Answers are grounded in this paper and cite their sources.
Mineral exploration using hyperspectral data that has high spectral resolution across visible and shortwave infrared wavelengths become an advanced method for recognizing potential mineral-rich zones. This study introduces a novel deep-learning model for identifying rocks that have associated with iron (banded iron formation) and chromite minerals in the Sittampundi region of Tamil Nadu state, India by using airborne visible infrared spectrometer (AVIRIS-NG) air borne hyperspectral data. Initially, the AVIRIS-NG reflectance data are employed by squeeze net architecture to produce clean denoised output data. Subsequently, the denoised image is processed by a chaotic Chebyshev artificial hummingbird optimization algorithm-based bidirectional gated recurrent unit, an optimized deep learning technique used to generate compressed data. The compressed data are analyzed using a dense attentional net model, which reconstructs the data through a reverse dual-level prediction operation. Building on these techniques, a hybrid deep learning model, an optimized bidirectional gated attention enclosed convolutional transformer, is used to identify different kinds of rocks having different minerals. Here, the multiverse optimizer is used to tune the hyperparameters. Finally, the results are explored in two different ways to compare the designed model. First, the hyperspectral data are directly fed to the mineral classification model and the performance is analyzed accordingly. Second, the hyperspectral data undergo different phases like denoising, compression, reconstruction and identification of rocks with the help of the proposed techniques are examined for evaluation. The proposed model accurately identified the rocks of the Sittampundi region with an accuracy of about 98.51% and a specificity of 99.1%.
No takes yet. Share an insight, caveat, or question.
Mohan et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: