LEDIG STILLING VED UIT NORGES ARKTISKE UNIVERSITET
PhD Fellow in Deep Learning and Satellite Remote Sensing within Maritime Applications
UiT The Arctic University of Norway
UiT is a multi-campus research university in Norway and the northernmost university of the world. Our central location in the High North, our broad and diverse research and study portfolio, and our interdisciplinary qualities make us uniquely suited to meet the challenges of the future. At UiT you can explore global issues from a close-up perspective.
Credibility, academic freedom, closeness, creativity and commitment shall be hallmarks of the relationship between our employees, between our employees and our students and between UiT and our partners.
The main task of the Faculty of Science and Technology is to conduct research and teaching at high national and international level. Prioritized research areas include energy, climate, environment, maritime, marine, nano-, space-, and information technology; addressing both general topics and topics relevant for the High North.
Faculty of Science and Technology
Visual Intelligence at The Department of Physics and Technology announces one vacant PhD position in the area of deep learning and satellite remote sensing within maritime applications.
The position is for a period of three years. The objective of the position is to complete research training to the level of a doctoral degree. Admission to the PhD programme is a prerequisite for employment, and the programme period starts on commencement of the position.
The workplace is at UiT in Tromsø. The position is available for commencement. You must be able to start in the position in Tromsø within a reasonable time, within 6 months after receiving the offer.
The studentship affiliation
The successful candidates will work at the research centre Visual Intelligence at the Department of Physics and Technology.
The Department of Physics and Technology consists of six research groups: Complex Systems Modelling, Earth Observation, Renewable Energy, Machine Learning, Space Physics, and Ultrasound, Microwaves and Optics. The department provides education at Bachelor, Master, and PhD levels; and hosts 22 permanent academic staff, and a technical / administrative staff of 12 persons.
The Centre is one of the newly established Norwegian centers for research-driven innovation, funded by the Research Council of Norway and consortium partners.
The goal of Visual Intelligence is to develop novel deep learning-based solutions to extract knowledge from complex image data to enable new innovations. Deep learning has led to a range of new image-based technologies that is rapidly changing society. Despite these advances, it is still a long way before the potential of deep learning for visual intelligence is realized for applications and industries relying on more complex visual data, e.g within medicine and health, the marine sciences, the energy sector, and within earth observation.
Visual Intelligence will bridge this gap by solving fundamental research challenges in deep learning to learn from limited data, to incorporate context and dependencies, to quantify uncertainties, and to provide interpretable solutions.
Visual Intelligence conducts research within machine learning, more specifically within deep learning (deep artificial neural networks). The research focus is broadly on developing the next generation deep learning solutions in order to
- Learn from limited data
- Capture context and dependencies (e.g. prior knowledge)
- Enable reliable systems capable of quantifying uncertainty associated with their own predictions and operations, and
- Develop interpretable learning methodology.
Visual Intelligence shall enable innovations across four interrelated Innovation Areas (medicine and health, marine sciences, energy, earth observation), all relying on creating value from complex image data. The current position is affiliated with Innovation Area Earth Observation, with close collaboration to the centre partner Kongsberg Satellite Services (KSAT).
Field of research and the role of the PhD Fellow
The recent advancements in sensing technology have enabled the rise of accurate and efficient systems and strategies for Earth observation through monitoring and prediction of hazard risks and for surveying and screening sea from air and space through exploitation of remote sensing images from satellites. Nevertheless, remote sensing data analysis is typically subject to the problem of limited and inadequate training data, as it can be extremely cumbersome and expensive to organize comprehensive field campaigns to collect records for validation, especially in extreme areas (e.g., Arctic), or on the ocean. The combination of multi-sensor data (e.g. from optical and radar sensors) and time dependencies is another key challenge.
A main aim of the research for this position is for innovating maritime surveillance services. The research along these lines will help enable KSAT to develop more efficient deep learning analytics and fast delivery of such products to improve service quality and decrease production time.
Exploring context and dependencies in satellite imagery over a combination of radar and optical satellites is of prime importance, as well as researching new AI solutions to quantify uncertainties in the detections. Advances in utilizing weak and/or noisy labels for learning from limited data will further increase the value of KSAT vast archive of historical data for research, which is a world leading but noncurated collection of analyses performed under strict time constraints and to non-identical customer requirements.
Modelling of contextual information may also enhance the performance, but important contextual issues like integration of physical properties have not yet been addressed. It is therefore important to address the development of advanced data analytics methods based on deep learning approaches, so to fully exploit, integrate and accurately extract the information provided by the sensors while guaranteeing efficiency and scalability of the data analysis scheme. This topic is particularly relevant for marine operations, such as vessel identification and classification, oil spill detection and characterization, as well as for water quality studies.
The research will be focused, but not limited to the development of deep learning architectures for object detection in marine environment, so to include:
- Development of physics-aware deep learning networks, e.g.,
- Adaptive identification and selection of relevant features in multimodal datasets (satellite, meteorological, AIS) for the characterization of the object under exam
- Multimodal data fusion at data, feature, and decision level to improve information extraction and robustness of the outcomes
- Development of confidence-aware deep learning networks, e.g.,
- Learn from limited labelled data and weakly labelled data
- Reliable information propagation in complex manifolds
- Development of uncertainty-aware deep learning networks, e.g.,
- Characterization of capacity and limits of deep learning-based object detection schemes for operational use
- Automatic understanding of relevant features to be used for optimal detection and transfer learning
- System integration and performance assessment.
Further information about the position is available by contacting:
- Professor Robert Jenssen, UiT: [email protected]
- Professor Camilla Brekke, UiT: [email protected]
- Associate Professor Andrea Marinoni, UiT: [email protected]
This position requires a Norwegian master degree in physics, mathematics/statistics, computer science, or similar, or a corresponding foreign master degree recognised as equivalent to a Norwegian master degree.
The suitable candidate must have:
- Background in signal and image processing
- Background in machine learning and automatic data analysis
- Experience with remote sensing data analysis (SAR and/or optical),
- Skills in programming and English.
Experience with deep learning (through courses, research projects, or similar), including hands-on experience with software tools such as Pytorch and Tensor Flow, will be considered a strength.
Knowledge of, pattern recognition and big data processing, plus previous experience in applications related to maritime operations (e.g., ship detection, oil spill) is considered as an asset.
Other required qualification skills include:
- Independence and self-motivation
- Creativity and ability to think outside the box
- Excellent work ethics and commitment to the job
Applicants must document fluency of in English and be able to work in an international environment. International experience is an advantage.
In the assessment, the emphasis is on the applicant's potential to complete a research education based on the master's thesis or equivalent, and any other scientific work. In addition, other experience of significance for the completion of the doctoral programme may be given consideration.
We will also emphasize motivation and personal suitability for the position.
As many as possible should have the opportunity to undertake organized research training. If you already hold a PhD or have equivalent competence, we will not appoint you to this position.
Admission to the PhD programme
For employment in the PhD position, you must be qualified for admission to the PhD programme at the Faculty of Science and Technology and participate in organized doctoral studies within the employment period.
Admission normally requires:
- A bachelor's degree of 180 ECTS and a master's degree of 120 ECTS, or an integrated master's degree of 300 ECTS.
- A master's thesis with a scope corresponding to at least 30 ECTS for a master's degree of 120 ECTS.
- A master's thesis with a scope corresponding to at least 20 ECTS for an integrated master's degree of 300 ECTS.
In order to gain admission to the programme, the applicant must have a grade point average of C or better for the master’s degree and for relevant subjects of the bachelor’s degree. A more detailed description of admission requirements can be found here.
Applicants with a foreign education will be subjected to an evaluation of whether the educational background is equal to Norwegian higher education, following national guidelines from NOKUT.
If you are employed in the position, you will be provisionally admitted to the PhD programme. Application for final admission must be submitted no later than two months after taking up the position.
Inclusion and diversity
UiT The Arctic University i Norway is working actively to promote equality, gender balance and diversity among employees and students, and to create an inclusive and safe working environment. We believe that inclusion and diversity is a strength and we want employees with different competencies, professional experience, life experience and perspectives.
If you have a disability, a gap in your CV or immigrant background, we encourage you to tick the box for this in your application. If there are qualified applicants, we invite least one in each group for an interview. If you get the job, we will adapt the working conditions if you need it. Apart from selecting the right candidates, we will only use the information for anonymous statistics.
Your application must include:
- Application and motivation letter (max 1 page)
- CV (max 2 pages)
- Diploma for bachelor's and master's degree
- Transcript of grades/academic record for bachelor's and master's degree
- Explanation of the grading system for foreign education (Diploma Supplement if available)
- Documentation of English proficiency
- Three references, preferably including the master thesis supervisor
- Master’s thesis, and up to 4 other academic works
- Description of your academic production (any publicatons)
Qualification with a master’s degree is required before commencement in the position. If you are near completion of your master’s degree, you may still apply and submit a draft version of the thesis and a statement from your supervisor or institution concerning termination of your master studies. You must document completion of your degree before commencement in the position. You must still submit your transcripts for the master’s degree with your application.
All documentation to be considered must be in a Scandinavian language or English. Diplomas and transcripts must also be submitted in the original language, if not in English or a Scandinavian language. We only accept applications and documentation sent via Jobbnorge within the application deadline.
We offer an interesting project within a highly innovative centre environment, opportunities to travel and meet other leading scientists within the field, independence in work, a fantastic work environment with nice colleagues, good remuneration, and a cosy hometown of Tromsø surrounded by the stunning landscape of Northern Scandinavia.
More practical information for working and living in Norway can be found here.
The appointment is made in accordance with State regulations and guidelines at UiT. At our website, you will find more information for applicants. The engagement is to be made in accordance with the regulations in force concerning State Employees and Civil Servants, and the acts relating to Control of the Export of Strategic Goods, Services and Technology. Candidates who by assessment of the application and attachment are seen to conflict with the criteria in the latter law will be prohibited from recruitment to the announced position.
A shorter period of appointment may be decided when the PhD Fellow has already completed parts of their research training programme or when the appointment is based on a previous qualifying position PhD Fellow, research assistant, or the like in such a way that the total time used for research training amounts to three years.
Remuneration of PhD fellow positions are in salary code 1017, and normally starts at salary grade 54 on the pay scale for Norwegian state employees corresponding to approx. 39 900 NOK/month. There is a 2 % deduction for contribution to the Norwegian Public Service Pension Fund.
We process personal data given in an application or CV in accordance with the Personal Data Act (Offentleglova). According to the Personal Data Act information about the applicant may be included in the public applicant list, also in cases where the applicant has requested non-disclosure. You will receive advance notification in the event of such publication, if you have requested non-disclosure.