TY  - JOUR
AU  - Arya, Suraj
AU  - Anju
AU  - Onah, Jonas Nnaemeka
PY  - 2026
DA  - 2026/01/12
TI  - A Data-Driven Framework for Methane Emission Prediction Using Machine Learning Methods
JO  - ICCK Transactions on Machine Intelligence
T2  - ICCK Transactions on Machine Intelligence
JF  - ICCK Transactions on Machine Intelligence
VL  - 2
IS  - 1
SP  - 53
EP  - 64
DO  - 10.62762/TMI.2025.782852
UR  - https://www.icck.org/article/abs/TMI.2025.782852
KW  - machine learning
KW  - methane emission
KW  - random forest regressor
KW  - prediction
AB  - Greenhouse gas Methane (CH$_4$) has 86 times more impact on global warming than carbon dioxide (CO$_2$). The emission of methane gas into the atmosphere is increasing due to the reliance on fossil-based resources in post-industrial energy consumption, along with the rise in food demand and the generation of organic waste that accompanies a growing human population. CH$_4$ acts as a vital pollutant in the air. The problem addressed in this study was to accurately estimate CH$_4$ emissions from functional urban areas. This study aims to predict CH$_4$ emissions using Time Series (TS) and Machine Learning (ML) models such as Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), Long Short-Term Memory (LSTM), Random Forest Regressor (RFR), and CatBoost Regressor (CABR), etc. The SARIMA model has the best combination of values (1,0,0) (1,1,0). The methane emission data was collected from the World Bank’s Group from 2019 to 2022. Among all models, the SARIMA model predicted CH$_4$ emissions more accurately than the other models. The results obtained in the study indicate that SARIMA outperforms other techniques. The SARIMA model performed the most accurate results in terms of R-squared score (R$^2$) = 94%; Root Mean Squared Error (RMSE) = 2.8129; Mean Squared Error (MSE) = 7.9126; Mean Absolute Error (MAE) = 1.8391, etc. This type of prediction enables the government to reduce CH$_4$ emissions at the global level.
SN  - 3068-7403
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Arya2026A,
  author = {Suraj Arya and Anju and Jonas Nnaemeka Onah},
  title = {A Data-Driven Framework for Methane Emission Prediction Using Machine Learning Methods},
  journal = {ICCK Transactions on Machine Intelligence},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {53-64},
  doi = {10.62762/TMI.2025.782852},
  url = {https://www.icck.org/article/abs/TMI.2025.782852},
  abstract = {Greenhouse gas Methane (CH\$\_4\$) has 86 times more impact on global warming than carbon dioxide (CO\$\_2\$). The emission of methane gas into the atmosphere is increasing due to the reliance on fossil-based resources in post-industrial energy consumption, along with the rise in food demand and the generation of organic waste that accompanies a growing human population. CH\$\_4\$ acts as a vital pollutant in the air. The problem addressed in this study was to accurately estimate CH\$\_4\$ emissions from functional urban areas. This study aims to predict CH\$\_4\$ emissions using Time Series (TS) and Machine Learning (ML) models such as Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), Long Short-Term Memory (LSTM), Random Forest Regressor (RFR), and CatBoost Regressor (CABR), etc. The SARIMA model has the best combination of values (1,0,0) (1,1,0). The methane emission data was collected from the World Bank’s Group from 2019 to 2022. Among all models, the SARIMA model predicted CH\$\_4\$ emissions more accurately than the other models. The results obtained in the study indicate that SARIMA outperforms other techniques. The SARIMA model performed the most accurate results in terms of R-squared score (R\$^2\$) = 94\%; Root Mean Squared Error (RMSE) = 2.8129; Mean Squared Error (MSE) = 7.9126; Mean Absolute Error (MAE) = 1.8391, etc. This type of prediction enables the government to reduce CH\$\_4\$ emissions at the global level.},
  keywords = {machine learning, methane emission, random forest regressor, prediction},
  issn = {3068-7403},
  publisher = {Institute of Central Computation and Knowledge}
}