Rice phenology estimation using SAR time-series data

Author

Cota, Napat ; Kasetkasem, Teerasit ; Rakwatin, Preesan ; Chanwimaluang, Thitiporn ; Kumazawa, Itsuo

Author_Institution

Thailand Adv. Inst. of Sci., Kasetsart Univ., Bangkok, Thailand

fYear

2015

fDate

22-24 March 2015

Firstpage

1

Lastpage

5

Abstract

The actual field survey data from the Rice Department of Thailand´s Ministry of Agriculture over a large area wastes a huge amount of resources. To solve this problem, this paper proposes a new approach to estimate rice phenology using SAR images derived from the RADARSAT-2 data. In this work, we divided the rice phenology into five stages, consisting of seedling, tillering, reproductive, ripening, and harvested stages and applied them to the hidden Markov model (HMM). Then, we estimated the backscattering coefficient time-series data to be used in the Viterbi algorithm. We were able to estimate the rice phenology, with 77.5 % accuracy when compared to the ground data.

Keywords

agriculture; crops; hidden Markov models; maximum likelihood estimation; radar imaging; synthetic aperture radar; time series; HMM; RADARSAT-2 data; SAR images; SAR time-series data; Viterbi algorithm; backscattering coefficient time-series data; harvested stage; hidden Markov model; reproductive stage; rice phenology estimation; ripening stage; seedling stage; tillering stage; Accuracy; Agriculture; Backscatter; Estimation; Hidden Markov models; Synthetic aperture radar; Viterbi algorithm; Hidden Markov Model; SAR(Synthetic Aperture Radar); Viterbi Algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Communication Technology for Embedded Systems (IC-ICTES), 2015 6th International Conference of

Conference_Location

Hua-Hin

Type

conf

DOI

10.1109/ICTEmSys.2015.7110833

Filename

7110833