Most of greenhouse growers desire a determined amount of yields in order to accurately meet market requirements. The purpose of this paper is to explore the dynamics of neural networks in forecasting crop (tomato) yield using environmental variables; here we aim at giving accurate yield amount. We use the Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS has only one output node, the yield. One of the difficult issues in predicting yield is that remote sensing data do not go long back in time. Therefore any predicting effort is forced to use a very restricted number of past years in order to construct a model to forecast future values.