1
|
Li X, Zhang X. A comparative study of statistical and machine learning models on carbon dioxide emissions prediction of China. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2023; 30:117485-117502. [PMID: 37867169 DOI: 10.1007/s11356-023-30428-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Accepted: 10/08/2023] [Indexed: 10/24/2023]
Abstract
The escalating levels of carbon dioxide (CO2) emissions represent the primary driver of global warming, and addressing them is of paramount importance. Timely and accurate prediction, as well as effective control of CO2 emissions, are pivotal for guiding mitigation measures. This paper aims to select the best prediction model for near-real-time daily CO2 emissions in China. The prediction models are based on univariate daily time-series data spanning January 1st, 2020, to September 30st, 2022. Six models are proposed, including three statistical models: grey prediction (GM(1,1)), autoregressive integrated moving average (ARIMA), and seasonal autoregressive integrated moving average with exogenous factors (SARIMAX), and three machine learning models: artificial neural network (ANN), random forest (RF), and long short-term memory (LSTM). The performance of these six models is evaluated using five criteria: mean squared error (MSE), root-mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2). Our findings reveal that the three machine learning models consistently outperform the three statistical models across all five criteria. Among them, the LSTM model demonstrates exceptional performance for daily CO2 emission prediction, boasting an impressively low MSE value of 3.5179e-04, an RMSE value of 0.0187, an MAE value of 0.0140, an MAPE value of 14.8291%, and a high R2 value of 0.9844. This underscores the robustness of the LSTM model in capturing and predicting complex emission patterns, positioning it as the most suitable option for near-real-time daily CO2 emission prediction based on the provided daily time series data. Moreover, our study's results provide valuable insights into emissions forecasting, enabling data-driven decision-making for policymakers and stakeholders. The accurate and timely predictions offered by the LSTM model can aid in the formulation of effective strategies to mitigate carbon emissions, contributing to a more sustainable future. Furthermore, the findings of this study can enhance our understanding of the dynamics of CO2 emissions, leading to more informed environmental policies and actions aimed at reducing carbon emissions.
Collapse
Affiliation(s)
- Xiangqian Li
- School of Statistics, Capital University of Economics and Business, Beijing, 100070, People's Republic of China
| | - Xiaoxiao Zhang
- School of Statistics and Data Science, Beijing Wuzi University, Beijing, 101126, People's Republic of China.
| |
Collapse
|
2
|
Gao J, Zhou C, Liang H, Jiao R, Wheelock ÅM, Jiao K, Ma J, Zhang C, Guo Y, Luo S, Liang W, Xu L. Monkeypox outbreaks in the context of the COVID-19 pandemic: Network and clustering analyses of global risks and modified SEIR prediction of epidemic trends. Front Public Health 2023; 11:1052946. [PMID: 36761122 PMCID: PMC9902715 DOI: 10.3389/fpubh.2023.1052946] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2022] [Accepted: 01/04/2023] [Indexed: 01/25/2023] Open
Abstract
Background Ninety-eight percent of documented cases of the zoonotic disease human monkeypox (MPX) were reported after 2001, with especially dramatic global spread in 2022. This longitudinal study aimed to assess spatiotemporal risk factors of MPX infection and predict global epidemiological trends. Method Twenty-one potential risk factors were evaluated by correlation-based network analysis and multivariate regression. Country-level risk was assessed using a modified Susceptible-Exposed-Infectious-Removed (SEIR) model and a risk-factor-driven k-means clustering analysis. Results Between historical cases and the 2022 outbreak, MPX infection risk factors changed from relatively simple [human immunodeficiency virus (HIV) infection and population density] to multiple [human mobility, population of men who have sex with men, coronavirus disease 2019 (COVID-19) infection, and socioeconomic factors], with human mobility in the context of COVID-19 being especially key. The 141 included countries classified into three risk clusters: 24 high-risk countries mainly in West Europe and Northern America, 70 medium-risk countries mainly in Latin America and Asia, and 47 low-risk countries mainly in Africa and South Asia. The modified SEIR model predicted declining transmission rates, with basic reproduction numbers ranging 1.61-7.84 in the early stage and 0.70-4.13 in the current stage. The estimated cumulative cases in Northern and Latin America may overtake the number in Europe in autumn 2022. Conclusions In the current outbreak, risk factors for MPX infection have changed and expanded. Forecasts of epidemiological trends from our modified SEIR models suggest that Northern America and Latin America are at greater risk of MPX infection in the future.
Collapse
Affiliation(s)
- Jing Gao
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China,Respiratory Medicine Unit, Department of Medicine and Centre for Molecular Medicine, Karolinska Institute, Stockholm, Sweden,Heart and Lung Centre, Department of Pulmonary Medicine, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Cui Zhou
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China
| | - Hanwei Liang
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China
| | - Rao Jiao
- Department of Mathematical Science, Tsinghua University, Beijing, China
| | - Åsa M. Wheelock
- Heart and Lung Centre, Department of Pulmonary Medicine, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Kedi Jiao
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China
| | - Jian Ma
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China
| | - Chutian Zhang
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China
| | - Yongman Guo
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China
| | - Sitong Luo
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China,Sitong Luo ✉
| | - Wannian Liang
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China,Wannian Liang ✉
| | - Lei Xu
- Vanke School of Public Health, Tsinghua University, Beijing, China,Institute for Healthy China, Tsinghua University, Beijing, China,*Correspondence: Lei Xu ✉
| |
Collapse
|