This paper presents a Fuzzy Neural Network-based irrigation water control system for realizing accurate irrigation and water saving. The control system consists of a PC based server with a FNN-based control module, data sampling device, CAN bus communication network and remote irrigation units with sensors and controller. It can estimate irrigation water compensation according to the irrigation environments. By using Fuzzy Logic function and Fuzzy Neural Network, the controller module can fuse multi-source information that from Internet, sensors and other sources to make decision of irrigation water compensation on the control spot. Experimental result indicates that the compensation generated by FNN have higher precision than that by FL in this irrigation water control system.