Evaluating deep learning architectures for CO2 emissions forecasting: TCN, LSTM, and hybrid approaches with hyperparameter optimization
Open Access
- 28 October 2025
- journal article
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 5 (10 (137)) , 20-32
Abstract
The object of the study is CO2 emission prediction using deep learning models. The problem lies in developing accurate models capable of handling temporal dependencies and periodic patterns in CO2 data. To address this, three deep learning models – temporal convolutional network (TCN), long short-term memory (LSTM), and a hybrid TCN-LSTM are evaluated. These models are optimized using random search and Bayesian optimization. Results indicate that the Hybrid TCN-LSTM model, optimized via random search, performs best, achieving MAE: 1.0269, R2: 0.9305, and MAPE: 4.47%. TCN excels at capturing periodic patterns through dilated convolutions, while LSTM handles long-term dependencies. Their integration combines these strengths, improving accuracy. Optimal hyperparameters (learning rate: 0.000539, dropout rate: 0.5) enhance robustness. Random search outperforms Bayesian optimization in navigating complex search spaces and avoiding local optima. Key findings include the hybrid model's ability to address short-term periodicity and long-term trends, and Random Search’s reliability over Bayesian methods in this context. These insights advance time series forecasting methodologies and support robust predictive frameworks. Practically, they aid environmental policy, energy planning, and carbon trading by enabling data-driven decisions for emission reduction. However, implementation requires high-quality historical data and sufficient computational resourcesKeywords
This publication has 26 references indexed in Scilit:
- A novel ultra-short-term wind power forecasting method based on TCN and Informer modelsComputers and Electrical Engineering, 2024
- Carbon emissions trading price forecasting based on temporal-spatial multidimensional collaborative attention network and segment imbalance regressionApplied Energy, 2024
- Leveraging Hybrid Deep Learning Models for Enhanced Multivariate Time Series ForecastingNeural Processing Letters, 2024
- Forecasting China's agricultural carbon emissions: A comparative study based on deep learning modelsEcological Informatics, 2024
- Dynamic spatial–temporal model for carbon emission forecastingJournal of Cleaner Production, 2024
- Robust multi-scale time series prediction for building carbon emissions with explainable deep learningEnergy and Buildings, 2024
- A hybrid deep learning model based on parallel architecture TCN-LSTM with Savitzky-Golay filter for wind power predictionEnergy Conversion and Management, 2024
- A refined ResNet18 architecture with Swish activation function for Diabetic Retinopathy classificationBiomedical Signal Processing and Control, 2023
- A novel optimized parametric hyperbolic tangent swish activation function for 1D-CNN: application of sensor-based human activity recognition and anomaly detectionMultimedia Tools and Applications, 2023
- A novel short-term carbon emission prediction model based on secondary decomposition method and long short-term memory networkEnvironmental Science and Pollution Research, 2022