Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions
The reduction of greenhouse gas emissions, in order to effectively address the issue of climate change, has critical importance worldwide. To achieve this aim and implement the necessary strategies and policies, the projection of greenhouse gas emissions is essential. This paper presents a forecasti...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Systems |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-8954/12/12/528 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850086780225716224 |
|---|---|
| author | Seval Ene Yalçın |
| author_facet | Seval Ene Yalçın |
| author_sort | Seval Ene Yalçın |
| collection | DOAJ |
| description | The reduction of greenhouse gas emissions, in order to effectively address the issue of climate change, has critical importance worldwide. To achieve this aim and implement the necessary strategies and policies, the projection of greenhouse gas emissions is essential. This paper presents a forecasting framework for greenhouse gas emissions based on advanced machine learning algorithms: multivariable linear regression, random forest, k-nearest neighbor, extreme gradient boosting, support vector, and multilayer perceptron regression algorithms. The algorithms employ several input variables associated with greenhouse gas emission outputs. In order to evaluate the applicability and performance of the developed framework, nationwide statistical data from Turkey are employed as a case study. The dataset of the case study includes six input variables and annual sectoral and total greenhouse gas emissions in CO<sub>2</sub> eq. as output variables. This paper provides a scenario-based approach for future forecasts of greenhouse gas emissions and a sector-based analysis of greenhouse gas emissions in the case country considering multiple input variables. The present study indicates that the stated machine learning algorithms can be successfully applied to the forecasting of greenhouse gas emissions. |
| format | Article |
| id | doaj-art-11ae053b5c8d497f898fb0bc52cf7f28 |
| institution | DOAJ |
| issn | 2079-8954 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Systems |
| spelling | doaj-art-11ae053b5c8d497f898fb0bc52cf7f282025-08-20T02:43:21ZengMDPI AGSystems2079-89542024-11-01121252810.3390/systems12120528Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas EmissionsSeval Ene Yalçın0Department of Industrial Engineering, Bursa Uludağ University, Görükle Campus, 16059 Bursa, TürkiyeThe reduction of greenhouse gas emissions, in order to effectively address the issue of climate change, has critical importance worldwide. To achieve this aim and implement the necessary strategies and policies, the projection of greenhouse gas emissions is essential. This paper presents a forecasting framework for greenhouse gas emissions based on advanced machine learning algorithms: multivariable linear regression, random forest, k-nearest neighbor, extreme gradient boosting, support vector, and multilayer perceptron regression algorithms. The algorithms employ several input variables associated with greenhouse gas emission outputs. In order to evaluate the applicability and performance of the developed framework, nationwide statistical data from Turkey are employed as a case study. The dataset of the case study includes six input variables and annual sectoral and total greenhouse gas emissions in CO<sub>2</sub> eq. as output variables. This paper provides a scenario-based approach for future forecasts of greenhouse gas emissions and a sector-based analysis of greenhouse gas emissions in the case country considering multiple input variables. The present study indicates that the stated machine learning algorithms can be successfully applied to the forecasting of greenhouse gas emissions.https://www.mdpi.com/2079-8954/12/12/528CO<sub>2</sub> emissionsforecastinggreenhouse gas emissionsmachine learning algorithms |
| spellingShingle | Seval Ene Yalçın Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions Systems CO<sub>2</sub> emissions forecasting greenhouse gas emissions machine learning algorithms |
| title | Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions |
| title_full | Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions |
| title_fullStr | Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions |
| title_full_unstemmed | Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions |
| title_short | Development of a Forecasting Framework Based on Advanced Machine Learning Algorithms for Greenhouse Gas Emissions |
| title_sort | development of a forecasting framework based on advanced machine learning algorithms for greenhouse gas emissions |
| topic | CO<sub>2</sub> emissions forecasting greenhouse gas emissions machine learning algorithms |
| url | https://www.mdpi.com/2079-8954/12/12/528 |
| work_keys_str_mv | AT sevaleneyalcın developmentofaforecastingframeworkbasedonadvancedmachinelearningalgorithmsforgreenhousegasemissions |