Identifying Pb-free perovskites for solar cells by machine learning

Im, Jino; Lee, Seongwon; Ko, Tae Wook; Kim, Hyun Woo; Hyon, Yun Kyong; Chang, Hyunju

doi:10.1038/s41524-019-0177-0

Cited by 176 publications

(136 citation statements)

References 52 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…It can be seen from the figure that the Pauling electronegativity has a considerable influence on the formation energy of perovskite. It is worth noting that X's importance score is more than twice higher than the second highest feature, which is consistent with the results of the two literatures [27,39] analyses. predict the formation energy of perovskites, we compare it with the descriptors proposed by Ong et al [33] (Ong_Descriptors) and the Magpie features.…”

Section: Selection Of the Best Materials Features And Analysis Of Featsupporting

confidence: 89%

Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning

Dan

Dong

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

As one of the most studied materials, perovskites exhibit a wealth of superior properties that lead to diverse applications. Computational prediction of novel stable perovskite structures has big potential in the discovery of new materials for solar panels, superconductors, thermal electric, and catalytic materials, etc. By addressing one of the key obstacles of machine learning based materials discovery, the lack of sufficient training data, this paper proposes a transfer learning based approach that exploits the high accuracy of the machine learning model trained with physics-informed structural and elemental descriptors. This gradient boosting regressor model (the transfer learning model) allows us to predict the formation energy with sufficient precision of a large number of materials of which only the structural information is available. The enlarged training set is then used to train a convolutional neural network model (the screening model) with the generic Magpie elemental features with high prediction power. Extensive experiments demonstrate the superior performance of our transfer learning model and screening model compared to the baseline models. We then applied the screening model to filter out promising new perovskite materials out of 21,316 hypothetical perovskite structures with a large portion of them confirmed by existing literature.

show abstract

Section: Selection Of the Best Materials Features And Analysis Of Featsupporting

confidence: 89%

Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning

Dan

Dong

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In contrast, the data‐driven approach starts from an initial large set of candidate features and down‐selects a subset of features. This down‐selection process can be automatic, e.g., using L 1 or L 0 regularization (least absolute shrinkage and selection operator, LASSO), feature importance, genetic algorithms, etc. However, a drawback of data‐driven feature selection is that the selected features do not imply causality with respect to the target and will be highly dependent on the chosen hyperparameters of the model .…”

Section: Featurizationmentioning

confidence: 99%

“…Most ML works on halide perovskites have thus far focused on inorganic perovskites, due to the difficulty in modeling rotational disorder in organic cations such as methylammonium. Im et al have used DFT to compute the heat of formation and bandgaps of 540 Pb‐free halide double perovskites (A 2 B(I)B(III)X 6 ) and subsequently used the data to develop gradient boosting regression trees (GBRT) models. The best achieved RMSE on heat of formation is 21 meV per atom, and that of GGA bandgap is 0.223 eV.…”

Section: Applicationmentioning

confidence: 99%

A Critical Review of Machine Learning of Energy Materials

Chen

Zuo

et al. 2020

Advanced Energy Materials

420

281

View full text Add to dashboard Cite

Machine learning (ML) is rapidly revolutionizing many fields and is starting to change landscapes for physics and chemistry. With its ability to solve complex tasks autonomously, ML is being exploited as a radically new way to help find material correlations, understand materials chemistry, and accelerate the discovery of materials. Here, an in‐depth review of the application of ML to energy materials, including rechargeable alkali‐ion batteries, photovoltaics, catalysts, thermoelectrics, piezoelectrics, and superconductors, is presented. A conceptual framework is first provided for ML in materials science, with a broad overview of different ML techniques as well as best practices. This is followed by a critical discussion of how ML is applied in energy materials. This review is concluded with the perspectives on major challenges and opportunities in this exciting field.

show abstract

“…However, excitons rapidly dissociate in these materials, therefore this pathway is not expected to be efficient. Further investigation into Ruddlesden-Popper type perovskite-inspired materials [84][85][86] and less toxic double perovskites, combined with machine learning approaches [87][88][89][90] to find suitable materials has the potential to break the field wide open. In sensitized UC, not only the perovskite can be tuned, rather, we can also tune the energetics of the upconverting species.…”

Section: Plos Onementioning

confidence: 99%

Engineering 3D perovskites for photon interconversion applications

Nienhaus

2020

PLoS ONE

View full text Add to dashboard Cite

In this review, we highlight the current advancements in the field of triplet sensitization by three-dimensional (3D) perovskite nanocrystals and bulk films. First introduced in 2017, 3D perovskite sensitized upconversion (UC) is a young fast-evolving field due to the tunability of the underlying perovskite material. By tuning the perovskite bandgap, visible-to-ultraviolet, near-infrared-to-visible or green-to-blue UC has been realized, which depicts the broad applicability of this material. As this research field is still in its infancy, we hope to stimulate the field by highlighting the advantages of these perovskite nanocrystals and bulk films, as well as shedding light onto the current drawbacks. In particular, the keywords toxicity, reproducibility and stability must be addressed prior to commercialization of the technology. If successful, photon interconversion is a means to increase the achievable efficiency of photovoltaic cells beyond its current limits by increasing the window of useable wavelengths.

show abstract

Identifying Pb-free perovskites for solar cells by machine learning

Cited by 176 publications

References 52 publications

Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning

Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning

A Critical Review of Machine Learning of Energy Materials

Engineering 3D perovskites for photon interconversion applications

Contact Info

Product

Resources

About