Developing a Satellite Based Automatic System for Crop Monitoring: the SBAM project

The SBAM (System Implementation and Capacity Building for satellite Based Agricultural Monitoring and Crop Statistics in Kenya) project, funded by the Italian Space Agency, aims at: developing a validated satellite based method for etimating and updating the agricultural areas in the region of Central-Africa; developing methods and products allowing the assessment of the crop status in test areas (Kenya) by combining ground and satellite data; implementing an automated process chain capable to periodically provide agricultural and land cover maps of the area of interest and, possibly, an estimate of the crop yield. we investigated the use of phenological information in supporting the use of remote sensing images for crop classification and monitoring based on Landsat8 and Sentinel-2 images. Kenyan countryside is mainly characterized by a high number of fragmented small and medium size farm holders that dramatically increas the classification difficulty; 30 m spatial resolution images are not enough detailed for a proper classification of such areas. A pan-sharpening FIHS (Fast Intensity Hue Saturation) technique has been implemented to increase image spatial resolution from 30 m to 15 m. Ground test sites have been selected searching for agricultural vegetated areas to pave the way to phenological information extraction. The paper is devoted to present the results of the proposed classification procedure.