AN ARTIFICIAL NEURAL NETWORK MODEL FOR SIMULATING PESTICIDE CONCENTRATIONS IN SOIL

Abstract

The simulation of pesticide concentrations in soil requires knowledge of complex physico-chemical processesthat pesticides undergo, in both unsaturated and saturated zones. Generally, conventional models are used for thispurpose. This article reports on the use of artificial neural networks (ANNs) to simulate pesticide concentrations inagricultural soils. The main advantages of ANN modeling are significantly fewer input parameters and a very shortexecution time. An ANN model can be executed in real-time, while the sprayer is working in the field, in order to adjustapplication rates to the real extent of the problem. In this study, an ANN model was built and trained with inputs of:accumulated daily rainfall, soil temperature, potential evapotranspiration, as well as tillage practices and the number ofdays elapsed after pesticide application. The outputs of the ANN model were the daily accumulated amounts of pesticidelevels in the soil. The results were compared with the data collected in 1992 and 1993 from an agricultural field inOttawa, Canada. The results show the benefits of ANNs in predicting pesticide concentrations in agricultural soils. In thisstudy, only six input parameters are required with fast execution. The ANN-based model can be very helpful in makingquick and appropriate decisions during real-time application of pesticides. In this study, the performance of ANNs wasinvestigated when the amount of available training data was limited. The results indicated that the performance of ANNswas good, in spite of limited data, with the values of root-mean-square error and standard deviation being generallylower than 0.2 g/g. However, the performance of ANNs could be improved with more training data obtained from fieldexperiments.