An artificial neural network for classifying and predicting soil moisture and temperature using Levenberg-Marquardt algorithm

Abstract

The purpose of this study was to design an artificial neural network that classifies soils and quantitatively predict the soil moisture and temperature in a given soil type based on the remotely sensed data. Two different training algorithms, viz., backpropagation (BP) and Levenberg-Marquardt (LM), were employed. The accuracy of the networks studied ranged from 96.68 to 98.8%. The networks trained with LM algorithm were faster. It is concluded that neural networks can be used as a paradigm in soil classification as well as in predicting the quantity of soil moisture and temperature accurately, using remotely sensed microwave data, and thus helps achieve a proper crop management.