Deep Learning-Based Methods for Lithology Classification and Identification in Remote Sensing Images

This study presents a deep learning model that integrates Vision Transformers (ViT) with Fourier spectral filtering for remote sensing lithology classification. The model automates the process of identifying and classifying various rock types in remote sensing images, addressing a multi-class classification challenge. It utilizes ViT for feature extraction, enhanced by pretrained weights for improved efficiency and accuracy in recognizing geographical features. Fourier spectral filtering further augments the model by leveraging frequency domain information for accurate classification. The model preprocesses images, extracts spatial features, applies spectral filtering, and employs a classification head to predict rock types. Optimization of parameters through backpropagation and gradient descent methods, coupled with regularization strategies, aims to prevent overfitting and ensure generalizability. This approach combines deep learning's capability for feature extraction with the analytical power of signal processing, offering a significant advancement for automatic rock type classification in remote sensing.