PhD position – Smart ecosystem monitoring through automated insect recognition combining novel sensing technologies with artificial intelligence

(ref. BAP-2022-586)

Laatst aangepast : 5/08/2022

The MeBioS group performs groundbreaking research on innovative sensor technologies and the associated data analysis methods to understand and control the quality of biological products and processes. Within the Biophotonics group of MeBioS, sensor research focusses on optical systems in different parts of the electromagnetic spectrum, including Vis/NIR spectroscopy, THz spectroscopy and imaging, hyperspectral imaging, thermography and smart cameras. The associated data research involves the optimal design of experiments, chemometrics, process monitoring and control, as well as artificial intelligence and deep learning.

Project
According to FAO estimates, pests cause up to 40% of the world's crop yield to be lost each year. Over $70 billion 

is lost annually to

invasive insects in the global economy. On a global scale, invasive species have a significant role in ecosystem services deterioration, biodiversity loss, and ecological degradation. A sensor system that allows for the rapid identification of flying insects is currently lacking, and identification of insects is mainly based on counting insects on specialized traps. This procedure is subjective and time consuming. As a result, it is only performed on a weekly basis, and at a limited number of locations. Therefore, a rapid system for insect detection would be highly valuable.

In the MeBioS division, basic research has been conducted to develop insect recognition sensor devices. We specialize primarily on image and wingbeat signature analysis, with an emphasis on insect pests in the fruit and vegetable producing industry. To this end, we collaborate with several partners in Flanders and abroad to bring together all required expertise. We have already demonstrated that similar species may be identified under laboratory conditions. Now, we want to conduct research on (1) more advanced setups that could potentially improve classification results; (2) robust systems, both from a hardware and software perspective, that enable accurate measurements in the field; (3) data analytics that combine information from multiple sources; and (4) the foundation for a remotely accessible sensor network.

Profile

To perform this research, the MeBioS Biophotonics group is looking for a highly motivated PhD candidate with an interest in technology and biology. Do you hold a master in (bioscience) engineering, computer science, data science or physics? Do you have a creative, critical, analytical and innovative mindset? Are you eager to combine scientific knowledge and challenges with hands-on experience in designing an automated trap – hardware as well as software? Do you have excellent oral and written communication skills in English? Then you may be the perfect candidate to join our team. Experience in one or more of following fields is a clear plus:  Image Analysis, Optics, Time-frequency Analysis, Deep Learning, Programming in MATLAB or Python (e.g. PyTorch or Tensorflow), Linux, Raspberry Pi, Sensor Data.

Offer

• We offer a full-time PhD position for 1 year. After positive evaluation, the contract can be extended to 4 years.   
• Excellent guidance by our young, dynamic and multidisciplinary team.
• State of the art research infrastructure.
• A challenging job in a young, dynamic environment.
• High level scientific training at a top-ranked university.
• Being part of a world-class research group.
• Remuneration according to the KU Leuven salary scales (https://www.kuleuven.be/personeel/jobsite/en/phd-info)

Interested?

For more information please contact Dr. ir. Bart De Ketelaere, tel.: +32 16 32 85 93, mail: [email protected] or Mr. Ioannis Kalfas, tel.: +32 16 19 43 33, mail: [email protected].

KU Leuven seeks to foster an environment where all talents can flourish, regardless of gender, age, cultural background, nationality or impairments. If you have any questions relating to accessibility or support, please contact us at [email protected].