Sea Cucumber Harvest Size Prediction for Aquaculture Farms
Developed a machine learning model to assist sea cucumber farmers in estimating final harvest size using environmental and stocking data.
About This Project
This project focuses on supporting sea cucumber farmers by predicting the expected harvest size based on farming conditions and stocking information. The study uses aquaculture farm data such as cultivation area, initial stock weight, and stocking density to estimate the final average harvest weight. Several machine learning models were explored to analyze the relationship between farming conditions and growth outcomes. The system aims to help farmers make informed decisions about stocking strategies and farm management practices in order to optimize yield and productivity. By providing early predictions of harvest size, the approach supports better planning, resource management, and sustainable aquaculture practices.
Technologies Used
Key Highlights
- Developed predictive models to estimate final harvest size of sea cucumbers using aquaculture farm data.
- Analyzed relationships between stocking density, cultivation area, and growth outcomes.
- Designed a decision-support approach to help farmers optimize stocking strategies.
- Supports sustainable aquaculture management through data-driven harvest planning.