CatBoost-Optimized Hyperspectral Modeling for Accurate Prediction of Wood Dyeing Formulations
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThis manuscript presents a technically sound and practically valuable study on CatBoost-based hyperspectral modeling for wood dyeing formulation. The multi-scale validation (HSI + SEM) and performance comparison are strong points. For improvement, we recommend clarifying the broader applicability, enhancing the interpretability discussion, and expanding performance evaluation. With these additions, the paper will be of high relevance to both forestry and intelligent manufacturing communities.
Comments for author File: 
Comments.pdf
Author Response
Dear Reviewer,
We sincerely appreciate the time and effort you invested in reviewing our manuscript. In response to your thoughtful and constructive comments, we have carefully prepared a point-by-point response and attached it as an attachment.
Thank you again for your valuable feedback, which helps improve the quality of our work.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThis work presents a modeling approach for accurately predicting wood dyeing formulations. The proposed model outperforms several conventional methods, owing to its use of an ordered boosting strategy. The framework also shows strong potential for extension to other wood species, dye systems, and processing conditions, thereby contributing to the advancement of real-time intelligent control in wood processing utilizations. This work aligns well with the scope of the Forests, particularly in the areas of wood properties and forest engineering. Thus, it is likely to attract broad interest from our readership. However, several improvements in data presentation, result visualization, and analytical methodology are necessary before this work can be recommended for publication in Forests.
(1) The authors selected three spectral bands as key sensitive features for dye concentration prediction and evaluated their corresponding importance scores. However, the methodology for calculating these scores, as well as their physical significance, is not clearly described. Please provide an explanation of the calculation process and clarify the relevance of these importance scores within the context of the model.
(2) The authors divided the hyperspectral reflectance data (400-700 nm) into three sensitive bands: 400-450 nm, 550-600 nm, and 600-650 nm. However, the wavelength range of 650-700 nm was not included. Please clarify the rationale for excluding this spectral region and explain why it can be considered negligible in the context of the study.
(3) Please revise Figure 4 to improve its overall quality. The current image resolution is too low, resulting in a blurry appearance. Additionally, the font size within the figure is too small to read clearly. It is also recommended to adjust the placement of the label “spectral reflectance,” as it currently overlaps with the rectangular frame, affecting visual clarity.
(4) Please revise Figure 7 by labeling the subfigures with (a), (b), (c), and (d) to enhance clarity and improve readability.
(5) Please ensure consistency in the number of decimal places between the text and the tables. For example, line 498 reports the importance scores as 0.364, 0.290, and 0.209, whereas Table 2 presents them as 0.364421, 0.290315, and 0.209364. This suggestion also applies to other tables throughout the manuscript.
(6) Please ensure consistent formatting throughout the manuscript. For example, in line 453, spaces should be added before and after equal signs to maintain proper typographic standards.
Author Response
Dear Reviewer,
We sincerely appreciate the time and effort you invested in reviewing our manuscript. In response to your thoughtful and constructive comments, we have carefully prepared a point-by-point response and attached it as an attachment.
Thank you again for your valuable feedback, which helps improve the quality of our work.
Author Response File: Author Response.pdf
