PhD position in Advanced Deep Data-Driven Nowcasting Models

Key Skills

Deep Learning, Keras software library, Linear Algebra, Machine learning techniques, Mathematical modeling, Python Programming, PyTorch, Statistical modeling, TensorFlow

Job Description

HOURS PER WEEK:38 to 40

FACULTY: Faculty of Science

DEPARTMENT: Department of Information and Computing, research group Algorithmic Data Analysis

APPLICATION DEADLINE: 9 January 2023

Job description

Meteorological services worldwide experience an ever-increasing demand of nowcasts, i.e., forecasts with short lead-times with a high temporal and spatial resolution, and a high update frequency. Nowcasting tremendously impacts the socioeconomic needs of many industrial sectors which rely on weather-dependent decision-making. Furthermore, nowcasting applications have found their way to the broad public, making it a ubiquitous feature of modern, industrialized societies as is used for planning, organization and management of a wide range of both personal and economic aspects of life. Therefore, making accurate nowcasting is a crucial factor in many weather-dependent systems (such as in modelling energy consumption, power load forecasting, traffic networks, Renewable Energy, environmental modelling) for cost savings, efficiency, health, safety and organizational purposes.

To date, the primary method for weather forecasts is numerical weather prediction (NWP). NWP relies on mathematical models that consider different physical properties of the atmosphere such as air velocity, pressure and temperature. The NWP-based models can generate accurate weather predictions of several hours to days into the future. However, they involve solving highly complex mathematical models which are computationally expensive and require enormous computing power and thus usually are performed on expensive super computers. Due to their high computational and time requirements, NWP models are less suitable for short-term forecasts.

Recent advances in Artificial Neural Network architectures (ANNs) have enabled data-driven based models to bridge the present gap for short-term forecasting. The research in this PhD project will be on developing a new theory to achieve more reliable and accurate nowcasting deep learning models. The key idea is to leverage large amount of unlabelled data for learning meaningful representation, incorporating several atmospheric variables and equipping the models with uncertainty quantification. The focus of this PhD project will be on developing novel self-supervised learning models to push the boundary of current deep data-driven nowcasting models.

You will join the department of Information and Computing Sciences where a team of enthusiastic researchers is developing new theories for applications in machine learning, control and biomedical signal processing.

This is a PhD position for 5 years, which includes research as well as teaching. You will spent approximately 30% of your time on varying teaching support activities. We offer the opportunity to take significant steps towards acquiring a basic teaching qualification (BKO), which qualifies you as a teacher in the Dutch higher education system.

Qualifications

We are looking for a motivated candidate to join our team. You are equipped with a critical mindset and recognise yourself in the following qualifications. You have:

• completed a relevant MSc degree in an applied sciences field relevant to the PhD research, i.e. Engineering, Computer Science, Statistics, Applied Mathematics;
• affinity with Machine Learning and Deep Learning Research;
• a strong mathematical background in (numerical) linear algebra, statistics and optimization;
• good programming skills in Python, TensorFlow, PyTorch or Keras.

Offer

• A position for 5 years;
• A full-time gross salary ranging from € 2541 to €3247 in scale P;
• 8% holiday bonus and 8.3% end-of-year bonus;
• A pension scheme, partially paid parental leave, and flexible employment conditions based on the Collective Labour Agreement Dutch Universities.

In addition to the employment conditions from the CAO for Dutch Universities, Utrecht University has a number of its own arrangements. These include agreements on professional development, leave arrangements and sports. We also give you the opportunity to expand your terms of employment through the Employment Conditions Selection Model. This is how we encourage you to grow.

Are you an international applicant? Our International Service Desk can prepare your stay (visa application etc.) and help you in case of questions regarding living in the Netherlands 

For more information, please visit working at Utrecht University.