PhD Position in Efficient Cloud-based Geocomputing

The rapid increase in geospatial data volumes arising from terrestrial, air- and space-borne sensors brings exciting opportunities for novel types of spatiotemporal monitoring, analysis, and modelling, yet also confronts us with complex choices of computational infrastructure on which to run the algorithms. Our group is interested in developing smart, time- and energy-efficient solutions to support the analytical workflows required to address challenging geospatial and Earth Observation applications, including machine learning and other GeoAI tasks.

You will design methods and develop tools that contribute to a better understanding of the computational and energy complexity of spatiotemporal algorithms, such that decisions for better performance or better energy efficiency can be made in an informed manner before computing takes place. This work involves the development of an experimental platform that implements a geospatial library in which space, time, and energy metrics are embedded such that complexity can be measured and calibrated, and optimization of hardware choices becomes possible.

Your work will shape in a collaboration between the GIP department and the Centre of Expertise in Big Geodata Science (CRIB). You will work in an environment that uses state-of-the-art parallel and distributed computing capabilities provided by modern hardware and software infrastructure (e.g., SIMD, multithreading, GPU, etc.). You will contribute to the development of open-source research software that implements such methods to improve the quality and efficiency of cloud-based geospatial computing platforms. You will publish your outputs and lessons learned as open-access scientific publications in line with Open Science and FAIR principles, and present them at scientific meetings and conferences.

The Department of Geo-information processing is a multidisciplinary scientific team that develops computational methods for processing (acquiring, organizing, analysing) spatiotemporal data and information, which in turn are used to build models, visualizations, and information systems to improve our understanding of dynamic spatial systems and to help in decision-making at multiple spatial and temporal scales.

The University of Twente wants to be an organisation that optimally deploys diversity, talents, and capabilities in the labour market for now and in the future. In the framework of our diversity and inclusiveness policy, we strongly stimulate people with a (work) disability to apply for this position.

The University of Twente is committed to providing a working environment where everyone is valued, respected, and supported to progress. Our priority is to ensure that no one is disadvantaged based on their ethnicity, gender, culture, disability, LGBTQ+ identities, family and caring responsibilities, age, or religion. We encourage everyone who meets the selection criteria and shares these values to apply.