Predicting photoresist sensitivity using machine learning

Abstract

We introduce a scheme for predicting photoresist sensitivity using machine learning (ML) work flow on the basis of previously reported experimental data. Different ML models, specifically Linear Regression, Kernel Ridge Regression, Gaussian Process Regressor, Random Forest Regressor, and Multilayer Perceptron Regressor, were evaluated to rapidly identify the best sensitivity prediction model. The experiment was carried out on the Google Colab platform using the Materials Simulation Toolkit for Machine Learning and Sci‐kit Learn. Different ensemble models were utilized without splitting the dataset to determine the prediction accuracy of the ML models. The hyperparameter optimization was established with a 70/30 ratio, followed by a K‐Fold cross‐validation to improve the model prediction performance. The optimized ML model showed a prediction performance of R2 = 0.83, RMSE = 10.53, and MARE = 0.68. Hence, by optimizing the hyperparameters used in the ML model, the sensitivity of the photoresist materials can be predicted with improved prediction performance.

SnSe: The rise of the ultrahigh thermoelectric performance material

“…102 It has been applied to various research fields such as polymer materials, 103 molecular structure predictions, 104 perovskite structure predictions, 105 and new medicine developments. 106,107 Experimental and theoretical studies on phonon scattering, defect engineering, band structure modulation, and heterogeneous structure formation by doping and alloying have provided effective strategies to improve TE properties of materials. ML can be a useful tool to predict new TE materials with optimal compositions and may help save time and labor.…”

Development of a machine‐learning model for microplastic analysis in an FT‐IR microscopy image

“…Machine learning (ML) has been recently utilized for the analysis of MPs in various matrices, as it is in the other analytical issues, such as mass spectrometry 38–42 . Ng et al, demonstrated that a 1D‐convolution neural network (1D‐CNN) model can screen the degree of MP contaminations for soils that were contained with polyethylene terephthalate (PET) or low‐density polyethylene (LDPE) mixtures using visible–near infrared spectra 43 .…”

Molecular structural descriptor‐assisted machine learning for organic photovoltaics with perylenediimide acceptors

“…[9][10][11][12][13][14] Therefore, machine learning (ML) approaches to screen numerous BHJ combinations in a short time and with little effort, based on a comprehensive understanding of the potential of OPV materials, have attracted considerable attention. 15,16 State-of-the-art OPV ML models achieved superior accuracy with a variety of input data types and algorithms. [17][18][19][20] However, the training of previous OPV ML models and obtaining predictions from them required at least one chemical property that could only be determined through experiment or calculation.…”