Publication Type:

Journal Article

Source:

International Journal of Pure and Applied Mathematics, Volume 119, Number 10, p.451-466 (2018)

URL:

http://www.acadpubl.eu/jsi/2018-119-10/issue10a.html

Abstract:

The principle aim of fertilization is to provide the nutrients in the soil to satisfy the requirements of plants. The identification and application of chemical fertilizers that add to the nutrients in the soil, help the agronomist in decision-making regarding crop yield. Different statistical or computational techniques are used for predicting fertilizers. Artificial Intelligence (AI) methods offer a more impressive way of predicting fertilizers under various cropping patterns. Artificial Neural Network (ANN) models can easily interpret complex input structure. This study describes the development of fertilizer’s application rate prediction model for Coconut Tree with the help of ANNs. The prediction model is developed with the soft technique of ANNs through the use of back propagation algorithm and multilayer neural network model. Today's farmers depend on advanced technology to reduce their overall labor and to increase production. In this study, the promising methodology in AI called deep learning is used to predict the application rate of fertilizers for Coconut Tree. The Deep Neural Network (DNN) achieved better accuracy as compared with standard ANN. These two methods are compared in the terms of their performance. The predicted accuracy rate for fertilizers Urea, MOP and Lime using Standard Neural Network Classifier is 85.95%, 81% and 93.39 % respectively. But the same measurement using DNN is 95.1%, 95.05% and 96.7% respectively which shows that DNN performs better than other neural network models in the agricultural system with large data.

Cite this Research Publication

M. S. Suchithra and Maya L. Pai, “Impact of Deep Neural Network on Predicting Application Rate of Fertilizers (Focus on Coconut Trees of Kerala Northern Coastal Plain Agro Ecological Unit)”, International Journal of Pure and Applied Mathematics, vol. 119, pp. 451-466, 2018.