Global Carbon Project's Fossil CO2 Emissions Case Study

Overview

The Global Carbon Project (GCP) is an in-depth dataset that looks into international CO2 emissions at the country level, dating back to 2001 (Andrew & Peters, 2022). The PDF describes the history of this process leading up to the technique used within the 2022 release of the GCP’s fossil CO2 emissions dataset, displaying how countries make a contribution to climate change on an international level. It is valuable to researchers, policymakers, and everyone inquisitive about the impact that human activities have on carbon emissions (Andrew & Peters, 2022).

This dataset was used to provide real-world data regarding fossil CO2 emissions and can be used to give LEAL Carbon, an environmentally friendly startup company, reliable and accurate information. Leveraging information from the Global Carbon Project (GCP), which covers emissions across various countries and sectors, organizations can create inclusive environments and develop AI-powered platforms. This, in turn, empowers individuals by identifying effective sustainability strategies for a greener future.

Content

Leal_Carbon_Case_Study.ipynb: Jupyter Notebook containing the complete code and analysis.

Fossil C02 emissions dataset: The dataset used in the analysis.

Results and Conclusions

Linear Regression Model

The Linear Regression model helped to indicate a strong correlation between the selected feature and CO2 emissions. This means that the chosen predictors contribute to explaining the variance in emissions

Visualization Insights

This code includes choropleth maps, pie charts, and line plots. All of these visualizations provide insight into global CO2 emissions trends and help in understanding the distribution of emissions, identifying top-emitting countries, and observing temporal patterns.

Time Series Analysis

Time series analysis using PCA, K-means clustering, and Isolation Forest reveals clusters of countries with similar emission patterns. This clustering approach aids in understanding the dynamics of emissions over time and identifies countries with anomalous behavior.

References

Andrew, R. M., & Peters, G. P. (2022, October 17). The Global Carbon Project’s Fossil CO2 Emissions Dataset. Zenodo.

https://zenodo.org/record/7215364

Bank for International Settlements. (n.d.). Basel Committee on Banking Supervision - Bank for International Settlements. bis.

https://www.bis.org/bcbs/publ/d517.pdf

Evans, S. (2022, May 12). Analysis: Which countries are historically responsible for climate change?. Carbon Brief.

https://www.carbonbrief.org/analysis-which-countries-are-historically-responsible-for-climate-change/

Hulten, G. (2018). Building Intelligent Systems A Guide to Machine Learning Engineering. Apress.

IEA (2021), Greenhouse Gas Emissions from Energy Data Explorer, IEA, Paris

https://www.iea.org/data-and-statistics/data-tools/greenhouse-gas-emissions-from-energy-data-explorer

Jorgenson, A. K., & Clark, B. (2013, February 20). The relationship between national-level carbon dioxide emissions and population size: An assessment of regional and temporal variation, 1960-2005. PloS one.

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3577780/

Ötker-Robe, İ. (2014, October). Global Risks and Collective Action Failures: What Can the International Community Do?. imf.

https://www.imf.org/external/pubs/ft/wp/2014/wp14195.pdf