Dataset for the Global Prediction Of Total Organic Carbon In Marine Sediments Using Deep Neural Networks (nn-toc)

The data folder contains the raw features and labels used for training machine learning models to predict total organic carbon in marine sediments. The data folder has three subfolders: raw : contains the labels, features and other data used to train the machine learnign models interim : transformed data, which has to be reproduced output : output from the models, used for analysis and visualisation The data folder has to be integrated in the Git repository nn-toc, to execute the code. Please refer to the latest version at: https://zenodo.org/records/17591552