2022
DOI: 10.1016/j.mtcomm.2022.104900
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning accelerates the materials discovery

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
10
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
10

Relationship

0
10

Authors

Journals

citations
Cited by 43 publications
(18 citation statements)
references
References 388 publications
0
10
0
Order By: Relevance
“…Many papers describe the process of ML algorithms. [84][85][86][87] Depending on the nature and characteristics of the problem, we need to choose the appropriate model architecture.…”
Section: Model Selection and Trainingmentioning
confidence: 99%
“…Many papers describe the process of ML algorithms. [84][85][86][87] Depending on the nature and characteristics of the problem, we need to choose the appropriate model architecture.…”
Section: Model Selection and Trainingmentioning
confidence: 99%
“…To face this problem, there is a need to produce a lot of experimental data of this massive interest in researching carbon-based SCs which provides us with the chance to apply machine learning (ML) algorithms to take advantage of these data and use them to educate ourselves and identify quantitative relations between input and output variables from existing data before introducing extrapolation predictions. In recent years, ML techniques have become an effective alternative to physics-based strategies [30][31][32]. ML approaches allow us to create effective connections between material qualities and performance without evoking the physical specifics if enough training data is supplied.…”
Section: Introductionmentioning
confidence: 99%
“…Due to the storing and querying of connected data, the advancement of graph databases and graph database management systems has been advantageous for machine learning applications . Machine learning can be used to understand and predict specific material properties by mapping the relationships between final material properties and synthetic variables through the drawing of information from recorded data . The use of machine learning in the design and property prediction of materials has recently gained attention for implementation in many material systems such as inorganic oxides, metals, metallic glasses, battery materials, and electrolyte materials, expediting the design and development lifecycle of these materials. , In this work, following the development of the SiAGDB and data cleaning methods, we use a neural network model to predict the surface area of silica aerogels from synthetic and processing conditions.…”
Section: Introductionmentioning
confidence: 99%