Cost-Effective Aerial Inventory of Spruce Seedlings Using Consumer Drones and Deep Learning Techniques with Two-Stage UAV Flight Patterns
Round 1
Reviewer 1 Report
This paper uses consumer drones and CNN method to detect and identify missing seedlings, the research is interesting and useful. The logic of this paper is reasonable and the structure is complete. There are some shortcomings need to be corrected, one, the paper lacks a technical roadmap; Two, Many illustrations(Fig. 1,2,3,4,5,7,8) are unclear and difficult to convey the corresponding information; Three, the discussion section should focus on two-stage UAV flight and CNN algorithm effect, which need to add chart analysis.
Minor editing of English language.
Author Response
Please see the attachment
Author Response File: 
Author Response.docx
Reviewer 2 Report
This study aims to develop a cost-effective solution for accurate inventory of spruce seedlings in Finland using consumer grade drones and deep-learning techniques. Overall, the paper is well organized, presenting the methods, results, and analysis clearly. It is an interesting application of both consumer grade drones and deep learning algorithms.
1. Line 175-178: due to varying formats of dates in different countries, it might be better to use the names of the months instead of numbers to avoid confusion.
2. Line 182-183: what were the criteria for selecting plot locations?
3. It is mentioned in the paper that both planted and naturally generated seedlings are accounted for in the study. Have you tried separating the two types of seedlings and assessing the detection accuracy in each type? It might be interesting to see whether the performance of the deep learning algorithm is different.
4. Figure 7 and 8: are they showing the entire study area, or only part of it? Please provide more detailed descriptions for the figures.
Some minor editing is recommended for correcting grammar and spelling.
Author Response
Please see the attachment.
