Real-time CO2 Emission Forecasting with Deep Learning: 
Construction and Validation of a Transformer-CBAM 
Model

Qiuyan Liu

doi:10.70711/frim.v2i11.5556

Real-time CO2 Emission Forecasting with Deep Learning: Construction and Validation of a Transformer-CBAM Model

Qiuyan Liu

Abstract

In order to better provide guidance and assist decision-making for the government, real-time and long-term CO2 emission prediction is particularly important. In this paper, we combine Convolutional block attention module and Transformer model to construct a new time
series prediction model, Transformer-CBAM. By using the near-real-time daily carbon emission data set of Chinas industries, the commonly
used time series prediction models such as ARIMA, RF, TCN, GRU, and LSTM are verified and compared with the Transformer-CBAM
model. MSE, RMSE, MAE, MAPE, R2
and other indicators were selected to comprehensively evaluate each model. The results show that the
MSE of Transformer-CBAM model is only 2.0441e-03, the MAPE is only 4.3962%, and the R2
is as high as 0.8907. In addition, other indicators are also better than the traditional model, which verifies the effectiveness and accuracy of the deep learning model based on Transformer-CBAM in CO2 emission prediction.

Keywords

CO2 emission prediction; Transformer-CBAM model; Deep learning; Time series forecasting

Full Text:

PDF

Included Database

References

[1] Li, Z., Zhang, X., & Dong, Z. (2023). TSF-transformer: a time series forecasting model for exhaust gas emission using transformer. Applied Intelligence, 53(13), 17211-17225. https://doi.org/10.1007/s10489-022-04326-1

[2] Liu, Z., Ciais, P., Deng, Z., Davis, S. J., Zheng, B., Wang, Y. L., ... Chevallier, F. (2020). Carbon Monitor, a near-real-time daily dataset

of global CO2 emission from fossil fuel and cement production. Scientific Data, 7(1). https://doi.org/10.1038/s41597-020-00708-7

[3] Sasal, L., Chakraborty, T., & Hadid, A. (2022). W-Transformers: A Wavelet-based Transformer Framework for Univariate Time Series

Forecasting. Paper presented at the 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA). https://

doi.org/10.1109/ICMLA55696. 2022.00111

[4] Wang, Z.-X., & Ye, D.-J. (2017). Forecasting Chinese carbon emissions from fossil energy consumption using non-linear grey multivariable models. Journal of Cleaner Production, 142, 600-612. https://doi.org /10.1016/j.jclepro.2016.08.067

[5] Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. Paper presented at the Proceedings of

the European conference on computer vision (ECCV). https://doi.org /10.1007/978-3-030-01234-2_1

DOI: http://dx.doi.org/10.70711/frim.v2i11.5556

Refbacks

There are currently no refbacks.