Perovskite-Prediction

KO | EN

gitlite — search

#python #react #ai #llm #go #golang #machine-learning #deep-learning #java #kubernetes #awesome-list #pytorch #ios #open-source

Perovskite-Prediction

(★ 16)

Predicting new perovskites with ensemble Machine Learning algorithms

Perovskite-Prediction 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Graph Representational Learning for bandgap prediction in varied perovskite crystals
Predicting new perovskites with Graph Neural Networks. <br>

<p align="justify">
Perovskites are a promising class of materials increasingly attracting the attention of material scientists world over for their applications in optoelectronic devices, solar cells in particular. This interest can be attributed to their ease of fabrication and their tuneable bandgaps - both handy properties for using them commercially as solar cells. In this project, the computational efficiency of Graph Neural Networks (GNNs) has been leveraged to help accelerate the discovery of new perovskite compounds (ABX3) with favourable properties. The GNN used in the model helps predict with a high degree of accuracy the bandgap of perovskites in a few milliseconds and given its high generalisability, it can do the same for any type of perovskite.

Using the pipeline built, material scientists and engineers can efficiently screen those inorganic perovskites with low bandgaps and experiment on the favourable compounds and synthesize them.

Our paper on the topic can be found at: 
Omprakash, Pravan, Bharadwaj Manikandan, Ankit Sandeep, Romit Shrivastava, and Devadas Bhat Panemangalore. "Graph representational learning for bandgap prediction in varied perovskite crystals." Computational Materials Science 196 (2021): 110530.
</p>

Perovskite-Prediction

Perovskite-Prediction 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Perovskite-Prediction

Perovskite-Prediction 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README