MSc thesis subject: Improving image-based yield predictions for sugarcane in Rwanda

Sugarcane is one of the most important crops in Rwanda. It is mainly grown in the flood prone valley of the Nyaborongo river near the capital Kigali. Sugar demand on the national market is claimed to rise, while domestic production only covers 30% of the demand. Adverse environmental conditions (e.g. flooding and diseases) and poor management (such as suboptimal timing of harvests) are negatively impacting sugarcane yields in Rwanda. Crop monitoring and yield prediction are seen as viable tools to prevent unnecessary losses.

In the project “Sugar make it work”, a simple method was developed for predicting sugarcane yields at plot level using weather data and vegetation index time series. Due to circumstances, successful image acquisition commenced about one year before project termination. Furthermore, only a small subset of agronomic data was allowed to be used for training the statistical prediction method; remaining data were reserved for assessing the accuracy of predictions. It is anticipated that the latter data will soon be made available so they can be further analysed. This gives opportunities for improving the yield prediction method by enhanced training and taking the ratoon cycle or other agronomic factors into consideration. Additionally, accounting for sub-field variability is expected to improve the predictions.


  • Use time series of weather data and remotely sensed imagery for sugarcane yield prediction
  • Segment plot imagery to recognize sub-plot elements such as replanted or harvested areas, erroneous plot boundaries or a changed river course.
  • Assess the feasibility of using satellite imagery.


  • Abdel-Rahman, E. M. and F. B. Ahmed (2008). "The application of remote sensing techniques to sugarcane (Saccharum spp. hybrid) production: A review of the literature." International Journal of Remote Sensing 29(13): 3753-3767.
  • Dorigo, W. A., R. Zurita-Milla, A. J. W. de Wit, J. Brazile, R. Singh and M. E. Schaepman (2007). "A review on reflective remote sensing and data assimilation techniques for enhanced agroecosystem modeling." International Journal of Applied Earth Observation and Geoinformation 9(2): 165-193.
  • Gitelson, A. A., Y. Peng, T. J. Arkebauer and J. Schepers (2014). "Relationships between gross primary production, green LAI, and canopy chlorophyll content in maize: Implications for remote sensing of primary production." Remote Sensing of Environment 144(0): 65-72.
  • Several project reports and thesis Jos Goris.


  • Interest in both GIS and remote sensing
  • Analytical skills
  • Preferably R scripting expertise

Theme(s): Sensing & measuring, Modelling & visualisation