Estimating Paddy Rice Biomass Using Radarsat-2 Data Based on Artificial Neural Network

DOI

10.2991/rsete.2013.103How to use a DOI?

Keywords

Biomass; BP neural network; Radarsat-2 data; HH, HV polarization

Abstract

Accurate estimation of rice biomass plays a role in crop growth monitoring and agricultural carbon cycle. Dual-polarization Radarsat-2 data were used in this study for rice biomass inversion. Artificial neural network (ANN) method has been applied to simulate the relation between rice canopy parameters (height, moisture content and biomass etc.) and radar backscattering coefficients. By comparing the network training performance and RMSE of different polarization combinations, HV data had better accuracy which was selected as input of the network for biomass inversion. The distribution of rice biomass was also mapped at regional scale. This study indicated that Radarsat-2 SAR data could be used to estimate rice biomass with the root mean square error (RMSE) of <108 g/m2.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhuo-xin Jing
AU  - Yuan Zhang
AU  - Ke-jing Wang
PY  - 2013/08
DA  - 2013/08
TI  - Estimating Paddy Rice Biomass Using Radarsat-2 Data Based on Artificial Neural Network
BT  - Proceedings of the 2013 the International Conference on Remote Sensing, Environment and Transportation Engineering (RSETE 2013)
PB  - Atlantis Press
SP  - 421
EP  - 424
SN  - 1951-6851
UR  - https://doi.org/10.2991/rsete.2013.103
DO  - 10.2991/rsete.2013.103
ID  - Jing2013/08
ER  -