Review Reports - WireDepth: IoT-Enabled Multi-Sensor Depth Monitoring for Precision Subsoiling in Sugarcane

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The paper's title and introduction emphasize "multi-sensor fusion" as a core innovation. However, the results section primarily evaluates each sensor individually against the reference standard. It is not clearly stated how the data from these four sensors are ultimately fused into a single, best-estimate depth value for the operational system (e.g., a weighted average based on real-time sensor health, a Kalman filter fusing all inputs). The description of the system's output in the architecture and app (Fig. 6d) implies a single depth value is displayed. The methodology and results need to explicitly describe and validate this fusion algorithm, as it is critical to the system's claimed advantage over single-sensor approaches.

The use of both LoRaWAN and NB-IoT/LTE-M is a notable feature. However, the manuscript would benefit from a more detailed discussion on the practical trade-offs observed during field testing. For instance:

a. What was the typical/practical data transmission rate achieved via LoRaWAN in this agricultural setting, given the 115-byte payload limit?

b. Were there significant differences in power consumption between the two modes, and how was the system powered (e.g., tractor battery, separate battery)? This is a critical practical consideration for adoption.

c. The statement about JSON being "25% larger" is a general claim; it would be more impactful to state the actual payload sizes used and how this influenced the choice of CSV for LoRaWAN.

The discussion of why ultrasonic and laser sensors perform poorly at shallow depths (soil/debris interference) is excellent and very useful. This could be slightly expanded by briefly suggesting potential mitigation strategies (even if not implemented in this study), such as protective housings, automated cleaning mechanisms, or sensor placement optimizations, to guide future work.

Author Response

We sincerely thank the reviewer for their insightful comments and constructive criticisms, which have significantly helped us improve the quality of our manuscript. We have carefully considered all points raised and have revised the manuscript accordingly. Our point-by-point responses are detailed below and revisions are highlighted in the manuscript (green for Reviewer 1, yellow for Reviewer 2, and light blue for Reviewer 3).

Comment 1: *The paper's title and introduction emphasize "multi-sensor fusion" as a core innovation. However, the results section primarily evaluates each sensor individually against the reference standard. It is not clearly stated how the data from these four sensors are ultimately fused into a single, best-estimate depth value for the operational system (e.g., a weighted average based on real-time sensor health, a Kalman filter fusing all inputs). The description of the system's output in the architecture and app (Fig. 6d) implies a single depth value is displayed. The methodology and results need to explicitly describe and validate this fusion algorithm, as it is critical to the system's claimed advantage over single-sensor approaches.

Response: We thank the reviewer for this critical and insightful observation. The reviewer is correct that the initial manuscript did not sufficiently detail the final sensor fusion logic used for the operational system's output. In the current implementation, the system does not employ a real-time dynamic fusion of all four sensors for the primary depth value. Instead, based on the comprehensive accuracy analysis presented in the results, the system is configured to rely on the most accurate sensor for the final operational output.

In Section 2.1 (WireDepth System Architecture and Functionality): We have added a sentence stating: "For the operational output displayed to the user and used in cloud analytics, the system prioritizes the depth reading from the linear potentiometer due to its superior accuracy and robustness, as determined by the validation study presented in Section 3. Data from all other sensors are logged for redundancy and diagnostic analysis."
In Section 3 (Results and Discussion): We have added a paragraph in the discussion to explicitly state this operational logic and frame the multi-sensor aspect as a validation and redundancy feature, while also acknowledging the potential for adaptive fusion in future work: "The comparative analysis of individual sensor performance directly informed the operational logic of the WireDepth system. Given its demonstrated highest accuracy (MAPE = 0.84%) and no statistically significant deviation from reference measurements (p > 0.05), the depth value from the linear potentiometer was selected as the definitive output for real-time display on the user interface (Fig. 6d) and for generating the cloud-based analytics and 3D depth maps. This design choice ensured maximum reliability for the end-user during subsoiling operations. The integration of multiple sensors, while not fused into a single value in the current implementation, provides critical redundancy and a diagnostic capability to monitor sensor health. Furthermore, this multi-sensor framework establishes a foundation for future work, where adaptive fusion algorithms, such as a Kalman filter or a weighted average based on real-time confidence metrics for each sensor, could be deployed to further enhance robustness across all field conditions."

We believe these clarifications accurately represent the system's current capabilities while strengthening the manuscript's scientific rigor.

Comment 2: The use of both LoRaWAN and NB-IoT/LTE-M is a notable feature. However, the manuscript would benefit from a more detailed discussion on the practical trade-offs observed during field testing. For instance:

*a. What was the typical/practical data transmission rate achieved via LoRaWAN in this agricultural setting, given the 115-byte payload limit?*
b. Were there significant differences in power consumption between the two modes, and how was the system powered (e.g., tractor battery, separate battery)? This is a critical practical consideration for adoption.
c. The statement about JSON being "25% larger" is a general claim; it would be more impactful to state the actual payload sizes used and how this influenced the choice of CSV for LoRaWAN.

Response: We thank the reviewer for these excellent suggestions regarding the practical implementation of the communication systems. We have expanded the discussion in the manuscript to address these points directly.

Response to 2a: The practical data transmission rate for LoRaWAN is indeed constrained by regional regulations (duty cycle) and payload size. In our configuration (Spreading Factor 9, Bandwidth 125 kHz), the airtime for a single 115-byte packet is approximately 825 ms. Adhering to a 1% duty cycle in the 868 MHz EU band, this limits transmission to roughly one packet every 0.825 seconds. Our system was configured to transmit data every 30 seconds during active operation, which was well within this regulatory limit and provided a sufficient temporal resolution for depth mapping. This detail has been added to Section 2.2. We have added a sentence stating:

“The practical data transmission rate for LoRaWAN was constrained by regional duty cycle regulations and the payload size limit. In this configuration, the airtime for a single packet was calculated to be approximately 825 ms. Adhering to a 1% duty cycle, transmissions were configured at 30 s intervals during active operation to remain within regulatory limits while providing sufficient data resolution. To minimize airtime, the payload size was optimized. The JSON structure used for cellular transmission was measured to be 142 bytes, while the equivalent data encoded in the CSV format was reduced to 67 bytes. This constituted a payload size reduction of ap-proximately 53%, which was critical for the efficient use of the LoRaWAN bandwidth.”

Response to 2b: This is a crucial point for practical adoption. The system was powered directly from the bulldozer’s 24V battery via a robust DC-DC converter with over-voltage and reverse-polarity protection. Regarding power consumption, measurements confirmed a significant difference: the NB-IoT modem (SIM7000E) had an average current draw of ~120 mA during active transmission, while the LoRaWAN module (RFM95W) drew only ~45 mA. While connected to the tractor's battery, this difference was manageable. However, for potential future deployments requiring standalone battery power, LoRaWAN's lower power consumption would be a decisive advantage. This discussion on power sourcing and consumption has been incorporated into Section 2.1. We have added a sentence stating:

“The entire system was powered directly from the bulldozer's 24V battery via a pro-tected DC-DC converter. Power consumption measurements were performed for the two primary wide-area communication modules. The NB-IoT/LTE-M modem was found to have an average current draw of ~120 mA during transmission, whereas the LoRaWAN module drew ~45 mA, indicating a significantly lower power demand for long-range communication.”

Response to 2c: The reviewer is absolutely right. We have replaced the general claim with specific, measured data. Our JSON payload for a single data point averaged 142 bytes. The equivalent data, when encoded into the compact CSV string format as described, was reduced to 67 bytes. This represents a ~53% reduction in payload size, which is even more significant than the previously cited general figure. This substantial saving was critical for efficiently utilizing LoRaWAN's limited bandwidth and minimizing airtime. We have updated Section 2.2 with these actual payload sizes and the calculated reduction percentage. That 25% number was declared by reference [17].

Comment 3: The discussion of why ultrasonic and laser sensors perform poorly at shallow depths (soil/debris interference) is excellent and very useful. This could be slightly expanded by briefly suggesting potential mitigation strategies (even if not implemented in this study), such as protective housings, automated cleaning mechanisms, or sensor placement optimizations, to guide future work.

Response: We appreciate the reviewer's positive feedback on this analysis. We agree that suggesting mitigation strategies enhances the value of the discussion for future research. We have added a new sentence to the relevant paragraph in Section 3:

"While the performance degradation of optical and acoustic sensors under these conditions is a recognized challenge, several mitigation strategies could be explored in future work. These may include the implementation of passive protective housings designed to deflect soil debris, the integration of low-power automated cleaning mechanisms such as air blasts or wipers, or the optimization of sensor placement on the implement to minimize exposure to the direct flow of displaced material."

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The manuscript is within the scope of the journal. The English language is satisfactory, and the readers will understand the information presented. The organization of the manuscript is within scientific merit. The Figures are Tables are visible and understandable. The study presented information on WireDepth, an innovative cloud-connected monitoring system that leverages edge computing and IoT technologies for real-time, spatially aware analysis and visualization of subsoiling depth. Statistical metrics such as Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) were calculated to assess the system accuracy. To ensure quality papers are published, it is necessary that the Authors revise their work according to the following comments:

Objectives at the end of the Introduction should be stated clearly. For example, The objectives of the study were to (i).................(ii)...............and (iii).
Only 12 references were provided in the Introduction, and the list of references is 25. Provide more references in the Introduction to support the rationale of the study as well as in the 'Results and Discussion' in comparison with other works of authors. Ensure at least 30-40 references are provided.
The transmission work flow (Fig. 2) and all the codes under the section should be provided as a supplementary material. Renumber all the figures accordingly in the text.
All equations numbers should properly be aligned to the right.
Please, provide the measured data in a table with mean +/- standard deviation and % coefficient of variation. Ensure that the new table number leads to renumbering all the tables in the text accordingly.
The information in Line193, where the 'fields represent' should be presented in a Table, and renumber all tables accordingly.
Apart from the paired t-test and correlation analysis, please, provide the ANOVA analysis or a more rigorous statistical analysis to understand the significance of the measured data in relation to the predictors or independent factors.

Author Response

Response to Reviewer #2

We thank the reviewer for their thorough review and positive assessment of our manuscript. The constructive comments are highly appreciated and have been instrumental in improving the quality and rigor of our work. We have addressed each point as detailed below and revisions are highlighted in the manuscript (green for Reviewer 1, yellow for Reviewer 2, and light blue for Reviewer 3).

Comment 1: Objectives at the end of the Introduction should be stated clearly. For example, The objectives of the study were to (i).................(ii)...............and (iii).

Response: We agree with the reviewer that a clear statement of objectives enhances the focus of the manuscript. We have revised the final paragraph of the Introduction to explicitly list the study's objectives as follows:

“This study introduces WireDepth, a next-generation subsoiling monitoring system that builds on previous IoT- and edge-computing approaches while addressing their key limitations. The objectives of this study were to: (i) develop and describe the architecture of the WireDepth system, an IoT-enabled platform integrating multiple sensor modalities with edge computing for robust depth estimation under real field conditions; (ii) rigorously evaluate and compare the accuracy and reliability of ultrasonic, laser, inclinometer, and potentiometer sensors using statistical metrics and significance tests; and (iii) validate the overall system's performance, leveraging dual wireless connectivity (LoRaWAN and NB-IoT/LTE-M) for reliable data transmission and cloud-based analytics to deliver 3D depth maps, efficiency metrics, and decision-support tools via user-friendly web and mobile applications. Collectively, these innovations position WireDepth as a fully cloud-connected, IoT-enabled solution for real-time precision subsoiling management.”

Comment 2: Only 12 references were provided in the Introduction, and the list of references is 25. Provide more references in the Introduction to support the rationale of the study as well as in the 'Results and Discussion' in comparison with other works of authors. Ensure at least 30-40 references are provided.

Response: We thank the reviewer for this suggestion. We have expanded the literature review in the Introduction and results and discussion by adding 5 new references:

[5] Jia, H.; Guo, M.; Yu, H.; Li, Y.; Feng, X.; Zhao, J.; Qi, J. An adaptable tillage depth monitoring system for tillage machine. Biosyst. Eng. 2016, 151, 187–199.

[6] Hu, K.; Zhang, W.; Qi, B.; Ji, Y. Tillage depth dynamic monitoring and precise control system. Meas. Control 2025, 58(3), 394–403.

[7] Kim, Y.S.; Siddique, M.A.; Kim, W.S.; Kim, Y.J.; Lee, S.D.; Lee, D.K.; Hwang, S.J.; Nam, J.S.; Park, S.U.; Lim, R.G. DEM simula-tion for draft force prediction of moldboard plow according to the tillage depth in cohesive soil. Comput. Electron. Agric. 2021, 189, 106368

[24] Zhu, Y.; Cui, B.; Yu, Z.; Gao, Y.; Wei, X. Tillage Depth Detection and Control Based on Attitude Estimation and Online Cali-bration of Model Parameters. Agriculture 2024, 14(12), 2130.

[28] Lou, S.; He, J.; Lu, C.; Liu, P.; Li, H.; Zhang, Z. A tillage depth monitoring and control system for the independent adjustment of each subsoiling shovel. Actuators 2021, 10(10), 250.

Comment 4: All equations numbers should properly be aligned to the right.

Response: We apologize for this formatting oversight. The equation numbers throughout the manuscript (Eqs. 1-10) have now been properly aligned to the right-hand margin.

Comment 5: Please, provide the measured data in a table with mean +/- standard deviation and % coefficient of variation. Ensure that the new table number leads to renumbering all the tables in the text accordingly.

Response: We thank the reviewer for this suggestion. We have carefully considered the request to provide a table with mean ± standard deviation and coefficient of variation. However, after analysis, we determined that providing these descriptive statistics for the raw depth measurements would be misleading. This is because the experiment was deliberately conducted across a wide and non-uniform range of depths (from near-surface to over 70 cm) to evaluate sensor performance under varying conditions. Consequently, the overall mean, standard deviation, and CV of the raw data are dominated by this experimental design and do not reflect the consistency or accuracy of the sensors.

Instead, we believe that Table 2 (now renumbered as Table 3 in the revised manuscript), which presents the Root Mean Square Error (RMSE) for each sensor across three distinct depth ranges, provides a more rigorous and meaningful analysis of measurement variability. The RMSE effectively captures the standard deviation of the sensor errors (the difference between sensor reading and reference value) within each specific operational context. This allows for a direct comparison of sensor precision at shallow, intermediate, and deep tillage settings, which we feel is the most relevant metric for assessing system performance.

Comment 6: The information in Line193, where the 'fields represent' should be presented in a Table, and renumber all tables accordingly.

Response: We agree that a table is a more clear and professional format for this information. The description of the CSV string fields (previously in a figure) has been converted into a formal table. This is now presented as Table 1 in the revised manuscript. All subsequent tables have been renumbered as mentioned in the previous response.

Table 1: Data fields and descriptions for the multi-sensor depth measurement system.

Field	Description
YY,MM,DD,HH,MM,SS	Timestamp
Latitude	GPS latitude (°)
Longitude	GPS longitude (°)
Ultrasonic_depth_cm	Depth from ultrasonic sensor
TOF_depth_cm	Depth from laser TOF sensor
IMU_depth_cm	Depth from MPU6050 inclinometer
Potentiometer_depth_cm	Depth from linear potentiometer
Sensor_health	Status flags (ultrasonic, TOF, IMU, potentiometer, GPS)

Comment 7: Apart from the paired t-test and correlation analysis, please, provide the ANOVA analysis or a more rigorous statistical analysis to understand the significance of the measured data in relation to the predictors or independent factors.

Response: We thank the reviewer for this suggestion to enhance the statistical rigor. In addition to the paired t-tests and correlation analysis, we have now performed a one-way Analysis of Variance (ANOVA). This analysis was used to test for statistically significant differences in the mean measurement errors between the four different sensor types. The ANOVA results confirmed a highly significant effect of sensor type on measurement error (p < 0.001). We have added a sentence stating:

“A one-way Analysis of Variance (ANOVA) was conducted to determine if there were statistically significant differences in the mean absolute error between the four sensor types. The results indicated a highly significant effect of sensor type on measurement accuracy (F(3, 1196) = 452.15, p < 0.001), confirming that the overall performance was not equivalent across the different sensing technologies (Table 3).”

Table 3. Analysis of Variance (ANOVA) for the effect of sensor type on absolute measurement error (N=300 per sensor, Total N=1200).

Source of Variation	df	SS	MS	F-value	p-value
Between Sensors	3	18550.42	6183.47	452.15	Yes (p < 0.001)
Within Sensors (Error)	1196	16345.18	13.6
Total	1199	34895.60

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The manuscript studied WireDepth, an IoT-enabled, multi-sensor depth monitoring system designed for precision subsoiling in sugarcane cultivation. The system combined ultrasonic, laser, inclinometer, and potentiometer sensors with dual wireless connectivity and edge computing for real-time, spatially resolved depth measurement. Field experiments in Khuzestan, Iran validated system performance using 300 reference measurements. However, several important limitations should be addressed before the manuscript can be considered for publication:

1) Although the Introduction section presents a thorough review of existing sensor-based subsoiling studies, it primarily summarizes technical progress rather than pinpointing the specific scientific or practical gap that WireDepth aims to fill. The authors should explicitly clarify how this system advances beyond prior IoT-based or multi-sensor frameworks in terms of methodology, analytical novelty, or field applicability. Without this clarification, the stated motivation appears incremental rather than transformative, weakening the overall sense of innovation.

2) The visual quality and clarity of some figures (e.g., Figures 1 and 2) are suboptimal and should be enhanced for publication standards. Figure 9, which illustrates the core application and visualization output of the system, should be revised to highlight the most critical content and improve interpretability. Moreover, Figures 5 and 8 seem largely illustrative and may not substantially contribute to the analytical value of the paper; the authors should reconsider whether they are essential or could be moved to supplementary materials.

3) The manuscript references several HTTP code structures and data transmission formats. To improve transparency and reproducibility, these code examples and data structures should be provided in the supplementary materials or appendix rather than embedded within the main text.

4) Currently, the Results and Discussion are interwoven, leading to a descriptive rather than analytical narrative. The authors are encouraged to clearly separate these two sections and expand the Discussion to interpret the underlying physical, computational, and environmental mechanisms driving the observed differences among sensors. This section should also include a more explicit reflection on system limitations, such as sensor durability, data latency, calibration needs, and environmental interferences, and their implications for large-scale or long-term application.

Author Response

Response to Reviewer Comments

Response to Reviewer #3

We sincerely thank Reviewer #3 for their thorough and constructive feedback, which has been invaluable in helping us strengthen the manuscript. We have carefully considered all points raised and have revised the manuscript accordingly. Our point-by-point responses and the actions taken are detailed below and revisions are highlighted in the manuscript (green for Reviewer 1, yellow for Reviewer 2, and light blue for Reviewer 3).

Comment 1: Although the Introduction section presents a thorough review of existing sensor-based subsoiling studies, it primarily summarizes technical progress rather than pinpointing the specific scientific or practical gap that WireDepth aims to fill. The authors should explicitly clarify how this system advances beyond prior IoT-based or multi-sensor frameworks in terms of methodology, analytical novelty, or field applicability. Without this clarification, the stated motivation appears incremental rather than transformative, weakening the overall sense of innovation.

Response: We thank the reviewer for this critical observation. We agree that the initial manuscript could have more sharply defined the specific niche and novelty of our work. To address this, we have substantially revised the final paragraphs of the Introduction to explicitly articulate the research gap and our system's transformative contributions:

Comment 2: The visual quality and clarity of some figures (e.g., Figures 1 and 2) are suboptimal and should be enhanced for publication standards. Figure 9, which illustrates the core application and visualization output of the system, should be revised to highlight the most critical content and improve interpretability. Moreover, Figures 5 and 8 seem largely illustrative and may not substantially contribute to the analytical value of the paper; the authors should reconsider whether they are essential or could be moved to supplementary materials.

Response: We thank the reviewer for these specific suggestions regarding the figures. We have taken the following actions:

Figures 1 and 2 (System Architecture and Workflow): We have re-exported these figures at a significantly higher resolution and optimized their layout to enhance readability, even at a reduced size. We will ensure the final versions submitted for production adhere strictly to the journal's high-resolution figure guidelines. Furthermore, we will also provide these high-resolution versions as part of the Supplementary Materials for readers who wish to examine the system's architectural details in greater depth.

Figure 9 (Depth Visualization): This figure has been revised to be more focused. We have removed unnecessary map details and added clear annotations to guide the reader's interpretation of the spatial depth data and its interactive features.

Figures 5 and 8 (Placement of linear potentiometer and Sensor Obstruction):

Figure 5 (Placement of linear potentiometer): We believe this figure is essential for the replicability of the study. It provides a clear, visual reference for the critical mechanical integration of the identified best-performing sensor (the potentiometer) within the hydraulic system. This directly aids other researchers and engineers in reconstructing the experimental setup.

Figure 8 (Sensors obstructed by dust): This figure is not merely illustrative; it serves as primary visual evidence for a key experimental finding and discussion point; the vulnerability of non-contact optical and acoustic sensors to field conditions. Keeping this figure in the main text strengthens the argument about environmental limitations by providing immediate, tangible context for the performance degradation discussed in Sections 3.

Comment 3: The manuscript references several HTTP code structures and data transmission formats. To improve transparency and reproducibility, these code examples and data structures should be provided in the supplementary materials or appendix rather than embedded within the main text.

Response: This is an excellent suggestion. As requested, we have moved the JSON payload structure and the data parsing algorithm, to appendix A.

Comment 4: Currently, the Results and Discussion are interwoven, leading to a descriptive rather than analytical narrative. The authors are encouraged to clearly separate these two sections and expand the Discussion to interpret the underlying physical, computational, and environmental mechanisms driving the observed differences among sensors. This section should also include a more explicit reflection on system limitations, such as sensor durability, data latency, calibration needs, and environmental interferences, and their implications for large-scale or long-term application.

Response: We thank the reviewer for the valuable suggestion to enhance the analytical depth of our manuscript. While we recognize the merit of separating the Results and Discussion sections, we have intentionally retained them as a combined Results and Discussion section to maintain a coherent flow between the presentation of findings and their immediate interpretation. Given the highly interdependent nature of the experimental results and the underlying physical, computational, and environmental mechanisms governing sensor performance, separating these sections would disrupt the logical continuity of the analysis. Instead, we have substantially expanded and deepened the discussion to provide a more comprehensive interpretation of these mechanisms, as detailed below:

“This observation is supported by the findings of [24], where distance-based methods were reported to suffer from signal attenuation and physical obstruction in fields with high stubble, rendering them ineffective.”

“While the performance degradation of optical and acoustic sensors under these conditions is a recognized challenge, several mitigation strategies could be explored in future work. These may include the implementation of passive protective housings de-signed to deflect soil debris, the integration of low-power automated cleaning mechanisms such as air blasts or wipers, or the optimization of sensor placement on the implement to minimize exposure to the direct flow of displaced material.”

“[28] reported an average error of 8.28% for an ultrasonic sensor-based tillage depth monitoring system in straw-covered fields, highlighting the challenges of non-contact sensing in real agricultural conditions.”

“The comparative analysis of individual sensor performance directly informed the operational logic of the WireDepth system. Given its demonstrated highest accuracy (MAPE = 0.84%) and no statistically significant deviation from reference measurements (p > 0.05), the depth value from the linear potentiometer is selected as the definitive output for real-time display on the user interface and for generating the cloud-based analytics and 3D depth maps. This design choice ensures maximum reliability for the end-user during subsoiling operations. The integration of multiple sensors, while not fused into a single value in the current implementation, provides critical redundancy and a diagnostic capability to monitor sensor health. Furthermore, this multi-sensor framework establishes a foundation for future work, where adaptive fusion algorithms—such as a Kalman filter or a weighted average based on real-time confidence metrics for each sensor—could be deployed to further enhance robustness across all field conditions.”

“The comparative analysis reveals that sensor accuracy is fundamentally governed by its underlying physical principle and its interaction with the dynamic soil environment. The superior performance of the potentiometer and inclinometer can be attributed to their direct mechanical linkage to the subsoiler shank. They measure depth indirectly via displacement and angle, effectively decoupling their accuracy from surface conditions that plague non-contact sensors. This mechanical coupling makes them inherently robust against the environmental interferences of dust, debris, and humidity, which were significant factors for the ultrasonic and laser sensors. In contrast, the higher errors observed in ultrasonic and laser sensors are rooted in their time-of-flight principle. The ultrasonic sensor's acoustic waves and the laser's optical signals can be prematurely reflected by soil clods, straw, and dust clouds kicked up by the implement, leading to measured distances that are shorter than the actual ground distance. This effect was particularly pronounced at shallow depths (0-60 cm), where soil disturbance is most violent, as evidenced by the higher RMSE values in this range (Table 3). Furthermore, as visually confirmed in Figure 8, the accumulation of dust and moisture on sensor lenses creates a persistent source of error, attenuating signals and reducing signal-to-noise ratio over extended operation.”

“The choice of sensor dictates the computational load at the edge. While the potentiometer and inclinometer provide relatively stable signals, the raw data from the inertial measurement unit (MPU6050) required filtering to be usable. The implementation of a Kalman filter was crucial to mitigate noise induced by high-frequency vibrations from the tractor and subsoiler, fusing the noisy but fast-updating gyroscope data with the stable but slow-responding accelerometer data to produce a reliable tilt angle. This highlights a trade-off: contact sensors often provide a more stable signal with less re-quired processing, whereas maximizing the accuracy of more vulnerable sensors (like the IMU) or interpreting noisy signals (from ultrasonics/lasers) demands more sophisticated edge-computing algorithms.”

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The revised version has potential for publication consideration. However, Figures 1 and 2 does not provide better visibility. Therefore, I suggest they are moved to Appendix.

This should be corrected during the proofreading stage when the manuscript is accepted.

Author Response

Response to Reviewer 2

Comment 1: "The revised version has potential for publication consideration. However, Figures 1 and 2 does not provide better visibility. Therefore, I suggest they are moved to Appendix."

Response: We thank the reviewer for this constructive suggestion. To improve the flow and readability of the main text, we have moved Figures 1 and 2 to the newly created Appendix A, as recommended. The figures are now referenced as Figure A1 and Figure A2 in the main text (Sections 2.1 and 2.2, respectively). This change allows readers to focus on the core narrative while still having access to the detailed architectural and workflow diagrams for reference.

Reviewer 3 Report

Comments and Suggestions for Authors

1) The formatting of the cited references is incorrect. For example, in [8], [9], [10], etc., the author names should be included in the text rather than using only numerical citations.

2) The font size in Figure 2 is too small, making the text difficult to read.

3) The code titled “The fused sensor data is packaged into JSON structure for HTTP transmission:” should be moved to the Appendix.

Author Response

Response to Reviewer 3

Comment 1: "The formatting of the cited references is incorrect. For example, in [8], [9], [10], etc., the author names should be included in the text rather than using only numerical citations."

Response: We thank the reviewer for raising this point. The numerical citation style (e.g., [8], [9]) was intentionally used as it aligns with the standard formatting guidelines of this journal. We have confirmed this by cross-referencing with several recently published papers in the journal, which consistently employ the same numerical citation format. We have attached one such example for the editor's and reviewers' reference. Therefore, we have maintained this formatting to ensure consistency with the journal's style. We are, of course, prepared to reformat all citations to an author-date style if the editorial office deems it necessary for this specific article.
Yassine, H.A.K.; El Saleh, M.; Nakhal, B.E.; El Chakik, A. Centralized Two-Tiered Tree-Based

Intrusion-Detection System (C2T-IDS). IoT 2025, 6, 67.

Comment 2: "The font size in Figure 2 is too small, making the text difficult to read."

Response: We agree with the reviewer and apologize for the lack of clarity. We have now addressed this issue in two ways:

As per Reviewer 2's suggestion, the figure has been moved to Appendix A (Figure A2).
2. We increased font size.

Comment 3: "The code titled 'The fused sensor data is packaged into JSON structure for HTTP transmission:' should be moved to the Appendix."

Response: We thank the reviewer for this suggestion. We have moved the JSON code block and its accompanying explanation to the newly created Appendix B. This helps to improve the main Materials and Methods section (Section 2.2) while keeping the technical details available for interested readers.

Author Response File: Author Response.pdf