Adsorption Capacity of Graphane Materials Prediction using Modified Artificial Neural Network

The method to merge the adsorption of Carbon Dioxide (CO2) data with different adsorbents depended on Graphene oxide that is generated from different formats of solid biomass. In this research, the data of various GO-depended solid adsorbents are extracted to develop the Machine Learning based Metho...

Full description

Saved in:
Bibliographic Details
Published in2024 Second International Conference on Data Science and Information System (ICDSIS) pp. 1 - 4
Main Authors Ma, Youliang, Qiang, Kejuan
Format Conference Proceeding
LanguageEnglish
Published IEEE 17.05.2024
Subjects
Adsorption
Adsorption capacity
Artificial Neural Network and Root Mean Square Error
Correlation coefficient
Graphene
Mean Absolute Error
Mean Square Error
Measurement
Modified
Radio frequency
Solids
Temperature distribution
Online AccessGet full text

Cover

More Information
Summary:The method to merge the adsorption of Carbon Dioxide (CO2) data with different adsorbents depended on Graphene oxide that is generated from different formats of solid biomass. In this research, the data of various GO-depended solid adsorbents are extracted to develop the Machine Learning based Method for predicting the adsorption capacity of graphene materials. The extracted data includes particular surface area, volume of pore, temperature and pressure are taken as input parameters and CO2 capacity is determines as response of method. In this research, the Modified - Artificial Neural Network (M-ANN) method is proposed to predict the adsorption capacity of graphene materials. The performance metrics used for evaluating the proposed method are Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and Correlation Coefficient R2. The proposed M-ANN method acquired MAE of 0.097, MSE of 0.024, RMSE of 0.153 and R2 of 0.994 which is effective than other algorithms like Support Vector Regression (SVR) and Random Forest (RF).
DOI:10.1109/ICDSIS61070.2024.10594276