Main Article Content
Abstract
CO2 emissions have been an environmental issue for decades. The trigger for the increasing concentration of CO2 in the atmosphere is the growth of industries related to burning fossil fuels for coal, natural gas, and petroleum. For nearly a century, several attempts have been made to suppress the rapid growth of CO2 . This study uses daily atmospheric CO2 levels observed in Mauna Loa laboratories. The method used is a Prophet that can handle seasonality and mark the change points. Almost 20% of data was missing value, which was then imputed using spline interpolation. Based on the analysis results, CO2 levels have an upward trend throughout the year and seasonality. There is no point of change in the last ten years that shows a decrease in CO2 levels. Using forward chaining cross-validation evaluation and error measurement, the prophet model can follow the pattern of CO2 levels well. The average RMSE value is less than 2.0, with an MAPE value bellow 0.5%.
Keywords
Article Details
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
- R. Betts and R. Keeling, “Atmospheric carbon dioxide at record high levels despite reduced emissions in 2020 - Met Office,” 2021. https://www.metoffice.gov.uk/research/news/2021/record-co2-levels-despite-lower-emissions-in-2020 (accessed Feb. 22, 2022).
- Z. Z. OO and S. PHYU, “Time Series Prediction Based on Facebook Prophet: A Case Study, Temperature Forecasting in Myintkyina,” Int. J. Appl. Math. Electron. Comput., vol. 8, no. 4, pp. 263–267, 2020, doi: 10.18100/ijamec.816894.
- T. Toharudin, R. S. Pontoh, R. E. Caraka, S. Zahroh, Y. Lee, and R. C. Chen, “Employing long short-term memory and Facebook prophet model in air temperature forecasting,” Commun. Stat. Simul. Comput., vol. 0, no. 0, pp. 1–24, 2020, doi: 10.1080/03610918.2020.1854302.
- H. Weytjens, E. Lohmann, and M. Kleinsteuber, “Cash flow prediction: MLP and LSTM compared to ARIMA and Prophet,” Electron. Commer. Res., no. 0123456789, 2019, doi: 10.1007/s10660-019-09362-7.
- R. S. Pontoh, S. Zahroh, H. R. Nurahman, R. I. Aprillion, A. Ramdani, and D. I. Akmal, “Applied of feed-forward neural network and facebook prophet model for train passengers forecasting,” J. Phys. Conf. Ser., vol. 1776, no. 1, pp. 0–9, 2021, doi: 10.1088/1742-6596/1776/1/012057.
- M. Lounis, “Predicting active , death and recovery rates of COVID-19 in Al- geria using Facebook ’ Prophet model,” Preprints, vol. 1, no. March, 2021, doi: 10.20944/preprints202103.0019.v1.
- S. Mahmud, “Bangladesh COVID-19 Daily Cases Time Series Analysis using Facebook Prophet Model,” SSRN Electron. J., no. June 2020, 2020, doi: 10.2139/ssrn.3660368.
- K. W. Thoning, A. M. Crotwell, and J. W. Mund, “Atmospheric Carbon Dioxide Dry Air Mole Fractions from continuous measurements at Mauna Loa, Hawaii, Barrow, Alaska, American Samoa and South Pole,” Boulder, Colorado, USA, 2021. doi: https://doi.org/10.15138/yaf1-bk21.
- C. L. Zhao and P. P. Tans, “Estimating uncertainty of the WMO mole fraction scale for carbon dioxide in air,” J. Geophys. Res. Atmos., vol. 111, no. 8, Apr. 2006, doi: 10.1029/2005JD006003.
- L. Guo, W. Fang, Q. Zhao, and X. Wang, “The hybrid PROPHET-SVR approach for forecasting product time series demand with seasonality,” Comput. Ind. Eng., vol. 161, no. February, p. 107598, 2021, doi: 10.1016/j.cie.2021.107598.
- G. Rafferty and an O. M. C. Safari, Forecasting Time Series Data with Facebook Prophet. Packt Publishing Ltd., 2021.
- S. Moritz and T. Bartz-beielstein, “imputeTS : Time Series Missing Value Imputation in R,” R J. Vol., vol. 9, no. 1, pp. 207–218, 2017.
- Z. Liu and X. Yang, “Cross validation for uncertain autoregressive model,” Commun. Stat. Simul. Comput., vol. 0, no. 0, pp. 1–12, 2020, doi: 10.1080/03610918.2020.1747077.
- M. Schnaubelt, “A comparison of machine learning model validation schemes for non-stationary time series data,” Nürnberg, No. 11/2019, 2019. [Online]. Available: http://hdl.handle.net/10419/209136.
References
R. Betts and R. Keeling, “Atmospheric carbon dioxide at record high levels despite reduced emissions in 2020 - Met Office,” 2021. https://www.metoffice.gov.uk/research/news/2021/record-co2-levels-despite-lower-emissions-in-2020 (accessed Feb. 22, 2022).
Z. Z. OO and S. PHYU, “Time Series Prediction Based on Facebook Prophet: A Case Study, Temperature Forecasting in Myintkyina,” Int. J. Appl. Math. Electron. Comput., vol. 8, no. 4, pp. 263–267, 2020, doi: 10.18100/ijamec.816894.
T. Toharudin, R. S. Pontoh, R. E. Caraka, S. Zahroh, Y. Lee, and R. C. Chen, “Employing long short-term memory and Facebook prophet model in air temperature forecasting,” Commun. Stat. Simul. Comput., vol. 0, no. 0, pp. 1–24, 2020, doi: 10.1080/03610918.2020.1854302.
H. Weytjens, E. Lohmann, and M. Kleinsteuber, “Cash flow prediction: MLP and LSTM compared to ARIMA and Prophet,” Electron. Commer. Res., no. 0123456789, 2019, doi: 10.1007/s10660-019-09362-7.
R. S. Pontoh, S. Zahroh, H. R. Nurahman, R. I. Aprillion, A. Ramdani, and D. I. Akmal, “Applied of feed-forward neural network and facebook prophet model for train passengers forecasting,” J. Phys. Conf. Ser., vol. 1776, no. 1, pp. 0–9, 2021, doi: 10.1088/1742-6596/1776/1/012057.
M. Lounis, “Predicting active , death and recovery rates of COVID-19 in Al- geria using Facebook ’ Prophet model,” Preprints, vol. 1, no. March, 2021, doi: 10.20944/preprints202103.0019.v1.
S. Mahmud, “Bangladesh COVID-19 Daily Cases Time Series Analysis using Facebook Prophet Model,” SSRN Electron. J., no. June 2020, 2020, doi: 10.2139/ssrn.3660368.
K. W. Thoning, A. M. Crotwell, and J. W. Mund, “Atmospheric Carbon Dioxide Dry Air Mole Fractions from continuous measurements at Mauna Loa, Hawaii, Barrow, Alaska, American Samoa and South Pole,” Boulder, Colorado, USA, 2021. doi: https://doi.org/10.15138/yaf1-bk21.
C. L. Zhao and P. P. Tans, “Estimating uncertainty of the WMO mole fraction scale for carbon dioxide in air,” J. Geophys. Res. Atmos., vol. 111, no. 8, Apr. 2006, doi: 10.1029/2005JD006003.
L. Guo, W. Fang, Q. Zhao, and X. Wang, “The hybrid PROPHET-SVR approach for forecasting product time series demand with seasonality,” Comput. Ind. Eng., vol. 161, no. February, p. 107598, 2021, doi: 10.1016/j.cie.2021.107598.
G. Rafferty and an O. M. C. Safari, Forecasting Time Series Data with Facebook Prophet. Packt Publishing Ltd., 2021.
S. Moritz and T. Bartz-beielstein, “imputeTS : Time Series Missing Value Imputation in R,” R J. Vol., vol. 9, no. 1, pp. 207–218, 2017.
Z. Liu and X. Yang, “Cross validation for uncertain autoregressive model,” Commun. Stat. Simul. Comput., vol. 0, no. 0, pp. 1–12, 2020, doi: 10.1080/03610918.2020.1747077.
M. Schnaubelt, “A comparison of machine learning model validation schemes for non-stationary time series data,” Nürnberg, No. 11/2019, 2019. [Online]. Available: http://hdl.handle.net/10419/209136.