| 40| 9.021|AEL\n 5|O96Si48 | 144|2417.286|2883.984| 19.857| -31.666| 48| 12.586|AEN\n 6|O144Si72| 216|4075.300|4325.976| 17.667| -31.674| 72| 11.831|AET\n 7|O96Si48 | 144|2786.810|2883.984| 17.224| -31.675| 48| 11.716|AFG\n 8|O48Si24 | 72|1400.247|1441.992| 17.140| -31.690| 24| 10.268|AFI\n 9|O64Si32 | 96|1764.823|1922.656| 18.132| -31.653| 32| 13.809|AFN\n10|O80Si40 | 120|2080.330|2403.320| 19.228| -31.707| 40| 8.632|AFO\n11|O64Si32 | 96|2097.384|1922.656| 15.257| -31.655| 32| 13.622|AFR\n12|O112Si56| 168|3820.116|3364.648| 14.659| -31.650| 56| 14.150|AFS\n13|O144Si72| 216|4732.720|4325.976| 15.213| -31.664| 72| 12.793|AFT\n14|O60Si30 | 90|1897.074|1802.490| 15.814| -31.659| 30| 13.268|AFV\n15|O96Si48 | 144|3154.885|2883.984| 15.214| -31.664| 48| 12.776|AFX\n16|O32Si16 | 48|1137.335| 961.328| 14.068| -31.591| 16| 19.790|AFY\n17|O48Si24 | 72|1283.812|1441.992| 18.694| -31.620| 24| 17.034|AHT\n18|O96Si48 | 144|2479.287|2883.984| 19.360| -31.681| 48| 11.155|ANA\n19|O64Si32 | 96|1797.086|1922.656| 17.807| -31.662| 32| 12.924|APC\n20|O64Si32 | 96|1751.393|1922.656| 18.271| -31.678| 32| 11.422|APD\nRows: 236 (showing first 20)\nKeys: density, energy_per_tsite, iza_code, n_tsites, relative_energy\n\n# Filtering of the database, e.g., for structures with relative energies < 10 kJ/(mol Si)\nase db IZA_NNPscan.db relative_energy\\<10 -c density,energy_per_tsite,n_tsites,relative_energy,iza_code\n# Output\ndensity|energy_per_tsite|n_tsites|relative_energy|iza_code\n 19.021| -31.703| 40| 9.021|AEL\n 19.228| -31.707| 40| 8.632|AFO\n 19.385| -31.695| 24| 9.802|ATV\n 18.778| -31.702| 34| 9.061|DOH\n 19.570| -31.693| 24| 9.959|EWO\n 18.401| -31.698| 32| 9.451|GON\n 18.551| -31.695| 112| 9.807|IHW\n 17.778| -31.693| 288| 9.972|IMF\n 19.154| -31.695| 6| 9.762|JBW\n 18.187| -31.695| 96| 9.734|MFI\n 19.278| -31.709| 48| 8.443|MRE\n 18.035| -31.698| 90| 9.481|MSO\n 20.417| -31.724| 44| 7.003|MTF\n 19.227| -31.704| 136| 8.898|MTN\n 18.542| -31.693| 28| 9.966|MTW\n 19.137| -31.695| 60| 9.798|PCR\n 20.037| -31.709| 144| 8.464|PSI\n 18.843| -31.703| 64| 9.004|SAF\n 18.371| -31.703| 112| 8.975|STO\n 19.894| -31.706| 17| 8.671|VET\nRows: 20 (showing first 20)\nKeys: density, energy_per_tsite, iza_code, n_tsites, relative_energy\n\n\n\tThe quantities shown above are available with the keys (besides standard ASE database keys):\n\n\n\n\t\n\t\t\n\t\t\tKey\n\t\t\tQuantity\n\t\t\tUnit\n\t\t\n\t\n\t\n\t\t\n\t\t\tid\n\t\t\tIdentifier\n\t\t\t \n\t\t\n\t\t\n\t\t\tformula\n\t\t\tChemical formula of the unit cell\n\t\t\t \n\t\t\n\t\t\n\t\t\tnatoms\n\t\t\tNumber of atoms\n\t\t\t \n\t\t\n\t\t\n\t\t\tvolume\n\t\t\tUnti cell volume\n\t\t\tÅ3\n\t\t\n\t\t\n\t\t\tmass\n\t\t\tAtomic mass of the unit cell\n\t\t\tamu\n\t\t\n\t\t\n\t\t\tdensity\n\t\t\tFramework density\n\t\t\tSi/nm3\n\t\t\n\t\t\n\t\t\tenergy_per_tsite\n\t\t\tNNPscan energy\n\t\t\teV\n\t\t\n\t\t\n\t\t\tn_tsites\n\t\t\tNumber of T-sites\n\t\t\t \n\t\t\n\t\t\n\t\t\trelative_energy\n\t\t\tEnergy with respect to quartz\n\t\t\tkJ/(mol Si)\n\t\t\n\t\t\n\t\t\tiza_code\n\t\t\tonly for 'IZA_NNPscan.db'\n\t\t\t \n\t\t\n\t\n\n\n\n\t Comma separated csv files for the quantities listed above: "DEEM_NNPscan.csv" and "IZA_NNPscan.csv"\n\n\n2. Neural network potentials (NNP) for silica\n\n\n\tSchNet [Schütt18,Schütt19] NNP files trained on DFT data at the PBE+D3 (NNPpbe) and SCAN+D3 level (NNPscan)\n\tSimulations can be performed using SchNetPack with its ASE calculator\n\tThis example shows a simple single-point calculation\n\n\nimport ase.io\nimport torch\nfrom schnetpack.interfaces import SpkCalculator\nfrom schnetpack.environment import AseEnvironmentProvider\n\n# check if GPU(s) are available\nif torch.cuda.is_available():\n device = "cuda"\nelse:\n device = "cpu"\n\n# load the NNP model\nmodel = torch.load('SiOscan1', map_location=device)\n\n# read some structure\natoms = ase.io.read( ... )\n\n# define SchNetPack calculator\ncalc = SpkCalculator(model=model,\n device=device,\n energy='energy',\n forces='forces',\n environment_provider=AseEnvironmentProvider(6.)\n )\n\n# attach calculator to atoms object\natoms.set_calculator(calc)\n\n# perform simulations, e.g., single-point calculation\nenergy = atoms.get_potential_energy()\nprint(energy)\n\n3. Test set used for accuracy evaluation (ASE database: test_set_NNPscan.db)
BibTeX
@inproceedings{erlebach2022supplementary,
author = {Andreas Erlebach and Petr Nachtigall and Lukáš Grajciar},
title = {{Supplementary data: Accurate large-scale simulations of siliceous zeolites by neural network potentials}},
booktitle = {Zenodo},
year = {2022},
doi = {10.5281/zenodo.5827897},
}Loading related content...