Leveraging AI for enhanced alignment of national biodiversity targets with the global biodiversity goals

Abstract

This research explores the innovative application of artificial intelligence (AI), specifically OpenAI's GPT-3.5 model, in assessing the alignment between National Biodiversity Targets (NBTs) and the Kunming-Montreal Global Biodiversity Framework (GBF). Addressing biodiversity loss requires aligning national efforts with global objectives, a complex task due to the vast amount of biodiversity data and the diversity of biodiversity strategies across countries. By leveraging AI, this study introduces a scalable, efficient method to evaluate the congruence between 599 NBTs from 26 countries and the GBF goals and targets. Our methodology combines traditional natural language processing techniques with large language model insights utilizing GPT-3.5 to examine the similarity between national and global biodiversity targets and identify recommendations to enhance target alignment. The study achieves two main objectives: 1) providing actionable insights for countries to accelerate alignment with the GBF through their National Biodiversity Strategy and Action Plan (NBSAP) Target Similarity Assessments, and 2) mapping the global landscape of biodiversity policy alignment to inform strategic planning for the 16th Biodiversity Conference of Parties (COP16). The analysis reveals strong alignment with GBF Goals A and B, as well as Targets 4, 10, and 14, while highlighting areas for improvement in gender equality, biosafety, and business sector engagement. This research demonstrates AI's capacity to streamline biodiversity policy alignment, offering specific guidance for nations to refine their biodiversity strategies. The study underscores the importance of human-centered, transparent AI applications in supporting global biodiversity goals, advocating for collaborative, multi-sectoral efforts to enhance policy coherence and achieve the ambitious objectives of the GBF.