Thesis subject

The Cyborg Farmer: The Ultimate Digital Twins Solution

The emergence of AI and automation has optimized many existing agricultural practices. From applying fertilizer based on soil samples and aerial photographs taken from drones, to advanced modelling of greenhouse climate conditions for greater energy efficiency. However, these methods seeking to improve decision making capabilities beyond human levels have one inherent flaw. They do not do justice to the amount of intuitive knowledge farmers have accumulated on their farms and crops over multiple years, decades and/or generations.

This research seeks to provide a method for integrating the knowledge of farmers into advanced machine learning methods using a wearable sensing platform. Such a device can give farmers the tools required to gather data from their perspective and to add useful labelling/metadata to supplement already powerful AI applications. Such a wearable sensing platform can help to better incorporate their intuitive knowledge into the new sensing technologies of the information age.

Objectives

The aim of this project is to improve the software/hardware design of the system previously developed. This will be achieved within the main steps:

  1. Review of the state-of-the art
  2. Improve the current system design
  3. Experiments in apple orchard
  4. Writing report

    Literature

    • The Cyborg Farmer. https://2020.design-united.nl/day-1-hybrids/the-cyborg-farmer/
    • Ampatzidis, Y. G., S. G. Vougioukas, and M. D. Whiting. 2011. ‘A Wearable Module for Recording Worker Position in Orchards’. Computers and Electronics in Agriculture 78(2):222–30
    • Aroca, Rafael V., Rafael B. Gomes, Rummennigue R. Dantas, Adonai G. Calbo, and Luiz MG Gonçalves. 2013. ‘A Wearable Mobile Sensor Platform to Assist Fruit Grading’. Sensors 13(5):6109–40

      Requirements (optional)

      • Enthusiast about cyborgs
      • Willing to learn more about open-source software and hardware
      • Excited to make tools to help people

        Theme(s): Sensing & measuring