PhD Candidate in Generative AI & Satellite Data for Urban Heat Prediction

Kungliga Tekniska Högskolan · Vollzeit

Brinellvägen 8, Stockholm, Schweden

Project Description Doctoral Field: Computer Science The Division of Robotics, Perception and Learning (RPL) is announcing a doctoral position for someone with a background in and strong interest in deep generative learning and computer vision/remote sensing. You will participate in a project funded by Digital Futures aimed at mapping air temperature in urban environments with high spatial and temporal resolution. Cities are experiencing increasing heat stress, both through extreme temperature peaks and prolonged heat periods. However, developing such high-resolution maps of air temperature in urban environments remains an unsolved problem. In the project, dense estimation of urban air temperature is treated as an inverse problem, where conditional diffusion models are used to fuse satellite data, forecast data, and crowdsourced station data into probabilistic maps. The challenge lies in conditioning generative models on large, heterogeneous, and incomplete data – meaning you will be working at the research frontier of machine learning to address an urgent societal need. You will participate in an ongoing collaboration between research groups led by Assistant Professor Josephine Sullivan at RPL, Professor Yifang Ban (the Department of Geoinformatics) at the School of Architecture and the Built Environment, and Sebastian Hafner at RISE in Kista. Supervisor: Assistant Professor Josephine Sullivan is proposed as the doctoral supervisor. Eligibility for Admission To be admitted to doctoral studies (Chapter 7, Section 39 of the Higher Education Ordinance), the applicant must meet basic eligibility requirements: have completed a degree at advanced level, or have completed course requirements of at least 240 higher education credits, of which at least 60 credits are at advanced level, or have acquired substantially equivalent knowledge in some other way within or outside the country. The project requires practical skills in deep learning. Documented competence in deep learning programming libraries, such as TensorFlow, PyTorch, or JAX, is therefore required, while experience with GPU-based experimentation and computing clusters (e.g., Docker, Slurm) is meritorious. In addition to the above, there is also a mandatory requirement for English equivalent to English B/6. Selection To succeed in your doctoral studies at KTH, you need to be goal-oriented and persistent in your work. In selecting applicants, the ability to: independently drive your work forward, collaborate with others, maintain a professional approach, and analyze and work with complex issues will be assessed. In the evaluation of applicants, emphasis will be placed on academic results, completed courses, and documented programming ability demonstrated through completed project work. Previous specialization in machine learning as well as experience in computer vision and/or remote sensing is highly meritorious. After meeting the eligibility requirements, significant weight will be given to personal qualities. Target Degree: Doctorate Information on Admission and Employment Only those admitted to doctoral studies may be employed as doctoral candidates. The total employment period may not exceed what corresponds to full-time doctoral level education for four years. An employed doctoral candidate may, to a limited extent (maximum 20%), perform certain tasks in, for example, education and administration. A new employment as a doctoral candidate is valid for a maximum of one year, and may thereafter be renewed for a maximum of two years at a time. For studies to be concluded with a Licentiate degree, the total employment period may not exceed what corresponds to full-time doctoral level education for two years. As a doctoral candidate, you will receive KTH employment benefits and a monthly salary according to KTH's agreement for doctoral candidate salaries. Read more about Doctoral Studies at KTH | KTH | Sweden. Trade Union Representatives Contact information for trade union representatives. Doctoral Student Section (Royal Institute of Technology Student Union) Contact information for the doctoral student section. Application You apply through KTH's recruitment system. As an applicant, you have primary responsibility for ensuring that your application is complete when submitted. Application Requirements Copies of diplomas and transcripts from previous university studies and evidence of fulfilled language requirements (see above). Translations into English or Swedish if the original document is not issued in one of these languages. Copies of originals must be certified. CV with relevant professional experience and qualifications. Cover letter with a brief account of why you wish to pursue doctoral studies, your academic interests, and how they relate to your previous studies and future goals. (Max 2 pages) Representative publications or technical reports. For longer documents, please attach a summary (abstract) and a web link to the full text. The application must be received by KTH no later than the application deadline at midnight, CET/CEST (Central European Time/Central European Summer Time). Other For information about the processing of personal data in connection with recruitment. An employment at KTH may be placed in a security classification. If this is the case for this position, a security vetting of the applicant will be conducted in accordance with the Security Protection Act (2018:585) upon consent. In these cases, a requirement for employment is that the applicant is approved following security vetting. We decline direct contact from staffing and recruitment firms and sellers of job advertisements. Become Part of KTH KTH shapes the future through education, research, and innovation. As a leading international technical university, we play an active role in driving and participating in the transition to a sustainable society. Here you are offered the opportunity to grow and develop in a creative and dynamic workplace with good working conditions and benefits. Equality, diversity, and equal opportunities are a quality issue and a natural part of KTH's values as a university and public authority. Read more about our benefits and what it is like to work and develop at KTH.