ML AB: Difference between revisions
Line 387: | Line 387: | ||
*We strongly advise to group structures with the same number of elements and atoms per element in the training data together, otherwise the code will automatically reorder the data, such that those are sticking together. This makes problems in the <code>diff</code> of an {{TAG|ML_AB}} file and it's corresponding {{TAG|ML_ABN}} file. | *We strongly advise to group structures with the same number of elements and atoms per element in the training data together, otherwise the code will automatically reorder the data, such that those are sticking together. This makes problems in the <code>diff</code> of an {{TAG|ML_AB}} file and it's corresponding {{TAG|ML_ABN}} file. | ||
*Adjust the header if needed (element types, maximum number of atoms, maximum number of atoms per element type, etc.). | *Adjust the header if needed (element types, maximum number of atoms, maximum number of atoms per element type, etc.). | ||
*The local reference configurations need to be recalculated, since they were only calculated for separate structures. To do this first set <code>The numbers of basis sets per atom type</code> to | *The local reference configurations need to be recalculated, since they were only calculated for separate structures. To do this first set <code>The numbers of basis sets per atom type</code> to 1 for each species. Then also set the block <code>Basis set for X</code> with dummy value <code> 1 1</code> for each species. After that run the code using {{TAG|ML_ISTART}}=3. This will select new local reference configurations on the scratch for the new combined training data. If calculations for {{TAG|ML_ISTART}}=3 are too time consuming using the default settings, it is useful to increase {{TAG|ML_MCONF_NEW}} to values around 10-16 and set {{TAG|ML_CDOUB}}=4. This often accelerates the calculations a factor 2-4. | ||
Revision as of 13:21, 12 October 2022
This file is used within the machine learning force field method. It contains the ab initio data from previous calculations: Bravais matrices, atom positions, energies, forces and stress tensors (the charge is also written out but only optionally used) . It is used for continuation runs (ML_ISTART=1 or ML_ISTART=2). The updated data is written to ML_ABN. Essentially the ML_AB and the ML_ABN files are the same and for continuation runs the ML_ABN file is just copied to ML_AB.
Here is a sample output how this file should look like:
1.0 Version ************************************************** The number of configurations -------------------------------------------------- 299 ************************************************** The maximum number of atom type -------------------------------------------------- 5 ************************************************** The atom types in the data file -------------------------------------------------- Pb I C N H ************************************************** The maximum number of atoms per system -------------------------------------------------- 96 ************************************************** The maximum number of atoms per atom type -------------------------------------------------- 48 ************************************************** Reference atomic energy (eV) -------------------------------------------------- -72.5297190000000 -35.4081430000000 -2.39269120000000 -4.60003440000000 -1.12020270000000 ************************************************** Atomic mass -------------------------------------------------- 20.0000000000000 20.0000000000000 12.0110000000000 14.0010000000000 8.00000000000000 ************************************************** The numbers of basis sets per atom type -------------------------------------------------- 130 1202 128 125 790 ************************************************** Basis set for Pb -------------------------------------------------- 1 1 100 8 1 3 100 4 1 5 1 6 ... ... ... ************************************************** Basis set for I -------------------------------------------------- 1 9 1 10 100 32 100 31 1 13 100 29 1 15 1 16 ... ... ... ************************************************** Basis set for C -------------------------------------------------- 100 39 101 40 104 40 101 39 101 38 108 40 101 37 ... ... ... ************************************************** Basis set for N -------------------------------------------------- 1 41 100 47 1 43 1 44 100 45 1 46 ... ... ... ************************************************** Basis set for H -------------------------------------------------- 101 96 108 96 101 95 101 94 108 95 101 93 101 92 ... ... ... ************************************************** Configuration num. 1 ================================================== System name -------------------------------------------------- Optimal ================================================== The number of atom types -------------------------------------------------- 5 ================================================== The number of atoms -------------------------------------------------- 96 ************************************************** Atom types and atom numbers -------------------------------------------------- Pb 8 I 24 C 8 N 8 H 48 ================================================== Primitive lattice vectors (ang.) -------------------------------------------------- 12.6230002000000 0.000000000000000E+000 0.000000000000000E+000 0.000000000000000E+000 12.6230002000000 0.000000000000000E+000 0.000000000000000E+000 0.000000000000000E+000 12.6322002000000 ================================================== Primitive lattice vectors (ang.) -------------------------------------------------- 3.53104385888580 2.84086367297985 2.90622172474177 9.81419124013876 2.65432768009571 3.05638374363947 3.26003769786731 9.08189602171279 2.78238128942769 9.68338433877730 9.01798419847282 3.33422943250601 3.97567522985842 2.30549969401587 9.43194287333753 10.2367187113626 2.60925731212548 9.47119538915201 3.14970369394084 8.58643640964228 9.24921780934012 9.89456550951183 9.28033187172892 9.29623786496524 10.2580847101708 12.3062955711284 3.18366035907868 3.82895321819843 12.3181255490181 2.42031967883849 10.1158676534974 5.94488260102727 2.75661681864481 3.42933902087078 6.02488805917889 2.84745157268693 9.18922717253027 12.1136591064009 9.46054840697861 4.09386338320418 11.6115721146332 9.19741414579098 10.8706574778817 5.69143379206153 9.19302841652753 3.28837848479649 5.54175742799501 9.53413058541621 0.296886340278756 8.76547030178476 2.14101850168883 6.59684935748724 8.79194887882670 3.82650473255966 0.428245756493863 2.59798612899847 3.75100434123024 6.70544911563391 2.85984511315708 2.37579642412770 0.167087945617848 9.78691660807122 9.55763154626161 6.34369358757671 8.38277722914886 8.74186174907648 0.559608821523150 2.07775553422575 9.20173753351574 6.87941885045959 3.56783791109442 9.82839336125391 3.07405022896748 3.09908590962395 12.5451964605531 10.9067521899973 2.28046049576184 0.104457094470827 4.17655919205017 9.00052367316014 12.4950366804108 9.57381442172574 9.63734691392405 12.5593223382356 4.06122044369206 2.81843048618285 6.28132394650503 10.0324883908695 2.67194263966303 6.42281604385187 2.79804490379300 8.38461292282242 5.91346560757258 9.74338219847610 9.86112720347275 6.30931718288953 1.02263147830728 11.8274672052164 12.2743957556041 6.71436142573495 0.386098550930723 12.0927367222414 0.991655629415002 6.29167324150435 2.378913781076451E-002 7.14212415871260 6.38847353848768 0.166929245025766 1.09263314243103 11.6784394398712 6.00501298083308 6.81239222852508 7.720564358957013E-003 5.81972148231710 12.2736872563375 6.43282169866644 5.66579243537609 7.03317153345761 5.14732535903573 5.99477016290181 0.858105285808099 0.283147091616275 0.675081476339173 6.64382772328535 11.9135358226671 0.486324292315528 12.1290965852444 6.41236307456918 12.4661996813288 5.82925852098534 5.86599668592475 12.2883714127747 12.6153725097845 12.5337698516607 6.56653663546619 6.35103756069245 11.3929376788950 6.53562500033421 0.778482961295645 5.56159346864120 6.14172445516157 5.73903474890177 5.82181169206098 6.35219235502436 1.39231326814732 10.9212146326541 0.149268424872883 3.939326025945113E-002 11.6437361612826 11.8110946376369 1.74935186413609 12.1799107044156 11.5239603745818 0.219251785556775 12.5863663388017 1.46495273189263 1.79629345326380 0.550477216917984 1.10264446811277 0.433027134776968 1.16136170079748 0.247301477080943 7.47084014873485 1.11657695587760 12.4232258809939 7.00037760733078 12.5578893937650 11.1284921930181 5.71954930570457 0.856496283120137 12.0251567066103 7.61085990373643 11.5168018815484 0.690630688278504 6.23853627489008 12.2728981918211 1.40342304304974 6.02740643486776 11.1126016632056 0.149460054228370 1.20781180142941 6.38205822816568 1.10090963496361 1.30703456185503 5.30675633519347 12.2743651983594 1.47630627851831 7.10433680255390 12.0901416833158 11.7621904754867 7.32187511263496 0.249279535632534 11.8726032953672 6.39920054504097 11.4325117583012 11.6159294130364 5.60757643872615 0.307208116835027 6.96316067118499 6.86949591238280 1.14246554953540 7.83304201553071 5.53589266661168 0.271337509118816 7.52808549088313 7.11797891936522 12.0681382077556 5.97661916021294 5.15415784597902 11.5100009830914 5.27799010316068 5.38983062639406 0.433243790796200 5.22843658841443 6.65494954981429 11.8991224872664 1.83172457256604 12.3416476290819 5.52649457958814 1.54972896640659 11.1181400817720 6.83705292263959 0.648621850029045 10.9903637641685 5.26684073441985 0.369786667605785 0.594001759550438 7.29113473843099 12.1416059949500 0.477902130144820 5.79947837064481 11.8694779019449 11.9372006513511 7.03844245269026 6.01989988334354 0.312232402782980 5.11664974019429 6.99096598595716 0.792723052203353 6.57274547477411 7.74224555756176 12.3874410373418 5.27964783721995 6.00339684612195 10.6587719270935 5.84683130722452 7.14282215559495 10.9600103940183 7.10141971883287 5.55376703796905 11.6135066184794 7.20693512529441 11.9406974346555 7.05504330939053 6.51257443020246 2.714098707952951E-002 7.06120520390067 4.84203332376256 11.4583680636654 5.77759486211653 5.31733197106969 1.66376098131111 6.13239021727701 6.29908869054496 0.531478524113899 5.08316854283047 7.06072975689720 1.00270039770073 4.80209855904143 5.42909365005565 7.64349842575924 5.86116484985319 5.41769547730595 7.54190860984904 4.86396863337472 6.93075006543724 6.79897064568669 4.25518530494504 5.39084316330668 5.45647449699007 6.52847427737476 5.60715687601479 4.94996304461365 5.11235831149750 6.44446782056207 5.82075594460117 6.34049825639383 7.27914125592649 ================================================== Total energy (eV) -------------------------------------------------- -1844.06244866897 ================================================== Forces (eV ang.^-1) -------------------------------------------------- 2.660349497586850E-002 -4.547882666592111E-003 0.190783123263071 0.130884508367191 0.299290099652476 1.596358887670635E-002 3.408685056302496E-002 -4.091615555857331E-002 0.178271772476586 -8.681206662816165E-002 -2.646077052932483E-002 -0.627496783708147 -2.387963973365542E-002 0.272206550808848 -0.188554040851596 -0.349175317569579 0.372666466514608 9.810640873955712E-002 0.508292852334109 2.851700722091148E-002 -0.297636066674050 -0.477466544993604 -0.767209034380190 0.537092981997701 1.081052495208487E-002 -0.454162570762754 -2.885905409516716E-002 5.233785861238309E-002 -4.907001101287316E-002 0.357709899123724 -0.230224912339896 -0.117150750780048 -0.139616094943659 0.102540834222563 -0.189192332090928 9.187250072345658E-002 -0.126562656993933 0.628538272647399 -0.196286321056689 6.400912781516797E-003 0.744239334702281 -6.458723081110410E-002 -5.767073532084405E-002 0.228774953892571 -1.163578545057205E-002 -0.173831332474762 -0.172806125471746 -0.265324184988485 1.606320476476653E-002 0.660725518682814 0.586717861519040 -2.231576570645055E-002 -1.560116870238250E-002 -1.805735858026897E-002 0.277268049005576 0.104449846788358 7.874861907744674E-002 5.093357421225891E-002 -3.720669225924848E-002 8.757906194611484E-002 0.347770128512301 -6.949672170195867E-002 -0.165017281025361 -1.269724232927270E-002 -9.689722526238803E-002 0.122560372172203 0.574529900215143 -0.101828666147038 7.727101789060012E-003 -7.991533025139014E-002 -0.370056241375952 -0.161435958643188 0.144376629787889 -8.956373239692209E-002 -6.544695680537893E-003 -0.400712836144330 0.625208458752742 -0.171877996812729 -1.962948749927612E-003 9.197469371301489E-003 -0.452887176022089 -3.715853555351770E-002 -0.173215539978128 0.332659777368484 -0.144627793865140 -0.187179133803005 0.107892570036324 -0.160253556891691 1.361217397710326E-002 -0.246257522509988 0.147313626899787 0.158811221976471 0.654642200063784 0.245982292413043 4.495057557062357E-002 -0.172033604940800 1.602619336194822E-002 8.940426700782211E-002 4.061537314007424E-002 -3.972686150744753E-003 2.478948137657966E-002 -0.150985239025978 -3.911336919224873E-002 -0.223506340362864 -8.407378751987249E-002 7.952842953777761E-002 -6.428570303620873E-003 -5.915601499825128E-002 -0.108683502802389 -2.302055674537051E-002 1.765387261678253E-002 2.267177236257645E-002 -1.092894411794276E-003 -8.732975406640264E-002 -2.098288054081188E-002 4.989421611240275E-002 9.353814616424660E-002 0.118098620110549 8.187916713641386E-003 3.656823747240168E-002 9.370910630657611E-002 0.208342417209851 0.565248897185937 0.267079688232096 -0.635114231083110 0.642873515340547 -0.817269057946005 -8.563202425841476E-002 -0.115036787077222 -0.823414722211538 -0.311977297712063 1.602079170174520E-002 -0.712711490118085 0.145541437665101 -0.261711591127002 -0.163832340621356 -0.600419571641310 1.897748175097558E-002 0.502339157552856 -0.954639324352480 0.438566129025636 -0.733917210494281 0.692432617735001 -0.124020907331446 -0.179177052816627 0.336358142948464 -0.266590593238711 0.429386892960721 0.100505339266029 0.259282259520863 -0.309972938504256 -0.137675637286257 0.253909602486682 0.647686654001155 0.497060905621999 -0.947304089068558 -0.938500364048072 -0.435288124795083 -0.377035602843034 0.191807545012799 -0.840984103180574 0.540112639284247 -0.358101325754663 -0.274123389441717 -0.172244311711192 -0.138125380866680 0.200340421917116 0.462689344137429 0.378464099600265 -0.143521062252049 0.118651189300695 -0.937055982021507 0.219148676843214 -0.410077569488035 0.250411992246748 -0.403749792486203 -1.02306843982497 0.614209418389904 0.781763931304182 0.497075299075630 -7.052131973808007E-002 -0.134395658412516 -0.625282520752103 -0.171136244885699 0.442365498861689 9.031855581644366E-002 -0.172681513960009 -0.318875802095300 0.287301141211352 0.374410416112840 -0.956235768527160 -0.310638532600879 8.059798362741355E-002 -0.180943976917728 0.772223434493475 0.533360186265331 1.05125252345256 -0.527874869139172 0.128728118145883 -0.154882692292142 -0.384641613788981 -0.299138550651608 0.354715067927667 2.577432037699579E-002 -0.132818810452223 -0.285936716858765 0.311358498598005 -7.303989129144473E-002 0.520269225771285 0.577131663286597 0.563093374511039 0.567300131480568 -0.965330423659155 0.563541406640260 -0.813823565323585 0.565027107920914 -0.286555856081272 -0.235045427102016 0.164788445010825 -0.207487589540055 0.233718068708780 -0.379010969096529 0.205013411671021 0.234686167300782 0.297283983626369 -0.441723372993105 -0.408131383768703 -0.419842346381472 0.443551792439487 -0.560261847190817 0.904620757344219 0.830023666442679 0.731507062178048 -0.589697080427258 0.322861509902754 -5.775184854104464E-002 0.294944575700402 -2.288662392739194E-002 -0.297057632221112 -0.343365983697753 -0.324770558686271 0.132355149522852 0.196751217295306 0.600539261544107 0.621937407783978 0.756384010497966 -0.977989248441274 0.379893549244113 -0.646092160273432 0.646686430512128 -0.329065562364926 -0.359231009354962 0.162733472498922 -0.236669896097235 -0.346842379000060 -0.126041720282131 -0.290232445613701 0.279895665961673 0.375133729061458 0.281223973696193 0.224595987021582 -0.818441966993585 -0.336796863407170 -0.184554781009615 0.218179773727040 0.523160572910113 -1.05750572256536 -0.301298005761141 0.685177042094319 0.725604212549017 -0.191421327844714 -0.301791749752562 0.232815392507705 -0.210336488468268 4.669582926755100E-002 -0.424875253104636 0.158608839394937 0.369479135587538 0.212208315938015 0.275039999794429 -0.769356293594466 0.949276743918999 0.740755625065134 0.488181150231506 -9.011843825240384E-002 -4.530946267273289E-002 -0.186973791838126 -0.887267373770487 ================================================== Stress (kbar) -------------------------------------------------- XX YY ZZ -------------------------------------------------- -12.6559383536223 -8.82753684858342 -13.1791695209263 -------------------------------------------------- XY YZ ZX -------------------------------------------------- -1.91691819690402 2.12274173946129 0.103818583636094 ************************************************** Configuration num. 2 ================================================== ... ... ...
Some general remarks:
- All element type dependent information is limited to 3 entries per line. For more than 3 types or multiples of 3 the entries are written over multiple lines.
- All element dependent quantities must follow the order of the element entries of the line
The atom types in the data file
. - The order of the entries for the header and also the data is fixed.
- The ledger lines cannot be omitted. "*****" and "-----" lines for the header. *****", "-----" and "=====" lines for the data.
Header
The number of configurations
: Total number of training configurations.The maximum number of atom type
: Union of the types of all configurations.The atom types in the data file
: Listing of all atom types (two characters for each type as in VASP) appearing in all structures. Multiple lines for more than 3 element types. Maximum 3 entries per line.The maximum number of atoms per system
: The largest number of atoms within one structure among all training structures.The maximum number of atoms per atom type
: The largest number of atoms per element within one structure among all elements within all training structures.Reference atomic energy (eV)
: Reference atomic energies used in the calculation for each element type. Multiple lines for more than 3 element types. Maximum 3 entries per line. This entry is only important forML_ISCALE_TOTEN=1
.Atomic mass
: Atomic mass of each element type. Multiple lines for more than 3 element types. Maximum 3 entries per line.The numbers of basis sets per atom type
: Number of local reference configurations for each type. Multiple lines for more than 3 element types. Maximum 3 entries per line.Basis set for X
: List of local reference configurations for each type. This line is followed by a block with two columns. The first column shows from which training structure the local reference configuration is taken. The second column shows the number of the atom in that training structure that is chosen as a local reference configuration. This whole block (together with the title line) is repeated for each element type in the force field.
Training structure data
Configuration num. n
: The data is stored for each configuration of the training data. The training structures have to be numbered consecutively starting with 1.System name
: Name of the structure. The length of the system names are limited to 40 characters (same as for the structure names in the POSCAR file).The number of atom types
: The number of atom types in the structure. This has to be at least a subset of element types ofThe atom types in the data file
in the header and can maximally have all element types of the header.The number of atoms
: Number of atoms in the structure.Atom types and atom numbers
: Atom types and number of atoms per type in the structure. Each type is written on a separate line.- Optional
CTIFOR
: Value of ML_CTIFOR used for the sampling of the structure. This line is optional and may not occur in your file. It is important, that either none of the training structures contain this entry or all of them contain it. It is not permitted to have mixed entries. Primitive lattice vectors (ang.)
: Bravais matrix of the structure. The units are in Angstrom.Wycoff positions (Cartesian)
: Ionic positions in Cartesian coordinates. The units are in Angstrom.Total energy (eV)
: Total energy (in eV) of the structure.Forces (eV ang.^-1)
: Forces (in eV/Angstrom) for each atom in the structure.Stress (kbar)
: 6 entries for the stress tensor (in kB) of the structure.
Merging different ML_AB files
- The training structure data can be simply concatenated, but the numbering of the structures needs to be renewed, so that it goes from 1 to the new maximum number of structures seamlessly.
- We strongly advise to group structures with the same number of elements and atoms per element in the training data together, otherwise the code will automatically reorder the data, such that those are sticking together. This makes problems in the
diff
of an ML_AB file and it's corresponding ML_ABN file. - Adjust the header if needed (element types, maximum number of atoms, maximum number of atoms per element type, etc.).
- The local reference configurations need to be recalculated, since they were only calculated for separate structures. To do this first set
The numbers of basis sets per atom type
to 1 for each species. Then also set the blockBasis set for X
with dummy value1 1
for each species. After that run the code using ML_ISTART=3. This will select new local reference configurations on the scratch for the new combined training data. If calculations for ML_ISTART=3 are too time consuming using the default settings, it is useful to increase ML_MCONF_NEW to values around 10-16 and set ML_CDOUB=4. This often accelerates the calculations a factor 2-4.
Important: The maximum size of the training structures ML_MCONF and the maximum size for the local configurations ML_MB in the INCAR file have to be set larger than the entries The number of configurations and The numbers of basis sets per atom type in the ML_AB file.