Integrated monitoring and prediction artificial intelligent based expert system: a case study on hydroponics strawberry cultivation

Abstract This paper presents an integrated monitoring and prediction system for managing the C/N ratio in hydroponic strawberry cultivation, utilizing an artificial neural networks (ANN) and an adapted autoregressive integrated moving average (ARIMA) model. The ARIMA model has been improved by incorporating the error between the ANN predictions and the actual C/N ratio, thereby leading to higher predictive accuracy. The study leverages real-world data collected from a hydroponic strawberry farm, including environmental variables such as temperature, humidity, CO2 levels, pH level, moisture content, electrical conductivity, and nutrient uptake rates (Nitrogen, Phosphorus, Potassium, Calcium). The system accurately predicts the C/N ratio and provides timely alarms for deviations in nutrient levels and environmental conditions, ensuring optimal plant health and growth. Model performance is evaluated using k-fold cross-validation, resulting in significant reductions in root mean squared error (RMSE) and mean absolute error (MAE), and improvements in the coefficient of determination ( $$\hbox {R}^{2}$$ ). The adaptive alarm mechanism adjusts thresholds based on seasonal changes, enhancing control and responsiveness. This case study demonstrates the practical application of advanced modeling techniques in hydroponics, contributing to improved crop management and productivity, and paving the way for more sustainable agricultural practices.