Land use/land cover (LULC) classification using deep-LSTM for hyperspectral images

Land Use/Land Cover (LULC) classification using hyperspectral images in remote sensing is a leading technology. However, LULC classification using hyperspectral images is a difficult task and time-consuming process because it has fewer training samples. To overcome these issues, we proposed a deep-Long Short-Term Memory (deep-LSTM) to classify the LULC. Before classifying the LULC, extracting valuable features from an image is needed, and after extracting the features, selecting the bands which are helpful for classification should be done. In this work, we have proposed an auto-encoder model for feature extraction, a ranking-based band selection model to select the bands, and deep-LSTM for classification. We have used three publicly available benchmark datasets; they are Pavia University (PU), Kennedy Space Centre (KSC), and Indian Pines (IP). Average Accuracy (AA), Overall Accuracy (OA), and Kappa Coefficient (KC) are used to measure the classification accuracy. The suggested technique has provided the top outcomes compared to the other state-of-the-art methods.