LCZ Generator

Welcome to the LCZ Generator!

Fast and easy Local Climate Zone mapping

Version 2.5.0 was released!

With version 2.5.0 of the LCZ-Generator a change was made to the way the test-train split works.

Previously, a simpler approach was taken, splitting the entire Training Area (TA) dataset randomly into 70% training data and 30% test data. This was done 25 times, each time shuffling the dataset. The split was achieved by creating a uniform distribution between 0 and 1, assigning a number to each polygon, and finally only selecting numbers ≤ 0.7. While in the best case all LCZ-classes should have a similar number of TA, this is not always the case, making it necessary to stratify each split by the LCZ-class.

This improvement was implemented in version 2.5.0, utilizing the train_test_split function from the scikit-learn package and performing the split offline. During this process, a set of new columns, named after the random seed used during the split, is added. One column for each bootstrap that will be performed is added, resulting in a new file structure with 25 columns, each marking test data as 0 and train data as 1.

Impact Assessment

A detailed impact assessment of the change was carried out and can be found on GitHub.

Getting started: ¶

Read Demuzere et al. (2021) it serves as the primary user guide

Download the Training Area Template kml file

Create your Training Areas following the guidelines

Once finished, use the submission form to submit your file.

Fill out the fields in the submission form; fields with an asterisk (*) are required.

Show detailed information

Fill out the first section containing your personal information
Select the continent and country of your Training Areas and fill out the city name
Select the kml Training Area file for upload
Select the date for which the Training Areas are representative / the aerial image was taken which was used for digitizing.
You may also provide a DOI or similar reference if the Training Area dataset is published in a (peer-reviewed) paper
You may add co-authors or other relevant information to the remarks field
Finally you can decide whether your name should be displayed in the results, including a suggestion how to cite your Training Area dataset. Otherwise it is left blank.

Submit the form. If you see a green box appear on the top of the page after clicking the submit button, your submission was successful and will be processed. If a red box appears, there was a problem with your Training Area file. Check out the FAQ for more information.

You will be notified via email once the processing has finished. Depending on the current load of the system it should take ~20 minutes.

After you received the email, your submission is also available in the submission table.

Please cite the tool using:¶

Demuzere, M., Kittner, J., Bechtel, B. (2021). LCZ Generator: a web application to create Local Climate Zone maps. Frontiers in Environmental Science 9:637455. https://doi.org/10.3389/fenvs.2021.637455