The purpose of this research is to estimate the affects of water content (27 37 and 47 % wet basis) cooking time (1 3 and 5 hr) at 110oC and germinating time (24 36 and 48 hr) on chemical composition structure and properties of germinated purple rice flour. A Box-Behnken design under the response surface methodology was performed to optimize their composition. Rajamangala University of Technology Lanna Nan was research place. Results demonstrated that germinating time had no significantly effect on protein and lipid content but resulted in increasing crude fiber and decreasing carbohydrate and amylose content with increase in germinating time. Scanning electron micrographs (SEM) revealed the presence of polyhedral shape and agglomerations. Birefringence was evidenced. Pasting properties of germinated purple rice flour showed an increase in the pasting temperature but a decrease the peak viscosity breakdown final viscosity and setback (p<0.05) as germinating time increased. Modified rice flour were increase in carbohydrate and amylose content and decrease in protein lipid ash and fiber as water content and cooking time at 110oC increased. Change in birefringence of starch granule after heating at 110oC was examined by a polarized light microscope. SEM showed the presence of creak surfaces and agglomerations. The swelling power of germinated purple rice flour decreased with increase in cooking time. The solubility at 85oC of germinated purple rice flour was increased in each level of water content.

In this paper proposed remote sensing using Normalized Difference Vegetation Index from NOAA STAR cluster value from k-means temperature rainfall number of rainy days and runoff to create runoff prediction model using Artificial Neural Network (ANN) and evaluated runoff models with the R2 and RMSE. The results show that the using of cluster value with other parameters to create predictive models can enhance forecasting results. When using Normalized Difference Vegetation Index with temperature value at lag time 1-2 month and cluster value at lag time 1 month to create model with ANN we have got the best performance which are RMSE=0.09 and R2=0.743. The experimental results shows that remote sensing data and cluster value from k-means can be used to predictive the runoff effectively.