Rapid humus soil quality evaluation and grading method based on image recognition and penetration type TDR (time domain reflectometry)

Abstract

The invention discloses a humus soil quality rapid evaluation and grading method based on image recognition and a penetration type TDR (time domain reflectometry). The method comprises the following steps: photographing humus soil in a field detection area by adopting a camera, carrying out image recognition processing to obtain quality parameters such as the mass ratio and the moisture content of the humus soil, obtaining a conductivity measurement value according to the quality parameter processing, and inserting a penetration type TDR probe into the humus soil to measure the conductivity measurement value. Comparing and judging whether the humus soil is consistent or not so as to adjust the field detection area, and evaluating and grading the humus soil quality in combination with the quality parameters. According to the method, a method of combining image recognition and penetration type TDR is adopted, efficient recognition and detection of humus soil key quality indexes are achieved, the time needed by traditional processing is effectively shortened, the detection efficiency is improved, and the detection cost is reduced; high automation and field adaptability are achieved, efficient detection can be carried out in a complex and changeable landfill environment, and the management efficiency and safety of engineering field disposal are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of humus soil quality assessment and grading, and in particular to a method for rapid assessment and grading of humus soil quality based on image recognition and penetrating TDR. Background Art

[0002] Humus soil refers to the soil-like material formed during the long-term degradation of municipal solid waste in landfills. It accounts for the largest proportion of landfill waste degradation products and, after processing, can be widely used in landscaping, ecological restoration, and other fields. The resource utilization of humus soil is key to improving the reuse of landfill waste. However, its disposal and resource utilization still face numerous challenges. First, humus soil has a high moisture content and poor screening efficiency. It is mixed with inorganic aggregates such as bricks and gravel, heavy impurities such as ceramics and metals, and lightweight impurities such as rubber and plastics, resulting in increased stockpiles and significant land use. Furthermore, excessive heavy metal levels are common in humus soil, making it difficult to directly utilize as a resource. Therefore, before humus soil can be utilized as a resource, its physical composition and properties, along with key quality indicators, must be tested to ensure landfill safety and subsequent reuse. However, China currently lacks a standardized technical system for humus soil quality testing. Existing testing methods primarily rely on traditional laboratory sampling and analysis, which are not only time-consuming and complex, but also difficult to meet the needs of rapid large-scale humus soil assessment. Therefore, for large-scale humus soil, it is urgent to build a set of efficient and accurate rapid quality detection methods to achieve quality assessment and quality classification of incoming humus soil.

[0003] Image recognition is a technology that enables computers to understand and analyze image content. Its primary goal is to identify various pieces of information in humus soil images through image processing and analysis, and further understand the meaning of this information. Algorithms such as YOLO have been widely used in tasks such as waste sorting and soil quality assessment, demonstrating excellent accuracy and efficiency. TDR (Transistor-Derivative Recognition) can rapidly measure electrical parameters such as the conductivity of humus soil by stimulating a step voltage pulse and analyzing the reflected signal in the medium. Therefore, combining image recognition with TDR technology enables efficient and accurate assessment of humus soil quality. Summary of the Invention

[0004] In order to solve the problems existing in the background technology, the present invention proposes a method for rapid assessment and classification of humus soil quality based on image recognition and penetrating TDR.

[0005] The method of the present invention uses a deep learning model to identify the proportion of fine particles, impurity content and moisture content of the surface humus soil, and adopts a penetrating TDR probe to measure the conductivity of the deep humus soil, thereby collaboratively realizing three-dimensional rapid detection of humus soil quality.

[0006] The present invention grades the quality of humus soil based on the detection results of image recognition and TDR, and selects the appropriate disposal or resource utilization method according to the classification results. It is suitable for humus soil production sites or landfill entrances to achieve rapid assessment and classification of humus soil quality, providing a scientific basis for the quality-based disposal and resource utilization of humus soil.

[0007] The technical solutions of the present invention are as follows:

[0008] The method comprises the following steps:

[0009] Step 1: Use a camera to take photos of the humus soil in the on-site inspection area and perform image recognition processing to obtain quality parameters such as the mass ratio and moisture content of various materials in the humus soil;

[0010] Step 2: Processing a portion of the quality parameters of the impurity content and moisture content obtained in step 1 to obtain a calculated value of the electrical conductivity of the humus soil;

[0011] Step 3: Use a penetrating TDR probe to insert into the humus soil to measure the conductivity value;

[0012] Step 4: Compare the conductivity calculation value obtained in step 2 with the conductivity measurement value obtained in step 3 to see if they are consistent. Adjust the humus soil in the on-site detection area based on the comparison results, and then quickly evaluate and grade the humus soil quality based on all the quality parameters obtained in step 1.

[0013] The step 1 is specifically as follows: using a multispectral high-definition camera array to capture the surface image of the humus soil. Specifically, the image size can be set to 640*640, the epochs can be set to 100, and the batch size can be set to 16. The surface image is recognized and processed using the YOLOv8 deep learning model to extract quality parameters such as the proportion of fine particles, impurity content, and moisture content.

[0014] In step 2, the electrical conductivity value EC of the humus soil is calculated based on the impurity content x and the moisture content w of the humus soil using the following formula:

[0015] EC=15.963e (-0.081x+0.077w)

[0016] Here, e represents a natural constant.

[0017] The step 3 specifically involves using a penetrating TDR probe to descend and insert into the deep humus soil for actual detection, thereby obtaining a conductivity measurement value of the humus soil.

[0018] The depth of the deep humus soil is 1 to 1.5 m.

[0019] In step 4, the calculated conductivity value of the humus soil obtained in step 2 is compared with the conductivity measurement value obtained in step 3 to see whether they are consistent, as follows:

[0020] If the deviation between the calculated and measured conductivity values ​​is within the preset ±5% threshold, the quality of the humus soil is evaluated and graded based on the quality parameter results obtained by image recognition in step 1. If the deviation between the calculated and measured conductivity values ​​is not within the preset ±5% threshold, the process returns to step 1, the soil in the on-site inspection area is turned over, image data is recollected and processed, and steps 1 to 3 are repeated until the deviation between the calculated and measured conductivity values ​​is within the preset ±5% threshold.

[0021] When the conductivity value calculated by image recognition is higher than the TDR test value, possible reasons include rainfall causing the surface moisture content to be higher, the surface impurity content to be lower, or the soil type of the deep landfill is different from the surface humus soil; conversely, if the image recognition value is lower than the TDR test value, it is because the surface humus soil has a lower moisture content or a higher impurity content.

[0022] This analysis revealed the factors that led to the large deviation between the two results. For both cases, the soil in the on-site detection area of ​​step 1 was turned over, and image data was recollected until the deviation between the conductivity calculation value and the conductivity measurement value was within the preset threshold of ±5%, to ensure that the final image calculation value was consistent with the TDR test value, thereby ensuring the accuracy of the humus soil quality classification.

[0023] In step 4, the quality of the humus soil is quickly evaluated and graded based on the comparison results combined with all the quality parameters obtained in step 1, as follows:

[0024] When the deviation between the calculated and measured conductivity values ​​is within the preset ±5% threshold, the quality parameter results obtained by image recognition in step 1 are processed as follows:

[0025] If the moisture content of the humus soil is less than or equal to 20%, the impurity content is less than or equal to 5%, and the proportion of fine aggregate is greater than or equal to 75%, the quality grade of the humus soil in the current on-site testing area is good;

[0026] If the moisture content of the humus soil is greater than 30%, the impurity content is greater than 8%, or the proportion of fine particles is less than 65%, the quality grade of the humus soil in the current on-site testing area is unqualified;

[0027] In other cases, the quality grade of humus soil in the current on-site inspection area is qualified.

[0028] The present invention first identifies the proportion of fine aggregate, impurity content and moisture content as key parameters for humus soil quality assessment, and combines conductivity as a comprehensive characterization parameter. The YOLOv8 model is used to identify fine aggregate, impurity content and moisture content in humus soil. The conductivity measurement value of the surface humus soil obtained by image recognition and the conductivity measurement value of the deep humus soil obtained by the penetrating TDR probe are combined to verify the consistency of the humus soil in each layer of the dump truck. Finally, the humus soil is quality assessed and graded.

[0029] The present invention adopts for the first time a method combining image recognition technology and penetrating TDR to grade the quality of humus soil.

[0030] Beneficial effects of the present invention:

[0031] The present invention adopts a method combining image recognition and penetrating TDR to achieve efficient identification and detection of key quality indicators of humus soil, effectively shortening the time required for traditional sampling, screening and laboratory testing, improving detection efficiency and reducing detection costs.

[0032] The present invention is highly automated and adaptable to site conditions, and can perform efficient detection in complex and changeable landfill environments. It provides a scientific basis for the quality grading of humus soil and significantly improves the management efficiency and safety of humus soil resource utilization and backfill disposal at engineering sites. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is the overall workflow diagram of the method of the present invention;

[0034] Figure 2 A diagram of the system device used in the method of the present invention;

[0035] Figure 3 This is a 25mm humus soil sample from Anhui Chaohu landfill;

[0036] Figure 4 This is a 20mm humus soil sample from Anhui Chaohu landfill;

[0037] Figure 5 This is a 20mm humus soil sample from the Shenzhen Apoji landfill;

[0038] Figure 6 This is a picture of a 20mm humus soil sample from the Changchun Mushroom Valley landfill.

[0039] Figure 7 Schematic diagram of the sampling point area of ​​Comparative Example 1. DETAILED DESCRIPTION

[0040] The present invention will be further described below with reference to the accompanying drawings and examples.

[0041] The present invention provides an overall system for implementing the method such as Figure 2 As shown, it includes a signal processing box 1, a probe lifting device 2, a penetrating TDR probe 3, a camera 4, a humus soil transport vehicle 5 and a control room 6.

[0042] The humus soil is placed in a humus soil transport vehicle 5, the signal processing box 1 and the probe lifting device 2 are placed above the humus soil transport vehicle 5, the penetrating TDR probe 3 and the camera 4 are installed at the bottom of the probe lifting device 2, the penetrating TDR probe 3 and the camera 4 are both facing downward toward the humus soil, and a control room 6 is set on the side. The probe lifting device 2, the penetrating TDR probe 3 and the camera 4 are electrically connected through the signal processing box 1 and the control room 6.

[0043] like Figure 1 As shown, the embodiment of the present invention includes the following steps:

[0044] Step 1: Use a camera to take photos of the humus soil in the on-site inspection area and perform image recognition processing to obtain quality parameters such as the mass ratio and moisture content of various materials in the humus soil;

[0045] Specifically, once the transport vehicle enters the inspection area, the multispectral high-definition camera array automatically adjusts its height to ensure coverage of at least 80% of the humus soil surface. In rainy or snowy weather, the wind and dust shield and adaptive fill light automatically activate to ensure high-quality image acquisition.

[0046] The camera array captures high-definition images of the humus soil surface from multiple angles and transmits them in real time to the signal processing box. Based on the YOLOv8 deep learning model, the images are segmented and feature extracted, outputting information such as the proportion of fine particles, impurity content, and moisture content. The image size is set to 640*640, the number of epochs is set to 100, and the batch size is set to 16.

[0047] The YOLOv8 deep learning model is obtained by training in advance by inputting the surface image of humus soil and its corresponding known quality parameters such as the proportion of fine particles, impurity content and moisture content as labels.

[0048] Step 2: Processing a portion of the quality parameters of the impurity content and moisture content obtained in step 1 to obtain a calculated value of the electrical conductivity of the humus soil;

[0049] The electrical conductivity value EC of humus soil is calculated based on the impurity content x and moisture content w of the humus soil using the following formula:

[0050] EC=15.963e (-0.081x+0.077w)

[0051] Here, e represents a natural constant.

[0052] The formula was obtained by fitting the humus soil conductivity-impurity content-moisture content model constructed by the previous TDR test.

[0053] Step 3: Use a penetrating TDR probe to lower and insert it into the humus soil at a depth of 1 to 1.5 m to perform actual testing and obtain the conductivity measurement value of the humus soil.

[0054] Step 4: Compare the conductivity calculation value obtained in step 2 with the conductivity measurement value obtained in step 3 to see if they are consistent. Based on the comparison result and all the quality parameters obtained in step 1, quickly evaluate and grade the humus soil quality.

[0055] 4.1) Compare the conductivity values ​​calculated by image recognition with the conductivity values ​​measured by penetrating TDR, as follows:

[0056] If the deviation between the calculated conductivity value and the measured conductivity value is within the preset threshold of ±5%, the quality of the humus soil is quickly evaluated and graded based on the quality parameter results obtained by image recognition in step 1;

[0057] If the deviation between the calculated conductivity value and the measured conductivity value is not within the preset difference threshold of ±5%, then return to step 1 and turn the soil in the on-site detection area. The error of inaccurate measurement is only in the water content. By turning the soil, the water content measurement is made more accurate. The image data is re-collected and processed, and steps 1 to 3 are repeated. The turning of the soil and the processing of steps 1 to 3 can be repeated continuously until the deviation between the calculated conductivity value and the measured conductivity value is within the preset difference threshold of ±5%.

[0058] When the conductivity value calculated by image recognition is higher than the TDR test value, possible reasons include rainfall causing the surface moisture content to be higher, the surface impurity content to be lower, or the soil type of the deep landfill is different from the surface humus soil; conversely, if the image recognition value is lower than the TDR test value, it is because the surface humus soil has a lower moisture content or a higher impurity content.

[0059] This analysis revealed the factors that led to the large deviation between the two results. For both cases, the soil in the on-site detection area of ​​step 1 was turned over, and image data was recollected until the deviation between the conductivity calculation value and the conductivity measurement value was within the preset threshold of ±5%, to ensure that the final image calculation value was consistent with the TDR test value, thereby ensuring the accuracy of the humus soil quality classification.

[0060] 4.2) If the deviation between the calculated conductivity value and the measured conductivity value is within the preset threshold of ±5%, the quality parameter results obtained by image recognition in step 1 are processed as follows:

[0061] If the moisture content of the humus soil is less than or equal to 20%, the impurity content is less than or equal to 5%, and the proportion of fine aggregate is greater than or equal to 75%, the quality grade of the humus soil in the current on-site testing area is good;

[0062] If the moisture content of the humus soil is greater than 30%, the impurity content is greater than 8%, or the proportion of fine particles is less than 65%, the quality grade of the humus soil in the current on-site testing area is unqualified;

[0063] In other cases, the quality grade of humus soil in the current on-site inspection area is qualified.

[0064] The quality of humus soil was quickly assessed and graded, and the results are shown in Table 1.

[0065] Table 1 Humus soil quality classification table

[0066]

[0067] To verify the accuracy and universality of this method in different landfills, the present invention conducted tests on humus soil mined from the Shenzhen Apoji Municipal Waste Landfill and the Anhui Chaohu Municipal Waste Landfill. The results are shown in Table 2.

[0068] Table 2 Verification of rapid test results of landfill humus soil quality

[0069]

[0070] As shown in Table 2 above, the YOLOv8 model has low recognition errors on different landfill samples, and the recognition errors of fine aggregate proportion, impurity content and moisture content are all less than 3%.

[0071] It can be seen from the above implementation that the present invention uses image recognition to obtain the quality parameters of humus soil, and then uses the quality parameters to obtain conductivity and compares the results with the actual measurement values ​​to determine whether the image recognition results are accurate. While ensuring accuracy, the image recognition results are used for rapid evaluation and grading, which can effectively shorten the detection cycle and improve the detection efficiency. It is particularly suitable for on-site rapid screening and quality control in large-scale humus soil treatment projects.

[0072] By introducing conductivity, a physical measurement, as a calibration step, a verification mechanism combining image recognition with measured data was established, significantly improving the accuracy and stability of recognition results. This approach effectively overcomes the misjudgment issues often associated with pure image recognition models in real-world applications due to factors such as weather and uneven material distribution, resulting in greater robustness and engineering applicability.

[0073] Comparative Example 1: Traditional Sampling Test

[0074] In actual projects, the detection of humus soil quality mainly relies on on-site sampling and laboratory analysis. The specific process is as follows:

[0075] (1) Take 10kg of humus soil sample at the production line site or in a transport vehicle.

[0076] (2) Take 5 kg of humus soil sample and put it into a tension vibrating screen with a pore size of 5 mm and perform two screening operations. The undersize is classified as fine particles, and the oversize is manually sorted into inorganic aggregates and impurities. After drying, the samples are weighed separately to calculate the mass ratio of fine particles and impurities in the humus soil.

[0077] (3) Weigh another 5 kg of humus soil sample and place it in a dry container. Dry it at 60-70°C until the mass change is less than 1% of the sample amount within 2 hours. Calculate the moisture content.

[0078] The data obtained by this test method is relatively accurate, but the test time takes 1 to 2 days, and it is necessary to entrust professional personnel of the testing unit to undertake this work, which is economically expensive. It is difficult to sample and test the quality of humus soil of each transport vehicle, and only random inspections can be carried out.

[0079] During a landfill excavation and screening project, humus soil from a transport truck was sampled six times at different locations, with each sample weighing 10 kg. Laboratory analysis and testing revealed, as shown in Table 1, an average fine aggregate content of 73.26% for the entire truckload of humus soil, an average impurity content of 3.94%, and an average moisture content of 24.83%, resulting in a passing quality grade. However, the test results reveal significant differences in the quality of the humus soil obtained from sampling at different locations. This method suffers from insufficient sampling representativeness, which can lead to misjudgments of the overall humus soil quality grade.

[0080] The method proposed in this invention was used to photograph the humus soil of the same transport truck. YOLOv8 was used to identify various indicators of the humus soil, and a TDR probe was used for penetration verification. The quality of the humus soil in the transport truck was tested, and the results showed that the fine aggregate content of the humus soil was 72.46%, the impurity content was 5.74%, and the moisture content was 22.83%. The quality grade was qualified, which is consistent with the average values ​​of the various indicators tested in Table 1. Therefore, the method of the present invention can achieve a rapid, convenient, and accurate assessment of the quality of humus soil.

[0081] Table 3 Indoor test results of humus soil samples taken from different areas of the same transport vehicle

[0082]

[0083]

[0084] Comparative Example 2: Using YOLOv8 throughout

[0085] In recent years, deep learning technologies, particularly object detection algorithms like YOLOv8, have made significant progress in areas such as waste sorting. However, there is currently no mature solution for rapid detection of humus soil quality.

[0086] Example (1): The landfill site to be treated is far away from the humus soil disposal site, and the transportation time is about 2 hours. The humus soil transport vehicle undergoes quality inspection at the entrance of the disposal site.

[0087] First, the humus soil in the transport vehicle was photographed, and YOLOv8 was used to identify the key quality indicators of the humus soil. The surface fine aggregate ratio was 72.69%, the impurity content was 7.25%, and the moisture content was 20.52%. Based on the identified parameters, the electrical conductivity EC value was calculated to be 43.08 mS / m. Then, a TDR probe was used to perform a penetration test on the humus soil. The actual EC value was 107.76 mS / m. The error between the two exceeded 5%, which was significantly beyond the reasonable threshold range. The soil needed to be turned over and re-photographed. The humus soil in the transport vehicle was turned over and mixed several times, and then photographed again for identification. The average parameters were: fine aggregate ratio of 76.68%, impurity content of 4.98%, and moisture content of 28.63%. The calculated EC value was 104.84 mS / m. The difference with the actual TDR measured value was within the reasonable threshold range. It can be judged that the quality grade of the humus soil in the vehicle is qualified, and the evaluation process is completed.

[0088] It can be seen that during long transportation, the surface humus soil is exposed to sunlight, resulting in a significant decrease in moisture content. Using YOLOv8 alone for humus soil image recognition would significantly underestimate the moisture content of the entire vehicle's humus soil. In contrast, supplemented by penetrating TDR probe testing, the actual conductivity value of the lower humus soil can be obtained to verify the image recognition data, thus addressing the shortcomings of YOLOv8 image recognition technology in quality grade assessment.

[0089] Example (2): A transport truck spreads humus soil on top of construction waste and transports it to a humus soil disposal site, where it undergoes quality inspection at the entrance of the disposal site.

[0090] First, the humus soil on the transport truck was photographed and YOLOv8 was used to identify key quality parameters of the humus soil. The results showed: a fine aggregate content of 81.42%, an impurity content of 2.13%, and a moisture content of 19.08%. Based on these parameters, the calculated EC value was 58.38 mS / m. Then, a penetrating TDR probe test was performed on the truck, and the measured EC value was 30.76 mS / m, with the error significantly exceeding the 5% threshold. After turning the soil, it was discovered that the truck was loaded with a large amount of construction waste, with only the surface covered with humus soil. The quality grade was unqualified and it was not allowed to enter the site for disposal. Therefore, combining image recognition and penetrating TDR can effectively prevent the transportation of construction waste, miscellaneous fill, undisturbed soil, and contaminated soil to humus soil disposal sites, thereby preventing the rapid depletion of storage capacity at humus soil disposal sites.

[0091] Therefore, using only YOLOv8 image recognition technology for humus soil detection has problems such as limited recognition range and large error in results.

[0092] The present invention combines image recognition with penetrating TDR to achieve a rapid, comprehensive and accurate assessment of humus soil quality.

[0093] The embodiments described above provide a detailed description of the technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, supplements and equivalent substitutions made within the scope of the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for rapid assessment and grading of humus soil quality based on image recognition and penetrating TDR, characterized by: The method comprises the following steps: Step 1: Use a camera to take photos of the humus soil in the on-site inspection area and perform image recognition processing to obtain quality parameters such as mass percentage and moisture content of the humus soil; Step 2: Processing a portion of the quality parameters obtained in step 1 to obtain a calculated value of the electrical conductivity of the humus soil; Step 3: Use a penetrating TDR probe to insert into the humus soil to measure the conductivity value; Step 4: Compare the conductivity calculation value obtained in step 2 with the conductivity measurement value obtained in step 3 to see if they are consistent. Adjust the humus soil in the on-site detection area based on the comparison results, and then quickly evaluate and grade the humus soil quality based on all the quality parameters obtained in step 1.

2. The method for rapid assessment and grading of humus soil quality based on image recognition and penetrating TDR according to claim 1 is characterized by: The step 1 specifically includes: using a multispectral high-definition camera array to capture the surface image of humus soil, using the YOLOv8 deep learning model to identify and process the surface image, and extracting quality parameters such as the proportion of fine particles, impurity content, and moisture content.

3. The method for rapid assessment and grading of humus soil quality based on image recognition and penetrating TDR according to claim 1 is characterized by: In step 2, the electrical conductivity value EC of the humus soil is calculated based on the impurity content x and the moisture content w of the humus soil using the following formula: <h2 style=";text-align:left;direction:ltr">EC=15.963e<h2 style=";text-align:left;direction:ltr"> (-0.081x+0.077w) Here, e represents a natural constant.

4. The method for rapid assessment and grading of humus soil quality based on image recognition and penetrating TDR according to claim 1 is characterized in that: The step 3 specifically involves using a penetrating TDR probe to descend and insert into the deep humus soil for actual detection, thereby obtaining a conductivity measurement value of the humus soil.

5. The method for rapid assessment and grading of humus soil quality based on image recognition and penetrating TDR according to claim 1 is characterized in that: In step 4, the calculated conductivity value of the humus soil obtained in step 2 is compared with the measured conductivity value obtained in step 3 to determine whether they are consistent, specifically as follows: if the deviation between the calculated conductivity value and the measured conductivity value is within a preset threshold of ±5%, then the quality of the humus soil is evaluated and graded based on the quality parameter results obtained by image recognition in step 1; If the deviation between the calculated conductivity value and the measured conductivity value is not within the preset threshold of ±5%, return to step 1, turn the soil in the on-site detection area, re-collect image data and repeat steps 1 to 3 until the deviation between the calculated conductivity value and the measured conductivity value is within the preset threshold of ±5%.

6. The method for rapid assessment and grading of humus soil quality based on image recognition and penetrating TDR according to claim 1, characterized in that: In step 4, the quality of the humus soil is quickly evaluated and graded based on the comparison results combined with all the quality parameters obtained in step 1, as follows: When the deviation between the calculated and measured conductivity values ​​is within the preset ±5% threshold, the quality parameter results obtained by image recognition in step 1 are processed as follows: If the moisture content of the humus soil is less than or equal to 20%, the impurity content is less than or equal to 5%, and the proportion of fine aggregate is greater than or equal to 75%, the quality grade of the humus soil in the current on-site testing area is good; If the moisture content of the humus soil is greater than 30%, the impurity content is greater than 8%, or the proportion of fine particles is less than 65%, the quality grade of the humus soil in the current on-site testing area is unqualified; In other cases, the quality grade of humus soil in the current on-site inspection area is qualified.

Images