Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Data-Centric Solutions for Earth Observation Challenges: Developing Cutting-Edge Techniques for Remote Sensing Analysis [SELF-FUNDED STUDENTS ONLY]


   Cardiff School of Computer Science & Informatics

  , Prof Paul Rosin  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

In today's data-driven landscape, the importance of data-centric machine learning methodologies cannot be overstated where they prioritize the quality, diversity, and accessibility of data, recognizing that the performance and reliability of machine learning models heavily depend on the data they are trained on. By delving into this research direction, PhD candidates have the opportunity to innovate methods for data collection, preprocessing, and augmentation, ensuring the integrity and richness of datasets. Moreover, advancements in data-centric machine learning not only enhance model accuracy and robustness but also promote fairness, transparency, and accountability in decision-making systems.

For the remote sensing image analysis research, the significance of data-centric techniques is paramount since remote sensing data, often acquired through satellites or aerial platforms, presents unique challenges such as noise, atmospheric interference, and varying spatial and spectral resolutions. Data-centric remote sensing methodologies play a pivotal role in addressing these challenges by enabling the extraction of meaningful information from vast and complex datasets.

This PhD research focused on data-centric approaches in remote sensing image/data analysis and is targeted to lead to the development of advanced algorithms for image preprocessing, feature extraction, and minimal supervision, ultimately enhancing the accuracy and efficiency of environmental monitoring, disaster management, urban planning, and agricultural assessment. Furthermore, by harnessing the power of data-centric techniques, this PhD is able to unlock valuable insights from remote sensing data, facilitating informed decision-making processes for sustainable resource management and environmental conservation efforts on a global scale.

Objectives of this PhD are given below:

1. Investigate the latest data-centric methodologies in machine learning and their suitability for analysing remote sensing data.

2. Explore new methods for preparing remote sensing data to improve its quality and address issues like noise, labelling inaccuracies, and artefacts.

3. Create advanced algorithms for extracting features from remote sensing data, considering its distinct characteristics such as radar, multispectral, and hyperspectral imagery, as well as ground measurements, from a multimodal perspective.

4. Develop original learning approaches, like deep learning models and transfer learning techniques, tailored for environmental applications in earth observation.

5. Assess the effectiveness and reliability of the developed algorithms by conducting thorough experiments on diverse remote sensing datasets, covering a range of environmental conditions and types of water and land cover.

Contact for information on the project:

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:

Computer Science (8) Geography (17)

Funding Notes

This project is offered for self-funded students only, or those with their own sponsorship or scholarship award.
Please note that a PhD Scholarship may also available for this PhD project. If you are interested in applying for a PhD Scholarship, please search FindAPhD for this specific project title, supervisor or School within its Scholarships category.

References

[1] Roscher, Ribana, et al. "Data-Centric Machine Learning for Geospatial Remote Sensing Data." arXiv preprint arXiv:2312.05327 (2023).
[2] Ma, Wanli, Oktay Karakus, and Paul L. Rosin. "Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning." arXiv preprint arXiv:2402.05305 (2024).

Register your interest for this project



How good is research at Cardiff University in Computer Science and Informatics?


Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Where will I study?