Machine learning approaches to predict the photocatalytic performance of bismuth ferrite-based materials in the removal of malachite green

Accurate prediction of gestational diabetes mellitus via a novel transformer method

“…The Decision Tree, Logistic Regression, and Random Forest algorithms are implemented by the tree, LogisticRegression, and RandomForestClassi er function in the sklearn module, respectively. The Xgboost algorithm is realized by calling the third-party library Xgboost in Python [22]. The optimal parameters of all models were obtained by using 3-fold cross-validation and standard grid search.…”

Analysis of the oxygen evolution activity of layered double hydroxides (LDHs) using machine learning guidance

“…To overcome this problem, additional information should be involved as extra features to compensate for data missing. Herein, inspired by other works, 28,32,36 which reveal the importance of measurement or reaction conditions in feature ranking (almost always rank 1st among all features), we added measurement conditions for overpotentials (e.g., scan rates for linear sweep voltammetry and iR-correlation information) as extra features to construct new ML models. After these features were added, the overpotential prediction accuracy was successfully improved with the highest R 2 of 0.768 (see Fig.…”

Crystal graph convolution neural networks for fast and accurate prediction of adsorption ability of Nb2CTx towards Pb(ii) and Cd(ii) ions

“…Machine learning (ML) techniques have proven to be a rapid and precise method for the prediction of the adsorption mechanism of various materials at a fraction of the computational cost. [19][20][21] In particular, crystal graph convolution neural networks (CGCNN) have been applied for the prediction of material characteristics due to their high learning capability and ability to extract features from raw dataset. 22,23 Recently, Xie and Grossman 24 developed a CGCNN framework to represent the periodic crystalline structure of materials, with the crystal information encoded using basic atomic features, including the group number and electron affinity.…”