Thesis subject

Sustainable Greenhouses using Digital Twins (MSc)

The increasing human population requires producing food in a sustainable and responsible manner. Although greenhouse horticulture can create optimized climate environments to boost crop production rates, they are the most energy demanding agricultural business and the largest CO2 emissions contributor among the whole Dutch agricultural industry. Digital agriculture, combined under precision agriculture and Agriculture 4.0, can enable a sustainable transition in greenhouses. In this thesis, we will design a holistic Digital Twin (DT) for greenhouse horticulture management and operation, that is smart, sustainable, and inclusive.

Short description

Due to critical challenges in food security, food safety, sustainability, and health, greenhouse horticulture production processes are becoming increasingly industrialised. Business and production processes are intensively monitored and controlled, enabled by advanced systems and sensors, e.g. for climate management, irrigation, fertigation, lighting, crop monitoring, disease scouting, harvesting, internal transportation, sorting, and packaging. As a result, greenhouse horticulture is becoming increasingly smart and data-driven. This trend has accelerated recently, driven by the fast pace of developments in ICT, such as cloud computing, Internet of Things, big data, machine learning, augmented reality, and robotics. Following this trend, we could state that every object in the greenhouse (such as plants, containers, greenhouse sections, and equipment) can, in principle, be virtualised and remotely controlled. A Digital Twin is a key enabler of this development.

Digital twins are an emerging technology which has three elements: models of real entities, data from the real world connecting to the models, and additional decision-making components, such as artificial intelligence, potentially connected back to the real world. Digital twins can be used to build virtual counterparts for (parts of) greenhouses to understand the complex underlying structures and processes, as well as to help with optimization and decision making. From a sustainability point of view, digital twins can also model and interface with sustainable energy consumption and production technologies (electricity and heat) grid to optimize energy use within a greenhouse in an environmental friendly and cost-effective manner.

The goal of this thesis is to provide a holistic Digital Twin (DT) design for greenhouse horticulture management and operation, that is smart, sustainable, and inclusive. Data from sensors and Internet-of-Thing (IoT) devices will be used by the DT for optimized operation of the greenhouse (in terms of energy, water and CO2 use), considering plant growth constraints and involvement of greenhouse owners in the process. The thesis focuses on the system architecture and design (rather than the implementation of the individual components), which should ultimately enable such a data-driven and smart operation of the greenhouse.

Objectives

  1. Review previous work on the application of digital twin approaches and architectures for sustainable greenhouses;
  2. Discover the main technical and environmental challenges in current greenhouse operation, and identify the requirements for alternative solutions potentially involving digital twins;
  3. Design and evaluate an architecture for a holistic digital twin for realizing sustainable and energy efficient greenhouses.

Tasks

The work in this thesis entails:

  • To collect full-text articles or PDFs from primary studies and literature reviews on digital twin approaches for sustainable greenhouses
  • To assess the different architectures for sustainable greenhouses, along with their advantages and challenges in the literature
  • Design an architecture of a holistic digital twin for realizing sustainable and energy efficient greenhouses
  • Evaluate the effectiveness of the architecture to support the realization of the greenhouse in terms of sustainability, efficiency and inclusion.

Literature

Requirements:

  • Courses: Programming in Python (INF-22306), (Optional) Software Engineering (INF-32306), Data Science Concepts (INF-34306), Big Data (INF-33806) or Machine Learning (FTE-35306)
  • Required skills/knowledge: basic data analytics/machine learning and willingness to learn new software tools, interest about greenhouses

Key words: Greenhouse, Digital Twins, Sustainable Energy Transition

Contact person(s)
Önder Babur (onder.babur@wur.nl)
Tarek Alskaif (tarek.alskaif@wur.nl)