66 datasets found

The 3BPA dataset is a benchmark dataset for Equivariant Many-body Interaction operations, consisting of 500 geometries sampled from different temperature molecular dynamics...

The dataset used in the paper is the Concrete Compressive Strength dataset, which contains 3,000 concrete compressive strength test results.

The Inorganic Crystal Structure Database (ICSD) contains information about inorganic crystal structures, including their space group and lattice parameters.

The SuperCon database contains information about superconductors, including their critical temperatures, and is used to train machine learning models to predict the critical...

A collection of 81.1 million scholarly publications in English from various academic fields, used to pre-train a language model.

A dataset of SEM images of polymer blends for miscibility recognition

The dataset consists of 2200 microstructure evolution trajectories by varying several simulation parameters: the deposition rate (v) from 0.3 to 1.0 (in simulation units), the...

A dataset of interatomic potentials for training machine learning models.

The dataset used to train the crystal graph convolutional neural networks (CGCNN) model to visualize the compositional and structural similarities between materials in an...

A dataset of catalytic materials for training machine learning models.

A broad benchmark for applying machine learning models to solid-state materials.

The dataset is used for stress field prediction and uncertainty quantification for diverse materials microstructures.

The dataset C consisted of images taken above Paris. It was obtained by two instruments on board the Earth Observing-1 Mission (EO-1) satellite.

The dataset used in the paper is a collection of digital breast tomosynthesis (DBT) stacks with single micro-calcifications or masses inserted in the center of the stack.

The dataset used in the paper is a collection of scattering intensities and corresponding size distributions.

The dataset used in the paper is a collection of virtual sample materials with diverse size distributions.

A dataset of 10,790 predicted perovskites, along with their 5 most similar experimental materials, used to test the effectiveness of the VAE model.

A dataset of 2104 experimental materials, including their crystal structure information, used to train a Variational Autoencoder (VAE) model.

An experimental database of disordered quaternary compositions, including 1758 distinct perovskites and 227 non-perovskites, along with their crystal structure information.

The dataset used for machine learning accelerated discovery of porous organic cages.