👍 On 19 Aug 2025, at 17:34, Kazume NISHIDATE <nisid...@iwate-u.ac.jp> wrote:
I would recommend reading the literature instead of asking a large-language model I completely agree with your opinion. I had been afraid that the questioner was satisfied with the Gemini's reply since there had not been a reply from him. Don't be deceived by a likely-sounding story. :) Just a supplementary note. The questioner posted his message as his AI returned the “(AI tells me that) it is possible" message. And he did not ask further on AI, but on this mailing list. It might mean that he thought that he would not have the correct answer if he asked further. I was surprised that the AI could reply to such a question, and wondered if it could reply further when it received an 'appropriate' question. And my last message inclued Gemini’s reply. Yes, the answer is misleading. But it may be helpful to make a template for an FAQ document. 2025/08/19 20:01、Lorenzo Paulatto <lorenzo.paula...@cnrs.fr>のメール: I would recommend reading the literature instead of asking a large-language model, but I admit there is a real risk of learning something useful beyond your query. Studying the literature to have an idea of the actual magnitude of the effect, how people have computed it in the past, and if it may impact your case will save you a lot of time in the long run. In any case, whatever Gemini has barfed is not wrong, but very generic and extremely unpractical for a system with more than a handful of atoms. If there is a well-separated vibrational mode associated with the molecule-surface interface, it is possible to find its energy via the phonon code (option nat_todo), or just with pw.x using frozen phonons. hth On 12/08/2025 15:14, Kazume NISHIDATE wrote: And I asked it to Gemini, Google’s AI. Here is her response 😲 ========================= Yes, it's possible to include the zero-point energy (ZPE) correction for both a 2D surface and a 2D surface with adsorbed atoms using Quantum ESPRESSO. This correction is crucial for accurately calculating energies, such as adsorption energies, as it accounts for the vibrational energy of the atoms even at absolute zero temperature (0 K). To calculate the ZPE correction, you must perform phonon calculations for your systems. Quantum ESPRESSO's phonon code, ph.x, is the primary tool for this. The ZPE is half the sum of all vibrational frequencies, represented by the following formula: ZPE=21i∑ℏωi Where: • ℏ is the reduced Planck constant. • ωi are the vibrational frequencies (eigenfrequencies) of the system's normal modes. 1. Zero-Point Energy Correction for a 2D Surface To calculate the ZPE for a 2D surface, you'll follow these general steps: • Optimize the geometry of your 2D surface slab to find the lowest-energy configuration. • Run a self-consistent field (SCF) calculation on the optimized structure. This calculation is a prerequisite for the phonon calculation. • Perform a phonon calculation using ph.x. This involves calculating the vibrational modes across a q-point grid in the Brillouin zone. The output will be the phonon frequencies. • Process the phonon output to get the total ZPE. This often involves using a post-processing tool like matdyn.x to diagonalize the dynamical matrices and sum up the positive frequencies. The ZPE is then calculated from this sum. For a 2D surface, it's important to use a supercell that is large enough to minimize the interactions between periodic images and to ensure a sufficient vacuum layer in the z-direction. 2. ZPE Correction for an Adsorbed System For a system with an adsorbed molecule on a 2D surface, the process is similar but with an important distinction: you need to calculate the ZPE correction for three separate systems to determine the corrected adsorption energy. The ZPE-corrected adsorption energy (ΔEadsZPE) is calculated as follows: ΔEadsZPE=(Eslab+adsorbateDFT+ZPEslab+adsorbate)−(EslabDFT+ZPEslab)−(EadsorbateDFT+ZPEadsorbate) Where: • EDFT is the ground-state electronic energy from a standard DFT calculation (e.g., using pw.x). • ZPE is the zero-point energy of each system. To get the ZPEs, you'll perform a phonon calculation for each of the three components: • Adsorbed System (Slab + Adsorbate): • Optimize the geometry of the combined system. • Run an SCF calculation. • Run a phonon calculation using ph.x. To save computational time, you can often freeze the atoms of the bulk surface layers and only allow the adsorbate atoms and the top surface layer atoms to move. This is a common approximation. • Calculate the ZPE from the phonon frequencies. • Isolated Surface (Slab): • Optimize the geometry of the clean surface slab. • Run an SCF calculation. • Run a phonon calculation. Again, you can freeze the bottom layers to reduce the computational cost. • Calculate the ZPE. • Isolated Adsorbate (Molecule): • Optimize the geometry of the isolated molecule in a large vacuum cell. • Run an SCF calculation. • Run a phonon calculation. For a molecule, all atoms are allowed to move. • Calculate the ZPE from the frequencies. After obtaining the ZPE values for all three systems, you can substitute them into the equation to get the final ZPE-corrected adsorption energy. 2025/08/12 17:28、Chiara Cignarella via users <users@lists.quantum-espresso.org>のメール: Dear Ashley, You can use the frequencies obtained by phonon calculations to compute the zero-point energy using the formula (you can find that in textbooks on the quantum harmonic oscillator part - for example Ashcroft pag. 451- ), i.e. doing the sum \sum_i 1/2 * \omega_i * hbar (divided by appropriate normalization factor for your sum) Note that the computed phonons do not contain themselves the ZPM contributions! Hope this is useful. Best regards, Chiara Cignarella ------------------------------------- Post-doc researcher University of Bremen On 12 Aug 2025, at 09:51, Barsha Pal <barsha....@aus.ac.in> wrote: Hello, I have a small doubt regarding whether or not zero-point energy calculation is possible in Quantum Espresso, I want to perform that for a 2D material and adsorption cases. The property that I aim, includes the zero-point energy correction for the 2D surface and the 2D surface with adsorbed atoms. AI tells me that it is possible to do by phonon calculation. If indeed this is possible, can you guide me towards a short example? Thank you. Ashley Cooper Phd _______________________________________________________________________________ The Quantum ESPRESSO Foundation stands in solidarity with all civilians worldwide who are victims of terrorism, military aggression, and indiscriminate warfare. -------------------------------------------------------------------------------- Quantum ESPRESSO is supported by MaX (www.max-centre.eu) users mailing list users@lists.quantum-espresso.org https://lists.quantum-espresso.org/mailman/listinfo/users _______________________________________________________________________________ The Quantum ESPRESSO Foundation stands in solidarity with all civilians worldwide who are victims of terrorism, military aggression, and indiscriminate warfare. -------------------------------------------------------------------------------- Quantum ESPRESSO is supported by MaX (www.max-centre.eu) users mailing list users@lists.quantum-espresso.org https://lists.quantum-espresso.org/mailman/listinfo/users 西館数芽 Kazume NISHIDATE Ph.D Department of Systems Innovation Engineering, Graduate School of Science and Engineering, Iwate University 4-3-5 Ueda, Morioka, Iwate, 020-8551 JAPAN Phone:+81-19-621-6391 kazume.nishid...@gmail.com, nisid...@iwate-u.ac.jp https://sites.google.com/site/nisidatelab/ _______________________________________________________________________________ The Quantum ESPRESSO Foundation stands in solidarity with all civilians worldwide who are victims of terrorism, military aggression, and indiscriminate warfare. -------------------------------------------------------------------------------- Quantum ESPRESSO is supported by MaX (www.max-centre.eu) users mailing list users@lists.quantum-espresso.org https://lists.quantum-espresso.org/mailman/listinfo/users -- Dr. Lorenzo Paulatto IR IMPMC - CNRS UMR 7590 / Sorbonne Université / MNHN phone: +33 (0)1 442 79822 / telegram: lpaulatto http://www.impmc.upmc.fr/~paulatto/ - https://anharmonic.github.io/ 23-24/423 B115, 4 place Jussieu 75252 Paris CX 05 _______________________________________________________________________________ The Quantum ESPRESSO Foundation stands in solidarity with all civilians worldwide who are victims of terrorism, military aggression, and indiscriminate warfare. -------------------------------------------------------------------------------- Quantum ESPRESSO is supported by MaX (www.max-centre.eu) users mailing list users@lists.quantum-espresso.org https://lists.quantum-espresso.org/mailman/listinfo/users 西館数芽 Kazume NISHIDATE Ph.D Department of Systems Innovation Engineering, Graduate School of Science and Engineering, Iwate University 4-3-5 Ueda, Morioka, Iwate, 020-8551 JAPAN Phone:+81-19-621-6391 kazume.nishid...@gmail.com, nisid...@iwate-u.ac.jp https://sites.google.com/site/nisidatelab/ _______________________________________________________________________________ The Quantum ESPRESSO Foundation stands in solidarity with all civilians worldwide who are victims of terrorism, military aggression, and indiscriminate warfare. -------------------------------------------------------------------------------- Quantum ESPRESSO is supported by MaX (www.max-centre.eu) users mailing list users@lists.quantum-espresso.org https://lists.quantum-espresso.org/mailman/listinfo/users
_______________________________________________________________________________ The Quantum ESPRESSO Foundation stands in solidarity with all civilians worldwide who are victims of terrorism, military aggression, and indiscriminate warfare. -------------------------------------------------------------------------------- Quantum ESPRESSO is supported by MaX (www.max-centre.eu) users mailing list users@lists.quantum-espresso.org https://lists.quantum-espresso.org/mailman/listinfo/users
