The present study demonstrated the application of remote sensing for the estimation of large crop and forest area covered in Aurangabad, (Maharashtra), India. The IRS-P6 Advanced Wide Field Sensors (AWiFS) 56m spatial resolution data were acquired during October & December 2012 which covers whole study areas with its swath of 740Km has been taken for the study. AWiFS having four spectral bands such as Green(0.52-0.59) Red(0.62-0.68) NIR(0.77-0.86) SWIR(1.55-1.70). The Maximum Likelihood Classification (MLC) and Knowledge Classification (KC) techniques based on Decision Tree approach were used. It has two elements knowledge engineer and knowledge classifier, Knowledge engineer provides an interface to build up decision tree define the rules and variables based on Calculated Normalized Difference Vegetation Index (NDVI), Soil Adjust Vegetation Index (SAVI), and Normalized Difference Water Index (NDWI) threshold value of each class, and knowledge classifier generate the output classification. The objective of this research work is to perform classification of crop and forest acreage estimation from AWiFS data and comparing the supervised classification techniques such MLC and KC. The comparative results shows that the two scene gives overall classification accuracy for the October 2012 based on MLC is 82% and for the December 2012 is 84%, as well as overall classification accuracy for October 2012 is 85% and December 88% based on KC. The classification results are based on KC provides better results than the MLC.