Predicting Daily CO₂ Emissions with Machine Learning and Deep Learning Models

The recent devastating wildfires in California serve as a reminder of the urgent need for actionable climate solutions. These events, fueled by rising global temperatures and unchecked CO₂ emissions, highlight the importance of understanding and predicting carbon output on a more granular level.
Like

Share this post

Choose a social network to share with, or copy the URL to share elsewhere

This is a representation of how your post may appear on social media. The actual post will vary between social networks

Read the paper

SpringerLink
SpringerLink SpringerLink

An examination of daily CO2 emissions prediction through a comparative analysis of machine learning, deep learning, and statistical models - Environmental Science and Pollution Research

Human-induced global warming, primarily attributed to the rise in atmospheric CO2, poses a substantial risk to the survival of humanity. While most research focuses on predicting annual CO2 emissions, which are crucial for setting long-term emission mitigation targets, the precise prediction of daily CO2 emissions is equally vital for setting short-term targets. This study examines the performance of 14 models in predicting daily CO2 emissions data from 1/1/2022 to 30/9/2023 across the top four polluting regions (China, India, the USA, and the EU27&UK). The 14 models used in the study include four statistical models (ARMA, ARIMA, SARMA, and SARIMA), three machine learning models (support vector machine (SVM), random forest (RF), and gradient boosting (GB)), and seven deep learning models (artificial neural network (ANN), recurrent neural network variations such as gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional-LSTM (BILSTM), and three hybrid combinations of CNN-RNN). Performance evaluation employs four metrics (R2, MAE, RMSE, and MAPE). The results show that the machine learning (ML) and deep learning (DL) models, with higher R2 (0.714–0.932) and lower RMSE (0.480–0.247) values, respectively, outperformed the statistical model, which had R2 (− 0.060–0.719) and RMSE (1.695–0.537) values, in predicting daily CO2 emissions across all four regions. The performance of the ML and DL models was further enhanced by differencing, a technique that improves accuracy by ensuring stationarity and creating additional features and patterns from which the model can learn. Additionally, applying ensemble techniques such as bagging and voting improved the performance of the ML models by approximately 9.6%, whereas hybrid combinations of CNN-RNN enhanced the performance of the RNN models. In summary, the performance of both the ML and DL models was relatively similar. However, due to the high computational requirements associated with DL models, the recommended models for daily CO2 emission prediction are ML models using the ensemble technique of voting and bagging. This model can assist in accurately forecasting daily emissions, aiding authorities in setting targets for CO2 emission reduction.

The journey behind this research started with a pressing question: how can we provide policymakers with accurate and actionable daily CO₂ emissions data to address the urgent threat of global warming? While annual CO₂ predictions dominate research, their limitations in capturing daily fluctuations inspired us to explore a more dynamic approach.

Our study examined 14 models—spanning statistical, machine learning, and deep learning techniques—to forecast daily CO₂ emissions in key regions: China, India, the USA, and the EU27&UK. This focus on daily data marked a critical gap in the literature and presented unique challenges, such as handling nonlinear patterns and seasonal variability.

One memorable challenge was ensuring data stationarity for statistical models, a task made possible through meticulous differencing techniques. Another breakthrough moment came when ensemble techniques like bagging and voting boosted the performance of machine learning models, highlighting their practical advantages over computationally intensive deep learning models.

The study's results exceeded our expectations. Machine learning models, enhanced with ensemble methods, demonstrated robust performance, proving to be a practical recommendation for policymakers seeking real-time emissions data. These insights can directly aid in setting short-term CO₂ reduction targets, an essential step in combating climate change.

Behind the scenes, our team drew on diverse expertise and a shared commitment to environmental sustainability. We hope this work not only advances predictive modeling in climate science but also inspires collaborative efforts to address global warming.

Have you faced similar challenges in predictive modeling or environmental research? We'd love to hear your thoughts and experiences!

Together, through collaboration and innovation, we can pave the way for a more sustainable future.

Please sign in or register for FREE

If you are a registered user on Research Communities by Springer Nature, please sign in