Performance analysis of perovskite solar cells in 2013–2018 using machine-learning tools

Odabaşı, Çağla; Yıldırım, Ramazan

doi:10.1016/j.nanoen.2018.11.069

Cited by 108 publications

(95 citation statements)

References 173 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is mostly based on statistical analysis, but lacks a clear relationship drawn with the predicted results and the physics behind the model used. [23] In this paper, we focus on the prediction of bandgap properties of perovskite materials and its correlation with the performance of PSCs by ML algorithms. Additionally, a deeper understanding of physical phenomena related to PSCs is derived from our ML studies.…”

Section: Introductionmentioning

confidence: 99%

Predictions and Strategies Learned from Machine Learning to Develop High‐Performing Perovskite Solar Cells

Pradhan

Gaur

et al. 2019

Advanced Energy Materials

119

107

View full text Add to dashboard Cite

Perovskite solar cells (PSCs) have recently received considerable attention due to the high energy conversion efficiency achieved within a few years of their inception. However, a machine learning (ML) approach to guide the development of high‐performing PSCs is still lacking. In this paper ML is used to optimize material composition, develop design strategies, and predict the performance of PSCs. The ML models are developed using 333 data points selected from about 2000 peer reviewed publications. These models guide the design of new perovskite materials and the development of high‐performing solar cells. Based on ML guidance, new perovskite compositions are experimentally synthesized to test the practicability of the model. The ML model also shows its ability to predict underlying physical phenomena as well as the performance of PSCs. The PSC model matches well with the theoretical prediction by the Shockley and Queisser limit, which is almost impossible for a human to find from an ensemble of data points. Moreover, strategies for developing high‐performing PSCs with different bandgaps are also derived from the model. These findings show that ML is very promising not only for predicting the performance, but also for providing a deeper understanding of the physical phenomena associated with the PSCs.

show abstract

Section: Introductionmentioning

confidence: 99%

Predictions and Strategies Learned from Machine Learning to Develop High‐Performing Perovskite Solar Cells

Pradhan

Gaur

et al. 2019

Advanced Energy Materials

119

107

View full text Add to dashboard Cite

show abstract

“…Devices with a p-i-n architecture are often constructed with a planar structure with a compact HTL. As shown from the statistical analysis in Figure 4 and reported in [4], the mesoporous configuration has been the one mostly adopted and the one responsible for the record efficiency. However, in the last year, also the planar configuration made enormous steps forward.…”

Section: State Of the Art On Materials And Device Stabilitymentioning

confidence: 90%

“…3b). Phenomena such as light induced ion movement, "photo-instability", or structural deformations not only disturb the material stability, but also alter the device behavior, contributing to the anomalous hysteresis observed in the device current-voltage characteristics that has not yet been clearly understood [3][4][5]. Despite the urgency, only in the last couple of years research attention has been devoted to…”

Section: Optoelectronic Propertiesmentioning

confidence: 99%

A new era for solar energy: hybrid perovskite rocks

Grancini

2019

Photoniques

View full text Add to dashboard Cite

With the world population swelling and rapid technological innovations imposing global network and connections, the growing energy demand has reached unprecedented levels: “The energy industry is facing decades of transformation,” reported the World Energy Council at the end of 2018 [1]. Increasing use of renewable energy sources and photovoltaics is thus utmost for Europe to meet the goals imposed by the Paris Agreement. From a research point of view, this pushes an enormous effort into discovery of new materials, new physical phenomena and development of new technologies to sustain such paradigm shift to a low-carbon society.

show abstract

“…[72] The average performance of the device based on the widely used ETL material and efficiencies distribution are shown in Figure S4a,b (Supporting Information), respectively. [72] The average performance of the device based on the widely used ETL material and efficiencies distribution are shown in Figure S4a,b (Supporting Information), respectively.…”

Section: Wwwadvancedsciencenewscommentioning

confidence: 99%

“…In a recent work by Odabaşı and Yildirım, performance analysis of 1921 PSCs was conducted by using machine-learning tools, the performance data points were derived from 800 publications on the PSCs published between 2013 and 2018. [72] The average performance of the device based on the widely used ETL material and efficiencies distribution are shown in Figure S4a,b (Supporting Information), respectively. Obviously, from Figure S4 (Supporting Information), although TiO 2 is still the popular option, SnO 2 seems to give higher performances; the cells with ZnO and without any ETL also have performances comparable to TiO 2 .…”

Section: Wwwadvancedsciencenewscommentioning

confidence: 99%

Simple, Robust, and Going More Efficient: Recent Advance on Electron Transport Layer‐Free Perovskite Solar Cells

Huang

2019

Advanced Energy Materials

View full text Add to dashboard Cite

Perovskite solar cells (PSCs) have shown great potential for photovoltaic applications with their unprecedented power conversion efficiency advancement. Such devices generally have a complex structure design with high temperature processed TiO2 as the electron transport layer (ETL). Further careful design of device configuration to fully tap the potentials of perovskite materials is expected. Particularly, for the practical application of PSCs, it is crucial to simplify their device structures thus the associated manufacturing process and cost while maintaining their efficiency to be comparable with the conventional devices. But how simple is simple? ETL‐free PSCs promise the simplest structured, thus simple manufacturing processes and low cost large area PSCs in practical applications. They can also help the further exploration of the great potential of perovskite materials and understanding the working principle of PSCs. Within this review, the evolution of the PSC is outlined by discussing the recent advances in the simplification of device configuration and processes for cost effective, highly efficient, and robust PSCs, with a focus on ETL‐free PSCs. Their advancement, key issues, working mechanism, existing problems, and future performance enhancements. This review aims to promote the future development of low cost and robust ETL‐free PSCs toward more efficient power output.

show abstract

Performance analysis of perovskite solar cells in 2013–2018 using machine-learning tools

Cited by 108 publications

References 173 publications

Predictions and Strategies Learned from Machine Learning to Develop High‐Performing Perovskite Solar Cells

Predictions and Strategies Learned from Machine Learning to Develop High‐Performing Perovskite Solar Cells

A new era for solar energy: hybrid perovskite rocks

Simple, Robust, and Going More Efficient: Recent Advance on Electron Transport Layer‐Free Perovskite Solar Cells

Contact Info

Product

Resources

About