Estimation of rice-planted area using competitive neural network

This paper considers a classification of estimation of rice planted area by using remote sensing data. The classification method is based on a competitive neural network and the sattelite data are remote sensing data observed before and after planting rice in 1999 in Hiroshima, Japan. Three RADAR Satellite (RADARSAT) and one Satellite Pour l'Observation de la Terre(SPOT)/High Resolution Visible (HRV) data are used to estimate rice-planted area. Synthetic Aperture Radar (SAR) back-scattering intensity in rice-planted area decreases from April to May and increases from May to June. Thus, three RADARSAT images from April to June are used in this study. The SOM classification was applied the RADARSAT and SPOT to evaluate the rice-planted area estimation. It is shown that the Self-Organizing feature Map (SOM) of competitive neural networks is useful for the classification of the satellite data by SAR to estimate the rice planted area.

本文考虑了一种利用遥感数据估算水稻种植面积的分类方法。该分类方法基于竞争神经网络，卫星数据是1999年日本广岛水稻种植前后观测到的遥感数据。使用了三颗雷达卫星（RADARSAT）和一颗地球观测卫星（SPOT）/高分辨率可见光（HRV）数据来估算水稻种植面积。水稻种植区的合成孔径雷达（SAR）后向散射强度从4月到5月下降，从5月到6月上升。因此，本研究使用了4月到6月的三颗RADARSAT图像。将自组织映射（SOM）分类应用于RADARSAT和SPOT数据以评估水稻种植面积估算。结果表明，竞争神经网络的自组织特征映射（SOM）对于利用SAR对卫星数据进行分类以估算水稻种植面积是有用的。