GeoAI Research Assistant

This Research Assistant will support the Fudan-Warwick funded project, “AI-driven deep learning prediction for subsurface characterisation using random fields”, with modelling, data analysis and research outputs.

The project aims to develop an image-based deep learning method using Convolutional Neural Networks (CNNs) and U-Net architectures to generate realistic subsurface field representations. Trained and tested using spatially sampled data from Warwick’s geotechnical database, the model will support automated geotechnical profile analysis and enable efficient prediction of complex spatial patterns in subsurface environments.

The Research Assistant will work closely with the project leads and collaborators to undertake essential research that underpins the project’s success. The also offers a unique opportunity to gain hands-on experience in research and project coordination, and to make a meaningful contribution to innovation in higher education.

Duties and responsibilities

The Research Assistant will be expected to:

• Analyse provided geotechnical and spatial datasets, including data cleaning, preprocessing, exploratory analysis and preparation of data for model development.
• Support the development, training and evaluation of AI-driven deep learning models, particularly using CNN and U-Net based approaches.
• Assist with the representation and interpretation of spatial variability in subsurface conditions, including approaches related to random fields where appropriate.
• Test model performance, document results and contribute to the interpretation of model outputs.
• Maintain clear records of modelling workflows, code, datasets and analytical decisions.
• Liaise with project members, attend project meetings and provide progress updates as required.
• Contribute to the preparation of research reports, presentation materials and academic manuscripts arising from the project.

Skills and experience

Essential

• Demonstrable expertise in AI-driven deep learning approaches.
• Experience in programming for data analysis and/or machine learning, preferably using Python.
• Experience with deep learning frameworks such as PyTorch, TensorFlow or equivalent.
• Ability to analyse, process and interpret quantitative or spatial datasets.
• Strong research reporting and academic writing skills.
• Ability to work independently, manage tasks effectively and communicate progress clearly.
• Interest in applying AI methods to environmental science, geotechnical analysis, GeoAI or related fields.

Desirable

• Experience with CNNs, U-Net architectures, computer vision or image-based prediction.
• Familiarity with random fields, spatial statistics, geostatistics, GeoAI or geotechnical data analysis.
• Experience working with geospatial, environmental, subsurface or engineering datasets.
• Experience of contributing to research publications, technical reports or project outputs.
• Experience of project coordination and supporting collaboration across project members or external stakeholders.

Location
Combination