Related Experiment Video
Updated: Aug 10, 2025

Watershed Planning within a Quantitative Scenario Analysis Framework
Published on: July 24, 2016
An Analytical Framework on Utilizing Various Integrated Multi-Trophic Scenarios for Basil Production
Ștefan-Mihai Petrea1,2, Ira Adeline Simionov1,3, Alina Antache1,4
1Food Science, Food Engineering, Biotechnology and Aquaculture Department, Faculty of Food Science and Engineering, "Dunarea de Jos" University of Galati, Domnească Street, No. 111, 800008 Galaţi, Romania.
This study introduces AI-driven aquaponics using Rapana venosa shells (R) as a sustainable substrate for basil and sturgeon. The innovative R substrate improved basil growth and quality, offering a promising alternative to traditional methods.
Area of Science:
- Aquaponics and Recirculating Aquaculture Systems (RAS)
- Artificial Intelligence (AI) in Sustainable Agriculture
- Waste Valorization in Food Processing
Background:
- Aquaponic systems integrate aquaculture and hydroponics for sustainable food production.
- Optimizing nutrient cycling and resource efficiency in aquaponics remains a key challenge.
- Utilizing industrial waste, such as Rapana venosa shells, can enhance system sustainability.
Purpose of the Study:
- To improve the sustainability of aquaponic basil-sturgeon recirculating systems.
- To implement AI for operational management and assess a novel R substrate.
- To evaluate the impact of R substrate on plant growth, quality, and nutrient dynamics.
Main Methods:
- Developed AI models (ARIMA, MLR, GAM, XGBoost) for biomass forecasting and virtual water quality sensing.
- Compared Rapana venosa (R) shells against LECA (H) substrate in high (A) and low (B) feed input scenarios.
- Analyzed nutrient reduction rates, plant biomass, leaf area, mineral content, and phytochemical profiles.
Main Results:
- AI models demonstrated good accuracy, particularly for N-NO3 prediction; PCA showed dissolved oxygen-pH correlation.
- R substrate significantly enhanced basil fresh weight (up to 22.59%) and leaf area (up to 9.49%) compared to H.
- R substrate showed slightly lower N-NH4 and N-NO3 reduction rates but comparable overall nitrogen removal.
Conclusions:
- Supervised learning frameworks effectively optimize operational management in aquaponic systems.
- Rapana venosa shells are a viable alternative substrate, improving plant performance and quality.
- Further research on long-term efficiency and broader application of AI models is recommended.
More Related Videos
05:04Author Spotlight: Understanding Riverine Nitrogen Impacts and Primary Productivity for Effective Nutrient Management
Published on: July 14, 2023
11:53Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
Published on: December 9, 2012
Related Concept Videos
Trophic Efficiency
Symbiosis
The Roles of Bacteria and Fungi in Plant Nutrition
Adaptations that Reduce Water Loss
Primary Production