Machine learning stability and band gap of lead-free halide double perovskite materials for perovskite solar cells

Guo, Zongmei; Lin, Bin

doi:10.1016/j.solener.2021.09.030

Cited by 32 publications

(21 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Predicting the basic physical information in perovskite can be of great help in the exploration of new materials, the mapping of experimental parameters and the understanding of structurefunction relationships. Many models have been developed to predict the physical properties of perovskite such as bandgap 110,119 , oxide ionic conductivity 120 , thermodynamic stability 121,122 , dielectric breakdown strength 123,124 , lattice parameters 125 , crystal structure 126 . For example, Zhang et al establish the lattice constants model based on cubic perovskites 127,128 .…”

Section: Types Of Perovskite Prediction Tasksmentioning

confidence: 99%

Machine learning in energy chemistry: introduction, challenges and perspectives

2023

Energy Adv.

View full text Add to dashboard Cite

show abstract

Section: Types Of Perovskite Prediction Tasksmentioning

confidence: 99%

Machine learning in energy chemistry: introduction, challenges and perspectives

2023

Energy Adv.

View full text Add to dashboard Cite

show abstract

“…Two lead-free inorganic double perovskites are eventually obtained using the XGBR ML model, having suitable bandgaps, high thermal stability, and good optical properties. Guo and Lin also explored various ML algorithms for high-speed and high-precision lead-free double perovskite material screening. They found that the XGBR and RF algorithms had the best prediction performance in terms of thermodynamic stability (with a mean absolute error of 0.0126) and bandgap (with an error of 0.1492), respectively.…”

Section: Artificial Intelligence Aided Nanotechnology For Renewable E...mentioning

confidence: 99%

AI for Nanomaterials Development in Clean Energy and Carbon Capture, Utilization and Storage (CCUS)

Chen

Zheng

et al. 2023

ACS Nano

View full text Add to dashboard Cite

Zero-carbon energy and negative emission technologies are crucial for achieving a carbon neutral future, and nanomaterials have played critical roles in advancing such technologies. More recently, due to the explosive growth in data, the adoption and exploitation of artificial intelligence (AI) as part of the materials research framework have had a tremendous impact on the development of nanomaterials. AI has enabled revolutionary next-generation paradigms to significantly accelerate all stages of material discovery and facilitate the exploration of the enormous design space. In this review, we summarize recent advancements of AI applications in nanomaterials discovery, with a special emphasis on the selected applications of AI and nanotechnology for the net-zero emission future including the development of solar cells, hydrogen energy, battery materials for renewable energy, and CO2 capture and conversion materials for carbon capture, utilization and storage (CCUS) technologies. In addition, we discuss the limitations and challenges of current AI applications in this area by identifying the gaps that exist in current development. Finally, we present the prospect for future research directions in order to facilitate the large-scale applications of artificial intelligence for advancements in nanomaterials.

show abstract

“…Previous studies have shown that random forest regression is well-suited to capturing nonlinearity, as seen across the band gap and the extracted physical features such as the highest occupied energy level [25]. As such, we construct a random forest regression model for predicting the band gap of double perovskite compounds, building upon a previous kernel ridge regression study [15].…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning Prediction of the Computed Band Gaps of Double Perovskite Materials

Zhang¹,

Li²,

Zhou³

2023

Computer Science and Machine Learning Trends 2023

View full text Add to dashboard Cite

Prediction of the electronic structure of functional materials is essential for the engineering of new devices. Conventional electronic structure prediction methods based on density functional theory (DFT) suffer from not only high computational cost, but also limited accuracy arising from the approximations of the exchange-correlation functional. Surrogate methods based on machine learning have garnered much attention as a viable alternative to bypass these limitations, especially in the prediction of solid-state band gaps, which motivated this research study. Herein, we construct a random forest regression model for band gaps of double perovskite materials, using a dataset of 1306 band gaps computed with the GLLBSC (Gritsenko, van Leeuwen, van Lenthe, and Baerends solid correlation) functional. Among the 20 physical features employed, we find that the bulk modulus, superconductivity temperature, and cation electronegativity exhibit the highest importance scores, consistent with the physics of the underlying electronic structure. Using the top 10 features, a model accuracy of 85.6% with a root mean square error of 0.64 eV is obtained, comparable to previous studies. Our results are significant in the sense that they attest to the potential of machine learning regressions for the rapid screening of promising candidate functional materials.

show abstract

Machine learning stability and band gap of lead-free halide double perovskite materials for perovskite solar cells

Cited by 32 publications

References 76 publications

Machine learning in energy chemistry: introduction, challenges and perspectives

Machine learning in energy chemistry: introduction, challenges and perspectives

AI for Nanomaterials Development in Clean Energy and Carbon Capture, Utilization and Storage (CCUS)

Machine-Learning Prediction of the Computed Band Gaps of Double Perovskite Materials

Contact Info

Product

Resources

About