Automated mapping between SDG indicators and open data: An LLM-augmented knowledge graph approach

Abstract

Meeting the Sustainable Development Goals (SDGs) presents a large-scale challenge for all countries. SDGs established by the United Nations provide a comprehensive framework for addressing global issues. To monitor progress towards these goals, we need to develop key performance indicators and integrate and analyze heterogeneous datasets. The definition of these indicators requires the use of existing data and metadata. However, the diversity of data sources and formats raises major issues in terms of structuring and integration. Despite the abundance of open data and metadata, its exploitation remains limited, leaving untapped potential for guiding urban policies towards sustainability. Thus, this paper introduces a novel approach for SDG indicator computation, leveraging the capabilities of Large Language Models (LLMs) and Knowledge Graphs (KGs). We propose a method that combines rule-based filtering with LLM-powered schema mapping to establish semantic correspondences between diverse data sources and SDG indicators, including disaggregation. Our approach integrates these mappings into a KG, which enables indicator computation by querying graph’s topology. We evaluate our method through a case study focusing on the SDG Indicator 11.7.1 about accessibility of public open spaces. Our experimental results show significant improvements in accuracy, precision, recall, and F1-score compared to traditional schema mapping techniques.