50

Existing patent classification systems often overlook the full spectrum of green and environmentally relevant technologies – especially pervasive technologies not originally designed for ecological purposes. This paper presents a novel methodological framework to identify, and classify both clean and pervasive technologies with relevance to biodiversity innovation. The approach combines the analysis of international patent data with machine learning techniques to enhance the accuracy and granularity of classification. In a two-step process, the study first identifies key biodiversity-related technologies and their corresponding IPC classes, and then maps innovation activity and geographic trends using patent-based indicators. By addressing limitations in existing international patent classification schemes, the framework enables more accurate ESG assessments and better-informed sustainability policies and investments. Ultimately, this work provides data-driven tools for tracking biodiversity-related technological progress, supporting robust ESG disclosure and strategic decision-making across sectors.