Summer school

Project name

AI-Driven Fish Biomass Estimation and Growth Trend Monitoring: A Practical Approach for Aquaculture

Leader

MSc. Mohammad Mehdi Ziaei

Description of the activities of the project

• Accurate biomass estimation is the cornerstone of efficient aquaculture management. Traditional methods often require manual weighing, which is labor-intensive, time-consuming, and stressful for the fish, often leading to physical injury or reduced growth rates.
• The objective of this project is to develop a non-invasive computer vision prototype capable of estimating fish biomass (weight and volume) and tracking growth trends over time. By leveraging deep learning, the system will analyze fish dimensions (length, height, and area) from video or image data to calculate total biomass within a cultivation unit without removing the fish from the water.
• During this three-week program, students will: Data Acquisition: Learn how to collect and preprocess underwater imagery for biomass calculation. AI Training: Use Python and Deep Learning frameworks (like YOLO or Mask R-CNN) to segment fish and detect key morphological points. Biometry & Modeling: Apply mathematical models to convert visual pixel data into physical weight/mass estimates. Trend Analysis: Develop a simple dashboard or script to track how biomass changes over the course of the project.
• The final outcome will be a prototype software tool that automatically estimates the biomass of a fish population and provides a visual report on growth trends for the cultivation unit.

Students

• Number of students - 1-2
• high school students students - NO
• university students - YES
• Prepositions (what should the students know): basics of programing