Greenhouse Gas Emission Estimation by Artificial Intelligence

Authors : Serkan Ertuğrul

Pages : 103-114

Doi:10.36222/ejt.1327275

View : 4 | Download : 20

Publication Date : 2024-12-24

Article Type : Research Paper

Abstract :Human activities, particularly the burning of fossil fuels (such as coal, oil, and natural gas) for energy production, industrial processes, transportation, and deforestation, release significant amounts of greenhouse gases into the atmosphere. Global agreements such as the Paris Agreement have started expressing the goal of reducing human activities and achieving net zero emissions. It is expected that all countries will set targets and work towards reducing greenhouse gas emissions by implementing sustainable and realistic programs. By utilizing data such as financial indicators, population, deforestation, Human Development Index (HDI), and energy consumption, machine learning methods were employed to calculate future greenhouse gas emission levels in some countries. For this purpose, a comparison was made by using deep learning methods, such as Long Short-Term Memory (LSTM) and a hybrid CNN-RNN model, separately with the help of the MATLAB program. Additionally, future greenhouse gas emission predictions were made by comparing the results of the study using LSTM modeling with the predictions obtained through NARX modeling for time-series data. The aim was to emphasize the need for countries to develop sustainable programs by considering various data in order to achieve their greenhouse gas emission reduction targets.
Keywords : Deep Learning, Climate Change, Carbon, Global Warming, Regression, Greenhouse Gas, Artificial Neural Networks