Publication details




Year of publication 2022
MU Faculty or unit

Faculty of Science

Description A program that assigns rhythmic profiles to individual grid cells. In total, the program predicts four variants of chronotopes distribution. Uniquely, it performs an initial data load from the datasets, merges the different data sources according to a unique cell identifier, filters the cells, splits them into training and validation sets, and also performs a final export of the cell geographies and their assigned rhythmic profiles to a vector dataset. After the cell filtering step, a section is performed to compute the chronotope type for each cell for all four variants in several steps. The first step is to select the best model type - a cross-validation method over the training dataset is used. Once the final model type is selected, the model is trained over the entire training set and its accuracy is evaluated using the validation set.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info