AUTHOR=Wei Xiaoyan , Xu Ying 

TITLE=Research on carbon emission prediction and economic policy based on TCN-LSTM combined with attention mechanism

JOURNAL=Frontiers in Ecology and Evolution

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/ecology-and-evolution/articles/10.3389/fevo.2023.1270248

DOI=10.3389/fevo.2023.1270248

ISSN=2296-701X

ABSTRACT=In the face of increasingly severe global climate change and environmental challenges, the reduction of carbon emissions has emerged as a critical worldwide priority. Deep learning, as a powerful artificial intelligence technology, has demonstrated remarkable capabilities in time series analysis and pattern recognition, opening new avenues for carbon emission prediction and policy formulation. To contribute to the development of a green and low-carbon economy, we have developed a carbon emission prediction model that combines Temporal Convolutional Networks (TCN) and Long Short-Term Memory (LSTM) with an attention mechanism. In this study, we carefully collected and preprocessed four datasets to ensure data reliability and consistency.Our proposed TCN-LSTM combined architecture effectively harnesses TCN's parallel computing ability and LSTM's memory capability to capture long-term dependencies in time series data more effectively. Moreover, the incorporation of the attention mechanism allows us to weigh the significant factors in historical data, thereby enhancing prediction accuracy and robustness.The outcomes of our research provide novel insights and methodologies for advancing carbon emission prediction. Furthermore, our findings offer valuable references for decision-makers and government agencies to devise scientifically effective carbon reduction policies. With the growing urgency to address climate change, the advancements made in this paper can contribute to a more sustainable and environmentally conscious future.