ML AB

From VASP Wiki
Revision as of 10:03, 13 October 2022 by Singraber (talk | contribs)

This file is used as input (with file name ML_AB) and output (ML_ABN) within the machine learning force field method. It contains the collection of 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 in the following situations:

  • ML_ISTART = 0 (starting from scratch): A complete ML_ABN file containing all ab initio data and the list of current local reference configurations is written whenever a learning step is performed (check the line STATUS in the log file ML_LOGFILE for entries learning and critical).
  • ML_ISTART = 1 (continuation run): Same ML_ABN output as for ML_ISTART = 0. In addition, upon start-up the user-provided ML_AB file is read and an initial machine-learned force field is generated from the contained data.
  • ML_ISTART = 3 (re-selection of local reference configurations): Same ML_ABN output as for ML_ISTART = 0. The ML_AB file is read and the contained structures are fed sequentially to the on-the-fly training algorithm. The list of local reference configurations in the ML_AB file is ignored.
Tip: The ML_AB file is not required for ML_ISTART = 2 (prediction only) because all necessary data (e.g. descriptors of local reference configurations) are already stored in the ML_FF file.

An ML_ABN output file from ML_ISTART = 0,1,3 can always be reused as input for ML_ISTART = 1,3 by just renaming (copying) it 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
==================================================
 ...
 ...
 ...

General format remarks

Important: All element-dependent quantities must follow the order of the element entries given in the header entry named The atom types in the data file.
  • 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.
  • 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 specification

  • 1.0 Version: In the very beginning of the header this entry specifies to the version of the ML_AB file. If in the future the contents of the file will be changed or extended the version number will ensure I/O compatibility. If not stated otherwise use 1.0 Version.
  • The number of configurations: Total number of training structures stored in this ML_AB file.
  • The maximum number of atom type: Total number of unique types listed in all structures (e.g. if the file contains some ab initio data for H2O and some data for NaCl, then the total number of types is 4).
  • 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 for ML_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 atoms 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 is 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 of The 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 the 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.


Warning: Training structures with a value for CTIFOR and without must not be combined. Either for all structuresCTIFOR is provided or for none of them.

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, the maximum number of atoms, the 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 block Basis set for X with dummy value 1 1 for each species. After that run the code using ML_ISTART=3. This will select new local reference configurations from 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 by a factor of 2-4.


Warning: The maximum size of the training structures ML_MCONF and the maximum size for the local reference 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.
Retrieved from "https://www.vasp.at/wiki/index.php?title=ML_AB&oldid=19051"