About the Project: The analysis and detection of changes in the vegetation and forest canopy play a crucial role in the early detection of deforestation and measuring the activities for reforestation. However, especially due to the lack of infrastructure collecting and exploiting field information for the forests is much more challenging than in other scenes. Remotely sensed imagery from satellites, airplanes, and drones provides the potential to observe forest ecosystems at much larger scales than is possible using field data collection methods alone. Despite this potential, each remote sensing modality accommodates both advantages and disadvantages, to name but a few: satellite imagery is mostly available for large scenes but with a relatively low spatio-temporal resolution, whilst airborne/drone-based imagery has higher resolution but suffers from small scene capacity, the need for operator dependency, and high costs. These suggest advanced computational approaches to extract useful information for the purpose of forest monitoring.
This project jointly aims (1) to measure the effectiveness of climate change mitigation activities on reforestation, and (2) to exploit already collected satellite-based remote sensing imagery along with the outputs of a deployed IoT system for analysing the health of the forests. Advanced computational imaging and machine learning approaches will be leveraged to extract detailed features from both satellite and airborne\drone remote sensing image information. Semantic scene information and statistics based on different tree types, and various spectral analyses based on tree canopies will be extracted and utilised to produce "forest health index maps" via novel machine learning approaches.
Danau Girang Field Centre (DGFC) which is a collaborative research and training facility managed by Sabah Wildlife Department (Malaysia) and Cardiff University (UK), will be the test area of this project. DGFC has data sets collected by researchers for wildlife species monitoring over the last decade, such as animal collar data, camera traps, satellite imagery, LiDAR, and environmental data, with each data set generated using different time frames, duration, and geographic areas. Besides, satellite remote sensing images for the aforementioned test area will be collected from sources such as Sentinel, ICEYE, and NovaSAR missions to feed the forest imagery pool both with space- and airborne-based imagery.
The successful candidate is going to contribute to the Forest Observatory project (for details please visit https://www.forest-observatory.org/)
Keywords: Remote Sensing, Computational Imaging, Machine Learning.
Academic criteria: The successful candidate should be an innovative individual with a distinction degree in computer science, engineering, applied maths/stats/physics, geography, or earth sciences. The student will be involved in a world-class and multi-disciplinary research team with access to super-computing sources and research facilities.
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.
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.
This project is accepting applications all year round, for self-funded candidates via https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/computer-science-and-informatics
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
- Qualification certificates and Transcripts
- Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
- References x 2
- Proof of English language (if applicable)
If you have any questions or need more information, please contact [Email Address Removed]