Not logged in.
Quick Search - Contribution
Contribution Details
| Type | Master's Thesis |
| Scope | Discipline-based scholarship |
| Title | A Greenhouse Gas Emission Mapping Tool: Considering the Interconnection in Corporate Value Chains Using Machine Learning to Promote Efficiency Gains |
| Organization Unit | |
| Authors |
|
| Supervisors |
|
| Language |
|
| Institution | University of Zurich |
| Faculty | Faculty of Business, Economics and Informatics |
| Number of Pages | 142 |
| Date | 2020 |
| Abstract Text | In the wake of climate change, it is essential to manage the concentration of greenhouse gases (GHGs) in the atmosphere by lowering overall emissions. If climate change is not tackled in a drastic way now, the consequences for planet Earth will be dramatic and irreversible. Corporates in particular account for the biggest share of GHG emissions and must, therefore, change the way they operate. The high-emitting sectors like electricity, transportation, forestry and land use, cement, steel and oil and gas (O&G) must undergo restructuring in order to reduce the industries’ emissions. Along the globalization of value chains, it becomes increasingly important to manage the emissions across them. This includes indirect emissions that companies are not directly responsible for, but which are a consequence of their activities. Consequently, these emissions can be influenced by the company so that it can incentivize GHG reductions upstream and downstream of their operations. This requires companies to disclose their environmental data and thus, increase the transparency of emission distributions across complete value chains. However, this degree of disclosure currently leaves much to be desired. The present thesis tries to tackle this issue by developing a tool that improves the transparency and thus, the understanding of the emission sources in value chains. The beneficiaries of this insights are the corporates themselves, as well as global asset owners and institutional investors seeking to hold zero-carbon portfolios. In their increasingly important role in driving and leading the transition towards a zero-carbon economy, institutional investors must build coalitions and engage with their investees to reduce overall corporate GHG emissions. By providing additional information about the distribution and interconnection of GHG emissions in value chains, possible inefficiencies and bottlenecks can be identified, which the investors then can engage with in order to reduce their emissions and thus, optimize the value chain’s sustainability degree. The proof-of-concept (POC) of the tool shows that there are issues linked to the data that serves as input. This result again points to the poor quality of environmental data and to the necessity to resolve this issue as soon as possible by companies disclosing this data and cooperating with their stakeholders, as well as by harmonizing the existing accounting and reporting rules. The tool is a valuable fundament to provide first hints of inefficiencies in value chains. Moreover, it offers many enhancement opportunities and once the underlying data is more complete and more accurate, the tool can provide more accurate insights. The optimization problem the tool tries to solve can be supported by machine learning applications in order to get high-quality insights that can be leveraged to substantially reduce GHG emissions in corporate value chains. This paper contributes to the literature on indirect value chain emissions and on machine learning applications in climate contexts. |
| Export |
BibTeX
|