Financial investors are increasingly considering environmental social governance (ESG) scores in their investment decisions, but they lack transparent standards for calculating them. For companies, an important measure for achieving a high ESG score is the mitigation of greenhouse gas (GHG) emissions that stem from energy consumption and transport. Using deep learning techniques on Earth observation data, information about a company’s access to renewable energy can be automatically generated. Data sets on the geographical sites of renewable energy generators around the world can thus be determined and combined with databases on existing energy infrastructure (such as power grids). SciNRGY merges this data with well-established energy system models to calculate long-term energy-related indicators for customisable scenarios. This allows for comprehensive and constantly updatable assessments of GHG mitigation roadmaps for companies and serves as an important ESG component for financial investors.
Karl-Kiên Cao, Christoph Schimeczek,
Manuel Wetzel, Niklas Wulff, Tobias Junne