Skip to main content

Automated calibration of the InVEST urban cooling model with simulated annealing

Project description

PyPI version Documentation Status Build Status Coverage Status GitHub license

InVEST urban cooling model calibration


Automated calibration of the InVEST urban cooling model with simulated annealing

Citation: Bosch, M., Locatelli, M., Hamel, P., Remme, R. P., Chenal, J., and Joost, S. 2020. "A spatially-explicit approach to simulate urban heat islands in complex urban landscapes". Under review in Geoscientific Model Development. 10.5194/gmd-2020-174

See the user guide for more information, or the lausanne-heat-islands repository for an example use of this library in an academic article.


This library requires specific versions of the gdal and rtree libraries, which can easily be installed with conda as in:

$ conda install -c conda-forge 'gdal<3.0' rtree 'shapely<1.7.0'

Then, this library can be installed as in:

$ pip install invest-ucm-calibration

An alternative for the last step is to clone the repository and install it as in:

$ git clone
$ python install


  • Allow a sequence of LULC rasters (although this would require an explicit mapping of each LULC/evapotranspiration/temperature raster or station measurement to a specific date)
  • Test calibration based on cc_method='intensity'
  • Support spatio-temporal datasets with xarray to avoid passing many separate rasters (and map each raster to a date more consistently)
  • Read both station measurements and station locations as a single geo-data frame


  • The calibration procedure is based simulated annealing implementation of perrygeo/simanneal
  • With the support of the École Polytechnique Fédérale de Lausanne (EPFL)

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for invest-ucm-calibration, version 0.4.1
Filename, size File type Python version Upload date Hashes
Filename, size invest-ucm-calibration-0.4.1.tar.gz (27.4 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page