Reducing potato losses by creating a predictive model for black dot disease PhD

This 3-year PhD project is fully funded by Cranfield University and Albert Barlett. Funding covers tuition fees and stipend (£15,400 per anuum). Critically, the work aims to use transformative phenotyping and machine learning to make the UK potato industry more resilient to emerging climatic changes. We would seek to attract a student with a passion for applying mathematical models to biological processes in order to reduce food loss and waste. A degree in plant science/plant pathology would be beneficial.

United Nations Sustainable Development Goal 12.3 aims to reduce food losses and waste by 50% by 2030. Black dot disease (Colletotrichum coccodes) is a significant cause of pre-pack quality loss for the UK potato industry costing £3M per annum. Black dot accounts for up to a 50 % loss during packhouse grading and the disease is predicted to become more problematic with climate change as UK pre-pack production moves from South to North.

Little research has been carried out on understanding the impact of environmental factors associated with the black dot disease incidence and the host/pathosystem and the underlying mechanisms, which govern susceptibility from field to store still remain elusive. The soil-borne pathogen infects tubers in the field but only tends to manifest itself during postharvest storage and these outbreaks are notoriously difficult to predict.

This PhD project will test whether in field environmental monitoring, digital plant phenotyping and improved postharvest management can be combined to predict black dot disease to avoid losing pre-pack quality during cold storage. The work aims to use sophisticated photonics and associated algorithms, machine learning and data integration methods across the pre and postharvest continuum to create a predictive model for black dot incidence and severity during storage and evaluate how resilience can be improved in response to different climate change scenarios; The model would predict when best to market a crop in cold storage and thereby reduce food loss and waste.

The main research objectives of this project include:
conducting a systematic review of black dot disease and potato resistance;
evaluating the effect of variety and preharvest ‘field factors’ (e.g. elevated temperature, soil type, inoculum load, horticultural maturity, fungicide application) on disease incidence using controlled growth studies and industry-led field trials;
validating the use of digital phenotyping and machine learning to associate tuber quality during storage, with black dot incidence;
evaluating the impact of postharvest curing (temperature pull down after harvest) and use of dynamically controlled storage to monitor tuber status and manage disease severity;
providing guidelines to storage practitioners on how to link field factors with better management of black dot to reduce loss and better inform storage release.

This is a cross-disciplinary project involving elements of plant pathology, digital phenotyping, machine learning, crop and disease modelling, and postharvest biology and pathology; The student will have opportunity to learn practical skills in potato agronomy, harvest, storage, packhouse operations and technical quality management at Albert Bartlett in Scotland and Eastern England. The student would attend in-house training in using plant phenotyping at Cranfield. In addition, the student would enrol on the two-week MSc modules in ‘Machine learning for Metabolomics’ and ‘Postharvest Technology’ as part of the MSc in Applied Bioinformatics and MSc in Food Systems Management, respectively, at Cranfield.

Interviews for shortlisted candidates will be held on Wednesday 22nd July, 2020.

Entry requirements

Applicants should have a first or second class UK honours degree or equivalent in a related discipline. This project would suit students with a degree in plant science/plant pathology, and AI and machine learning –or related subjects.


How to apply

For further information please contact:
Name: M.Carmen Alamar
Email: [Email Address Removed]
T: (0) 1234 750111

If you are eligible to apply for the PhD, please complete the online PhD application form stating the reference No. SWEE0110