Dataset Information

Predictive Modeling of Critical Temperatures in Superconducting Materials.

ABSTRACT: In this study, we have investigated quantitative relationships between critical temperatures of superconductive inorganic materials and the basic physicochemical attributes of these materials (also called quantitative structure-property relationships). We demonstrated that one of the most recent studies (titled "A data-driven statistical model for predicting the critical temperature of a superconductor" and published in Computational Materials Science by K. Hamidieh in 2018) reports on models that were based on the dataset that contains 27% of duplicate entries. We aimed to deliver stable models for a properly cleaned dataset using the same modeling techniques (multiple linear regression, MLR, and gradient boosting decision trees, XGBoost). The predictive ability of our best XGBoost model (R2 = 0.924, RMSE = 9.336 using 10-fold cross-validation) is comparable to the XGBoost model by the author of the initial dataset (R2 = 0.920 and RMSE = 9.5 K in ten-fold cross-validation). At the same time, our best model is based on less sophisticated parameters, which allows one to make more accurate interpretations while maintaining a generalizable model. In particular, we found that the highest relative influence is attributed to variables that represent the thermal conductivity of materials. In addition to MLR and XGBoost, we explored the potential of other machine learning techniques (NN, neural networks and RF, random forests).

SUBMITTER: Sizochenko N

PROVIDER: S-EPMC7792800 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictive Modeling of Critical Temperatures in Superconducting Materials.

Sizochenko Natalia N Hofmann Markus M

Molecules (Basel, Switzerland) 20201222 1

In this study, we have investigated quantitative relationships between critical temperatures of superconductive inorganic materials and the basic physicochemical attributes of these materials (also called quantitative structure-property relationships). We demonstrated that one of the most recent studies (titled "A data-driven statistical model for predicting the critical temperature of a superconductor" and published in Computational Materials Science by K. Hamidieh in 2018) reports on models th ...[more]

PMID: 33375023

Similar Datasets

Project description:Miscanthus is an intriguing cellulosic bioenergy feedstock because its aboveground productivity is high for low amounts of agrochemical inputs, but soil temperatures below -3.5 °C could threaten successful cultivation in temperate regions. We used a combination of observed soil temperatures and the Agro-IBIS model to investigate how strategic residue management could reduce the risk of rhizome threatening soil temperatures. This objective was addressed using a historical (1978-2007) reconstruction of extreme minimum 10 cm soil temperatures experienced across the Midwest US and model sensitivity studies that quantified the impact of crop residue on soil temperatures. At observation sites and for simulations that had bare soil, two critical soil temperature thresholds (50% rhizome winterkill at -3.5 °C and -6.0 °C for different Miscanthus genotypes) were reached at rhizome planting depth (10 cm) over large geographic areas. The coldest average annual extreme 10 cm soil temperatures were between -8 °C to -11 °C across North Dakota, South Dakota, and Minnesota. Large portions of the region experienced 10 cm soil temperatures below -3.5 °C in 75% or greater for all years, and portions of North and South Dakota, Minnesota, and Wisconsin experienced soil temperatures below -6.0 °C in 50-60% of all years. For simulated management options that established varied thicknesses (1-5 cm) of miscanthus straw following harvest, extreme minimum soil temperatures increased by 2.5 °C to 6 °C compared to bare soil, with the greatest warming associated with thicker residue layers. While the likelihood of 10 cm soil temperatures reaching -3.5 °C was greatly reduced with 2-5 cm of surface residue, portions of the Dakotas, Nebraska, Minnesota, and Wisconsin still experienced temperatures colder than -3.5 °C in 50-80% of all years. Nonetheless, strategic residue management could help increase the likelihood of overwintering of miscanthus rhizomes in the first few years after establishment, although low productivity and biomass availability during these early stages could hamper such efforts.

Dataset Information

Predictive Modeling of Critical Temperatures in Superconducting Materials.

Publications

Predictive Modeling of Critical Temperatures in Superconducting Materials.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets