I am currently enrolled for my PhD degree under the supervision of Professor Slippers. My research project is focused on the precision diagnostics of maize foliar disease development by integration of genomic, phenotypic, and environmental data using machine learning analysis approaches.

 Maize production is of critical importance in Africa for food security and the economy. Pests and diseases are amongst the most serious threats to current and future production, along with climate change. Exserohilum turcicum is the causal agent of northern leaf blight (NLB; also called northern corn leaf blight) of maize, as well as a number of other grass species and crops, and is one of the most widespread and serious diseases in South Africa. This pathogen co-occurs with a number of other leaf diseases in various regions of the country, which together can significantly affect maize yields.

 The detection, quantification and diagnosis of plant diseases is critical for precision agriculture. Frontier developments in areas such as RNA sequencing, image sensing and environmental sensing make this possible at levels of precision, and at earlier stages, than ever before. Highly precise observation of physical and physiological changes occurring during plant disease development, beyond the visible spectrum and observation, is possible through hyperspectral sensing. When these images are coupled with pathogen infection trials, field monitoring of disease development and sensor data of environmental changes, then it makes highly precise quantitative phenotyping possible. Such data can be used for the development of disease development models, and identification of signature spectra linked to various stages of disease development, before and after disease symptoms become visible to the naked eye. Thus, it is important that these powerful tools are applied to South African crop diseases to improve precision and impact of monitoring and management practices.