Suparto, Marjuenz (2025) Analisis proyeksi emisi karbon di Indonesia untuk net zero emission menggunakan model time series. Bachelor thesis, Universitas Pelita Harapan.
![Title [thumbnail of Title]](http://repository.uph.edu/style/images/fileicons/text.png)
Title.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (199kB)
![Abstract [thumbnail of Abstract]](http://repository.uph.edu/style/images/fileicons/text.png)
Abstract.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (203kB)
![ToC [thumbnail of ToC]](http://repository.uph.edu/style/images/fileicons/text.png)
ToC.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (273kB)
![Chapter1 [thumbnail of Chapter1]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (338kB)
![Chapter2 [thumbnail of Chapter2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (597kB)
![Chapter3 [thumbnail of Chapter3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (670kB)
![Chapter4 [thumbnail of Chapter4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (891kB)
![Chapter5 [thumbnail of Chapter5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (245kB)
![Bibliography [thumbnail of Bibliography]](http://repository.uph.edu/style/images/fileicons/text.png)
Bibliography.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (219kB)
![Appendices [thumbnail of Appendices]](http://repository.uph.edu/style/images/fileicons/text.png)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
Abstract
Global climate change is one of the greatest challenges of this century, primarily driven by the increase in greenhouse gas emissions. The concept of Net Zero Emissions NZE is officially outlined in the Paris Agreement of 2015, particularly in Article 4.1, which serves as a key foundation for defining NZE within the framework of global climate action. This study aims to propose exploratory data analysis methods (EDA) and models for predicting and projecting carbon emissions in Indonesia through the year 2060. To develop and determine the most appropriate model, a comparison is conducted between several machine learning algorithms, namely Multiple Linear Regression (MLR), Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX), Long Short- Term Memory (LSTM), and Transformer (TF).
The dataset used in this research is secondary data from Our World in Data: CO2 and Greenhouse Gas Emissions. An exploratory data analysis (EDA) is conducted to identify the factors influencing carbon emissions in Indonesia based on historical data. The processed data is then implemented into the respective machine learning models. Performance evaluation indicates that MLR produces the best results, with a Mean Squared Error (MSE) of 15,997, Root Mean Squared Error (RMSE) of 4,00, Mean Absolute Error (MAE) of 3,321, Mean Absolute Percentage Error (MAPE) of 0,5885%, and an R-squared (R²) score of 0,990.
These findings demonstrate that MLR is the most optimal model for predicting carbon emissions based on the given dataset. Consequently, MLR is used to project Indonesia’s carbon emissions through 2060. The interpretation of the model underscores the importance of addressing the factors contributing to carbon emissions, such as recommendations for optimizing the gradual reduction of coal- fired power plants, in order to support the achievement of Indonesia's commitments in the Paris Agreement and the NZE target in 2060.
/
Perubahan iklim global merupakan salah satu tantangan terbesar pada abad ini, dengan peningkatan emisi gas rumah kaca sebagai penyebab utamanya. Konsep Net Zero Emissions (NZE) secara resmi tertuang dalam Perjanjian Paris 2015, khususnya pada Pasal 4.1, yang menjadi landasan penting dalam mendefinisikan NZE dalam kerangka aksi iklim global. Penelitian ini bertujuan untuk mengusulkan metode exploratory data analysis (EDA) dan implementasi time series model dalam memprediksi serta memproyeksikan emisi karbon di Indonesia hingga tahun 2060. Untuk membangun dan menentukan time series model yang paling tepat, dilakukan perbandingan antara beberapa algoritma machine learning, yaitu Multiple Linear Regression (MLR), Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX), Long Short-Term Memory (LSTM), dan Transformer (TF).
Dataset yang digunakan pada penelitian ini merupakan data sekunder dari Our World in Data: CO2 and Greenhouse Gas Emissions. Proses exploratory data analysis (EDA) dilakukan untuk mengidentifikasi faktor-faktor yang memengaruhi emisi karbon di Indonesia berdasarkan data historis. Selanjutnya, data yang telah diproses diimplementasikan ke dalam model-model machine learning tersebut. Evaluasi performa menunjukkan bahwa model MLR memberikan hasil terbaik, dengan skor Mean Squared Error (MSE) sebesar 15,997, Root Mean Squared Error (RMSE) sebesar 4,00, Mean Absolute Error (MAE) sebesar 3,321, Mean Absolute Percentage Error (MAPE) sebesar 0,5885%, dan R-squared (R²) sebesar 0,990.
Temuan ini menunjukkan bahwa MLR merupakan model paling optimal dalam memprediksi emisi karbon berdasarkan dataset yang digunakan. Oleh karena itu, MLR dipilih untuk memproyeksikan emisi karbon di Indonesia hingga tahun 2060. Hasil interpretasi model menekankan pentingnya penanganan faktor-faktor penyebab emisi karbon seperti rekomendasi optimalisasi pengurangan PLTU batu bara secara bertahap, guna mendukung pencapaian komitmen Indonesia dalam Perjanjian Paris dan target NZE pada tahun 2060.
Item Type: | Thesis (Bachelor) |
---|---|
Creators: | Creators NIM Email ORCID Suparto, Marjuenz NIM01082210013 marjuenzo110@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Samosir, Feliks NIDN0319049302 feliks.parningotan@uph.edu Thesis advisor Diana, Marta NIDK6657777678230102 marta.diana@uph.edu |
Uncontrolled Keywords: | net zero emission; exploratory data analysis; time series model; prediction; forecast |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | University Subject > Current > Faculty/School - UPH Karawaci > School of Information Science and Technology > Informatics Current > Faculty/School - UPH Karawaci > School of Information Science and Technology > Informatics |
Depositing User: | MARJUENZ HENRY SUPARTO |
Date Deposited: | 01 Jul 2025 08:49 |
Last Modified: | 01 Jul 2025 08:49 |
URI: | http://repository.uph.edu/id/eprint/69031 |