Accurate property prediction with interpretable machine learning model for small datasets via transformed atom vector

From bulk effective mass to 2D carrier mobility accurate prediction via adversarial transfer learning

“…ML heavily relies on the quantity and quality of training data as a data-driven approach. However, high-fidelity data for complex properties are often insufficient, compromising its prediction accuracy 11 , 12 . In addition, data insufficiency may also cause incompleteness, which can lead to the ML model constantly suffering from overfitting and poor generalizability 13 .…”

Combined Machine Learning and High-Throughput Calculations Predict Heyd–Scuseria–Ernzerhof Band Gap of 2D Materials and Potential MoSi2N4 Heterostructures

“…All ML algorithms were conducted by the open-source code Scikit-learn and PyTorch package in the Python3 environment. A spectrum of supervised ML regression algorithms has proven efficacious, including gradient boosting regression (GBR), artificial neural networks (ANN), kernel ridge regression (KRR), and extreme gradient boosting (XGBoost) . Notably, these algorithms afford the dual benefit of accurately predicting material properties akin to density functional theory (DFT) while also furnishing atomic-level chemical insights.…”

“…A spectrum of supervised ML regression algorithms has proven efficacious, including gradient boosting regression (GBR), 26 artificial neural networks (ANN), 27 kernel ridge regression (KRR), 28 and extreme gradient boosting (XGBoost). 29 Notably, these algorithms afford the dual benefit of accurately predicting material properties akin to density functional theory (DFT) while also furnishing atomic-level chemical insights. In the context of our study, we leverage seven distinct ML regression algorithms, namely, XGBoost, GBR, ANN, KRR, support vector regression, Gaussian process regression, and decision tree regression.…”

Photocatalytic activity of dual defect modified graphitic carbon nitride is robust to tautomerism: machine learning assisted ab initio quantum dynamics

“…It is developing rapidly and has already been applied to a wide range of systems and processes. [33][34][35][36][37][38][39] ML methods are paving the way to uncover complex reaction paths and to correlate and predict material structure and properties, providing a balance between accuracy and efficiency. Generation of long MD trajectories with ab initio quality results is now feasible with the aid of ML force fields (MLFFs).…”