Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) for the Prediction of Quartz Grain Color from the Ivorian Onshore Basin

This study contributes to the digital transformation of geosciences by integrating artificial intelligence into sediment characterization, a field traditionally dominated by manual and visual techniques. Quartz grains collected from onshore drilling in the Ivorian basin were first subjected to granulometric analysis and then to morphoscopic study. The resulting photographs formed a novel database used to train two neural network models: the Multilayer Perceptron (MLP) and the Convolutional Neural Network (CNN). The main objective was to automatically predict quartz grain color, thereby reducing subjectivity and improving reproducibility in sedimentological analyses. Three categories were identified: translucent, oxidized, and transparent. These chromatic distinctions provide key insights into geological history, mineral composition, and depositional environments, allowing for more refined reconstructions of physico-chemical conditions during sediment transport and deposition. Performance evaluation confirmed the feasibility of applying AI to sediment analysis. While both models produced satisfactory results, the CNN consistently outperformed the MLP, demonstrating greater robustness and accuracy. This highlights the suitability of convolutional architectures for image-based geological tasks. By combining traditional petrographic methods with advanced computational techniques, this research demonstrates the potential of automated sediment characterization and underscores the relevance of digital approaches in modern sedimentology. It opens new perspectives for reproducibility and contributes to the ongoing digital transformation of geosciences.