Leveraging geospatial data for ESG analysis

Introduction

In this case study, we explore the collaboration between NHM (Natural History Museum) and Vivid Economics (McKinsey) along with lead project partner, Neural Alpha. The aim of this partnership was to develop a comprehensive dataset that brings transparency to geospatial data, connecting companies to physical assets, infrastructure, and agricultural assets. This dataset facilitates the overlay of metrics like the Biodiversity Intactness Index for TNFD (Task Force on Nature-related Financial Disclosures) analyses. The resulting dataset provides valuable insights into the ownership, distribution, and capacities of physical assets and enables rapid portfolio-level analysis of exposures to ESG (Environmental, Social, and Governance) issues such as biodiversity intactness.

Partner and Product Overview

Partners: NHM (Natural History Museum) and Vivid Economics (McKinsey)

Product/Service

‍A comprehensive dataset designed to bring transparency to geospatial data. It connects companies to physical assets, infrastructure, and agricultural assets. The dataset contains information about commodities produced, capacity, and locations, and covers 30 asset types, including power stations, factories, mines, oil wells, and more. It incorporates 20+ key data attributes for assets, including universal and sector-specific data points, and links asset capacity data to 250+ commodities conformed to HS codes.

Objectives/Goals/Challenges

The main objectives of this project were:

• Understand the ownership, distribution, and capacities of physical assets across a vast range of commodity types.
• Enable rapid portfolio-level analysis of exposures to ESG issues, with a specific focus on biodiversity intactness.

Solutions

To achieve the objectives, the partners leveraged the expertise of Neural Alpha in combining disparate datasets using graph technologies. Neural Alpha built a knowledge graph that connected assets owned by companies to financial datasets, thereby linking geospatial data to the company level. This holistic view allowed for comprehensive analysis of supply chains, portfolios, and their connections to specific geolocations and various ESG risks.

Benefits/Results

The partnership and development of the knowledge graph led to several notable benefits and results:

• Over 42,000 operating and owning companies were linked to their ultimate parent entities at the legal entity resolution.
• The dataset covered 300,000+ physical assets globally, providing a rich and extensive set of geospatial data.
• Asset-level biodiversity impacts were integrated, offering insights into environmental risks associated with various asset types.
• Rapid traversal and analysis of supply chains and portfolios became possible, enabling efficient identification of potential ESG risks.
• The dataset facilitated the overlay of metrics like the Biodiversity Intactness Index for TNFD analyses, enhancing the assessment of biodiversity-related risks.

Conclusion

The collaboration between NHM, Vivid Economics, and Neural Alpha resulted in the creation of a valuable geospatial dataset. This dataset has significantly enhanced transparency in understanding the relationships between companies, their physical assets, and the associated ESG risks, particularly related to biodiversity intactness. By leveraging the power of graph technologies, the partners have provided businesses with a comprehensive tool to analyze their supply chains, portfolios, and environmental impact with greater efficiency and accuracy. The knowledge graph developed through this collaboration marks a significant step forward in data-driven ESG analysis and its implications for sustainable decision-making across industries.