Design of an optimized deep learning algorithm for automatic classification of high-resolution satellite dataset (LISS IV) for studying land-use patterns in a mining region Step:1 Generated of LISS-IV satellite image land-use dataset. Step:2 Model development of the proposed framework architecture of DCNN algorithm with the learning of samples (size: 6x6). Step: 3 Model optimization with the tuning of hyperparameters values and measure the optimizer the performance of robust accuracy Step: 4 Accuracy Assesment of model Step:5 Study of the mining region using designed optimised DCNN+SGDM model Step 6: Analysis for the classification of land use patterns in mining regions