“…A non-linear dimensionality reduction technique called t-distributed Stochastic Neighbour Embedding (t-SNE) 52 was employed to investigate the similarity in the properties of the five materials in comparison with the 8059 materials (all crystal structures) from the training set (Fig. 5F).…”
Section: Methodsmentioning
confidence: 99%
“…44 Specically, Zhou et al achieved a room temperature power factor value of 120 mW cm −1 K −2 for p-type NbFeSb, which decreased to ∼80 mW cm −1 K −2 at 600 K. Other top performing predicted materials with diverse chemistries were also studied, and the results can be found in ESI Section 12. † A non-linear dimensionality reduction technique called tdistributed Stochastic Neighbour Embedding (t-SNE) 52 was employed to investigate the similarity in the properties of the ve materials in comparison with the 8059 materials (all crystal structures) from the training set (Fig. 5F).…”
We train several machine learning models on a dataset comprised by Materials Project and calculated thermoelectric power factor. We show that a random forest model outperforms more complex approaches for the dataset and allows for interpretability.
“…A non-linear dimensionality reduction technique called t-distributed Stochastic Neighbour Embedding (t-SNE) 52 was employed to investigate the similarity in the properties of the five materials in comparison with the 8059 materials (all crystal structures) from the training set (Fig. 5F).…”
Section: Methodsmentioning
confidence: 99%
“…44 Specically, Zhou et al achieved a room temperature power factor value of 120 mW cm −1 K −2 for p-type NbFeSb, which decreased to ∼80 mW cm −1 K −2 at 600 K. Other top performing predicted materials with diverse chemistries were also studied, and the results can be found in ESI Section 12. † A non-linear dimensionality reduction technique called tdistributed Stochastic Neighbour Embedding (t-SNE) 52 was employed to investigate the similarity in the properties of the ve materials in comparison with the 8059 materials (all crystal structures) from the training set (Fig. 5F).…”
We train several machine learning models on a dataset comprised by Materials Project and calculated thermoelectric power factor. We show that a random forest model outperforms more complex approaches for the dataset and allows for interpretability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.