我校太阳成集团的官方网站帅传敏老师在T2级别期刊——《International Journal of Environmental Science and Technology》上发表题为“Analysis of energy consumption and greenhouse gas emissions trend in China, India, the USA, and Russia”。论文作者帅传敏为太阳成集团的官方网站教授，博士生导师。

Abstract / 摘要：

With the growth of industries and population, the need for energy consumption has increased, which has inevitably increased greenhouse gas emissions. Further use of fossil fuel for energy consumption exacerbates the situation making it one of the major issues for climate change. China, India, the USA, and Russia are the world’s leading countries in energy consumption and emissions and are responsible for climate change. These countries account for 54% of carbon dioxide (CO₂) emissions in the global environment. This paper investigates the energy consumption of China, India, the USA, and Russia and its trend in greenhouse gas emissions. Using four available datasets from 1980 to 2018 for China, India, USA, and 1992 to 2018 for Russia, we employed three advanced machine learning algorithms (support vector machine, artificial neural network, and long-short term memory) and verified its predicted capability with actual greenhouse gas emissions. The obtained results were evaluated with three statistical metrics (route mean square, mean absolute percentage error, and mean bias error). The predicted results with three machine learning algorithms were very close to actual greenhouse gas emissions. Besides, we forecasted the trend of greenhouse gas emissions in these countries from 2019 to 2023. The forecasted results with the long-short term memory model confirm an increase in CO₂, methane, and Nitrous oxide (N₂O) emissions in the case of China and India; in contrast, the results indicate a slowdown of CO₂, methane, and N₂O emissions in the USA and Russia.

论文信息;

Title/题目:

Analysis of energy consumption and greenhouse gas emissions trend in China, India, the USA, and Russia

Authors/作者:

Ahmed M.;Shuai C.;Ahmed M.

Key Words / 关键词 ：

Energy consumption;CO;emissions;Methane emissions;N;O emissions;Machine learning algorithms

DOI: 10.1007/S13762-022-04159-Y

全文链接：https://link.springer.com/article/10.1007/s13762-022-04159-y