I am very familiar with the WOFOST model and the dataset used by the author. It is not a good simulation project, not only because the simulation accuracy did not meet industry standards, but also because the author withheld many critical details and settings of the WOFOST in the manuscript, which makes it difficult for me to assess the rationality and scientific validity of the simulation. Earth System Science Data, as the name suggests, focuses on the application of datasets, but the author's professionalism in describing and processing the dataset is not good. Moreover, the description of CRU is severely inadequate. After reading the entire manuscript, I still do not understand the role of the CRU used by the author in this study.

1. The study spanned from 2019 to 2023, but the sampling data was only from 2022 and 2023 (Fig.1). The author should explain this issue in the text.
2. The soil data should be described in more detail, for example, which soil parameters were used in this study.
3. The author used statistical data from 1980 to 2022, but the study's time scale is from 2019 to 2023. This is confusing for the readers. Please provide an explanation.
4. The technology roadmap that needs improvement. 1) The author mentioned agro-management data in Figure 2, but it is not mentioned in Section 2.2 Data collections. 2) The sampling data mentioned in the Data collections section is not reflected in the figures, as well as meteorological data from National Meteorological Information Center. 3) The method of combining remote sensing data and model output through GRU is described too simplistically. 4) The author allocates a large proportion of the figures to how WOFOST conducts simulations, but this is not the focus of this study. The focus of this study should be on how to use models and remote sensing coupled for yield estimation, just as the author introduces in the research objective: "Designing a hybrid model coupling crop growth model and deep learning model for soybean yield estimation." The technology roadmap should more detailed display the research focus.

1. Which sub-model of PCSE did the author use? LINTUL3 or Wofost72_PP?
2. As far as I know, VAP is not included in the ERA5 dataset. How did the author obtain the VAP data?
3. Line 209-215: The description of the calculation process for soil parameters is too simplistic; a detailed calculation process should be provided. For example, which parameters from the Chinese soil database were used in the study, and what theories/formulas were utilized to calculate the SMW, SMFCF, SM0, and K0 required by the WOFOST model? Is Table 2 a lookup table? Where did it come from?
4. Line 215: The description of Table 3 is redundant. It suffices to directly list the values and sources of the WOFOST crop parameters. Table 4 should list all crop parameters in WOFOST, not just the main crop parameters.
5. Line 235: What’s the setting of the fertilizer application rate and timing in the WOFOST?
6. Line 244: After reading Section 3.2 Development of the Grated Recurrent Unit model (GRU), I am still unclear about the role of GRU in this study. The author's explanation of the principles of GRU is unclear. It does not directly describe how GRU combines the output of the WOFOST model with remote sensing data, as shown in the technical roadmap. Figure 3 lacks self-explanatory power, leaving it unclear what exactly the inputs and outputs of the GRU are.
7. Why is MODIS data mentioned again in Line 315? MODIS data was not mentioned in the data collection section.
8. As shown in Figures 6, 7, and A2, the model simulation accuracy is below industry standards.
9. By the way, Line 240:” 3.1.2 Multi-scenarios crop simulations”, author said:” The four different types of model parameters were arranged and combined to generate various simulation scenarios”. Where could I read the scenario settings and the results of this part in the manuscript?

The overall structure of the article is clear and logically organized. The research demonstrates innovation by integrating crop growth models with deep learning algorithms for soybean yield estimation, representing a promising direction in agricultural remote sensing. The research objectives are well-defined, aiming to address existing limitations in soybean yield data (insufficient spatial resolution and reliance on ground observations), thereby supporting optimized soybean production distribution and agricultural decision-making.

Specific Comments:

1 Introduction: The section comprehensively highlights soybean's global food security significance and limitations of current yield estimation methods, establishing a solid research rationale. However, the comparative discussion of data-driven and knowledge-driven methods could be more concise to better emphasize core issues and proposed solutions. Additionally, enhancing explanations of environmental factors' mechanisms (e.g., how climatic conditions affect growth cycles and photosynthesis, or how soil properties constrain nutrient uptake and water retention) would provide a more systematic understanding of key yield determinants and their interactions.

2 Data Collection: The dataset (field measurements, meteorological/soil data, satellite imagery, crop distribution maps, and statistics) is comprehensive and representative. However, data processing steps (e.g., meteorological data interpolation, satellite image preprocessing) require more detailed technical descriptions to improve reproducibility. Furthermore, explicit clarification is needed regarding spatial alignment and scale conversion methods employed for integrating multi-resolution datasets.

3 Results: Results are effectively visualized through figures/tables demonstrating WOFOST model simulations, multi-scale estimation accuracy, and spatial yield patterns. The analysis appropriately discusses model accuracy, stability, and spatiotemporal pattern recognition capabilities. However, deeper interpretation of anomalies (e.g., regional/yearly estimation errors) is needed. Notably, the systematic overestimation in field-scale validation suggests potential model biases (e.g., systematic errors or overfitting), warranting further investigation.

4 Discussion: When discussing MODIS-Sentinel-2 complementarity, quantitative comparisons of their performance under varying conditions (weather/vegetation coverage) would strengthen data selection guidance. Future research directions could be expanded by aligning with emerging trends (e.g., integration with IoT/blockchain technologies, precision agriculture applications), thereby enhancing both theoretical depth and practical relevance for agricultural challenges.

This study presents a well-structured and logically organized framework for high-resolution soybean yield estimation. The combination of process-based modeling with deep learning offers a novel perspective for enhancing agricultural monitoring capabilities. The objectives are clearly articulated, with a strong focus on improving soybean yield data accuracy to support agricultural decision-making and production optimization. The methodological approach is rigorous, leveraging diverse production scenarios to train the GRU model and applying time-series Sentinel-2 data for large-scale yield estimation. The evaluation using in-situ measurements and government statistical data provides strong validation, and the reported accuracy metrics indicate reliable model performance across spatial and temporal scales. There are some suggestions as follows, which can be considered for further improvement of the manuscript.

The research is well-founded and presents significant innovations. However, the abstract and introduction sections could benefit from more professional and polished language to enhance readability and better highlight the study’s contributions. Refining the writing style would improve clarity, strengthen the articulation of the research objectives, and more effectively emphasize the novelty of the proposed hybrid framework.

Figure 1: where is the soybean classification map from? What is the accuracy?

Figure 5 appears blurry, which affects the clarity and readability of the presented data. I suggest organizing box plots and histograms as subfigures.

The discussion on the advancements of the proposed method is embedded within the “Limitations and future developments” section. To better highlight the strengths of this study, I recommend extracting this content into a standalone subsection. This would allow for a clearer and more structured presentation of the method’s advantages, making it easier for readers to appreciate its contributions in comparison to existing approaches.

The conclusion effectively summarizes the study but could be further refined to better highlight the innovation in dataset construction and its practical applications in agricultural management.