Code and supplementary materials for the research paper titled 'Advancing Geological Image Segmentation: Deep Learning Approaches for Rock Type Identification and Classification', published in Applied Computing and Geosciences (Elsevier).

Rock & mineral identification from hand-specimen photos using multimodal RAG — a MATLAB app fusing CNN features, colour histograms, and vision-LLM reasoning via Ollama (local or cloud). Open class inventory: add new rock types without retraining.

A Decision Tree model to classify igneous rocks (Basalt, Andesite, Rhyolite) using SiO₂, FeO, and Al₂O₃ geochemical data from EarthChem.

Rock Classifier AI: A production-grade geological identification system using PyTorch and AWS. Features an 18-class CNN model (EfficientNet-B0) deployed via SageMaker Serverless and Lambda, with real-time Android and Web interfaces.

Detecting the difference between a rock or a mine based on the response of the 60 separate sonar frequencies using Knn classifier