SUPERVISED MACHINE LEARNING BASED DYNAMIC ESTIMATION OF BULK SOIL MOISTURE USING COSMIC RAY SENSOR
| Autor: | Claire D'Este, Ritaban Dutta |
|---|---|
| Rok vydání: | 2013 |
| Předmět: | |
| Zdroj: | International Journal of Research in Engineering and Technology. :248-253 |
| ISSN: | 2319-1163 2321-7308 |
| DOI: | 10.15623/ijret.2013.0208040 |
| Popis: | In this paper artificial neural network based senso r informatics architecture has been investigated; i ncluding proposed continuous daily estimation of area wise surface soil moisture using cosmic ray sensor’s neutron count time serie s. Study was conducted based on cosmic ray data available from two Australian locat ions. The main focus of this study was to develop a data driven approach to convert neutron counts into area wise ground surfac e soil moisture estimates. Independent surface soil moisture data from the Australian Water Availability Project (AWAP) was us ed as ground truth. A comparative study using five different types of neural networks, namely, Feed Forward Back Propagation (FF BPN), Multi-Layer Perceptron (MLPN), Radial Basis F(RBFN), Elman (EN), and Probabilistic networks (PNN) was co nducted to evaluate the overall soil moisture estim ation accuracy. Best performance from the Elman network outperformed all other neural networks with 94% accuracy with 92% s ensitivity and 97% specificity based on Tullochgorum data. Overall hig h accuracy proved the effectiveness of the Elman ne ural network to estimate surface soil moisture continuously using cosmic ray sensors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|