Optimal control of aquaponic farms for food production using Internet of Things (IoT) and Artificial Intelligence (AI)

An opportunity to apply for a full-time PhD in the Faculty of Environment and Technology. The studentship will be funded by the Faculty of Environment and Technology in collaboration with/part-funded by industrial partner, Sciflair: Ref 2022-JAN-FET02.

The expected start date of this studentship is January 2022.

The closing date for applications is 16 September 2021.

Research at the Computer Science Research Centre (CSRC) addresses a wide range of topics relating the implementation in industry of novel and emerging technologies e.g., Data Science, Internet of Things (IoT) and Big Data Analytics, Artificial Intelligence, etc. The purpose of this project is to investigate novel mechanisms to maximise the food production in an Aquaponics farm by collecting sensor data using Internet of Things (IoT) and apply machine learning algorithms/Artificial Intelligence to optimise the farm parameters.

Background 

Conventional methods of growing food are becoming unsustainable and obsolete. There is a need to find new ways of food production which are more efficient, use fewer natural resources and independent of climatic changes. Food is traditionally grown as fruit and vegetables in the soil, keeping livestock, raising birds in poultry farms, and capturing fish in sea and inland waters. Currently, wild fish catch is dwindling and Aquaponic is emerging as an optimal habitat for both fish and plants to grow during their whole life cycle. A typical aquaponics system consists of tanks, filters, sump, floating rafts, media beds, pump, and aerator to produce food in a controlled agricultural setting. However, there is still a research gap to obtain optimal control of aquaponic farms for food Production using Internet of Things (IoT) and Artificial Intelligence (AI), to avoid some of the major resource inefficiencies present in the conventional agriculture. 

Aims 

The primary aim of the proposed PhD project is investigating the extent to which food production can be increased by obtaining an optimal control of aquaponic farms using Internet of Things (IoT) and Artificial Intelligence (AI). Specifically, the project will aim to:

• research on the parameters and existing findings to obtain optimal control of aquaponic farm
• design and setup a small-scale experimental aquaponics farm. Identify, install, and integrate IoT sensors in an aquaponics farm to obtain data related to water quality, water level and flow, light intensity, airflow, CO2 level, plant growth, early disease detection and pest control
• identify and apply state of the art machine learning algorithms to analyse IoT data to discover patterns, provide control feedback and notifications to change farm parameters
• develop statistical models for yield prediction, validation with ground-truth data and analyse farm throughput vs capacity to measure efficiency.

Methods

This PhD study will focus on detecting patterns and getting new insight from sensor data to optimise the food production. A prototype of small-scale testing farm shall be built which shall have IoT sensors to collect data, automate fish feeding and control the farm environment. Data from multiple sensors shall be stored in a cloud and fused to determine corrective measures such as adjustment in water quality, flow of nutrients, pest control to optimize growth in both plants and fish. It would be preferable to get the sensors that can communicate using open protocols. A web application shall also be developed to collect data from sensor, visualise it online, and the system should generate automatic notifications to assist in the management / optimisation of the farm operation.

Impact

• The project aligns with multiple UN Sustainable Development Goals directly and indirectly, such as No Poverty, Zero Hunger, Sustainable Cities and Communities, Climate Action. The outcome of the PhD study will have huge impact especially in the era of pandemic, when growing food locally is the need of the day.
• The project is one of the UKRI’s six strategic GCRF portfolios; and directly, food systems. The outcome will be a considerable step towards ensuring food security when all people will have the opportunity of a heathy lifestyle, access to safe and nutritious food, grown locally, all year around and independent of climate change.
• Application of IoT and machine learning in aquaponics is a very new area of research. Many conventional aquaponics farms of the past could not optimise the farm elements due lack of timely data availability and too many factors at play in parallel. The PhD will provide an insight into complex relationships of upstream, midstream, and downstream food production processes. The results will be published and help in improving standards, fish welfare, establish best practices and further the knowledge.

For an informal discussion about the studentship, please email Dr Kamran Munir (Kamran2.Munir@uwe.ac.uk),

The studentship is available from January 2022 for a period of three years, subject to satisfactory progress and includes a tax exempt stipend, which is currently £15,609 per annum.

In addition, full-time tuition fees will be covered for up to three years.

Applicants must have a good first degree or, ideally, a Masters. Students from under-represented groups are particularly encouraged to apply. The studentship is available both for UK and overseas applicants.

A recognised English language qualification is required.

We are specifically looking Computer Science and Electronics experience in: 

• Software development with in-depth knowledge of threads, sockets, and event programming (Embedded C, C#, Python)
• Electronics, Embedded system design, Microcontrollers, PCB design and testing
• Industrial product design, hardware manufacturing and assembly of mechanical parts
• Knowledge of human centric front-end design and large data visualisation (Javascript, Node.js, HTML, CSS etc.)
• Understanding of Internet of Things architecture and protocols
• Knowledge of building low power battery operated wireless sensor network (LoRa, Sigfox, Bluetooth etc.) 
• SQL/NOSQL databases (MongoDB, mySQL, etc.) and integration with cloud services (AWS, Microsoft Azure, Google)
• Data security and encryption algorithms
• Wireless communication systems

Knowledge of:

• Data Analytics 
• Natural Language Processing (NLP)
• Machine Learning and Artificial intelligence
• Aquaponic system

Please submit your application online. When prompted, use the reference number 2022-JAN-FET02.

Applicants have the opportunity to discuss their studentship with Directors of Studies via a webinar to take place on Wednesday 8 September 2021 from 10:00 to 12:00 BST. Please use the registration form to reserve your place at this webinar.

Supporting documentation: You will need to upload your research proposal, all your degree certificates and transcripts and your proof of English language proficiency as attachments to your application, so please have these available when you complete the application form.

Research proposal: Use the studentship details to prepare a proposal on the topic of “Optimal control of aquaponic farms for food production using Internet of Things (IoT) and Artificial Intelligence (AI)” and include sections such as title, objectives and goals, requirements, brief literature review, methods, and a descriptor of the proposed solution.

References: You will need to provide details of two referees as part of your application. At least one referee must be an academic referee from the institution that conferred your highest degree. Your referee will be asked for a reference at the time you submit your application, so please ensure that your nominated referees are willing and able to provide references within 14 days of your application being submitted.

Closing date

The closing date for applications is 16 September 2021.

It is expected that interviews will take place on the week commencing 4 October 2021. If you have not heard from us by 30 September 2021, we thank you for your application but, on this occasion, you have not been successful.