DFT Calculations - Science topic

I would like to know if I need to form the .xyz file of the twisted bilayer first and then do the relaxation or I can just use the monolayer input file and add a twist angle in the input file to do the calculations. It would be helpful if anyone could provide me with the input file for the twisted bilayer of graphene for relaxation or scf calculations.

Hi, folks!

I am studying the hyperpolarizability of a crystal using DFT calculations. I learned that Gaussian code is able to do that with POLAR keyword in the input file. As Gaussian is not professional at dealing with periodic structures, I abandoned the crystal box and took out the coordinates of its unit cell as well as 1*1*2，1*2*1, 2*1*1, 1*1*3 supercells for input structures of Gaussian. The calculations are performed at CAM-B3LYP/6-311++g(d,p) level. Below are some results of total beta in the unit of 10^-30 esu.

1*1*1: 33

1*1*2: 97

1*2*1: 78

2*1*1: 53

1*1*3: 199

As can been see, these values diff largely and do show any convergence. What is the correct way to simulate the crystal? How large size of crystal structure should be used?

Thank you very much in advance!

How can I apply Discrete Fourier Transform (DFT) in MATLAB for aeroelastic analysis of wind turbines? Specifically, I am looking for guidance on using DFT to analyze wind turbine structural response data (e.g., vibrations, loads) in the frequency domain. Any advice on MATLAB code, libraries, or methodologies for incorporating DFT into aeroelastic simulations would be greatly appreciated!

Hello everyone, I am performing a BSSE (Basis Set Superposition Error) calculation using the Counterpoise=2 option to calculate the hydrogen bonding energy between two small molecules with gaussian 16.

For this purpose, I first performed Opt and Freq calculations using the following input:

# OPT(MaxCycle=200) Freq MP2/aug-cc-pVDZ NoSymm pop=npa geom=AllCheckpoint

Then, I conducted the BSSE calculation with the following input:

# SP MP2/aug-cc-pVDZ Counterpoise=2 NoSymm pop=npa

I have two questions regarding this process:

1. Is it generally correct to include the Counterpoise=2 option only in the SP calculation, as shown above? Should the BSSE option also be included in the Opt and Freq calculations?

2. I would like to obtain the partial charge information of the atoms from the BSSE calculation results. However, while the BSSE calculation converges, an error occurs during the NPA (Natural Population Analysis) process. Is it not possible to use the pop=npa option in BSSE calculations? If so, are there any alternative methods to obtain the partial charges aside from NPA?

If anyone has answers to these two questions, I would greatly appreciate your input.

Thank you very much!

Dear all,

I'm trying to run EFG calculations for LiK molecules using Gaussian16 software. As far as I'm aware the TD keyword produces excited state calculations using TDDFT. However if I then want to use the excited states for other property calculations such as EFGs or other hyperfine constants, I'm not quite sure what to do.

Choosing different roots in the TD option seems to give the same values of the EFG tensor, which makes me suspect that it calculates the ground state values instead of the excited state.

Can anyone give me any pointers on how to make it do hyperfine constant calculations for excited states specifically? Is it in the definition of the molecule or can I simply use some keyword?

Thank you!

Hi RG Community,

While running wannier90.x to compute the MLWFs, I encountered the following error:

------------------------------------------------------------------------------

Cycle: 1

wann_main: ZHEEV in internal_new_u_and_m failed, info= 151

trying Schur decomposition instead

wann_main: SCHUR failed, info= 152

Exiting.......

wann_main: problem computing schur form 1

------------------------------------------------------------------------------

I have already performed the sequence: SCF, NSCF, wannier90.x -pp, and pw2wannier90.x. The problem arises during the wannier90.x calculation.

Does anyone know how to resolve this issue?

Thank you in advance for your help!

Rgds,

Gabriel Vinicius

I need the last version of P4V, all of the links in vasp.at and p4vasp.at are expired.

I'm trying to do geometry optimization of KAgO3 perovskite material in the material studio using CASTEP by setting cutoff energy 500 ev and various k points 888,999,101010,121212. but every time it fails showing the messages mentioned in the pictures. What is the possible reason and solution for successful optimization?

need an explanation from experts. Thank you.

#Material_studio #Geometry_optimization #Failure

I need to do DFT calculations and theoretical studies on the sensing of my carbon dots. Can I use DFT method for getting HOMO LUMO energy levels of the carbon dots? some papers used Cyclic volametric studies for that.

This the deal , when I try to run siesta, e.g.:

mpirun -np 4 /home/guilherme/siesta-3.2/Obj/siesta < AlFeO3.fdf | tee saida.out

appeared the mensage:

mpirun noticed that process rank 1 with PID 17811 on node guilherme-Inspiron-N5010 exited on signal 6 (Aborted).

And when I change -np 4 to -np 1 like:

mpirun -np 1 /home/guilherme/siesta-3.2/Obj/siesta < AlFeO3.fdf | tee saida.out

it's ok... but this way it's a normal way... without parallel mode!!

Anyone know what is going on?!

Hi everyone,

I have been working on obtaining a transition state for the deprotonation of a carbocation by histidine, where I froze the bond lengths between the histidine nitrogen and the proton, as well as between the proton and the methyl group being deprotonated. This resulted in a single imaginary frequency of over -1000, and the transition state was confirmed through IRC calculations.

My question is: is such a transition state acceptable and publishable given that the bond lengths were frozen? I attempted to release the constraints and recalculate the transition state (including using key words like calcfc, calcall, scf=qc, IOP(1/8=1),, each besides this level of theory # opt=(ts,noeigen) freq mpw1pw91/6-31+g(d,p)), but the structure did not converge. Can I rely on the optimized transition state with frozen bonds, or should I keep trying to achieve a fully unconstrained optimization?

Thanks

I am currently working on obtaining the transition state for the deprotonation of a carbocation by histidine. Initially, I froze the bond lengths between the histidine nitrogen and the proton, as well as between the proton and the methyl group being deprotonated. This approach resulted in a single imaginary frequency of over -1000 cm⁻¹ (please see the attached files: 1_input and 1_output).

I then attempted to release these constraints and recalculate the transition state. I have tried various keyword combinations, including calcfc, calcall, scf=qc, and IOP(1/8=1) in conjunction with the level of theory # opt=(ts,noeigen) freq mpw1pw91/6-31+g(d,p). However, the structure did not converge. The energy oscillates uniformly without reaching a minimum (attached is a graph showing this behavior).

Could you provide any suggestions on how to address this issue ?

Thank you for your time and assistance.

I have synthesized a series of organic compounds that can bind with anions. I have the single crystal of the ligand. now, the obstacle is that my synthesized ligand is neutral and it can bind with an anion. Now, if I want to optimize the structure of the compound after binding with anion then how should I consider the charge of the compound? precisely, for an example, during DFT calculation for a metal complex, if the complex is neutral we give the charge o as input for our complex, and if the complex has an uncoordinated anion to neutralize the overall charge and we aim to optimize the complex only in that case we put +1 charge as input.

My question is, what will be the charge in the input file for my compound after binding with anion/s? Should I consider the whole molecule as a neutral or—ve-charged species?

Respected Sir/Madam, please help me to figure out this problem

Hi,

I want to calculate the magnitude of k point(in Brillouin zone) of graphene which has a hexagonal unit cell. The lattice parameters of graphene are given below:

&CONTROL calculation = 'scf' / &SYSTEM ibrav = 4 a = 2.46639 c = 18 ATOMIC_SPECIES C 12.0107 C.upf ATOMIC_POSITIONS (crystal) C 0.333333333 0.666666666 0.000000000 C 0.666666666 0.333333333 0.000000000 K_POINTS (automatic) 35 35 1 0 0 0

ibrav 4 has the following lattice vectors.

📷 (check attachment)

If I open the scf.out and choose a k point (as follows)

cart. coord. in units 2pi/alat k( 44) = ( 0.3000000 0.5773503 0.0000000), wk = 0.0300000

How can I calculate the magnitude of the |k| in the hexagonal reciprocal unit cell? considering that I know the value of (kx, ky, 0). The lattice is a parallelogram so that |k| does NOT simply equal to sqrt(kx^2+ky^2), right?

I want to plot the phonon dispersion of Au. I successfully ran pw.x and ph.x. (I am sharing the input files as follows). However, while running q2r.x, I have found the error " nc already filled: wrong q grid or wrong nr". Would you please see the inputs where I have made any mistakes?

%%%%%%%%%%%%%%%%%%%

&CONTROL   calculation = 'scf'   outdir = './out/'   prefix = 'Au'   pseudo_dir = './' / &SYSTEM   degauss =  0.01   ecutwfc =   100   ibrav = 0   nat = 1   ntyp = 1   occupations = 'smearing'   smearing = 'mp'   nosym = .TRUE.   noinv = .TRUE. / &ELECTRONS   diagonalization='cg'   conv_thr =   1.0e-10   mixing_beta =   0.4 / ATOMIC_SPECIES Au     196.966569 Au_ONCV_PBEsol-1.0.upf ATOMIC_POSITIONS crystal Au           0.0000000000       0.0000000000       0.0000000000 K_POINTS automatic 15 15 15 0 0 0 CELL_PARAMETERS angstrom    0.000000235   2.037568691   2.037568574    2.037568691   0.000000117   2.037568574    2.037568691   2.037568574   0.000000000

%%%%%%%%%%%%%%%%%%%

Ph.x

&inputph     amass(1) = 196.966569,     prefix = 'Au',     outdir = './out',     ldisp = .true.,     fildyn = 'Au.dyn',     tr2_ph = 1.0d-14,     nq1 = 4,     nq2 = 4,     nq3 = 4 /

%%%%%%%%%%

q2r.x

&input fildyn = 'Au.dyn' zasr = 'crystal' flfrc = 'Au.fc' /

%%%%%%%%%%%%

The error message while running q2r.x is:

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%      task #        36     from init : error #         1        nc already filled: wrong q grid or wrong nr %%%%%%%%%%%%%%%%%%%%%%%%%%%%%      nc already filled: wrong q grid or wrong nr Thank you in advance for your time.

I am currently new to DFT calculations in QE. I am particularly interested in calculating the ground state magnetic moment of FeTiO3. I've noticed that most of the published papers used VASP but when we used QE the results were quite different than VASP. Could you please guide me on the steps I should follow to calculate the AFM and FM magnetic states? I plan to use the DFT + U method for these calculations.

I would greatly appreciate any clarification you can provide.

Thank you very much for your assistance!

#QuantumEspresso #DFT #AFM #FM

I am using MedeA VASP for DFT calculations but do not have the MT module, which helps generate distorted structures for stiffness tensor calculations. Could anyone suggest GNU software or provide a tutorial for manually generating distorted structures to calculate mechanical properties?

I am performing relax calculation using DFT, on Quantum espresso. I have accidentally deleted the out directory (temp folder). My calculations are still running without that folder. Are those calculations considered as valid?

I would like to calculate the dielectric function in the EUV region (photon energy = 92 eV) for a cluster-type material using VASP. When I added the LOPTICS tag in the INCAR file and performed the calculation, the dielectric function was only computed up to around 30 eV, and I am not getting results for higher energy ranges. I am wondering how I can modify my calculation to obtain the dielectric function in the 92 eV region. Since this is my first time calculating the dielectric function, I would greatly appreciate any assistance you could provide. Thank you in advance!

Hello everyone,

I am interested in DFT calculation and liquid electrolytes.

I want to make some kind of my own data base of electrolytes, and I want to add dielectric constant information in it.

So, is it possible to calculate dielectric constant with gaussian 16 DFT calculation?

I want to know how to calculate it with DFT, conceptual DFT(CDFT) or other way.

I would greatly appreciate your assistance.

Thank you.

When doing catalytic DFT calculation, there are W,Nb elements, DFT+U. How much should this U value be added? Could you please provide relevant literature? Thank you

Hello Researchers,

Can anyone please answer, how to optimize the Nickel complex using gaussian 16 software. It was showing convergence error in Maximum displacement RMS displacement while optimizing the Ni complex. How to resolve this?

With regards,

Maithra N.

Research Scholar

How does no. of k-points affect DFT calculations and how many k-points are generally required for calculation of magnetic susceptiility in DFT+eDMFT framework?

Hi,

I am interested in calculation dielectric function of bulk materials. I have seen there are many ways to do that e.g, DFT epsilon.x, yambo Independent Particle: Random Phase Approximation, yambo BSE. Would someone please explain me the basic difference among the ways to calculate dielectric function?

Thanks

I've been working on the TiO2 anatase and rutile. the bandgap value is always less by 1 even when I apply hubbard correction.

In the attachment, $S(\omega)$ is a transmission function, $\epsilon_1$ and $\epsilon_2$ are real and imaginary dielectric functions respectively. If we notice the equation carefully, we need $\epsilon (q, \omega)$ since the summation includes all the q points in the 1st BZ.

Normally if I do DFT using Quantum Espresso, I would get the dielectric function ($\epsilon$) over frequency ($\omega$) ranges. Are there anyway I would get dielectric function $\epsilon(\omega)$ at each q point?

The link of the paper related to the equation (9) (https://journals.aps.org/prapplied/abstract/10.1103/PhysRevApplied.14.024080)

Thank you in advance for your time.

Hello dear researchers

Please I have a problem with pdos using qe

I have calculated dos, and I get it, but when I calculated pdos using projwfc.x, I got 0 values for all orbitals!!!!

I used paw pps and I don't know why this happen?

Please if someone can help me or met this problem before!?

I put some files attached here: dos.in, projwfc.in and some orbitals files (all pdos files are set to 0, you can see that all the columns are 0)!!

Hello everyone,

I am running a DFT calculation on a cationic molecule that was optimized in the gas phase, and I am trying to calculate frequencies in a solvent. My problem is that my calculation stops almost immediately without any error message. I tried both increasing and lowering the %mem and %nprocshared, but it doesn’t seem to make any difference. It also doesn’t seem to be a problem of free memory. I will add the start of the input file and the output file.

Any suggestions are greatly appreciated.

The input file:

%nprocshared=4

%mem=4GB

%chk=posmetabutylsolvent.chk

# freq geom=connectivity scrf=(cpcm,solvent=chloroform) bp86 def2svp empiricaldispersion=gd3 scf=xqc

Title card required

1 1

The outputfile (log) ends in:

Error on total polarization charges = 0.01698

SCF Done: E(RB-P86) = -1697.90030406 A.U. after 18 cycles

NFock= 18 Conv=0.22D-08 -V/T= 2.0122

QCSCF skips out because SCF is already converged.

Range of M.O.s used for correlation: 1 778

NBasis= 778 NAE= 139 NBE= 139 NFC= 0 NFV= 0

NROrb= 778 NOA= 139 NOB= 139 NVA= 639 NVB= 639

Number of processors reduced to 2 by ecpmxn.

Symmetrizing basis deriv contribution to polar:

IMax=3 JMax=2 DiffMx= 0.00D+00

G2DrvN: will do 82 centers at a time, making 1 passes.

Calling FoFCou, ICntrl= 3507 FMM=T I1Cent= 0 AccDes= 0.00D+00.

I am using Materials Studio and the CASTEP software package. I would like to apply Hubbard U corrections to a model that includes transition metals. Should I directly adjust the Hubbard U values for the atoms in the "Electronic Configuration" section, and do I need to enable the LDA+U option during the calculations?

If I don't use LDA+U, will the system be unable to recognize the Hubbard U correction values?

Hi,

I'm currently working on a project where I need to plot the atom-projected band structure using GPAW.

I've been able to calculate the band structure for my material, but I'm having trouble figuring out how to separate and visualize the contributions from different atomic species.

I need something like https://vaspkit.com/_images/hse-band3.png

Hello dear colleagues and professors

Please what is the recommended type of pseudopotentials for QE? ultrasoft or norm conserving??

And from where get all types of pseudos (us, nc, pbe, pbesol,......)

Tanks in advance

Hello!

I am trying to calculate the sumatriptan molecule, but it has been counting for five days and it does not stop. It seems to me that it is too long and I am doing something wrong. Please tell me what could be the problem?

Input:

# avogadro generated ORCA input file

# Basic Mode

#

! BP RI OPT FREQ def2-TZVP def2/J MORead

%moinp "sum.gbw"

* xyz 0 1

N -1.99683 -0.61751 0.56068

C -3.38421 -1.05078 0.53663

S -1.46076 0.59672 -0.38865

O -0.60439 1.41760 0.41204

H -4.06231 -0.32173 0.98125

H -3.45379 -1.98810 1.08542

H -3.70087 -1.22880 -0.48731

H -1.53765 -0.61339 1.45140

C -0.46185 -0.19150 -1.64040

C 0.72017 -0.96656 -1.11643

C 0.68937 -2.35779 -1.09780

C 1.77154 -3.09770 -0.62587

C 2.88728 -2.42792 -0.16698

C 2.92766 -1.02970 -0.17915

C 1.85318 -0.29474 -0.65060

H -0.18968 -2.87637 -1.45847

H 1.87232 0.78581 -0.64740

H 1.72750 -4.17956 -0.62422

C 4.23502 -0.58695 0.36624

C 4.93830 -1.67431 0.69163

C 4.18600 -2.94746 0.39508

H 5.93031 -1.67976 1.11862

H 4.03032 -3.54919 1.29574

H 4.71826 -3.58102 -0.32107

H -1.14698 -0.81816 -2.20688

H -0.16123 0.63830 -2.28024

O -2.58377 1.16383 -1.07227

C 4.56722 0.87357 0.52634

C 6.00389 1.26215 0.89652

H 3.89398 1.26473 1.29479

H 4.30255 1.40727 -0.38913

N 6.84232 1.59565 -0.23722

C 8.04565 2.28579 0.15422

C 7.10642 0.51320 -1.15266

H 7.66638 0.88911 -2.00983

H 6.17908 0.08687 -1.52887

H 7.69254 -0.30320 -0.70096

H 8.59085 2.61615 -0.73072

H 8.72882 1.66328 0.75482

H 7.79999 3.17177 0.74083

H 6.46026 0.48850 1.53323

H 5.94667 2.15757 1.51494

*

I am doing adsorption calculations on different surfaces of a metal using DFT, calculating work functions and adsorption energies. Is it Possible that a certain surface of a metal has higher work function as compare to other surfaces but certain elements are adsorbed easily on the same high work function surface as compared to other surfaces. I have attached the picture for a reference to look. the adsorption energy shows easier adsorption as compare to other surfaces, but the same surface has the highest work function as compare to other surfaces. I will be really thankful, if someone can explain it.

I'm trying to study the effects of introducing vacancy defects in my material. If I optimize my structure and find the lattice parameter before introducing vacancy, should I again optimize my structure after creating the vacancy?

Kindly give your thoughts!

Hello dear colleagues and professors

Please what is the recommended type of pseudopotentials for QE? ultrasoft or norm conserving??

And from where get all types of pseudos (us, nc, pbe, pbesol,......)

Tanks in advance

I am trying for the structure optimization via Gaussian16 DFT calculation, for a system consisting of C,H, N, O and Ce atoms. Where I am using B3LYP/ 6,311G(d,p) C, H, N and O and B3LYP/SDD for Ce. I am having error termination Error termination via Lnk1e in /share/apps/gaussian/g16/l502.exe

Any suggestion for normal termination?

Hello dear researchers, I hope you are doing well.

I want to ask you a question. I have a unit cell with 24 atoms (4 A, 4 B and 16 X) and I want to substitute X atom by another atom (for example changing one X by other element).

My question is, can I substitute it within the unit cell without making supercell?? or should I make a supercell??

I want to perform DFT calculations for a triple cation mixed crystal. Which software is preferable and free?

Dear RG Members,

Does anyone know about a software/package/utility for finding out all the possible interstitial sites for doping in any crystal structure provided depending upon dopant radii or some other parameter?

This is in regard to the first-principle DFT calculations of interstitially doped systems.

Also please share your experiences in this regard!

Thank you

Rohit

I have seen during DFT calculation some authors comment that LDA/GGA functional overestimates/underestimates the band gap/lattice constant of some materials. Before going to the main calculation, it is recommended that we can plot phonon dispersion plot (say) to verify results with literature data so that future calculations goes well.

For example: my intention is to calculate optical properties (say dielectric function) of a material (say GaAs). And I am using a GGA functional which underestimate the band gap from experimental value. At that position, what should I do? Should I use that pseudopotential to run the necessary executables (scf, nscf, epsilon etc)? Or I have to improve the band gap first and make it close to experimental value and after that I should run the executables (scf, nscf, epsilon etc) to find out optical properties?

Hi Collegues,

To calculate entropy (T*S) and Gibbs (G) free energy of electroreductions using computational hydrogen electrode (CHE) model (according to this equation, G = E + ZPE - TS + U), can we use vaspkit after frequency calculation by VASP? I have attached some examples they mentioned on the vaspkit.

Thank you.

Dear Researchers,

I hope this email finds you well.

I am currently working on research involving DFT calculations to study the mechanism of CO2 reduction using a catalyst with water as the reactant. I am utilizing Gaussian software for this purpose. However, I am encountering difficulties in setting up and running the reaction mechanism within Gaussian.

I am reaching out to see if anyone with experience in this area could provide some guidance or advice on how to proceed. Any help or suggestions would be greatly appreciated.

Thank you very much for your assistance.

I have intel iris xe graphic card. i want to run dft calculation in gaussian using a gpu. what are the necessary modifications to the input file? my input file read like this:

%chk=gagl.chk

%mem=1gb

%nprocshared=4

# opt b3lyp/6-311+g(d,p) geom=connectivity

i tried increasing processor and memory but the program terminate

Would anyone please guide me stepwise how can I find lattice parameters of a material, for example: Si, GaAs, at a finite temperature using Car-Parrinello Molecular Dynamics (CPMD)?

Thank you

When I optimize the structure, there is a difference in energy with and without LORBIT tags under exactly the same conditions.

Does anyone know why there is this difference?

I am trying to run geometry optimization and MD for Li3Sb strucutre but GFN2-xTB doesn't converge. I tweaked max iterations, fmax, scf accuracy and mixer damping etc. values as much as possible but no success at all. Same parameters work for GFN1-xTB.

I am using TBLite with ASE. Tried BFGS and FIRE optimizers until now.

Using Langevin for MD calculation.

Is it possible to somehow make it work?

You can see the .xyz file attached.

Here are the parameters which work for GFN1-xTB:

--method GFN1-xTB --task opt --structure data/li3sb_2x_vacx2.xyz \ --pbc --cell 13.118 13.118 13.118 --fmax 0.15 --steps 5000 \ --maxstep 0.05 --mixer_damping 1 --scf_accuracy 1 --max_iterations 5000 \ --optimizer FIRE --verbosity 1 \ # --charge 0 --multiplicity 1 \

Hello dear researchers, I hope you are doing well.

I want to ask you a question. I have a unit cell with 24 atoms (4 A, 4 B and 16 X) and I want to substitute X atom by another atom (for example changing one X by other element).

My question is, can I substitute it within the unit cell without making supercell?? or should I make a supercell??

Hi, I am using VASP to simulate interface of 2 block material slabs. After bringing them together I can get the stress tensor for the whole simulation box from OUTCAR. However, is there any way to calculate local stress tensors for these 2 sides of the interface separately?

I'm a fresh research scholar working on DFT, where i used Gaussian for computational method. Currently, i'm working on water-silver complex. But i cannot run the program as it shows error which is given below. Please help me out!

QPErr --- A syntax error was detected in the input line.

'

Last state="Top"

TCursr= 1082 LCursr= 0

Error reading general basis specification

I attempted calculations for hydrogen adsorption on transition metal-doped g-C3N4.

I want to know if it is possible to perform geometry optimization without enabling spin polarization, and then enable spin polarization for a second calculation with the optimized structure. Will the results obtained this way be correct?

Hello everyone,

I want to learn about high-throughput DFT calculations, but I have no idea so far where to start or what tools to use. I want to learn it from scratch. Any suggestions (papers, tools, website, YouTube video) would be really helpful for a beginner like me.

Thanks.

Hello everybody !

I am working on a medium size organic molecule (around 40 atoms) and I try to check the presence of a conical intersection between S1 and S0. I used DFT and TD-DFT to compute the PES of S0 and S1 in my molecule along different modes and motions but for now no conical intersection was identified.

Do you think it would be a possible and interesting approach to use TD-DFT/MD simulation to start from the S1 optimized geometry and apply temperature to check the evolution of the geometry in the S1 state of the molecule in time ? Will it go back to the S0 optimized geometry in the case of an easy accessible conical intersection ?

Thank you for any help you may provide and for your interesting comments about it.

Hello,

I hope this message finds you well. I have just started to learn gaussian software. While running NLO calculations I used the keyword:

#p b3lyp/6-31g(d,p) geom=connectivity gfinput polar=(DCSHG, Cubic) CPHF=RdFreq 

Later I came to know the common keyword used for NLO is:

Which is the most apt set of keyowrds. And what is the difference between # and #p.

The structure of hydroxyurea has been mentioned in different papers as a and b (attached figure). However, when I try to optimize the structure without restriction (at different theoretical levels), the resulting output is c. why does it happen?

Hi

There are various types of antiferromagnetic states,of which A-,C- and G- type are of my interest.These types depend upon the configuration of spins.

When the (magnetic) atoms are at corners, it is easy to assign spin orientation to each to get the three states.However,when they are face-centered and edge-centered, i face issues in assigning the orientations.Kindly, help me out.,which to keep up and which down.

Regards

Dear Siesta users,

I'm new using Siesta. I read some tutorials and the manual, but I don't understand how to set the Electronic Temperature properly. It is a smearing function, that is quite useful for metallic systems, with the default value of 300 K.

However, how can I know it is the best value? I'll work with crystal structures that usually show a bandgap between 3-6 eV... Is it ok to use 300K or should I change it?

Finally, during my convergence test (meshcutoff and k-points), ETot and FreeEng are different.. Which one should I use to plot the Energy x mesh/kpoints curves?

Thank you for your help

Dear Colleagues,

I am a beginner in the field of computational chemistry, and my interests are primarily focused on the calculation of magnetic states and exchange interactions for 3d- and 4f-block metal coordination compounds. In particular, I am interested in the broken-symmetry DFT calculation for a binuclear Gd(III) complex using ORCA 5 software. The overall procedure seems clear to me, yet the following issue arises.

First of all, I generate a "fragmented" initial guess orbitals via separate DFT calculations for gadolinium centers and organic ligands, and then combine them together through the orga_mergefrag routine. Nevertheless, when I use this guess for the further DFT calculation of the overall molecule (no matter, HS or BS state), the SCF convergence exhibits a sudden increase in energy (ca. 0.0006 Eh) after resetting KDIIS, and eventually, the SCF converges to a higher energy than one could expect.

I use DKH approximation with the appropriate basis sets (DKH-DEF2-SVP and SARC2-DKH-QZVP for organic ligands and Gd, respectively) and PBE0 functional. Additionally, the RIJ-COSX approximation was implied.

Which set of ORCA parameters would be appropriate in my case to achieve a stable and reliable SCF convergence for binuclear gadolinium complexes? Perhaps I should use !SlowSCF or !defgrid3 instructions?

Hi all,

I encountered an error while running SCF with SOC+U using Quantum Espresso 7.3.

Here is the error%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

Error in routine c_bands (1):

too many bands are not converged

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

How to solve this error?

Thanks

Log(output) file preview is as below:

Search did not lower the energy significantly.

No lower point found -- run aborted.

Error termination via Lnk1e in /opt/g16/l508.exe

Job cpu time: 0 days 14 hours 4 minutes 28.9 seconds.

Elapsed time: 0 days 2 hours 54 minutes 57.4 seconds.

File lengths (MBytes): RWF= 138 Int= 0 D2E= 0 Chk= 8 Scr= 1

I was trying to relax my monoclinic structure, but after the calculation in the output file the lattice vectors are written instead of lattice parameters for next scf calculation. From the lattice vectors I have calculated the lattice parameters but somehow I am getting wrong

What are the efficient online sources to self-learn DFT calculations useful for students with chemistry background ?

I am calculation for optimization of TS of an aromatic molecule and a hydroxyl radical. In this DFT calculation, I am using the functional B3lyp/6-311+G(d,p) in the Gaussian16. The charge and multiplicity was ensured as 0, 2. But at the end it gives the following error message:

Error on total polarization charges = 0.05019

SCF Done: E(UM062X) = -323.942120576 A.U. after 401 cycles

NFock=400 Conv=0.36D-03 -V/T= 2.0041

<Sx>= 0.0000 <Sy>= 0.0000 <Sz>= 0.5000 <S**2>= 0.7612 S= 0.5056

<L.S>= 0.000000000000E+00

SMD-CDS (non-electrostatic) energy (kcal/mol) = 2.33

(included in total energy above)

Annihilation of the first spin contaminant:

S**2 before annihilation 0.7612, after 0.7501

Convergence failure -- run terminated.

Hello. I was trying to simulate the hydrated Nickel cation [Ni(H₂O)₆]²⁺ and my calculation setup is not working.

For that, I used the aug-cc-pVDZ basis sets for H and O; and Lanl2DZ for Ni. Attached are my code and two figures.

As I know for there should be inversion symmetry breaking.For gold layer this symmetry has broken.But how can I implement this symmetry broken in quantum espresso ?

By just taking the slab model and turn on the lspinorb or I have to applied an external field using tefield to break the symmetry ?

I did a branch of the DFT calculation to find the stable cell parameter (a) .

I didn't get the smooth curve for energy(E) v.s a. There is some point out of concave curve that I had to repeat calculation for them to get the best energy.

Now I doubt about the result and I look for techniques to test the stability of wave function like like something in GAUSSIAN code.

does increasing or decreasing size of supercells affect these in DFT calculation?