Soil Quality Evaluation for Cotton Fields in Arid Region Based on Graph Convolution Network

Round 1

Reviewer 1 Report

The manuscript concerns the important issue of an accurate assessment of soil quality is a crucial prerequisite for enhancing soil management techniques and addressing soil pollution. However, traditional methods for evaluating soil quality are burdensome in terms of calculation, inefficient, and often lack precision, resulting in significant discrepancies in the assessment outcomes. This research aims to present a novel and precise approach to soil quality evaluation based on a graph convolution network (GCN). In this investigation, parameters such as soil organic matter (SOM), alkaline hydrolyzable nitrogen (AN), available potassium (AK), salinity, and heavy metals (iron (Fe), copper (Cu), manganese (Mn), and zinc (Zn)) were identified and assessed using the soil quality index (SQI). Subsequently, the introduction of the graph convolution network (GCN) into soil quality assessment enabled the creation of an assessment model, and its findings were compared to those obtained through SQI. Finally, the GCN model's assessment outcomes were visualized in terms of their spatial distribution. The findings indicated that soil salinity exhibited the highest variation coefficient (86%), followed by soil heavy metals (67%) and nutrients (30.3%). Remarks and comments: In the context of this study, it's important to understand why this particular approach is the most suitable for conducting the analysis. Furthermore, additional details should be provided regarding the reference selection, taking into consideration the following reference, eg. The Vital Roles of Parent Material in Driving Soil Substrates and Heavy Metals Availability in Arid Alkaline Regions: A Case Study from Egypt. Water 2023, 15, 2481. https://doi.org/10.3390/w15132481, Long-Term Impact of Wastewater Irrigation on Soil Pollution and Degradation. Water 2021, 13, 2245. https://doi.org/10.3390/w13162245 concerning the issue of the considerable amount of research has focused on the long-term monitoring of soil salinization, and the spatiotemporal evolution trend of soil salinization has become an emerging research topic. Are there specific actions that can be suggested, and to what extent can the results be applied to broader contexts? The conclusion needs to be clarified, with a stronger emphasis on the results. Additionally, it's important to outline potential directions for future research. Moreover, it is essential to underscore the distinctive contributions and originality of this paper. Examining the extra value of the research is crucial to emphasize its importance and uniqueness within the field.

Author Response

1. Remarks and comments: In the context of this study, it's important to understand why this particular approach is the most suitable for conducting the analysis.

Response: Thank you for your advice. The data of the complex soil has a complex nonlinear relationship. The GCN can clarify the nonlinear relationship between soil parameters, highlight the soil characteristics and information on the associated nodes in the soil data structure, and extract hidden and weak soil features. Therefore, the GCN can fully express the soil data structure. Besides, the calculation of the next layer of features of each node is only related to itself and its neighbor nodes in the GCN, so GCN is a kind of local structure connection. This effectively reduces the computational complexity, making this method simple and efficient. However, for the traditional method SQI, it is first necessary to calculate the weight of each index, then calculate the membership degree of each index, following by the addition by a formula to obtain the soil quality index. Therefore, SQI is more complicated and cumbersome. (Line 412-422 of revised manuscript)

2. Furthermore, additional details should be provided regarding the reference selection, taking into consideration the following reference, eg. The Vital Roles of Parent Material in Driving Soil Substrates and Heavy Metals Availability in Arid Alkaline Regions: A Case Study from Egypt. Water 2023, 15, 2481. https://doi.org/10.3390/w15132481, Long-Term Impact of Wastewater Irrigation on Soil Pollution and Degradation. Water 2021, 13, 2245. https://doi.org/10.3390/w13162245.

Response: Thank you for your advice. We have cited these two references in our manuscript. Please see line 428 and 430.

3. concerning the issue of the considerable amount of research has focused on the long-term monitoring of soil salinization, and the spatiotemporal evolution trend of soil salinization has become an emerging research topic. Are there specific actions that can be suggested, and to what extent can the results be applied to broader contexts?

Response: Thank you for your interest in this critical issue. In this study, the soil quality evaluation problem is transformed into a nonlinear problem by GCN method. The GCN method extracts the irregular features of the graphical data, effectively reduces the model error, and improves the objectivity and accuracy of the evaluation results. In our future research, more indicators will be added, such as soil physical indicators (soil bulk density, soil moisture, etc.), soil biological indicators (catalase, protease, biodiversity, etc.), remote sensing data (band, vegetation index), and environmental covariates (rainfall, altitude, slope, temperature), to improve the accuracy of soil quality evaluation, explore the contribution of different variables to soil quality evaluation, and identify the main variables affecting soil quality. The GCN method is a comprehensive evaluation index, which can be tried to be applied to the evaluation of water pollution and vegetation growth in the future, to verify the evaluation effect of this method in the evaluation of water pollution and vegetation growth, and explore the versatility of the GCN method. For example, PH, heavy metals, organophosphorus, sulfide, and other indicators can be used to construct a comprehensive water pollution evaluation index based on GCN; Leaf area, biomass, yield, plant height, and other indicators can be used to construct a comprehensive vegetation growth evaluation index based on GCN. (Line 441-445 and 474-490 of revised manuscript).

4. The conclusion needs to be clarified, with a stronger emphasis on the results.

Response: Thank you for your advice. We have added the following content in the conclusion. Please see lines 448-462.

In the study area, the soil salinity was evaluated at grade V (average value: 5.25 g/kg), the SOM and AN contents were evaluated at grade IV (average value: 18.59 mg/kg and 72.86 mg/kg, respectively), and the AK content was evaluated at grade II (average value: 188.78 mg/kg). Soil heavy metal content was generally high. The coefficients of variation of the evaluation indices were 20% ~ 86%, i.e., there was a large variation, among which soil salinity variation was the largest (86%) and SOM variation was the smallest (20%). From the perspective of spatial distribution, soil salinity gradually increased from west to east, while soil nutrient content gradually decreased. Fe content was high in the northern region and low in the western and central regions. Soil samples with higher Cu, Mn, and Zn content were mainly distributed in the central region. Therefore, the spatial distribution of soil heavy metals were similar. Besides, there was a positive correlation between soil salinity and SOM, AN, and heavy metals (p < 0.01) as well as between Cu and Zn (p < 0.01). Based on the spatial distribution and correlation analysis results, it was concluded that there was a high homology between soil salinity and heavy metals as well as between heavy metals.

5. Additionally, it's important to outline potential directions for future research.

Response: Thank you for your advice. We have added the following content in the conclusion. Please see lines 474-490.

In this study, the GCN model was used to evaluate soil salinity/heavy metals, soil nutrients, and soil quality. These indicators are limited. Therefore, in our future studies, more indicators will be added, such as soil physical indicators (soil bulk density, soil moisture, etc.), soil biological indicators (catalase, protease, biodiversity, etc.), remote sensing data (band, vegetation index), and environmental covariates (rainfall, altitude, slope, temperature), to improve the accuracy of soil quality evaluation, explore the contribution of different variables to soil quality evaluation, and determine the main variables affecting soil quality in this area. In addition, this method is a comprehensive evaluation index, which can be tried to be applied to water pollution and vegetation growth in the future. For example, pH, heavy metals, organophosphorus, sulfide, and other indicators can be used to construct a comprehensive water pollution evaluation index based on GCN; Leaf area, biomass, yield, plant height, and other indicators can be used to construct a comprehensive vegetation growth evaluation index based on GCN, to verify the performance of GCN method in the evaluation of water pollution and vegetation growth, and explore the versatility of the GCN method. Finally, the GCN model constructed in this study has limitations in network depth. We will increase the network depth in the future or optimize GCN through other networks to improve the stability and versatility of the GCN model.

6. Moreover, it is essential to underscore the distinctive contributions and originality of this paper. Examining the extra value of the research is crucial to emphasize its importance and uniqueness within the field.

Response: Thank you for your advice. We have added the following content in the manuscript. Please see lines 83-95.

By constructing a comprehensive soil quality evaluation model for cotton fields in arid areas through GCN method, the soil quality evaluation problem was transformed into a nonlinear problem. This effectively reduced the model error, and made the operation convenient, simply, and efficient. This study provides a new method for soil quality evaluation and improves the accuracy and efficiency of soil quality evaluation. It can provide data for farmland management in arid areas, and help farmers formulate appropriate fertilization strategy to improve crop yield. Besides, accurate and efficient soil quality evaluation results can show soil pollution status in time, helping reduce the risk of land degradation and protect the environment.

Author Response File: Author Response.docx

Reviewer 2 Report

Well written article and find very minor mistakes that are given below for corrections.

1. Table 3 is almost similar to Table 1 and 2. Not able to understand the need of table 3. 

2. Typographical errors mainly the parameter 'organic matter' is mentioned as 'organ matter' which needs to be corrected throughout the manuscript 

Author Response

Comments and Suggestions for Authors

Well written article and find very minor mistakes that are given below for corrections.

1. Table 3 is almost similar to Table 1 and 2. Not able to understand the need of table 3. 

Response: Thank you for your advice. According to the Grading Standards of China's Second National Soil Census, soils can be classified into four grades by soil nutrients, and five grades by soil heavy metals and salinity. Because the soil quality evaluation in this paper was a synthesis of three categories (soil nutrients, soil heavy metals, soil salinity), to maintain the consistency of the grading standards in modeling, the grades of soil nutrients (Table 1), soil heavy metals and soil salinity (Table 2) were re-divided into five grades (Table 3). Otherwise, the model outputs were individual grades of soil nutrients, soil heavy metals, and soil salinity. This did not meet the requirement of comprehensive evaluation.

2. Typographical errors mainly the parameter 'organic matter' is mentioned as 'organ matter' which needs to be corrected throughout the manuscript.

Response: Thank you for your interest in this critical issue. We have corrected them in the manuscript.

 

Author Response File: Author Response.docx

Reviewer 3 Report

Overall Assessment:

 

The paper presents a clear and concise overview of the study's objectives, methodology, and key findings. It successfully conveys the significance of accurate soil quality evaluation in soil management and pollution remediation, which provides a strong motivation for the research. The use of GCN, a cutting-edge technology in machine learning, for soil quality evaluation is intriguing and addresses the mentioned limitations of traditional methods.

 

Strengths:

Clear Objectives: The Introduction outlines the specific objectives of the study, providing a clear sense of purpose and direction for the research.

Relevance: The study's relevance to soil management and pollution remediation is well-established, making it valuable for environmental and agricultural applications.

Methodology Description: It briefly describes the steps involved in the study, from data collection to model application, providing a clear roadmap for readers.

Key Findings: The abstract presents essential findings regarding soil quality, salinity, heavy metals, and nutrients, which adds substance to the study's claims.

Evaluation Accuracy: Highlighting the accuracy of the GCN model's evaluation results provides evidence of its potential as an effective tool for soil quality assessment.

I find this paper novel and should be accepted for publication in your journal.

Author Response

Comments and Suggestions for Authors Overall Assessment:

 The paper presents a clear and concise overview of the study's objectives, methodology, and key findings. It successfully conveys the significance of accurate soil quality evaluation in soil management and pollution remediation, which provides a strong motivation for the research. The use of GCN, a cutting-edge technology in machine learning, for soil quality evaluation is intriguing and addresses the mentioned limitations of traditional methods.

 Strengths:

Clear Objectives: The Introduction outlines the specific objectives of the study, providing a clear sense of purpose and direction for the research.

Relevance: The study's relevance to soil management and pollution remediation is well-established, making it valuable for environmental and agricultural applications.

Methodology Description: It briefly describes the steps involved in the study, from data collection to model application, providing a clear roadmap for readers.

Key Findings: The abstract presents essential findings regarding soil quality, salinity, heavy metals, and nutrients, which adds substance to the study's claims.

Evaluation Accuracy: Highlighting the accuracy of the GCN model's evaluation results provides evidence of its potential as an effective tool for soil quality assessment.

Response: Many thanks for your comments.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Accept in the present form.