15 phd-position-in-data-modeling PhD positions at Cranfield University in United Kingdom
Sort by
Refine Your Search
-
, environmental science, urban sustainability, geospatial analysis, or quantitative modelling. We particularly welcome applicants who are excited about integrating ecological understanding with data-driven methods
-
strengths and interests (e.g. geospatial data science or socio-environmental modelling). Funding Sponsored by the Leverhulme Trust and Cranfield University, this Connected Waters Leverhulme Doctoral programme
-
/position/type of hardware. Cranfield overview and Sponsor Information/Background: We have a long history in space systems, having undertaken space studies since the 1960s. Our current research has
-
This is an exciting PhD opportunity to develop innovative AI and computer vision tools to automate the identification and monitoring of UK pollinators from images and videos. Working at
-
Advances in computing, experiments, and information will continue to reshape engineering in the next decade. This PhD position will nurture a multidisciplinary innovator with the tools to unravel
-
AI techniques for damage analysis in advanced composite materials due to high velocity impacts - PhD
for automated, data-driven diagnostics, integrating AI with high-resolution imaging and sensing offers a transformative solution. AI models can learn to recognize subtle damage patterns, enabling faster, more
-
and kinematic models with machine-learning-based channel state information (CSI) prediction to enable robust, low-latency connectivity across multi-layer NTN systems. This PhD project sits
-
integrating Machine Learning (ML) with physics-based degradation modelling will enhance early fault detection, reducing unplanned downtime. This PhD is hosted at Cranfield University, a global leader in
-
highly attractive to both the tech industry and government agencies. They will gain extensive practical skills in full-stack AI development, from data curation and model training to system deployment and
-
the computational inefficiencies of physics-based models and enabling faster, potentially more accurate predictions. However, AI models require substantial volumes of high-quality, labelled training data, which