Q2. How many sites could be clearly assigned to specific LCZ classes?
Approximately 50 sites could be clearly assigned to specific LCZ classes that are present in the Augsburg region (LCZs 2, 5, 6, 8, A, B, D).
Q3. What is the LCZ methodology used in the case of Tandil city, Argentina?
Preparing urban climate maps using the LCZ methodology for improving communication with urban planners: the case of Tandil city, Argentina.
Q4. What is the reference for Europe?
A good reference for Europe is the EEA (European Environment Agency) soil sealing data set, which is freely available at a 20 m and 100 m resolution.
Q5. What were the quality measures used to evaluate the LCZ maps?
The consistency and accuracy measures used to evaluate the quality indicated that both the quality of the TA data sets and the resulting LCZ maps were poor to moderate.
Q6. What was the main approach used to train the classifiers?
Finally, a combination of the co‐training approach with other classifiers, such as a support vector machine (SVM), was used to further enhance the final classification accuracy.
Q7. What is the impact of the operators on the classification accuracy?
The impact of the operators on the classification accuracy was found to be considerable based on experiences from the HUMINEX, which stresses the necessity of strict quality assessment and review.
Q8. What is the process of releasing a LCZ map?
Before the LCZ maps are released to the wider community via the WUDAPT portal, they must undergo quality assessment and are then published with metadata related to the quality achieved.
Q9. How many TA sets should be used for a city?
From these results, the HUMINEX concludes that at least ten individual TA sets from untrained operators should be used for one city to produce an LCZ map of good quality, although this aspect needs further investigation (Bechtel et al., 2017b).
Q10. What is the advantage of using online processing platforms?
Such online processing platforms can also facilitate implementation of the online cross‐ validation bootstrapping procedure (see section 3.1), and provide the ability to scale‐up from single cities over countries to continents.
Q11. Where are the LCZ maps and metadata made available?
The LCZ maps and metadata are made accessible via the the WUDAPT portal (https://wudapt.cs.purdue.edu/), where several additional tools are available.
Q12. What is the way to evaluate LCZ maps?
For example, the LCZ maps might be resampled to a coarser resolution for input into global atmospheric models and be less sensitive to accuracy at the 100 m resolution.
Q13. What are the main components of the LCZ quality assessment procedure?
In particular the bootstrapping cross‐validation and the review were described, which are currently part of the standard LCZ quality assessment procedure.