Replication data for: Topological Feature Engineering for Machine Learning Based Halide Perovskite Materials Design (doi:10.21979/N9/CVJWZ9)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Replication data for: Topological Feature Engineering for Machine Learning Based Halide Perovskite Materials Design

doi:10.21979/N9/CVJWZ9

DR-NTU (Data)

2022-12-01

1

Anand, D Vijay; Xu, Qiang; Wee, Junjie; Xia, Kelin; Sum, Tze Chien, 2022, "Replication data for: Topological Feature Engineering for Machine Learning Based Halide Perovskite Materials Design", https://doi.org/10.21979/N9/CVJWZ9, DR-NTU (Data), V1

Replication data for: Topological Feature Engineering for Machine Learning Based Halide Perovskite Materials Design

doi:10.21979/N9/CVJWZ9

Anand, D Vijay (Nanyang Technological University)

Xu, Qiang (Nanyang Technological University)

Wee, Junjie (Nanyang Technological University)

Xia, Kelin (Nanyang Technological University)

Sum, Tze Chien (Nanyang Technological University)

python

matlab

vasp

M4081842.110

RG109/19

MOE-T2EP50120-0004

MOE-T2EP20120-0013

NRF-NRFI2018-04

DR-NTU (Data)

Sum, Tze Chien

Xu, Qiang

2022-09-10

https://doi.org/10.21979/N9/CVJWZ9

Mathematical Sciences, Physics, Mathematical Sciences, Physics, topology, machine learning, halide perovskite

Accelerated materials development with machine learning (ML) assisted screening and high throughput experimentation for new photovoltaic materials holds the key to addressing our grand energy challenges. Data-driven ML is envisaged as a decisive enabler for new perovskite materials discovery. However, its full potential can be severely curtailed by poorly represented molecular descriptors (or fingerprints). Optimal descriptors are essential for establishing effective mathematical representations of quantitative structure-property relationships. Here we reveal that our persistent functions (PFs) based learning models offer significant accuracy advantages over traditional descriptor based models in organic-inorganic halide perovskite (OIHP) materials design and have similar performance as deep learning models. Our multiscale simplicial complex approach not only provides a more precise representation for OIHP structures and underlying interactions, but also has better transferability to ML models. Our results demonstrate that advanced geometrical and topological invariants are highly efficient feature engineering approaches that can markedly improve the performance of learning models for molecular data analysis. Further, new structure-property relationships can be established between our invariants and bandgaps. {We anticipate that our molecular representations and featurization models will transcend the limitations of conventional approaches and lead to breakthroughs in perovskite materials design and discovery.

calculated data

<a href="https://github.com/ExpectozJJ/PF-OIHP"> https://github.com/ExpectozJJ/PF-OIHP</a>

10.1038/s41524-022-00883-8

Anand, D. V., Xu, Q., Wee, J., Xia, K., & Sum, T. C. (2022). Topological feature engineering for machine learning based halide perovskite materials design. npj Computational Materials, 8(1), 1-8.

10356/165413

Anand, D. V., Xu, Q., Wee, J., Xia, K. & Sum, T. C. (2022). Topological feature engineering for machine learning based halide perovskite materials design. Npj Computational Materials, 8(1).

Label:

dfpt.tar.gz

Text:

raw data of dielectric constant of perovskites

application/x-gzip

Label:

fig.1.tar.gz

Text:

Data for replication and high-resolution image for Figure 1.

application/x-gzip

Label:

fig.2.tar.gz

Text:

Data for replication and high-resolution image for Figure 2.

application/x-gzip

Label:

fig.3.tar.gz

Text:

Data for replication and high-resolution image for Figure 3.

application/x-gzip

Label:

fig.4.tar.gz

Text:

Data for replication and high-resolution image for Figure 4.

application/x-gzip

Label:

fig.5.tar.gz

Text:

Data for replication and high-resolution image for Figure 5.

application/x-gzip

Label:

fig.SI.tar.gz

Text:

Data for replication and high-resolution images for Supplementary Figures (total of 3 figures).

application/x-gzip

Label:

HOIP_database_DRYAD.rar

Text:

database of perovskites for Figure 4, Figure 5, and Supplementary Figures (total of 3 figures).

application/x-rar-compressed

Label:

MAPbX3_sc333_pdb.tar.gz

Text:

raw data of perovskite structures for Figure 4, Figure 5, and Supplementary Figures (total of 3 figures).

application/x-gzip

Label:

md_structure.tar.gz

Text:

raw data of perovskite MD structures for Figure 3.

application/x-gzip