2020
DOI: 10.1038/s41467-020-17945-4
|View full text |Cite|
|
Sign up to set email alerts
|

How machine learning can help select capping layers to suppress perovskite degradation

Abstract: Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We featurize 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI3) films, age them under accelerated conditions, and determine features governing stability using supervised mac… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
84
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 93 publications
(84 citation statements)
references
References 60 publications
0
84
0
Order By: Relevance
“…Generally, experimentation strategies with high reliance on user guidance and operation, require increased time commitment and level of expertise. Recent advances in AI, including deep neural networks (DNN) and reinforcement learning, for rapid chemical space exploration, [49][50][51][52][53][54][55][56][57][58][59][60][61] provide an exciting opportunity to reshape the development and on-demand manufacturing of colloidal nanomaterials. Consequently, a number of self-optimizing microfluidic reactors have been developed to take advantage of continuous material exploration in a low chemical consumption system.…”
Section: Doi: 101002/aisy202000245mentioning
confidence: 99%
“…Generally, experimentation strategies with high reliance on user guidance and operation, require increased time commitment and level of expertise. Recent advances in AI, including deep neural networks (DNN) and reinforcement learning, for rapid chemical space exploration, [49][50][51][52][53][54][55][56][57][58][59][60][61] provide an exciting opportunity to reshape the development and on-demand manufacturing of colloidal nanomaterials. Consequently, a number of self-optimizing microfluidic reactors have been developed to take advantage of continuous material exploration in a low chemical consumption system.…”
Section: Doi: 101002/aisy202000245mentioning
confidence: 99%
“…Among various techniques developed, introducing relatively bulkier, more hydrophobic organic moieties endowed with specific functional groups on top of the HPs layer has become one of the primary solutions to address the intrinsic chemical instability and defect states of the material. [27][28][29] Notably, such approach often involves the use of hybrid organic-inorganic salts with the cation being ammonium-based molecules (e. g., n-butylammonium, [30,31] 4hydroxybutan-1-aminium, [32] 2-phenylethylammonium, [24,33] 4-(carboxymethyl)-1H-imidazol-3-ium, [34] and 1-naphthylmethylammonium), [35] while the anion being the halides, in particular iodide. [30,[36][37][38][39][40] The relatively soft ionic character of HPs, in combination with the use of solution processing techniques, unavoidably generates a substantial amount of ionic defects at the materials surfaces.…”
Section: Introductionmentioning
confidence: 99%
“…Being Lewis bases, halide anions can bind to the undercoordinated Pb 2 + present on HPs surface by donating their electron lone pairs, forming coordinative acid-base complexes, which then passivate the defect sites. [28,29] However, they are also known to be relatively reactive. For example, iodide ion readily transforms to the elemental iodine, capable of forming triiodide complex both in solution and solid states.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations