Accurate forecasting of water requirements is crucial for optimizing irrigation and water preservation. This paper presents a real-time intelligent irrigation system for the various growth stages of coriander plants, utilizing Internet of Things (IoT) sensors and hybrid machine learning (ML) models optimized with a genetic algorithm (GA). A novel method is introduced for the first time to estimate net solar radiation based on sunshine duration data collected via the BH1750 sensor, helping to calculate evapotranspiration ( \(EV_{T0}\) ) for precise crop-specific water requirements. Based on the selection, mutation and crossover operators of GA, nine hybrid artificial neural network (ANN) models are developed to predict \(EV_{T0}\) . It may be mentioned here that hybrid machine learning model 4 (HML4) showed the best performance with \(R^2\) 0.98 among the nine hybrid models evaluated. Furthermore, the exact water requirements are determined for each growth stage of the coriander plants using the predicted \(EV_{T0}\) and crop-coefficient ( \(C_C\) ). To enhance the applicability of the proposed system, an Android application is designed and implemented for the remote monitoring and management of intelligent irrigation system, demonstrating its effectiveness in optimizing irrigation practices. The proposed intelligent system can significantly minimize flood irrigation, water consumption, and labour expenses showing a new direction in smart agriculture.
