Analysing Dynamics of Innovation Networks in Climate Technologies

Innovation networks play a crucial role in the development, commercialization, and adoption of climate technologies, yet their structure and dynamics remain poorly understood. To address this gap, researchers at the Net Zero Lab use large language models to analyze 26 million LinkedIn posts, mapping a global network of 166,459 organizations and 442,250 collaborations (~1.4 million direct partnerships) across 189 countries. The dataset spans 27 climate technologies and diverse types of collaborations, such as demonstration projects, product launches, and equity investments. The machine learning approach presented in this Decarbonization Seminar/Joint Seminar ZEW and MISES provides a scalable, real-time methodology for tracking innovation networks over time, with broad applications for industrial analysis and policy evaluation beyond climate-tech.