Hyperspectral Imaging for Detection and Quantification of Microorganisms in Aquatic Environments

Background

Water quality monitoring is critical for aquaculture, environmental protection, and public health. Traditional methods for detecting microorganisms and algae often rely on manual sampling and laboratory analysis, which are time consuming and unsuitable for continuous monitoring. Hyperspectral imaging offers the potential to capture rich spectral signatures that can be used to identify and quantify biological content in water.

While hyperspectral imaging has been explored in environmental monitoring, many challenges remain in reliably identifying microorganisms under varying lighting, water turbidity, and environmental conditions. Moreover, integration with behavioral monitoring of aquatic animals remains underexplored.

Objectives

This project aims to investigate the feasibility of using hyperspectral imaging combined with machine learning to detect, identify, and quantify microorganisms in water, with a long term perspective toward deployment in aquaculture ponds or natural water bodies. The project will be a good foundation for further and more complex researches.

Research questions

• Can hyperspectral signatures be used to distinguish between different types of microorganisms or algae?
• What level of quantification accuracy is achievable under realistic conditions?
• How robust are models to changes in water quality and environmental conditions?
• Can spectral information be combined with spatial and temporal cues to improve reliability?

Methodology

The student will:

• Review existing work on hyperspectral imaging for water analysis and biological sensing.
• Collect or work with controlled hyperspectral datasets of water samples.
• Develop preprocessing and feature extraction pipelines.
• Train and evaluate machine learning models for identification and quantification tasks.
• Explore extensions toward monitoring aquatic animal presence or movement using spectral and spatial cues.

Type of internship: Master internship

Duration: 6-9 months

Required educational background: Bioscience Engineering, Chemistry/Chemical Engineering, Computer Science, Electrotechnics/Electrical Engineering

Supervising scientist(s): For further information or for application, please contact Hyun-su Kim ([email protected]) and Tien Nguyen ([email protected])

The reference code for this position is 2026-INT-078. Mention this reference code in your application.

Applications should include the following information:

• resume
• motivation
• current study

Incomplete applications will not be considered.