The conventional application of nitrogen fertilizers via irrigation is likely to be responsible for the increased nitrate concentration in groundwater of areas dominated by irrigated agriculture. This requires appropriate water and nutrient management to minimize groundwater pollution and to maximize nutrient use efficiency. To fulfill these requirements, drip fertigation is an important alternative. This study deals with fuzzy modeling of nitrate leaching from a potato field under a drip fertigation system. In the first part of the study, a two-dimensional model (HYDRUS-2D) was used to simulate nitrate leaching from a sandy soil with varying emitter discharge rates and various amounts of fertilizer. The results from the modeling were used to train and validate a Mamdani fuzzy inference system (MFIS) in order to estimate nitrate leaching. The centers of triangular membership functions in MFIS were tuned by Genetic Algorithm. The correlation coefficient, normalized root mean square error and relative mean absolute error percentage between the data obtained by HYDRUS-2D and the estimated values using MFIS model were 0.986, 0.086 and 2.38 respectively. It appears that MFIS can predict nitrate leaching from the field accurately. The proposed methodology can be used to reduce the effect of uncertainties in relation to field data.
International Journal of Agriculture, 2012, Vol 2, Issue 5, p. 608-617