Abstract :
[en] This research aims to model the biological and chemical interactions in aquaponic, bioponic, and hydroponic systems to evaluate their efficiency in plant growth, nutrient cycling, and overall system stability. The study focuses on three key components: pisciculture, biofiltration, and plant growth, with an emphasis on nitrogen dynamics, microbial activity, and biomass production. Understanding these interactions is crucial for optimizing resource use, minimizing waste, and improving the sustainability of soilless agricultural systems.
To achieve this, a hybrid approach combining mathematical modeling and machine learning is employed. Differential equations describe the transformation and flow of nitrogen compounds (NH₄⁺ → NO₂⁻ → NO₃⁻), while machine learning algorithms help optimize parameters that are difficult to model explicitly, such as microbial efficiency and nutrient uptake rates. This combined approach ensures that the model can capture both the predictable and complex, nonlinear behaviors of the system.
The next step is to collect data to verify that the model accurately reflects the reality of the system and to assess the degree of precision with which it can replicate observed behaviors. Data collection is crucial for validating the model and adjusting its parameters to ensure it aligns with real-world observations. By comparing model outputs with collected data, the model can be fine-tuned for better accuracy and functionality under real conditions.
To achieve this, regular measurements of fish biomass, plant growth, and nitrogen compound concentrations (NH₄⁺, NO₂⁻, NO₃⁻) are taken at different time points. Additionally, water quality parameters such as pH, dissolved oxygen, temperature, and electrical conductivity are monitored using real-time sensors to assess their influence on nutrient cycling and plant health.
For plant growth assessment, destructive sampling methods are used to measure fresh biomass, providing a precise evaluation of growth dynamics. Environmental factors, such as light intensity, humidity, and water availability, are also considered to determine their impact on system performance and plant growth.
By integrating these modeling techniques and collecting detailed data, the research aims to provide a comprehensive, quantitative comparison of aquaponic, bioponic, and hydroponic systems. This will offer valuable insights into system optimization and inform decisions for large-scale implementation and sustainability.
