Prediction of CO2 Emissions Using ANN, ARIMAX, and Hybrid ARIMAX-ANN Models

Afifah Dayan Syaharani; Hervira Nur Shafira; Hikmal Mardian Irianto; Fitri Kartiasih

doi:10.30812/varian.v8i3.5045

Authors

Afifah Dayan Syaharani Politeknik Statistika STIS, East Jakarta, Indonesia
Hervira Nur Shafira Politeknik Statistika STIS, East Jakarta, Indonesia
Hikmal Mardian Irianto Politeknik Statistika STIS, East Jakarta, Indonesia
Fitri Kartiasih Politeknik Statistika STIS, East Jakarta, Indonesia

DOI:

https://doi.org/10.30812/varian.v8i3.5045

Keywords:

ANN, ARIMAX, CO2 Emissions, Energy Consumption, GDP, Hybrid ARIMAX-ANN

Abstract

The escalation of carbon dioxide (CO₂) emissions has emerged as a critical environmental concern, particularly in the context of Indonesia’s pursuit of sustainable development. This study aims to forecast CO₂ emissions in Indonesia using annual time-series data spanning 1967–2023. Three methodological approaches are employed: an artificial neural network (ANN), an autoregressive model with exogenous variables (ARIMAX), and a hybrid ARIMAX-ANN model. The dataset comprises Gross Domestic Product obtained from the World Bank, along with per capita CO₂ emissions, per capita natural gas consumption, and per capita hydropower consumption sourced from Our World in Data. The findings of this research demonstrate that the hybrid ARIMAX-ANN model provides the best forecasting performance, as evidenced by the lowest RMSE, MAPE, and MAE values among the other two models. These results suggest that the hybrid model is currently the most reliable for predicting CO₂ emissions in the Indonesian context. The study enriches the expanding literature on emission forecasting by providing empirical evidence to support data-driven policymaking for climate change mitigation and sustainable energy development in Indonesia.

Downloads

Download data is not yet available.

References

Agbulut, U. (2022). Forecasting of transportation-related energy demand and CO2 emissions in Turkey with different machine learning algorithms. Sustainable Production and Consumption, 29, 141–157. https://doi.org/10.1016/j.spc.2021.10.001

Alam, T., & AlArjani, A. (2021). A Comparative Study of CO2 Emission Forecasting in the Gulf countries Using Autoregressive Integrated Moving Average, Artificial Neural Network, and Holt-Winters Exponential Smoothing Models (A. Donateo, Ed.). Advances in Meteorology, 2021, 1–9. https://doi.org/10.1155/2021/8322590

Ali, M. U., Gong, Z., Ali, M. U., Wu, X., & Yao, C. (2021). Fossil energy consumption, economic development, inward FDI impact on CO2 emissions in Pakistan: Testing EKC hypothesis through ARDL model. International Journal of Finance & Economics, 26(3), 3210–3221. https://doi.org/10.1002/ijfe.1958

Amalia, M. F., Junianto, R. R., Kartiasih, F., & Rahmadani, R. (2025). Examining the Impact of Energy Use, Economic Growth, and Forest Area on CO2 Emissions: Consequences for Achieving the SDGs. Jurnal Ilmiah Pendidikan Lingkungan dan Pembangunan, 25(02), 1–26. https://doi.org/10.21009/plpb.v25i02.42230

Bashir, A., Susetyo, D., SUHEL, S., & Azwardi, A. (2021). Relationships between Urbanization, Economic Growth, Energy Consumption, and CO2 Emissions: Empirical Evidence from Indonesia. The Journal of Asian Finance, Economics and Business, 8(3), 79–90. https://doi.org/10.13106/JAFEB.2021.VOL8.NO3.0079

Han, T. T. T., & Lin, C.-Y. (2025). Exploring long-run CO2 emission patterns and the environmental kuznets curve with machine learning methods. Innovation and Green Development, 4(1), 100195. https://doi.org/10.1016/j.igd.2024.100195

Iftikhar, H., Khan, M., Zywiołek, J., Khan, M., & Lopez-Gonzales, J. L. (2024). Modeling and forecasting carbon dioxide emission in Pakistan using a hybrid combination of regression and time series models. Heliyon, 10(13), e33148. https://doi.org/10.1016/j.heliyon.2024.e33148

Janhuaton, T., Ratanavaraha, V., & Jomnonkwao, S. (2024). Forecasting Thailand’s Transportation CO2 Emissions: A Comparison among Artificial Intelligent Models. Forecasting, 6(2), 462–484. https://doi.org/10.3390/forecast6020026

Kartiasih, F., Azhari, A., & Rinangku, R. E. B. I. (2025). Carbon Trading Potential in the Forest Sector: Analysis at the Province Level in Indonesia. EKO-REGIONAL: Jurnal Pembangunan Ekonomi Wilayah, 20(1), 14–29. https://doi.org/10.32424/er.v20i1.14668

Kartiasih, F., & Pribadi, W. (2020). Environmental Quality and Poverty Assessment in Indonesia. Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management), 10(1), 89–97. https://doi.org/10.29244/jpsl.10.1.89-97

Kartiasih, F., Sandi, I. M., Abioga, N. R., Aditya, R. D., & Sabrina, R. (2025). Analysis of Carbon Emissions in ASEAN Manufacturing: Input-Output and Panel Data Approach. Efficient: Indonesian Journal of Development Economics, 8(1), 323–329. https://doi.org/10.15294/jsnnrt53

Kartiasih, F., & Setiawan, A. (2020). Aplikasi Error Correction Mechanism dalam Analisis Dampak Pertumbuhan Ekonomi, Konsumsi Energi, dan Perdagangan Internasional terhadap Emisi CO2 di Indonesia. MEDIA STATISTIKA, 13(1), 104–115. https://doi.org/10.14710/medstat.13.1.104-115

Khan, M., Rana, A. T., & Ghardallou, W. (2023). FDI and CO2 emissions in developing countries: The role of human capital. Natural Hazards, 117(1), 1125–1155. https://doi.org/10.1007/s11069-023-05949-4

Lin, F.-L., Inglesi-Lotz, R., & Chang, T. (2018). Revisit coal consumption, CO2 emissions and economic growth nexus in China and India using a newly developed bootstrap ARDL bound test. Energy Exploration & Exploitation, 36(3), 450–463. https://doi.org/10.1177/0144598717741031

Mahmood, H., Hassan, M. S., Rej, S., & Furqan, M. (2023). The Environmental Kuznets Curve and Renewable Energy Consumption: A Review. International Journal of Energy Economics and Policy, 13(3), 279–291. https://doi.org/10.32479/ijeep.14270

Mahmudi, M., Safitri, I. B., & Zulkifli, D. U. (2024). Modeling Rainfall in Jakarta with Hybrid ARIMAX-ANN Model. Kontinu: Jurnal Penelitian Didaktik Matematika, 8(1), 1. https://doi.org/10.30659/kontinu.8.1.1-20

Marwa, T., Bashir, A., Atiyatna, D. P., Hamidi, I., Mukhlis, M., & Sukanto, S. (2022). The Link between Economic Growth, Electricity Consumption, and CO2 Emissions: Evidence from Indonesia. Signifikan: Jurnal Ilmu Ekonomi, 11(2), 253–272. https://doi.org/10.15408/sjie.v11i2.26286

Mehraaein, M., Afroz, R., Rahman, M. Z., & Muhibbullah, M. (2021). Dynamic Impact of Macroeconomic Variables on the Ecological Footprint in Malaysia: Testing EKC and PHH. The Journal of Asian Finance, Economics and Business, 8(5), 583–593. https://doi.org/10.13106/JAFEB.2021.VOL8.NO5.0583

Miswa, S. D., & Kartiasih, F. (2025). Nexus between rural poverty and environmental quality: Empirical evidence from Indonesia. Asia-Pacific Journal of Regional Science, 9(1), 57–81. https://doi.org/10.1007/s41685-024-00370-6

Siregar, M. R., Halma, K., Alifiyanti, R., & Kartiasih, F. (2025). Nexus between Extreme Poverty and CO2 Emissions in Indonesia: An Empirical Investigation with VECM Approach. Journal of Economics Research and Social Sciences, 9(2), 264–281. https://doi.org/10.18196/jerss.v9i2.26339

Sufyanullah, K., Ahmad, K. A., & Sufyan Ali, M. A. (2022). Does emission of carbon dioxide is impacted by urbanization? An empirical study of urbanization, energy consumption, economic growth and carbon emissions - Using ARDL bound testing approach. Energy Policy, 164, 112908. https://doi.org/10.1016/j.enpol.2022.112908

Supriya, K. (2020). A Study on the Performance of ARIMAX-ANN Hybrid Model over the Other Forecasting Models while Forecasting the Damage Caused by Brown Plant Hopper (Nilaparvata lugens) in Telangana State. International Journal of Current Microbiology and Applied Sciences, 9(9), 2609–2616. https://doi.org/10.20546/ijcmas.2020.909.326

Sutthichaimethee, P., & Ariyasajjakorn, D. (2017). Forecasting Energy Consumption in Short-Term and Long-Term Period by Using Arimax Model in the Construction and Materials Sector in Thailand. Journal of Ecological Engineering, 18(4), 52–59. https://doi.org/10.12911/22998993/74396

Wahidah, F. P., Wahyuningsih, S., & Siringoringo, M. (2024). Forecasting the Value of Indonesia’s Exports using Model Hybrid Arimax-NN. Science & Technology Asia, 29, 6274. https://doi.org/10.14456/SCITECHASIA.2024.71

Wongsathan, R., & Chankham, S. (2016). Improvement on PM-10 Forecast by Using Hybrid ARIMAX and Neural Networks Model for the Summer Season in Chiang Mai. Procedia Computer Science, 86, 277–280. https://doi.org/10.1016/j.procs.2016.05.062

Yamacli, D. S., & Tuncsiper, C. (2024). Modeling the CO2 Emissions of Turkey Dependent on Various Parameters Employing ARIMAX and Deep Learning Methods. Sustainability, 16(20), 8753. https://doi.org/10.3390/su16208753

Zhang, Z., Beck, M. W., Winkler, D. A., Huang, B., Sibanda, W., & Goyal, H. (2018). Opening the black box of neural networks: Methods for interpreting neural network models in clinical applications. Annals of Translational Medicine, 6(11), 216–216. https://doi.org/10.21037/atm.2018.05.32