Water and Air Quality in Modern Farms Using Neural Network

In this paper, Artificial Neural Network(ANN) is used to solve the problems being faced by the farmers in Istanbul and to increase the productivity of farm produces. We implemented two methods in this research in order to classify the soil quality, namely; Curve fitting and Pattern classification. Curve-fitting method use the approach of representing an attempt for the neural network to identify and approximate an arbitrary input-output relation and once the relation has been modeled the necessary accuracy by the network, it can be used for a variety of tasks, such as series prediction, function approximation, and function optimization. Curve-fitting method has the objective of selectin parameter values which minimizes the total error over the set of data points being considered, hence, the reason for its implementation in this research. Pattern classification involves building a function that maps the input feature space to an output space of two or more classes or more. The goal of pattern classification is to assign input patterns to one of a finite number of classes. And, it is a method that have been tested in previous research and gave positive results, hence, the reason for its implementation of this noble method in this study. Moreover, these models can predict the status of the soil and inform the farmers with the right decision to protect their fields. The simulation results showed that Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) methods are the best methods of the seven methods investigated. The accuracy of the networks studied ranged from 94.4 to 99.2%. Networks trained with LM algorithm were observed to be faster.