RECORD
Exploring diamond-like lattice thermal conductivity crystals via feature-based transfer learning
Materials Science · Submitted 25 Sep 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Herein we show that big data can complement small data for accurate predictions when lower-order feature properties available in big data are selected properly and applied to transfer learning.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Ultrahigh lattice thermal conductivity materials hold great importance since they play a critical role in the thermal management of electronic and optical devices. Models using machine learning can search for materials with outstanding higher-order properties like thermal conductivity. However, the lack of sufficient data to train a model is a serious hurdle. Herein we show that big data can complement small data for accurate predictions when lower-order feature properties available in big data are selected properly and applied to transfer learning. The connection between the crystal information and thermal conductivity is directly built with a neural network by transferring descriptors acquired through a pre-trained model for the feature property. Successful transfer learning shows the ability of extrapolative prediction and reveals descriptors for lattice anharmonicity. Transfer learning is employed to screen over 60000 compounds to identify novel crystals that can serve as alternatives to diamond.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Ultrahigh lattice thermal conductivity materials hold great importance since they play a critical role in the thermal management of electronic and optical devices. | background 1.00 | 0.04 | 0.02 | asserted 0.99 |
| s1 | Models using machine learning can search for materials with outstanding higher-order properties like thermal conductivity. | background 0.98 | 0.08 | 0.04 | asserted 0.82 |
| s2 | However, the lack of sufficient data to train a model is a serious hurdle. | gap 0.90 | 0.08 | 0.02 | asserted 1.00 |
| s3 | Herein we show that big data can complement small data for accurate predictions when lower-order feature properties available in big data are selected properly and applied to transfer learning. | contribution 0.82 | 0.77 | 0.59 | asserted 0.99 |
| s4 | The connection between the crystal information and thermal conductivity is directly built with a neural network by transferring descriptors acquired through a pre-trained model for the feature property. | method 0.99 | 0.85 | 0.13 | asserted 1.00 |
| s5 | Successful transfer learning shows the ability of extrapolative prediction and reveals descriptors for lattice anharmonicity. | interpretation 0.91 | 0.82 | 0.22 | asserted 1.00 |
| s6 | Transfer learning is employed to screen over 60000 compounds to identify novel crystals that can serve as alternatives to diamond. | contribution 0.55 | 0.93 | 0.31 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Ultrahigh lattice thermal conductivity materials hold great importance since they play a critical role in the thermal management of electronic and optical devices. Models using machine learning can search for materials with outstanding higher-order properties like thermal conductivity. However, the lack of sufficient data to train a model is a serious hurdle. Herein we show that big data can complement small data for accurate predictions when lower-order feature properties available in big data are selected properly and applied to transfer learning. The connection between the crystal information and thermal conductivity is directly built with a neural network by transferring descriptors acquired through a pre-trained model for the feature property. Successful transfer learning shows the ability of extrapolative prediction and reveals descriptors for lattice anharmonicity. Transfer learning is employed to screen over 60000 compounds to identify novel crystals that can serve as alternatives to diamond.
Human review
How the literature uses it
1 arXiv paper cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Cites it as background 1 paper
-
Recently various machine learning techniques have been used to predict the thermal conductivity, like Bayesian optimization [ref] , Gaussian process regression [ref] or transfer learning [ref] .
Descriptors of intrinsic hydrodynamic thermal transport: screening a phonon database in a machine learning approach · RESULTS AND DISCUSSION · 0.94
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.