SAR and optical data are widely used in image fusion to provide the complimentary information of each other and obtain the spatial and spectral features for improved classifications. This paper proposes to use multi-temporal data form Sentinel-1 (VV & VH polarization) and Sentinel-2 sensors for the fusion and classification over an agricultural area. Convolutional Neural Network (CNN)- based Pyramid method for fusion and Bayesian Optimized 2-D CNN for classification of fused multi-temporal data was used to extract spatial-spectral information. Results in terms of classification accuracy suggests slightly better performance by VV polarized fused images than the VH and also suggests an improved performance by multi-temporal data in comparison to the single date data over the study area.