Careful implementation of a fi ltration system is essential for maintaining the operation of an irrigation system. Failure to maintain a fi ltration system can have a negative eff ect on irrigation pressure and uniformity. To avoid this problem, it is important to clean the fi lters, which can be done either manually or automatically. Predicting the correct time to clean the fi lters helps maintain the pressure and effi ciency of the system. The aim of this study was to model backwash pressure as a function of water quality and the fi lter inlet pressure load using artifi cial neural networks. The characteristics of the water were determined using sensors to measure the pH (hydrogen potential), turbidity, total dissolved solids (TDS), and temperature. A pressure transducer was used to quantify the drop in pressure and the need to clean the fi lters. To predict the need for cleaning the irrigation fi lters, a hydraulic structure was constructed that included a screen fi ltration system with a mesh size of 120, cleaned by backwashing. The need for cleaning estimated by the multilayer perceptron feedforward artifi cial neural networks with 2-4-1 architecture performed well in modelling the temporal evolution of the pressure load in the screen fi ltration system (120 mesh), whereas adjusting the pressure load based on the water quality characteristics (pH, turbidity, total dissolved solids and temperature) performed poorly.