This work investigates the use of electronic tongues for monitoring nutrient solution compositions in closed soilless systems. This is a horticultural technique in which the nutrient solution is continuously recirculated and an automatic recomposition system maintains the concentration of the different ions in the optimum range for the plants. Electronic tongues used in this study comprised an array of potentiometric sensors and complex data processing by artificial neural networks. A first experiment was able to carry out the simultaneous inline monitoring of ammonium, potassium, sodium, chloride, and nitrate ions during the winter. In the second and third applications, done during summer, some changes were introduced in the sensor array to improve its response toward chloride ions and to incorporate phosphate in the model. This electronic tongue was validated with real greenhouse samples and was also able to detect the variations in the ion concentrations caused by an incorrect configuration of the recomposition system.