Searching for Anomalies on Mars [SELF-FUNDED STUDENTS ONLY]

In recent years, space agencies such as NASA and the European Space Agency (ESA) have conducted extensive planetary surveys, amassing a colossal volume of data from various celestial bodies, including Mars, the Moon, and through radar surveys of Venus and smaller celestial objects. The sheer scale of this data, rich with high-resolution images, presents a significant challenge for human analysis, potentially concealing unusual geological formations or sites that could harbour life or be of interest for future exploration missions.

Notably, despite the abundance of high-quality imagery, vast regions of Mars' surface remain virtually “unexplored” due to the impossibility of meticulously examining every image. This PhD project aims to address this challenge by developing advanced deep learning models capable of identifying anomalies and features of interest within images of Mars' surface. Such models could revolutionize our approach to planetary exploration, enhancing our ability to pinpoint locations for further study or mission planning. Relevant datasets for this endeavour are publicly available, including from NASA's Mars Reconnaissance Orbiter and ESA's Mars Express, offering a treasure trove of data for training and validating the proposed models.

The lack of available annotations of data necessitates unsupervised learning regimes. This project will thus leverage recent advances in anomaly detection techniques (and potentially advance the field of anomaly detection) to develop innovative algorithms and models capable of detecting anomalies and features in planetary data that escape the human analysis. These could range from unusual geological formations to potential sites of past life, opening new chapters in our quest to understand the Red Planet.

In particular the project will address and investigate:

● Data preprocessing: standardisation, normalisation, curation, integration with GIS systems.

● Unsupervised feature learning.

● Anomaly detection framework.

● Change detection in sequential surveys.

● Interactive tools for semi-supervised exploration.

This project offers a groundbreaking opportunity to leverage artificial intelligence in the service of space exploration, potentially unlocking

secrets of our neighbouring planets.

Contact for information on the project: [Email Address Removed]

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.

How to apply:

This project is accepting applications all year round, for self-funded candidates.

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below.

Please submit your application via Computer Science and Informatics - Study - Cardiff University

In order to be considered candidates must submit the following information:

·       Supporting statement

·       CV

·       In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD

·       In the funding field of your application, please provide details of your funding source.

·       Qualification certificates and Transcripts

·       References x 2

·       Proof of English language (if applicable)

Interview - If the application meets the entrance requirements, you will be invited to an interview. 

If you have any additional questions or need more information, please contact: [Email Address Removed]