Project summary
The project aims to develop an advanced AI-driven system for the precise estimation and management of NPK (Nitrogen, Phosphorus, Potassium) levels in hydroponic cultivation systems. Utilizing deep learning methods, the system will employ a combination of the chemistry-known standard addition method and a calibration-free spectroscopy system to accurately measure NPK concentrations. These macronutrients will then be fed into a decision tree algorithm for precise adjustment of NPK and pH levels from available fertilizer salts, optimizing plant growth and health in hydroponic environments.
The project will include cultivation trials with various crops in soilless systems to evaluate the effectiveness of different fertigation schemes. These trials will assess the nutritional parameters of the solution and plant analyses, focusing on biomass production and internal quality parameters such as antioxidants in edible parts. Additionally, the project will evaluate the photosynthetic activity of plants under different fertigation schemes and LED triggering spectra, as well as the root zone microbiome and microbial activities in inoculation experiments. The system will be tested in an aquaponics unit, also, to ensure its versatility and effectiveness in diverse agricultural environments.
This comprehensive approach will provide valuable insights into the optimal management of plant nutrition in hydroponic cultivation, contributing to sustainable and efficient agricultural practices in the EU and Japan. This research proposal directly addresses the call's focus on digital technology, precision farming, artificial intelligence, and machine learning. By integrating advanced AI-driven methods and deep learning algorithms, the project emphasizes the use of cutting-edge digital technologies to optimize nutrient management in hydroponic systems. The use of remote sensors and continuous monitoring aligns with the call's objectives, ensuring the project's relevance to the future needs of agriculture.