Spinach (Spinacia oleracea L.) Growth Model in Indoor Controlled Environment Using Agriculture 4.0

Area of Science:

• Controlled environment agriculture
• Plant science
• Computational modeling

Background:

• Growing demand for nutrient-dense crops like spinach necessitates advanced agricultural solutions.
• Current agricultural systems require improved computational models for accurate plant growth forecasting.
• Optimizing vegetable growth in urban agriculture addresses food security and resource efficiency.

Purpose of the Study:

• To develop an enclosed agriculture system for growing and modeling spinach (Spinacia oleracea L.).
• To apply data science, machine learning, and mathematical modeling for precise plant growth prediction.
• To evaluate the effectiveness of computational models in optimizing controlled environment agriculture.

Main Methods:

• Constructed an enclosed growth system with LED lighting, automated irrigation, and environmental controls.
• Collected 60 days of data on temperature, humidity, substrate moisture, and light spectra.
• Utilized polynomial regression models to forecast spinach growth patterns based on collected data.

Main Results:

• Polynomial regression models demonstrated effectiveness in predicting spinach growth.
• Leaf length prediction achieved a minimum Mean Squared Error (MSE) of 0.158.
• Leaf width and stem length models showed high accuracy with low MSE values, indicating reliable predictability.

Conclusions:

• The developed enclosed agriculture system and modeling approach are effective for spinach cultivation.
• Computational models, particularly polynomial regression, offer precise forecasting for plant growth in controlled environments.
• This research contributes to optimizing resource utilization and enhancing food security through advanced agricultural technologies.