Subsurface drainage performance study using SALTMOD and ANN models

Relative performance of artificial neural networks (ANNs) and the conceptual model SALTMOD was studied in simulating subsurface drainage effluent and root zone soil salinity in the coastal rice fields of Andhra Pradesh, India. Three ANN models viz. Back Propagation Neural Network (BPNN), General Regression Neural Network (GRNN) and Radial Basis Function Neural Network (RBFNN) were developed for this purpose. Both the ANNs and the SALTMOD were calibrated and validated using the field data of 1998–2001 for 35 and 55 m drain spacing areas. Data on irrigation depth, evapotranspiration, drain discharges, water table depths, mean monthly rainfall and temperature and drainage effluent salinity were used for ANN model training, testing and validation. It was observed that the BPNN model with feed forward learning rule with 6 processing elements in input layer and 1 hidden layer with 12 processing elements performed better than the other ANN models in predicting the root zone soil salinity and drainage effluent salinity. Considering coefficient of determination, model efficiency and variation between the observed and predicted salinity values as the evaluation parameters, the SALTMOD performed better in predicting root zone soil salinity and the BPNN performed better in predicting the drainage effluent salinity. Therefore, it was concluded that the BPNN with feed forward learning algorithm was a better model than SALTMOD in predicting salinity of drainage effluent from salt affected subsurface drained rice fields.