Predicting Climate Change with Artificial Neural Networks within the Framework of Environmental and Economic Policies: The Case of the G20

Climate change is a significant issue that directly affects the environment and well-being of every living organism on Earth. In addition to environmental concerns, it exacerbates socio-economic burdens, especially in developing countries, and further worsens ongoing social inequalities. The effects of climate change and the difficulty of reversing these effects necessitate international collaboration and policies that prioritize sustainability. At this point, it is important to predict how climate change and trends will evolve in the future in order to minimize the adverse effects and take necessary measures. The aim of this study is to forecast the trajectory of global climate change, based on the goals of the United Nations 2030 Agenda for Sustainable Development, with a focus on the G20 countries, which are considered to be most affected by environmental issues. For analysis, the Artificial Neural Networks method, which has recently emerged in forecasting studies, is used. The dependent variable in the analysis is the change in temperature, which is an indicator of climate change. The independent variables include per capita CO2 emissions, population, GDP change, consumption of oil, coal, natural gas, nuclear energy, urban population, and carbon tax implementation. Referring to the United Nations Environment Conference, the data range is limited to 1972-2022, and the average temperature change until 2030 is predicted. According to the analysis results, it is found that the average global temperature change by 2030 will exceed the United Nations target of 1.5 degrees Celsius.