Inverse design with deep generative models: next step in materials discovery
Authors:
Open Access
- 11 June 2022
- journal article
- editorial
- Published by Oxford University Press (OUP) in National Science Review
- Vol. 9 (8) , nwac111
Abstract
Data-driven inverse design for inorganic functional materials is a rapidly emerging field, which aims to automatically design innovative materials with target properties and to enable property-to-structure material discovery.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFA1500700, 2017YFA0204800)
- National Natural Science Foundation of China (BK20180353, 22033002, 21525311, 22003009)
- Scientific Research Foundation of the Graduate School of Southeast University (YBYP2140)
This publication has 13 references indexed in Scilit:
- Inverse design of nanoporous crystalline reticular materials with deep generative modelsNature Machine Intelligence, 2021
- Generative Adversarial Networks for Crystal Structure PredictionACS Central Science, 2020
- Coupling a Crystal Graph Multilayer Descriptor to Active Learning for Rapid Discovery of 2D Ferromagnetic Semiconductors/Half‐Metals/MetalsAdvanced Materials, 2020
- Machine-enabled inverse design of inorganic solid materials: promises and challengesChemical Science, 2020
- Inverse design of porous materials using artificial neural networksScience Advances, 2020
- Inverse Design of Solid-State Materials via a Continuous RepresentationMatter, 2019
- A robotic platform for flow synthesis of organic compounds informed by AI planningScience, 2019
- Search for Catalysts by Inverse Design: Artificial Intelligence, Mountain Climbers, and AlchemistsChemical Reviews, 2019
- Inverse molecular design using machine learning: Generative models for matter engineeringScience, 2018
- Machine learning for molecular and materials scienceNature, 2018