Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal bit-Tech Jurnal Komtika (Komputasi dan Informatika)
Paramarta, Valentinus
Unknown Affiliation
Computer Science & IT Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparative Analysis of K-Means and Gaussian Mixture Model in Clustering Global CO2 Emissions Paramarta, Valentinus; Rahman, Alrafiful; Priska, Lely; Roken Gurning, Rizon; Ayu Purwati, Widya
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2805

Abstract

As global CO2 emissions continue to rise, identifying meaningful patterns across countries has become increasingly vital for shaping effective climate policies. However, many existing approaches rely on uniform benchmarks that overlook national emission heterogeneity. To address this gap, this study applies two unsupervised machine learning techniques K-Means and Gaussian Mixture Model (GMM) to cluster countries based on CO2 emissions from both energy and industrial sectors. The dataset consists of six key indicators, including total emissions, growth rate, and sectoral shares. After handling missing values and applying Min-Max normalization, Principal Component Analysis (PCA) was used to reduce dimensionality and aid visualization. The core objective is to compare the effectiveness of K-Means and GMM in identifying emission-based country groupings. K-Means produced three distinct clusters with strong separation, including a unique cluster dominated solely by China due to its exceptional emission profile. GMM, by contrast, generated more flexible probabilistic clusters, better capturing overlapping patterns and internal variabilities among countries. Evaluation metrics showed that K-Means outperformed GMM in silhouette score and inertia, indicating clearer boundaries, while GMM was more adept at modeling complex, non-spherical distributions. These findings reveal the trade-offs between clarity and adaptability in clustering approaches. The study demonstrates how unsupervised learning can offer actionable insights for emission-based segmentation, enabling more nuanced and differentiated mitigation strategies. By highlighting algorithm-specific strengths, this research contributes to the advancement of machine learning applications in climate informatics and supports the development of targeted international environmental responses.
Perbandingan Kinerja SVR dan XGBoost untuk Peramalan Emisi CO₂ Global berbasis Machine Learning Rahman, Alrafiful; Paramarta, Valentinus; Ida, Agnes Novita; Akbar, Mohammad Harits; Simanjuntak, Vica Sonya M
Jurnal Komtika (Komputasi dan Informatika) Vol 9 No 1 (2025)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/komtika.v9i1.13449

Abstract

The increase in global carbon dioxide (CO2) emissions has become a major concern in climate change studies. This research aims to compare the performance of two machine learning algorithms, namely Support Vector Regression (SVR) and XGBoost, in predicting global CO2 emission trends based on historical data. The dataset used includes related variables such as energy consumption, gross domestic product (GDP), and population, obtained from open data sources like Our World in Data. SVR is optimized through grid search to obtain the best parameters, while XGBoost is used as the main comparator due to its ability to handle non-linear relationships and feature interactions. Model evaluation was conducted using the MAE, RMSE, and R2 metrics. The results show that XGBoost is significantly superior with an MAE of 1745.70 and an RMSE of 2663.18, as well as an R2 value of 0.93, compared to SVR which has an MAE of 5476.54, an RMSE of 8153.37, and an R2 value of 0.82. The visualization of the prediction results also indicates that XGBoost is more accurate in following the fluctuation patterns of actual data, especially in detecting sharp changes. These findings suggest that XGBoost is a more suitable method for forecasting CO2 emissions in complex and non-linear global contexts.
Co-Authors Akbar, Mohammad Harits Ayu Purwati, Widya Ida, Agnes Novita Priska, Lely Rahman, Alrafiful Roken Gurning, Rizon Simanjuntak, Vica Sonya M