This study develops a deep-learning (DL) based Python package-SHAFTS to extract 3D building information (average building height and footprint) from publicly available satellite imagery. Compared to conventional machine learning-based models and single-task DL models, the proposed multi-task DL models can effectively improve the prediction accuracy. This study involves the fusion of multi-source input data and many machine learning and deep learning models, which undoubtedly requires huge and solid work from the authors. Although I am not the expert in computer science, the evaluation framework presented in Section 3 is scientifically sound from my perspective – very quantitative from patch-level to city level. And I will consider using the developed package in the future. I only have the following minor comments.  

Minor comments:

1. Line 368, the caption of Figure 4, need to denote the source of reference values when calculating RMSE, MAE, etc.

2. Figure 5, is the density of scatter points normalized to [10^-4, 1] instead of [10^-3, 1]?

3. Line 385, this paragraph shall better describe the stratified error, which is helpful to the readers who are not familiar with it.

4. Line 404-405, “Both SVR and DL models show relatively unfavourable RMSE and NMAD for the low-value domain but DL models behave slightly better.” What does it mean? I think the RMSE and NMAD are both smaller in the low-value domain (Fig. 8).

5. Line 463, what is contextual information?

6. 12 and 13, why the feature patterns of STDL and MTDL have large differences?

7. Line 509, I think STDL model gives better predictions than others from Fig. 15?

This study develops a deep-learning-based (DL) Python package–SHAFTS to extract average building height and footprint proportion at a pixelated level. I briefly read the paper, and think it is well-written and solid. I, therefore, believe it deserves publication.