Discrimination of newly planted and ratoon crops of sugar cane using multidate IRS-1C liss III data: A knowledge based approach

An advanced and accurate information of sugar cane production is an important component for the management of sugar cane industry. Remote Sensing is most viable technique which can provide the above information well in advance. Stratified sampling technique practiced in Crop Acreage and Production Estimation (CAPE) programme holds good for major crops with non-overlapping growth stages. Discrimination of ratoon and newly planted sugar cane crop is a challenging task. Single date remote sensing data does not suffice to discriminate the above two types of sugar cane. In the present paper, an attempt has been made to show how two date remote sensing data coupled with knowledge based approach dramatically improves the classification accuracy (98%) of sugar cane crop as compared to the stratified sampling approach (less than 90%). This has been demonstrated in a case study comprising parts of two districts of western Uttar Pradesh.