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

  Developing a Water Quality Visualisation Tool for Aquaculture farms (WQVA)


   School of Computer Science and Technology

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr Tahmina Ajmal, Dr Bushra Ahmed, Prof Yanqing Duan, Dr Elias Eze  Applications accepted all year round  Competition Funded PhD Project (UK Students Only)

About the Project

The PhD Aim is to develop a robust visualization tool for aquaculture farms using real time data. This PhD proposal WQVA is related to a recently completed international research project, ADPAC (https://www.adpac.info/) on precision aquaculture. ADPAC project has seen development of a sensor cabinet installed at two sites in UK (Shuttleworth College, Harper Adams University) and another in China (Mingbo Farm). This cabinet can measure data for 7 water quality parameters continuously every minute. WQVA will use the data from the cabinets to extend the ADPAC multivariate forecasting model (developed in MATLAB), using correlations between various parameters and additional inputs (e.g, fish health, mortality etc) from the aquaculture farm stakeholders. The developed model can be integrated in the edge computing system of the cabinet, so the modelling and forecasting results are easily understood by the end user.

This PhD will start with a review of 1) correlations between various parameters like Ammonium, Tryptophan, dissolved Oxygen in the aquaculture environment and their impact on the fish health and 2) time series data analysis and statistical methods that can be used to analyse the data and present it more effectively to the end user. This is expected to be completed in the first year of research and ideally results published.

Next stage will be to develop the model. A multi parameter model is already available (see references for example) which can be refined/extended, or another method can be chosen. The data analytics model is expected to have made sufficient progress by the end of second year and results published in a conference or a journal. Any language can be used for developing the model; however, Python and R are the two preferred languages in time-series data analytics. If analytics is completed in Python, this will have the benefit of integrating the code with the edge computing system of the cabinet. This aspect will be completed in the third year (i.e. integration with the existing platform) and there will be an opportunity to gather feedback from the aquaculture farms which could result in a final article.

Travel to the sensor sites in UK and meeting with industrial partners will form an essential aspect of this PhD program. WQVA will provide a platform for enriching the research through regular interactions with the industrial partners involved in the design of the sensor cabinet together with the aquaculture farms. The candidate will be expected to present their findings at these meetings in a professional way and proactively seek collaboration opportunities with the industrial partners.

Agriculture (1) Computer Science (8) Environmental Sciences (13)

Funding Notes

This is a fee only PhD studentship, so the candidate will need to arrange for their living expenses. However, the school usually has hourly paid teaching positions available for suitable students. So, this option will be available to the candidate.

References

1. Developing a Novel Water Quality Prediction Model for a South African Aquaculture Farm. E. Eze, S. Halse, T. Ajmal, Water 2021, 13, 1782. https://doi.org/10.3390/w13131782
2. Time Series Chlorophyll-A Concentration Data Analysis: A Novel Forecasting Model for Aquaculture Industry. E.Eze, S.Kirby, J.Attridge, T. Ajmal, Eng. Proc. 2021, 5, 27. https://doi.org/10.3390/engproc2021005027
3. Dissolved Oxygen Forecasting in Aquaculture: A Hybrid Model Approach. E. Eze; T. Ajmal, Appl Sci- Environmental and Sustainable Science and Technology Appl. Sci. 2020, 10(20), 7079; https://www.mdpi.com/853284