Title :
An artificial neural network for classifying and predicting soil moisture and temperature using Levenberg-Marquardt algorithm
Author :
Atluri, Venkata ; Hung, Chih-Cheng ; Coleman, Tommy L.
Author_Institution :
Dept. of Math. & Comput. Sci., Alabama A&M Univ., Normal, AL, USA
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
Keywords :
agriculture; backpropagation; computerised monitoring; feedforward neural nets; pattern classification; soil; Levenberg-Marquardt algorithm; agriculture; backpropagation; crop management; feedforward neural network; soil classification; soil moisture; soil temperature; Artificial neural networks; Backpropagation algorithms; Crops; Hydrology; Moisture measurement; Remote sensing; Soil measurements; Soil moisture; Temperature measurement; Temperature sensors;
Conference_Titel :
Southeastcon '99. Proceedings. IEEE
Conference_Location :
Lexington, KY
Print_ISBN :
0-7803-5237-8
DOI :
10.1109/SECON.1999.766079
