Abstract
The fusion of multi-sensor and multi-resolution details of an effective exploiting the complimentary nature of different data types, especially the obtained image from multi sensor have the clearly different characteristics such as the SAR image and multi-spectral image including with the characteristics of wavelength, sensor and measuring technique. The Radar image uses the back- scattering wave technique in the antenna direction gives two dominant characteristics ; discontinuity/roughness of the object surface assign the reflected wave direction, the object absorption depending on the moisture. However, the classification and interpretation of SAR image are quite difficult with low precision according to both characteristics vary with the structure and different object type. Therefore, the dominant data addition of multi-spectral image into SAR image will make the data analysis to be comfortable and easy.

This paper proposes the mixed data of SAR and OPS ( optical sensor ) obtained form JERS-1 satellite in the flood period of central area of Thailand as study region. This region is water hole with flooding. To use the wavelet decomposition based on low wavelet coefficient of SAR image is included with OPS image, the wave absorption from the object moisture is combined with the other physical data by using the multi -layer perception ( MLP) neural network based on the back propagation ( BP) algorithm suitably for multi-spectral image . thus, the classification and analysis of flood area will be high resolution and high accuracy.

1. Introduction
There have been several efforts to monitor and assess flood area. Especial, the monsoon region were suddenly inundated by slash flood caused by the storm and others natural hazard, such as El Nino, LA Nina I and etc. this flood caused much damage to the environment, people's live and properties. Several Techniques have been applied to estimate the flood area . [1] using the NDVI ( normalized difference vegetation index derived from multi-spectral data and 3-second grid DEMs ( digital elevation models to investigate and identify the damage area depending on elevation intervals.

However, the SAR images have been known an efficiently flood detection, because of the object absorption property depending on the moisture, of the back-scattering wave in Radar image. as the multi-spectral images provide necessary information for land cover interpretation. The fusion of multi-sensor images achieves the complementary nature of theses different data types. Therefore, the fusion techniques have been adopted to perform the flood area classification. To assess the flood areas, , JERS-1 SAR data acquired on June 03, 1997 and August 30, 1997 were taken before and during flood hazard form the tropical storm Zita, in Surat Thani province, were used. Because of this cloud penetration capability and shown in Fig. 1 and 2, respectively. Fusion these images with JERS-1 OPS data acquired on March 14, 1997 war performed to distinguish flood area.

Fig. JERS -1 SAR image acquired on June 03, 1997, Surat Thani Province



Fig 2. JERS-1 SAR image acquired on August 30, 1997.



Fig 3 JERS-1 OPS data acquired on March 14, 1997.
To study the flood assessment, the image classification is used as a revolutionary computing methodology known as the artificial neural network ( ANN) computing, which has been performed. This method presents how the neuron in the human brain process the data to identify the complex and noisy patterns of infor4emation. An error back-propagation artificial neural network structure is used in this paper.