Skip to content  

Werken bij de TU/e

PhD position on deep learning for plant growth

PhD position on deep learning for plant growth

Challenging PhD position on deep learning for plant growth. In the future, food will often grow in vertical farms. We need deep learning models to track, predict, and optimize plant growth based on images and sensor data. We will use deep learning (CNNs, RNNs) and meta-learning to achieve this.
Aanstellingsfunctie(s)
Promovendus
Faculteit(en)
Mathematics & Computer Science
Graduate Program(s)
Computer Science
FTE
1,0
Sluitdatum
07/12/2020
Aanvraagnummer
V32.4605

Functieomschrijving

We are seeking a highly creative and motivated PhD candidate to join the Data Mining Group at the Eindhoven University of Technology. The candidate will be working in collaboration with Joaquin Vanschoren and his team to develop new fundamental machine learning methods and tools to automatically track how plants grow in vertical farms, and predict the ideal circumstances (light, nutrients, water) to make them grow optimally.

In the (near) future, we will increasingly grow food in ‘vertical farms’, in which plants are grown on many stacked layers with LED light. They require 20x less land, a lot less water, less transport, and significantly reduce pollution and food waste. They are also key to tackle climate change and allow space exploration. However, providing the right conditions can be tricky: plants need different amounts of light, nutrients, and water throughout their life cycle, and we need to minimize the amount of energy and resources (light, heating, water,…).

Deep learning can be used to learn the complex interactions between the plant genotype, growing conditions, and plant quality. This can be done by installing cameras inside vertical farms and tracking plant growth over time, and then relating this to the plant’s growing conditions, existing plant growth models, and unique genotype. This poses several fundamental challenges. First, tracking plant growth itself requires high-quality identification of plants and individual overlapping leaves from images, also through time. Second, models must be robust against anomalies such as misshapen or burned leaves. Finally, they must also work with limited amounts of data, for instance by pretraining models on artificial data generated by Generative Adversarial Networks (GANs), and by applying meta-learning (e.g. transfer learning and few-shot learning) to transfer information from models previously trained on different plant species.

This PhD position provides the ideal conditions for tackling these challenges. It is part of the ‘Sky High’ project, a large collaboration between Dutch universities and companies that already use vertical farms, which provides the required infrastructure for collecting data and testing models. You will help design the data gathering and processing, so you have full control to secure the right training data. Finally, the data mining group has the required experience in deep learning and meta-learning to solve the fundamental research questions, and the required infrastructure to carry out this research.

All this offers a unique opportunity for a bright student to tackle this hard problem, publish their work at top venues, and have a significant real-world impact, since this technology will be crucial to be able to grow sufficient and high-quality food under all circumstances.

Functie-eisen

We are looking for a motivated candidate with:

  • A Master of Science degree in Computer Science (or similar);
  • Advanced knowledge of machine learning techniques;
  • Strong mathematical and analytical skills;
  • Excellent programming skills. Experience with open source development is an asset;
  • Excellent communication skills in spoken and written English;
  • Creativity, free thinking, perseverance.

Arbeidsvoorwaarden

We offer you:

  • An exciting job in a dynamic work environment
  • A full time appointment for four years at Eindhoven University of Technology (www.tue.nl/en)
  • The salary is in accordance with the Collective Labour Agreement of the Dutch Universities, increasing from € 2,395 per month initially, to € 3,061 in the fourth year.
  • An attractive package of fringe benefits, including end-of-year bonus (8,3% in December), an extra holiday allowance (8% in May), moving expenses and excellent sports facilities.

Informatie en sollicitatie

If you are interested in this PhD student position, use the ‘apply now’ button.

To be considered, you must upload the following documents (in pdf):

  • A cover letter explaining your motivation, background and qualifications for the position,
  • A detailed Curriculum Vitae (including a list of publications and awards),
  • Contact information of two references,
  • Copies of diplomas and a list of your courses taken and grades obtained,
  • Half-page summary of your MSc thesis,
  • Proof of English language skills (if applicable), and
  • All other information that might be relevant.
    Please be aware that you can upload only 5 documents up to 2 MB each.

Questions regarding the academic content of the position can be directed to:

Dr.ir. Joaquin Vanschoren, email: j.vanschoren[at]tue.nl

For information concerning employment conditions you can contact:

HR Services Mathematics and Computer Science (HRServices.MCS[at]tue.nl)

More information on employment conditions can also be found here:

https://www.tue.nl/en/working-at-tue/why-tue/compensation-and-benefits/