Professor Karl Behrendt

Supervisor Details

Contact Details

Harper Adams Business School, Harper Adams UniversityLink opens in a new window

Scientific Background

Research Interests

I am an applied agricultural economist specialising in agricultural systems, innovation and decision support. My interdisciplinary research integrates economics, science and systems thinking to evaluate how technologies, policies and management practices affect productivity, resilience and sustainability. My expertise includes bioeconomic and techno-economic modelling with particular skills in process-based modelling of livestock and grazing systems, risk and investment analysis, and agribusiness strategy, with applications from farm and industry decision-making to policy development.

Research Groups

Global Institute for Agri-Tech EconomicsLink opens in a new window

Agroecology for Sustainable Food SystemsLink opens in a new window

Supervision Style

In three words or phrases: supportive, student centred, detail-orientated.

Provision of Training

The student is expected to be self-driven and curious, and as they develop and evolve through their PhD journey they are expected to become increasingly independent and figure out appropriate methods and changes to methodology. Guidance and training would be provided as needed to ensure research is conducted at the highest level.

Progression Monitoring and Management

I will expect you to take full ownership of your progression, and will expect to see evidence of progress on a regular basis, and if progression is not sufficient, we will always discuss a plan of action together.

Communication

I often communicate out of normal office hours, but will not expected students to do the same, as they will be expected to manage their own life/work balance. I will always make myself available to discuss any issues that are impacting your ability to fulfil your potential.

Meetings

PhD Students can expect scheduled meetings with me at least once per month. These meetings will be a mixture of face-to-face and via video chat or telephone. I am usually contactable for an instant response on every working day.

Work Patterns

The timing of work in my lab is completely flexible, and (other than attending pre-arranged meetings) I expect students to manage their own time.

Notice Period for Feedback

I need at least 1 week's notice to provide feedback on written work of up to 5,000 words.

MIBTP Project Details

Primary supervisor for:

Knowledge-Guided Machine Learning for forecasting UK pasture growth and managing climate-resilient grazing systems

See the PhD Opportunities section to see if this project is currently open for applications via MIBTP.

Please Note: The main page lists projects via BBSRC Research Theme(s) quoted and then relevant Topic(s).

Knowledge-Guided Machine Learning for forecasting UK pasture growth and managing climate-resilient grazing systems

Secondary Supervisor(s): Dr Kanthu Joseph Mhango, Dr Sarah Morgan

University of Registration: Harper Adams University

BBSRC Research Themes:

Sustainable Agriculture and Food (Plant and Crop Science)

Project Outline

UK grazing livestock systems are increasingly exposed to drought, heat, waterlogging and changing pasture-growing seasons. Their resilience depends on anticipating pasture quantity and quality, yet prediction is difficult because weather, soils, sward condition, fertilisation, liming and grazing interact dynamically. Process-based models represent these mechanisms but contain structural and parameter uncertainty. Machine-learning models can identify complex relationships, but may require large datasets, violate biological constraints and extrapolate poorly to climatic extremes.

This project will develop a Knowledge-Guided Machine Learning (KGML) framework for forecasting UK pasture growth and quality under climate uncertainty. Mechanistic knowledge and simulated states from the established Sustainable Grasslands Model (SGM) (Behrendt et al, 2020) will guide learning from weather, soil, pasture, management and remote-sensing observations. An initial data-readiness assessment will establish whether available datasets provide adequate temporal, spatial and management coverage, and identify priority gaps.

Process-based, conventional machine-learning and KGML models will be compared using validation across withheld sites, years and extreme climatic periods. KGML methods may include process-model residual correction, biologically informed predictors, and constraints on biomass accumulation, grazing removal and regrowth. Performance will be assessed through accuracy, uncertainty, biological consistency and transferability between upland and lowland systems.

The best-performing pasture model will be integrated within the SGM. Stochastic simulation and bioeconomic optimisation will evaluate grazing, fertilisation, liming and supplementary-feeding strategies. The project will test whether better real-time forecasts reduce feed deficits and downside financial risk, improving the resilience and profitability of UK livestock farms under climate and market uncertainty.