Anatomy of climate change research in Italian doctoral dissertations using a machine learning approach

Climate change is one of the defining challenges of our time, yet little is known about how early-career researchers contribute to this field through doctoral research. This study provides the first comprehensive mapping of climate change-related doctoral dissertations in Italy across all disciplines, spanning a 14-year period (2008-2021). Doctoral dissertations offer a unique lens into the formative stages of scientific inquiry, where new ideas, methods, and agendas take shape. Using a machine learning approach on a novel dataset of over 74,394 dissertations, we conduct the first large-scale classification of climate change dissertations in Italy. We identify climate-related dissertations and analyze their thematic, disciplinary, and geographical distribution, highlighting emerging research trends in areas such as energy transition, biodiversity conservation, and extreme weather events. While technical disciplines dominate among English-language dissertations, those written in Italian reveal a more balanced disciplinary landscape, with a stronger presence of the social sciences and humanities-though these remain underrepresented overall. Although climate-related research spans a variety of topics, regional variation also emerges: water in the North, energy in the Centre and South, and governance in the Islands. This study marks an important step toward recognizing doctoral research as a strategic asset in building resilient climate knowledge systems and guiding long-term policy planning.