"PhD Position Physics-informed Learning and Layered Control Architectures for High-tech Greenhouses"

Job Summary

High-tech greenhouses are essential for sustainable food production. This PhD project addresses challenges in autonomous greenhouse control by developing physics-informed graph neural networks (GNNs) combined with nonconventional sensors like computer vision. The goal is to create generalizable, explainable, and data-efficient machine learning for crop-greenhouse systems, focusing on predictive and optimization-based control methods. This will redesign control layers to improve flexibility and explainability, culminating in large-scale experiments.

Responsibilities

• Explore physics-informed GNNs and nonconventional sensors for machine learning in greenhouse systems.
• Use GNNs in predictive and optimization-based control methods.
• Develop tailored control formulations and optimization algorithms.
• Redesign control layers and communication strategies for autonomous greenhouse systems.
• Collaborate with a team from TU Delft, Wageningen University and Research, Erasmus University Rotterdam, and industrial partners.
• Conduct experiments, including research trials and validation in actual greenhouses.

Qualifications and Requirements

• Completed a relevant MSc degree in systems and control, engineering, applied mathematics, or a related field.
• Strong background or interest in systems and control, machine learning, and biological systems.
• Some experience in conducting, designing, and/or managing experiments for physical or biological systems is preferred but not required.

What the Employer Offers

A 4-year employment contract (initially 1.5 years with assessment, followed by 2.5 years). Salary ranges from €3059 to €3881 per month. Enrollment in the TU Delft Graduate School for skill development. Additional benefits include a customizable compensation package, health insurance discounts, monthly work costs contribution, and support for international relocation through the Coming to Delft Service.