A Simulation Model for Crop Yield under Varying Soil and Different Amount of Nutrients Conditions using Artificial Neural Networks in Back Propagation Algorithm

N. Manoharan1, R. Balasubramanian2 and J. Jeyabaskaran3

1Department of Computer Science, SRM Arts and Science Colloge, Kattangulathur, Chennai, Tamil Nadu.

2Faculty of Computer Applications, Erode Builder Educational Trust’s Group of Institutions, E.B.E.T. Knowledge Park, Kangeyam, Tiruppur District-638108

3Soil Scientist in National Research Centre for Banana, Trichy, Tamil Nadu


This paper proposed a simulation model of crop growth which is effected by major nutrient factors, nitrogen, phosphorus and potassium. Decision-making processes in agriculture often require reliable crop yield response models to assess the impact of specific land management. Setting a realistic yield goal in each part of the field is one of the critical problems in precision agriculture. Factors affecting crop yield, such as soil, weather, and land managements, are so complex that traditional statistics cannot give accurate results. The artificial neural network (ANN) is an attractive alternative for processing the massive data set generated by precision farming production and research. This paper investigates the potential of predicting crop yield responses under varying soil and different amount of nutrients conditions by applying three different adaptive techniques, general linear models (GLMs), regression trees (RTs) and artificial neural networks (ANNs). The crop yield in GLM and RT gives only single iteration result and poorest result in terms of modeling accuracy, prediction accuracy, and model uncertainty, which might suggest its inability to model the non-linear causal relationships present in complex soil–land and crop-management interactions. The feed-forward, completely connected, back-propagation ANN was used to approximate the nonlinear yield function relating crop yield to factors influencing yield. The objective of this work is to develop an artificial neural network model to predict crop yield using a back-propagation tanning approach.

Keywords: Artificial neural networks, Regression tree, General linear model, Back-propagation, Yield prediction.

     Back to TOC