Accelerated discovery of high-efficient N-annulated perylene organic sensitizers for solar cells via machine learning and quantum chemistry

Ju, Lifei; Li, Minjie; Tian, Lumin; Xu, Pengcheng; Lü, Weijie

doi:10.1016/j.mtcomm.2020.101604

Cited by 15 publications

(10 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eight linear models targeting the PCEs for each structure type were built along with their detailed feature interpretations, while ten new materials were designed with better predicted target values. Our group also has conducted relevant studies, especially on the interpretation of more abstract descriptors [92,93] . In our work [92,93] , 3 hardly interpretable descriptors were successfully unveiled in the relations between the structures of sensitizers and their PCE values, as illustrated in Section S2, where Mor14p and Mor24m could be explained in favor of C sp3 −S, C sp ≡ C sp , C sp2 = C sp2 and C-O bonds rather than the C sp3 − C sp3 bond.…”

Section: Molecular Descriptorsmentioning

confidence: 99%

“…Our group also has conducted relevant studies, especially on the interpretation of more abstract descriptors [92,93] . In our work [92,93] , 3 hardly interpretable descriptors were successfully unveiled in the relations between the structures of sensitizers and their PCE values, as illustrated in Section S2, where Mor14p and Mor24m could be explained in favor of C sp3 −S, C sp ≡ C sp , C sp2 = C sp2 and C-O bonds rather than the C sp3 − C sp3 bond. R2s depicts that the sensitizer structures should have a lower density of geometrically marginal atoms, owing to the stronger electronegativity or higher bond order of the R=O, R−F, and R≡N bonds.…”

Section: Molecular Descriptorsmentioning

confidence: 99%

“…A linear model is usually fitted by reducing the residual sum of squares between the observed and approximate target values via the ordinary least square method. In spite of its simplicity, there are still a large number of applications in photovoltaic fields [89,90,92,[147][148][149] . For example, in the works of Kar [89,90,[150][151][152][153] , the LR algorithm was largely employed to fit multiple robust linear models for DSSCs.…”

Section: Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Recent progress in the data-driven discovery of novel photovoltaic materials

Liu¹,

Li²,

Lü³

et al. 2022

J Mater Inf

Self Cite

View full text Add to dashboard Cite

The discovery of new photovoltaic materials can facilitate technological progress in clean energy and hence benefit overall societal development. Machine learning (ML) and deep learning (DL) technologies integrated with domain knowledge are revolutionizing the traditional trial-and-error research paradigm that is associated with high costs, inefficiency, and significant human effort. This review provides an overview of the recent progress in the data-driven discovery of novel photovoltaic materials for perovskite, dye-sensitized and organic solar cells. The integral workflow of the ML/DL training progress is briefly introduced, covering data preparation, feature engineering, model building and their applications. The cutting-edge challenges and issues in the ML/DL workflow are summarized specifically for photovoltaic materials. Real examples are emphasized to illustrate how to utilize ML/DL techniques in the discovery of novel photovoltaic materials. The prospects and future directions of the data-driven discovery of novel photovoltaic materials are also provided.

show abstract

Section: Molecular Descriptorsmentioning

confidence: 99%

Section: Molecular Descriptorsmentioning

confidence: 99%

Section: Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Recent progress in the data-driven discovery of novel photovoltaic materials

Liu¹,

Li²,

Lü³

et al. 2022

J Mater Inf

Self Cite

View full text Add to dashboard Cite

show abstract

“…ML needs quantum calculations to predict the efficiency of theoretically designed dyes. [298] The internet of things (IoT) has brought about changes in both domestic and industrial sectors. IoT has changed human life, too.…”

Section: Machine Learning (Ml) and Internet Of Things (Iot) In Dsscmentioning

confidence: 99%

Mapping the Progress in Natural Dye‐Sensitized Solar Cells: Materials, Parameters and Durability

Alim

Repon

Islam³

et al. 2022

ChemistrySelect

View full text Add to dashboard Cite

The rapid growth of the population severely influences the supply of energy, accordingly ensuring clean energy has become a big challenge now and will be in the future. Fossil fuels have been satisfying the energy demand until now, but fossil fuels, being non‐renewable sources, will not be able to satisfy the energy demand in the future and will have a negative impact on the environment. Renewable energy sources have become the most demanding topic for researchers in this crisis. The solar cell, which is an abundant renewable energy resource, converts solar power into electrical energy without any environmental damage. Silicon solar cells have higher efficiency, but their high manufacturing cost, complicated procedures and environmental issues restrict their usage. Then dye‐sensitized solar cells (DSSCs) have been introduced as an alternative to silicon solar cells. In DSSC, both natural and synthetic dyes are used. Though synthetic dyes provide higher efficiency, they are environmentally harmful. Afterward, the concept of natural dye‐sensitized solar cells (NDSSC) have been materialized where only natural dyes are used. Researchers and environmentalists are looking for natural dyes as a replacement for synthetic dyes in recent times, as natural dyes are plentiful, can be collected naturally and have no environmental effects. Natural dyes in the form of anthocyanins, carotenoids, flavonoids, chlorophylls, tannins and betalains are extracted from various portions of plants that include leaves, roots, flowers, fruits, seeds, barks, etc. In this review, we investigate natural sources of dyes, natural sensitizers (dyes), shortcomings and remedies, improvements in efficiency and stability, developments, and commercialization. In addition, recent advances and the comparison of natural and synthetic dyes have been discussed in this review.

show abstract

“…While the underlying problem is similar to before, i.e., finding suitable materials from large configuration spaces, here the constraints on suitability are based on electrical properties such as the band gap or the photoelectric conversion coefficient (PCE). ML has been employed in a number of studies [240], [241], [242], [243], [244], [245], [246], [247], [248], [249], [250], [251], [252], [253], [254], [236], [255], [256], [257], [258], [259], [260], [261], [262], [263], [264], [265], [266], [267].…”

Section: Discovery Of Novel Stable Materialsmentioning

confidence: 99%

A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry

Fiedler¹,

Shah²,

Bußmann³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the growth of computational resources, the scope of electronic structure simulations has increased greatly. Artificial intelligence and robust data analysis hold the promise to accelerate large-scale simulations and their analysis to hitherto unattainable scales. Machine learning is a rapidly growing field for the processing of such complex datasets. It has recently gained traction in the domain of electronic structure simulations, where density functional theory takes the prominent role of the most widely used electronic structure method. Thus, DFT calculations represent one of the largest loads on academic high-performance computing systems across the world. Accelerating these with machine learning can reduce the resources required and enables simulations of larger systems. Hence, the combination of density functional theory and machine learning has the potential to rapidly advance electronic structure applications such as in-silico materials discovery and the search for new chemical reaction pathways. We provide the theoretical background of both density functional theory and machine learning on a generally accessible level. This serves as the basis of our comprehensive review including research articles up to December 2020 in chemistry and materials science that employ machine-learning techniques. In our analysis, we categorize the body of research into main threads and extract impactful results. We conclude our review with an outlook on exciting research directions in terms of a citation analysis.

show abstract

Accelerated discovery of high-efficient N-annulated perylene organic sensitizers for solar cells via machine learning and quantum chemistry

Cited by 15 publications

References 50 publications

Recent progress in the data-driven discovery of novel photovoltaic materials

Recent progress in the data-driven discovery of novel photovoltaic materials

Mapping the Progress in Natural Dye‐Sensitized Solar Cells: Materials, Parameters and Durability

A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry

Contact Info

Product

Resources

About