Evolutionary trajectories of biomass energy: Strategic patent analytics through machine learning approaches

Against net-zero targets, policymakers view biomass as indispensable, but systematic foresight on its technology pathways and innovation niches is still scarce. Employing machine learning techniques, this study analyzes 26,865 patents (1970–2022) using topic modeling, document embeddings (Doc2Vec), social-network analysis, and deep neural network to identify technological themes, emerging innovations, and strategic patenting directions. Our analysis identifies 17 core technological themes, pinpointing five significant emerging areas: solid fuel production technologies, biomass drying technologies, biomass fermentation technologies, reactor design, and waste treatment technologies. The study introduces an innovative integrated analytical framework combining patent data analytics and policy semantics, alongside a dynamic four-stage technological lifecycle model, significantly enhancing the accuracy of technological forecasting. These concrete findings offer strategic guidance for policymakers and industry stakeholders, fostering targeted innovations and sustainable biomass energy development.