Optimal guidance whale optimization algorithm and hybrid deep learning networks for land use land cover classification

Abstract Satellite Image classification provides information about land use cover (LULC) and this is required in many applications such as Urban planning environmental monitoring. Recently, deep learning techniques were applied for satellite image achieved higher efficiency. The existing have limitations of overfitting problems due to the convolutional neural network (CNN) model generating more features. This research proposes optimal guidance-whale optimization algorithm (OG-WOA) technique select relevant features reduce problem. guidance increases exploitation search by changing position agent related best fitness value. increase helps avoid problems. input images are normalized AlexNet–ResNet50 feature extraction. OG-WOA extracted Finally, selected processed using Bi-directional long short-term memory (Bi-LSTM). proposed OG-WOA–Bi-LSTM has an accuracy 97.12% on AID, 99.34% UCM, 96.73% NWPU, SceneNet 89.58% 95.21 NWPU dataset.