This PhD position at Delft University of Technology (TU Delft) focuses on developing machine learning models to detect early warning signals of positive tipping points in the innovation and diffusion of clean energy technologies. Positive tipping points can accelerate progress towards a net-zero energy system, but their emergence and timing are difficult to anticipate. The successful candidate will create a machine learning module that analyzes techno-economic data to identify early signs of these tipping points, enabling policymakers to design adaptive strategies for rapid and resilient decarbonization. The research will integrate time-series analysis, supervised and unsupervised learning, and explainable AI methods to uncover dynamic patterns that precede technological breakthroughs or large-scale adoption events. Validation will be performed using both historical datasets and scenario data from Integrated Assessment Models (IAMs), which are large climate-economic models used to map future decarbonization pathways. The project also involves designing policy portfolios that respond to emerging tipping dynamics and assessing their trade-offs in terms of economic feasibility, equity, and robustness. The PhD will be part of the ERC-funded RIPPLE project, led by Professor Giacomo Marangoni, and embedded within the Policy Analysis section of the Multi-Actor Systems department. The candidate will collaborate with an interdisciplinary team at the intersection of simulation, optimization, and policy modelling, and connect with TU Delft’s Climate Action Programme and Climate Governance theme. TU Delft offers a dynamic, international research environment with excellent facilities, strong mentorship, and tailored training for academic and professional development. The position includes a 4-year employment contract (split into 1.5 and 2.5 years, subject to progress assessment), competitive salary, holiday allowance, end-of-year bonus, flexible work schedules, and support for relocation. Applicants must have a Master’s degree in a relevant field, proficiency in coding and quantitative analysis, interest in machine learning and climate challenges, and excellent English communication skills. Applications must be submitted online by 23 November 2025, including a CV, motivation letter, and degree transcripts. The selection process includes online interviews and a risk assessment for knowledge security.