2021-09-06, 15:30–17:00, Succes Avenue (former Kleine veer zaal)
Software requirements: opengeohub/py-geo docker image (gdal, rasterio, eumap, scikit-learn)
Content:
Theoretical background for Ensemble ML and python implementations
General concepts and main advantages of spatiotemporal machine learning
Why use LandMapper?
Spacetime overlay to prepare the training samples
Spacetime cross-validation to evaluate the EML model performance
Hyperparameter optimization to tune the EML model
Fitting the final EML model
Generating spatial predictions using the fitted model
This speaker also appears in:
This speaker also appears in: