logo
ResearchBunny Logo
Predicting the synthesizability of crystalline inorganic materials from the data of known material compositions

Chemistry

Predicting the synthesizability of crystalline inorganic materials from the data of known material compositions

E. R. Antoniuk, G. Cheon, et al.

Explore the groundbreaking SynthNN, a deep learning model developed by Evan R. Antoniuk and colleagues, that revolutionizes the prediction of synthesizability in inorganic crystalline materials, outpacing traditional methods and experts alike in speed and accuracy.

00:00
00:00
Playback language: English
Abstract
This paper introduces SynthNN, a deep learning model that predicts the synthesizability of inorganic crystalline materials. SynthNN leverages a database of known synthesized inorganic compositions and outperforms both DFT-calculated formation energies and human experts in predicting synthesizability, achieving higher precision and significantly faster prediction speeds. The model implicitly learns chemical principles like charge-balancing and chemical family relationships, demonstrating its potential to improve computational materials screening workflows.
Publisher
npj Computational Materials
Published On
Aug 25, 2023
Authors
Evan R. Antoniuk, Gowoon Cheon, George Wang, Daniel Bernstein, William Cai, Evan J. Reed
Tags
deep learning
SynthNN
inorganic materials
synthesizability
computational materials
formation energies

Related Publications

Explore these studies to deepen your understanding of the subject.

Predicting Synthesizability of Crystalline Materials via Deep Learning
Engineering and Technology

Predicting Synthesizability of Crystalline Materials via Deep Learning

A. Davariashtiyani, Z. Kadkhodaie, et al.

The impact of COVID-19 on the debate on open science: a qualitative analysis of published materials from the period of the pandemic
Interdisciplinary Studies

The impact of COVID-19 on the debate on open science: a qualitative analysis of published materials from the period of the pandemic

M. B. Marshall, S. Pinfield, et al.

Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data
Computer Science

Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data

C. H. Martin, T. (. Peng, et al.

From remote sensing and machine learning to the history of the Silk Road: large scale material identification on wall paintings
Humanities

From remote sensing and machine learning to the history of the Silk Road: large scale material identification on wall paintings

S. Kogou, G. Shahtahmassebi, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny