Skip to content

machine learning for the buried-interface engineering by organic modifiers

License

Notifications You must be signed in to change notification settings

Swordshinehjy/ML_perovskite_buired_interface

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ML_perovskite_buired_interface

Introduction

Source code for the paper Machine-Learning-Assisted Design of Buried-Interface Engineering Materials for High-Efficiency and Stable Perovskite Solar Cells

Cooperated with Qi Zhang.

Requirements

enviroments.yaml contains the required packages and versions.

Usage

Data Preparation

Follow the format of the data in the new_mol.csv file and put your data in the same format. The data should be in the form of a csv file with the following columns:

  • NumHAcceptors, NumHDonors, TPSA, MolLogP: Generated by RDKit
  • alkyl_num: Alkyl length of the linker (e.g., 2 for 2PACz and 4 for 4PACz)
  • frag_sym: Symmetry of the tail fragment (e.g., 1 for 2PACz because the carbazole ring is symmetric)
  • HOMO_calc, LUMO_calc: the HOMO and LUMO energies of the molecule in eV, calculated at the B3LYP-D3(BJ)/def2-SVP level of theory
  • dipole: the dipole moment of the molecule in Debye
  • MPI: molecular polarity index calculated by Multiwfn in kcal/mol (load the wavefunction file then input command 12 then 0)
  • surface_min: the surface minimum calculated by Multiwfn in kcal/mol (commond 12 then 0, see "Minimal value")
  • surface_max: the surface maximum calculated by Multiwfn in kcal/mol (commond 12 then 0, see "Maximal value")
  • PSA: the polar surface area (|ESP| > 10 kcal/mol) calculated by Multiwfn in Angstrom^2 (commond 12 then 0, see "Polar surface area (|ESP| > 10 kcal/mol)")
  • control_PCE: control PCE without modification
  • anchor_end: BA is for boronic acid, CA for carboxylic acid, PA for phosphonic acid, PO for phosphonate, SA for sulfonic acid, SH for thiol, SiO for siloxane, and NO for other nitrogen/oxygen-containing groups
  • MetalOxide: materials for the buried metal oxide

Prediction

load_pretained.ipynb contains the code for loading the pre-trained model and making predictions.

Citation

If you use this code in your research, please cite the following paper:

Zhang, Qi, et al. "Machine-Learning-Assisted Design of Buried-Interface Engineering Materials for High-Efficiency and Stable Perovskite Solar Cells." ACS Energy Letters 9 (2024): 5924-5934.

About

machine learning for the buried-interface engineering by organic modifiers

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published