Modeling and long-term forecasting of CO2 emissions in Asia: An optimized Artificial Neural Network approach with consideration of renewable energy scenarios

Modeling and long-term forecasting of CO2 emissions in Asia: An optimized Artificial Neural Network approach with consideration of renewable energy scenarios

Blog Article

Carbon dioxide (CO2) is one of the most important greenhouse gases (GHGs) that possess a significant role in environmental concerns like climate change and global warming.Understanding and forecasting the future trends of CO2 emissions is crucial for developing effective strategies to mitigate their impact on the environment and achieving global agreement targets.The current study aims to model and forecast CO2 emissions rates in six Asian countries, including China, Iran, Saudi Arabia, India, Japan, and Turkey, until 2035.

A multilayer perceptron artificial neural network (MLP-ANN) is developed for modeling and prediction of CO2 emissions.Five parameters, such as population (POP), gross domestic product (GDP), electrical energy consumption (EEC), primary energy consumption (PEC), and getpureroutine.com annual mean surface air temperature (AMT) from 1971 to 2020, are considered as input variables for the model, with CO2 emissions as the output variable.After preprocessing the data, a 5-6-1 MLP-ANN that is optimized with two metaheuristic algorithms (PSO and GWO) is utilized to train and validate the model for each country.

Also, in order to predict the CO2 emission from 2021 to 2035, the input variables are forecast using the nonlinear autoregressive exogenous (NARX) for implementation in the optimal ANN model.The results indicate that the proposed model demonstrates high stuart products emcelle tocopherol accuracy for all nations based on various evaluation metrics.Based on the prediction, the CO2 emissions trends are increasing for all countries.

In addition, the effects of employing renewable energy scenarios on reducing CO2 emissions are also investigated.