Soil pore structure monitoring method and system based on low-field nuclear magnetic resonance imaging

Abstract

The present invention relates to the technical field of soil pore structure monitoring, and discloses a soil pore structure monitoring method, system, device, and storage medium based on low-field nuclear magnetic resonance imaging. The method comprises acquiring raw data and preprocessing it to obtain first corrected data; calculating second corrected data based on the first corrected data; extracting and enhancing the second corrected data to generate third corrected data; reconstructing a three-dimensional pore model and extracting a first pore feature dataset from the three-dimensional pore model; establishing a first quantitative correlation model using a support vector machine algorithm combined with a preset biological model; and optimizing the pore feature dataset based on a simulated annealing algorithm to obtain a final quantitative correlation model. Through multi-step data processing and modeling, this method can efficiently and accurately reveal the quantitative relationship between soil pore structure and plant root function, addressing the problem of low accuracy of feature extraction results in traditional microscopic image analysis methods.

Description

Technical Field

[0001] The present invention relates to the technical field of soil physical property monitoring, and in particular to a soil pore structure monitoring method, system, electronic equipment and storage medium based on low-field nuclear magnetic resonance imaging. Background Art

[0002] Currently, monitoring and analyzing soil pore structure is of great significance in fields such as agricultural production, environmental protection, and geological research. Soil pore structure directly affects soil permeability, aeration, and nutrient transport, playing a vital role in crop root growth, water resource management, and ecosystem stability. However, existing technologies for monitoring soil pore structure still face many problems and challenges.

[0003] One existing technique involves traditional microscopic image analysis, which uses microscopic observation of two-dimensional (2D) sections to obtain soil pore information. However, sample preparation often involves operations such as cutting, polishing, or staining, which often disrupt the original soil structure and alter the actual pore morphology and size. Furthermore, 2D images provide only limited pore information and lack a description of the 3D pore distribution and connectivity. This limitation results in insufficient data integrity, impacting the accuracy and reproducibility of the results.

[0004] In summary, the pore information obtained by traditional microscopic image analysis methods is limited and the data is incomplete, resulting in low accuracy of pore feature extraction results. Summary of the Invention

[0005] The present invention provides a soil pore structure monitoring method, system, electronic equipment and storage medium based on low-field nuclear magnetic resonance imaging to achieve higher-precision soil pore characteristic analysis.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging, comprising:

[0007] Acquiring low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and performing preprocessing to obtain first correction data;

[0008] Calculating magnetic field inhomogeneity based on the first correction data, and obtaining second correction data according to the magnetic field inhomogeneity;

[0009] Extracting and enhancing features from the second corrected data to generate third corrected data;

[0010] reconstructing a high-resolution three-dimensional pore model from the third corrected data, and extracting a first pore characteristic data set from the three-dimensional pore model;

[0011] Using a support vector machine algorithm to classify the pores in the first pore characteristic data set into large, medium, and small pores, and combining it with a preset biological model to establish a first quantitative correlation model between pore structure and root function;

[0012] The imaging parameters were adjusted based on the simulated annealing algorithm to obtain the optimized imaging parameters, the pore characteristic data set under the optimized parameters was re-obtained, and the final quantitative correlation model between pore structure and root function was output.

[0013] In one embodiment, the step of obtaining low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and preprocessing the data to obtain first correction data includes:

[0014] Obtain low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of soil samples;

[0015] Ensure the alignment of data from different sources in the time dimension through interpolation algorithms;

[0016] The original data is adjusted using a preset temperature compensation coefficient and a preset moisture correction coefficient to obtain first corrected data.

[0017] In one embodiment, the calculating the magnetic field inhomogeneity based on the first correction data and obtaining the second correction data according to the magnetic field inhomogeneity includes:

[0018] constructing a magnetic field gradient map based on the first correction data, and calculating magnetic field inhomogeneity according to the magnetic field gradient map;

[0019] When the magnetic field inhomogeneity exceeds a preset inhomogeneity threshold, a uniformity optimization algorithm based on magnetic field gradient mapping is applied to process the first correction data to obtain second correction data; when the magnetic field inhomogeneity does not exceed the preset inhomogeneity threshold, the first correction data is directly used as the second correction data.

[0020] In one embodiment, the step of extracting and enhancing features from the second corrected data to generate third corrected data includes:

[0021] Extracting and enhancing the second corrected data to obtain an enhanced feature set;

[0022] The enhanced feature set is subjected to wavelet transformation to remove high-frequency noise, while retaining and strengthening the multi-scale low-frequency features of the pore structure, thereby generating third correction data.

[0023] In one embodiment, reconstructing a high-resolution three-dimensional pore model from the third corrected data and extracting a first pore characteristic dataset from the three-dimensional pore model includes:

[0024] Using voxelization and isosurface extraction techniques, a high-resolution pore 3D model is reconstructed from the third-rectified data;

[0025] Multidimensional features are extracted from the three-dimensional pore model to establish a first pore feature data set; wherein the multidimensional features reflect pore size, shape, orientation and connectivity.

[0026] In one embodiment, the method of using a support vector machine algorithm to classify the pores in the first pore characteristic dataset into large, medium, and small pores, and combining it with a preset biological model to establish a first quantitative association model between pore structure and root function includes:

[0027] The preset biological model includes root function data of plants in soil samples;

[0028] The support vector machine algorithm is used to classify the pores in the first pore characteristic data set into large, medium and small pores to obtain the pore structure category;

[0029] The pore structure class is fused with the root function data to obtain a first quantitative association model between pore structure and root function.

[0030] In one embodiment, adjusting imaging parameters based on a simulated annealing algorithm to obtain optimized imaging parameters, reacquiring a second pore characteristic dataset under the optimized parameters, and outputting a final quantitative correlation model between pore structure and root function include:

[0031] Initializing imaging parameters, wherein the imaging parameters include echo time and sampling frequency;

[0032] Optimizing the imaging parameters using a simulated annealing algorithm to minimize an objective function value;

[0033] When the objective function value is lower than a preset target threshold, the imaging parameters at this time are used as optimized imaging parameters;

[0034] Reacquiring optimized nuclear magnetic resonance imaging data using the optimized imaging parameters;

[0035] generating a second pore characteristic data set based on the optimized MRI data;

[0036] The second pore characteristic data set is integrated with the first quantitative correlation model to output a final quantitative correlation model.

[0037] In a second aspect, the present invention provides a soil pore structure monitoring system based on low-field nuclear magnetic resonance imaging, comprising:

[0038] A data acquisition and preprocessing module, configured to acquire low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and perform preprocessing to obtain first correction data;

[0039] a magnetic field correction module, configured to calculate magnetic field inhomogeneity based on the first correction data, and obtain second correction data according to the magnetic field inhomogeneity;

[0040] a feature enhancement module, configured to generate third corrected data by performing wavelet transformation and nonlinear enhancement on the second corrected data;

[0041] a pore feature extraction module, configured to reconstruct a high-resolution three-dimensional pore model from the third corrected data and extract a first pore feature data set from the three-dimensional pore model;

[0042] a model generation module for classifying the pores in the first pore characteristic dataset into large, medium, and small pores using a support vector machine algorithm, and establishing a first quantitative association model between pore structure and root function in combination with a preset biological model;

[0043] The imaging parameter optimization module is used to adjust the imaging parameters based on the simulated annealing algorithm to obtain the optimized imaging parameters, reacquire the pore characteristic data set under the optimized parameters, and output the final quantitative correlation model between pore structure and root function.

[0044] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging as described above is implemented.

[0045] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned soil pore structure monitoring methods based on low-field nuclear magnetic resonance imaging.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention discloses a soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging, comprising obtaining low-field nuclear magnetic resonance imaging data, temperature data and moisture data of a soil sample and preprocessing them to obtain first correction data; calculating magnetic field inhomogeneity based on the first correction data, and obtaining second correction data according to the magnetic field inhomogeneity; extracting and enhancing features from the second correction data to generate third correction data; reconstructing a high-resolution three-dimensional pore model from the third correction data, and extracting a first pore characteristic data set from the three-dimensional pore model; classifying pores in the first pore characteristic data set into large, medium and small pores using a support vector machine algorithm, and establishing a first quantitative correlation model between pore structure and root function in combination with a preset biological model; adjusting imaging parameters based on a simulated annealing algorithm to obtain optimized imaging parameters, reacquiring the pore characteristic data set under the optimized parameters, and outputting a final quantitative correlation model between pore structure and root function.

[0048] This method combines support vector machines with a simulated annealing optimization algorithm to effectively preprocess and enhance features on limited data. This method maintains good performance even with relatively small data volumes, ensuring accurate reflection of the true state of soil pores while improving the accuracy of monitoring results. The resulting quantitative correlation model between pore structure and root function helps understand the impact of soil pore structure on plant growth and guides precision agriculture practices. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 1 is a flow chart of a soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging provided by the first embodiment of the present invention;

[0050] Figure 2 It is a structural schematic diagram of a soil pore structure monitoring system based on low-field nuclear magnetic resonance imaging provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0052] Reference Figure 1 The first embodiment of the present invention provides a soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging, comprising the following steps:

[0053] S100, acquiring low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and performing preprocessing to obtain first correction data;

[0054] S200, calculating magnetic field inhomogeneity based on the first correction data, and obtaining second correction data according to the magnetic field inhomogeneity;

[0055] S300, extracting and enhancing features from the second corrected data to generate third corrected data;

[0056] S400, reconstructing a high-resolution three-dimensional pore model from the third corrected data, and extracting a first pore characteristic data set from the three-dimensional pore model;

[0057] S500, using a support vector machine algorithm to classify the pores in the first pore characteristic dataset into large, medium, and small pores, and establishing a first quantitative correlation model between pore structure and root function in combination with a preset biological model;

[0058] S600: Adjust the imaging parameters based on the simulated annealing algorithm to obtain optimized imaging parameters, reacquire the pore characteristic data set under the optimized parameters, and output the final quantitative correlation model between pore structure and root function.

[0059] In step S100 , it is necessary to obtain low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample.

[0060] Low-field nuclear magnetic resonance imaging (LF-NMR) data refers to soil microstructural information obtained using LF-NMR technology. It provides detailed images of the spatial distribution, size, and connectivity of soil pores, forming the basis for constructing high-resolution three-dimensional pore models. Temperature data reflects the temperature changes of the soil sample, including the environment in which it is located. Moisture data indicates the water content in the soil.

[0061] In step S200, it is necessary to calculate the magnetic field inhomogeneity based on the first correction data.

[0062] In one implementation, first, it is necessary to construct a magnetic field gradient mapping based on the first correction data. This step evaluates the spatial distribution characteristics of the magnetic field through frequency domain analysis techniques, such as Fourier transform. Specifically, by converting the spatial domain signal into the frequency domain, frequency domain characteristic parameters reflecting the inhomogeneity of the magnetic field can be obtained. For an ideal uniform magnetic field, its spectrum should have only one main frequency component; however, the actual magnetic field often has inhomogeneities, which will appear as additional frequency components in the spectrum. The amplitude and frequency of these additional components can quantify the degree of inhomogeneity of the magnetic field. Based on the frequency domain characteristic parameters, a magnetic field gradient mapping model can be constructed, which can intuitively show the changes in magnetic field intensity in space. By analyzing the gradient mapping, the position distribution of the gradient peaks can be determined. These peaks often correspond to areas where the magnetic field changes most dramatically, and are related to the distribution of paramagnetic substances in the soil.

[0063] Next, the magnetic field inhomogeneity index is calculated, a key parameter for evaluating magnetic field quality. It can be obtained by calculating the ratio of the standard deviation of the magnetic field intensity to the mean value. If this ratio exceeds the preset inhomogeneity threshold, it indicates that the magnetic field inhomogeneity has reached a level that affects measurement accuracy, and the magnetic field uniformity optimization algorithm needs to be activated. The assessment of magnetic field inhomogeneity is not limited to overall statistical indicators but also needs to consider local magnetic field variations. Therefore, in some cases, more sophisticated methods, such as the sliding window method or the local mean method, are used to calculate the magnetic field inhomogeneity in different areas. In addition, to ensure the reliability of the evaluation results, multiple independent measurements are performed and the results are averaged to reduce the impact of random errors.

[0064] If it is confirmed that the magnetic field inhomogeneity exceeds the preset inhomogeneity threshold, the uniformity optimization algorithm based on the magnetic field gradient mapping is started. This algorithm is an iterative optimization method that improves the magnetic field uniformity by adjusting the magnetic field distribution to make the gradient flat. This process involves adjusting the position or intensity of the magnetic field source, or adding a compensation coil. After each iteration, the magnetic field gradient mapping is recalculated until the expected uniformity level is reached. Assuming that the initial magnetic field distribution causes the gradient to be abnormally high in certain areas, the optimization algorithm will gradually adjust the magnetic field source near these areas to make the magnetic field more consistent throughout the measurement volume. During the optimization process, experimental verification is also combined to ensure that the final magnetic field distribution meets the design requirements through repeated testing and adjustment. Preferably, a machine learning algorithm can also be introduced to assist the optimization process to automatically find the best magnetic field configuration scheme.

[0065] Next, the optimized magnetic field distribution is used as a constraint condition to perform a secondary correction on the first correction data to obtain second correction data with improved magnetic field uniformity. For example, if the magnetic field intensity in a certain area is 5% higher than the average value, the signal intensity in that area can be reduced by 5% accordingly to ensure that the measurement results at different locations are comparable. This correction ensures that the data at all locations can be reliably used to describe the soil pore structure. In addition, after completing the secondary correction, a series of quality checks are required, including but not limited to verifying the improvement effect of the magnetic field uniformity, confirming that no new error sources have been introduced, and ensuring the overall consistency of the data. Only data that has been strictly reviewed can be used for the next step - feature extraction and enhancement.

[0066] In another implementation, if it is confirmed that the magnetic field inhomogeneity does not exceed the preset inhomogeneity threshold, the first correction data is directly used as the second correction data without optimization.

[0067] In step S300, the second corrected data needs to be subjected to feature extraction and enhancement to generate third corrected data.

[0068] In one implementation, feature extraction is first performed on the second corrected data. This step aims to identify and quantify key soil pore properties, such as pore size distribution, shape characteristics (including circularity, aspect ratio, etc.), and pore connectivity. Analyzing these characteristics provides a more comprehensive understanding of the complexity and diversity of soil pore structure. To achieve this, a variety of image processing techniques are employed, including morphological operations to define pore boundaries, gray-level co-occurrence matrices (GLCMs) to capture texture information, and statistical methods to describe the distribution of pore size and shape.

[0069] Next, to improve the data quality and feature discernibility, feature enhancement is performed. Methods used here include applying filters to remove noise, enhancing image contrast using techniques such as histogram equalization or contrast stretching, and edge detection algorithms to highlight pore boundaries.

[0070] Preferably, multi-feature fusion is also performed, that is, different types of features (such as pore size, shape, connectivity) are combined to form a comprehensive feature representation, which can not only capture the information of individual features but also reflect the relationships between them.

[0071] Finally, all extracted and enhanced features are combined to generate the third-corrected data. This process ensures that each pore is described in detail and all features are normalized to the same scale for subsequent quantitative analysis. To ensure data quality, necessary quality checks are also performed at this stage to eliminate new sources of error.

[0072] In step S400, a high-resolution three-dimensional pore model needs to be reconstructed from the third corrected data, and a first pore characteristic data set is extracted from the three-dimensional pore model.

[0073] In one implementation, a voxelization algorithm is first applied to the third corrected data, discretizing the continuous pore space into regular voxel units. This process transforms the complex pore structure into a digital representation that is easy to calculate and analyze. An isosurface extraction algorithm then constructs a triangular mesh between adjacent voxels, forming a three-dimensional surface model of the pores. This method not only restores the pore geometry but also preserves the complexity of the internal structure.

[0074] From the reconstructed 3D model, various features reflecting pore size distribution can be extracted, including pore volume, surface area, and equivalent diameter, as well as features characterizing pore geometry, including pore aspect ratio, sphericity, and roundness. Furthermore, the angle between the principal pore directions and the coordinate axes is calculated based on the 3D pore model to obtain orientation data characterizing the 3D pore angular distribution. Finally, by analyzing the connectivity between pores, the number and size of connected pore clusters can be calculated, yielding characteristic data that measure pore connectivity.

[0075] All of these extracted features—multidimensional, heterogeneous characteristics such as pore size, shape, orientation, and connectivity—were integrated to construct the first pore characterization dataset that comprehensively captures the diversity and complexity of soil pore structure. This first pore characterization dataset reflects the spatial distribution of soil pores and also contains information about the potential functions of the soil. This distribution map can be used to guide precision agriculture practices, such as optimizing irrigation strategies or evaluating the effectiveness of soil improvement measures.

[0076] In step S500, a support vector machine (SVM) algorithm is used to classify the pores in the first pore characteristic dataset into large, medium, and small pores, and a first quantitative association model between pore structure and root function is established in combination with a preset biological model.

[0077] First, a pre-built biological model is used that incorporates plant root function data from soil samples. This data, derived from laboratory cultivation experiments or field observations, provides information on functional parameters such as root growth preferences and nutrient uptake capacity. This type of biological model can help understand how different types of pore structure influence root growth and function.

[0078] Next, based on the first pore characteristic dataset described above, a support vector machine algorithm was applied to classify pores. Through training, the SVM algorithm can classify pores into heterogeneous categories such as large, medium, and small pores. This classification relies not only on pore size but also considers multidimensional features such as shape, orientation, and connectivity, thereby more accurately describing the spatial distribution of soil pores. This detailed pore classification can better reveal the influence of soil structure on water movement, gas exchange, and root activity.

[0079] Finally, the classified pore structure categories are integrated with root function data from a pre-defined biological model. This step aims to establish a quantitative correlation model that can quantify the relationship between pore structure (such as pore size distribution and connectivity index) and root function (such as root extension and nutrient uptake efficiency). For example, macropores (diameter greater than 200 microns) primarily influence soil drainage, while mesopores (50-200 microns) are crucial for plant root growth, and micropores (less than 50 microns) determine soil water retention. In this way, it is possible not only to determine which pore characteristics significantly influence root growth and nutrient uptake, but also to predict plant performance under different pore conditions.

[0080] In step S600 , it is necessary to adjust the imaging parameters based on the simulated annealing algorithm to optimize the acquired pore characteristic data, and finally output the final quantitative correlation model between pore structure and root function.

[0081] Initializing the imaging parameters is the first step in the optimization process. At this stage, initial imaging parameters must be set, primarily including the echo time and sampling frequency. These parameters directly impact image quality and information content. For example, in practical applications, researchers used a 0.5 Tesla low-field NMR instrument equipped with a probe suitable for soil samples. The initial settings were an echo time of 10 milliseconds and a sampling frequency of 1000 Hz. This initial setting provides a starting point for subsequent optimization and serves as the spatial foundation for the simulated annealing algorithm to begin its search for the optimal solution.

[0082] Next, the simulated annealing algorithm was used to optimize the imaging parameters, aiming to minimize the objective function. Simulated annealing is a global optimization method inspired by the annealing process in metallurgy. In this study, it was used to optimize key parameters of low-field MRI, namely echo time and sampling frequency. These parameters not only affect image quality and information content, but also determine important properties such as signal intensity, signal-to-noise ratio, and spatial resolution. The simulated annealing algorithm iteratively adjusts the echo time and sampling frequency, re-performing low-field MRI imaging based on the parameters obtained at each iteration to obtain the corresponding pore structure and root function data. The residuals of the acquired pore structure and root function data with the first quantitative correlation model were then calculated, and minimizing these residuals was used as the objective function for the simulated annealing optimization. A key feature of this optimization method is its ability to escape from local optima. In practice, this means that even if a slightly inferior result is obtained on a particular iteration, the algorithm will still have a certain probability of accepting this result in order to explore a wider solution space. For example, during the optimization process, even if a particular iteration increases the residual from 0.05 to 0.06, the algorithm still accepts this change because it leads to a better global optimal solution. The optimization process sets a convergence criterion or a maximum number of iterations. For example, convergence is considered when the residual improves by less than 0.1% for 50 consecutive iterations, or a maximum of 1000 iterations. This balances achieving sufficiently good results while controlling computational costs.

[0083] When the objective function value is lower than the preset target threshold, it means that a set of optimized imaging parameters has been found. The imaging parameter combination at this time is the optimal solution, which can significantly improve the image quality and the predictive ability of the associated model. Once the optimized imaging parameters are determined, the stage of re-acquiring high-quality imaging data begins. Using the optimized parameters for nuclear magnetic resonance imaging, the root structure in the image will be clearer and the pore boundaries will be sharper. This improvement allows researchers to more accurately quantify soil structural characteristics and root morphology at the micron level, improving the accuracy of the analysis.

[0084] Finally, a new pore characterization dataset was generated based on the optimized MRI data reacquired using the optimized imaging parameters. This step ensured the most up-to-date and accurate soil pore structure information for further analysis and modeling. Based on this high-quality data, a second pore characterization dataset was constructed. This dataset not only had higher spatial resolution and improved signal-to-noise ratio, but also more accurately reflected the true nature of soil pores. This second pore characterization dataset was then combined with the previously established first quantitative correlation model for integrated analysis. This approach further validated and improved the original correlation model, ensuring it more accurately described the relationship between pore structure and root function. The final output was an optimized and validated quantitative correlation model that not only revealed the impact of soil pore structure on plant growth but also provided a reliable scientific basis for precision agriculture practices, such as guiding farmers to optimize tillage practices to increase crop yields and resource use efficiency. The entire process embodies an integrated solution, from data acquisition to model construction to optimization and validation, designed to provide the most accurate representation of the soil-plant system.

[0085] To facilitate understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0086] In another implementation, the first pore characteristic data may also be classified based on a CNN convolutional neural network.

[0087] First, the first pore feature data is preprocessed, including denoising and normalization, to improve data quality and consistency. This preprocessing step ensures that the data input to the CNN model has a high signal-to-noise ratio and that all features are compared at the same scale, providing a solid foundation for subsequent feature extraction and classification.

[0088] Next, a CNN model specifically designed for identifying and classifying pore structures was constructed. This model consists of multiple convolutional layers, pooling layers, and fully connected layers. The convolutional layers scan the input image using a sliding window to extract local features such as edges and textures. The pooling layers reduce the spatial size of the feature map while retaining important information, reducing computational effort and preventing overfitting. The fully connected layers globally integrate the features extracted by the convolutional and pooling layers to form a higher-level feature representation that better captures the essential properties of pore structures.

[0089] During the training phase, the CNN model is trained using a labeled pore structure dataset. During training, the model parameters are adjusted using a backpropagation algorithm to accurately identify and classify different pore types. To ensure the robustness and generalization of the model, the training dataset should be as diverse as possible, covering pore structure characteristics under various soil conditions. Furthermore, data augmentation techniques such as rotation and flipping can be used to further increase the number and variability of training samples.

[0090] After training, test the trained CNN model on an independent dataset to evaluate its classification accuracy and generalization ability. If the model's performance is unsatisfactory, you can improve it by adjusting the network structure, adding more training data, or optimizing hyperparameters. You can try adding more convolutional layers to extract more complex features, or adjusting hyperparameters such as the learning rate and regularization coefficient to improve the model's learning performance.

[0091] Finally, the trained CNN model was applied to new low-field MRI data to automatically identify and classify pore structure and generate detailed pore feature datasets. These datasets not only contain geometric features such as pore size, shape, and distribution density, but also multidimensional heterogeneous features such as connectivity and orientation, providing a rich information foundation for subsequent analysis. Finally, the pore feature datasets identified and classified by the CNN model were integrated and analyzed with the first quantitative correlation model previously established. This approach not only further validates and improves the original correlation model, but also ensures that it more accurately describes the relationship between pore structure and root function. The final output is an optimized and verified quantitative correlation model that not only reveals the impact of soil pore structure on plant growth but also provides a reliable scientific basis for precision agriculture practices.

[0092] The following describes the working process of the present invention using a relatively common scenario as an example.

[0093] First, multiple soil samples were collected from farmland and placed in a low-field nuclear magnetic resonance imaging (LNF-NMR) instrument in the laboratory. LF-NMR imaging data, temperature data, and moisture content data were acquired for each soil sample under a freeze-thaw cycle. These data were timestamped to ensure temporal alignment of data from different sources. Over a 100-second experimental period, LF-NMR data was recorded every 0.1 seconds for a total of 1000 data points; the temperature sensor sampled every 5 seconds, generating 20 data points; and the moisture sensor sampled every 10 seconds, generating 10 data points.

[0094] An interpolation algorithm adjusts the time-misaligned data. Then, using a preset temperature compensation factor (for sandy soil, the signal intensity decreases by 0.5% for every 1°C increase) and a moisture correction factor (an increase in moisture content from 10% to 20% results in a 30% increase in signal intensity), the original data is corrected to eliminate the effects of temperature and moisture variations, resulting in the first corrected data. This process makes the data, previously affected by temperature and moisture fluctuations, more stable and reliable, ensuring more accurate subsequent analysis results.

[0095] Next, the magnetic field inhomogeneity in the first correction data is analyzed, and a magnetic field gradient map is constructed. Based on this, a secondary correction is performed to improve magnetic field uniformity, generating the second correction data. If the magnetic field inhomogeneity index exceeds 5%, a magnetic field uniformity optimization algorithm is activated, ultimately flattening the magnetic field gradient. This correction reduces the signal intensity in that area by 5%, improving data consistency and comparability.

[0096] A wavelet transform was used to remove high-frequency noise while preserving and enhancing the multi-scale low-frequency features of the pore structure, generating third-corrected data. A pre-set inhomogeneity threshold of 0.8 was used, so any high-frequency coefficient with an absolute value greater than 0.8 was treated as noise and reset to zero. This process significantly reduced high-frequency noise while preserving the key features of the pore structure. The accuracy of pore identification increased from 85% to 95%, while also reducing the noise level by 70%.

[0097] Based on this, the gradient direction information from the magnetic field gradient map is extracted and combined with features such as pore size, shape, and orientation to form an enhanced feature set that fuses the magnetic field information. The fused feature set is [0.2, 0.1, 0.7, 5, 0.8, 30], where the first three numbers represent the gradient direction, and the next three numbers represent pore size, roundness, and inclination, respectively. This fusion allows for the simultaneous consideration of magnetic field variations and pore morphology, facilitating a more accurate description and classification of pore regions.

[0098] Based on the third correction data, voxelization and isosurface extraction techniques are used to reconstruct a high-resolution three-dimensional pore model. A 1 cubic centimeter soil sample is divided into 1 million cubic voxels with a side length of 100 microns. Each voxel is marked as a pore or soil particle according to its location. By setting an appropriate threshold, such as considering voxels with a grayscale value greater than 128 as pores, the algorithm can construct a triangular mesh between adjacent voxels to form a three-dimensional surface model of the pores. From the reconstructed three-dimensional model, a variety of features reflecting the pore size, shape, orientation and connectivity can be extracted, including pore volume, surface area, equivalent diameter, aspect ratio, sphericity, roundness, etc. These features can comprehensively characterize the diversity and complexity of soil pore structure, laying the foundation for further analysis.

[0099] A support vector machine algorithm was used to classify the pores in the first pore characteristic dataset into large, medium, and small pores. Combined with a pre-defined biological model, a first quantitative correlation model between pore structure and root function was established. This model incorporated root function data from plants in the soil samples, such as root growth preferences and nutrient uptake capacity. The rationality of the classification results was verified by comparing the large pore-enriched regions in the classification results with the gradient peak positions of the magnetic field gradient mapping. If the overlap exceeded 80%, the classification results were considered highly reliable. The final output, a pore heterogeneity distribution map, not only reflects the spatial distribution of soil pores but also contains information on the soil's formation history and potential functions.

[0100] To further improve the model's predictive performance, parameters such as the echo time and sampling frequency of LF-NMR imaging were adjusted based on a simulated annealing algorithm to minimize the residual error in the association between pore structure and root function. The initial settings were an echo time of 10 milliseconds and a sampling frequency of 1000 Hz. Through a simulated annealing process, these parameters were optimized to an echo time of 8.5 milliseconds and a sampling frequency of 1200 Hz, thereby improving image resolution and signal-to-noise ratio. Using the optimized parameters, LF-NMR imaging data of the soil samples were reacquired to generate three-dimensional pore structure images with higher spatial resolution and better signal-to-noise ratio. Before optimization, only pores with diameters greater than 150 microns could be distinguished, but after optimization, pores with diameters greater than 80 microns could be clearly identified, greatly improving the accuracy of the analysis.

[0101] A cross-validated nonlinear regression algorithm was used for the final pore characteristic dataset to establish a nonlinear relationship between pore surface area and volume, root growth rate, and nutrient uptake flux. Independent validation samples were used to assess the generalization ability of the correlation model and ensure its reliability. The model achieved an R² of 0.85 when predicting root growth rate, but only 0.70 when predicting nutrient uptake flux. This suggests that the influence of pore structure on root growth is more direct or easier to model than its influence on nutrient uptake. Based on the validation results, the nonlinear regression model was fine-tuned and optimized to improve its robustness and adaptability, ensuring that it accurately describes the quantitative relationship between pore structure and root function.

[0102] In summary, the present invention provides a soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging, which includes: obtaining low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and preprocessing them to obtain first correction data; calculating magnetic field inhomogeneity based on the first correction data, and obtaining second correction data based on the magnetic field inhomogeneity; extracting and enhancing the second correction data to generate third correction data; reconstructing a high-resolution three-dimensional pore model from the third correction data, and extracting a first pore characteristic dataset from the three-dimensional pore model; classifying pores in the first pore characteristic dataset into large, medium, and small pores using a support vector machine algorithm, and establishing a first quantitative correlation model between pore structure and root function based on a preset biological model; adjusting imaging parameters based on a simulated annealing algorithm to obtain optimized imaging parameters, reacquiring the pore characteristic dataset under the optimized parameters, and outputting a final quantitative correlation model between pore structure and root function. By performing a series of complex preprocessing, modeling, and optimization steps on the soil pore structure data, the method achieves a detailed characterization of soil pore structure and an in-depth understanding of its quantitative relationship with root function. This method not only improves the accuracy and reliability of soil structure analysis, but also provides a scientific basis for precision agriculture practices, helping to optimize farming methods and increase crop yields and resource utilization efficiency.

[0103] Reference Figure 2 A second embodiment of the present invention provides a soil pore structure monitoring system based on low-field nuclear magnetic resonance imaging, comprising:

[0104] A data acquisition and preprocessing module, configured to acquire low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and perform preprocessing to obtain first correction data;

[0105] a magnetic field correction module, configured to calculate magnetic field inhomogeneity based on the first correction data, and obtain second correction data according to the magnetic field inhomogeneity;

[0106] a feature enhancement module, configured to generate third corrected data by performing wavelet transformation and nonlinear enhancement on the second corrected data;

[0107] a pore feature extraction module, configured to reconstruct a high-resolution three-dimensional pore model from the third corrected data and extract a first pore feature data set from the three-dimensional pore model;

[0108] a model generation module for classifying the pores in the first pore characteristic dataset into large, medium, and small pores using a support vector machine algorithm, and establishing a first quantitative association model between pore structure and root function in combination with a preset biological model;

[0109] The imaging parameter optimization module is used to adjust the imaging parameters based on the simulated annealing algorithm to obtain the optimized imaging parameters, reacquire the pore characteristic data set under the optimized parameters, and output the final quantitative correlation model between pore structure and root function.

[0110] It should be noted that the soil pore structure monitoring system based on low-field nuclear magnetic resonance imaging provided in an embodiment of the present invention is used to execute all the process steps of the soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0111] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an imaging parameter optimization program. When the processor executes the computer program, the steps in each of the above-mentioned embodiments of the soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the imaging parameter optimization module.

[0112] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0113] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0114] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the electronic device and connects various parts of the entire electronic device using various interfaces and lines.

[0115] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0116] If the module / unit integrated into the electronic device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0117] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0118] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging, characterized in that: Executed by a computer, including: Acquiring low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and performing preprocessing to obtain first correction data; Calculating magnetic field inhomogeneity based on the first correction data, and obtaining second correction data according to the magnetic field inhomogeneity; Extracting and enhancing features from the second corrected data to generate third corrected data; reconstructing a high-resolution three-dimensional pore model from the third corrected data, and extracting a first pore characteristic data set from the three-dimensional pore model; Using a support vector machine algorithm to classify the pores in the first pore characteristic data set into large, medium, and small pores, and combining it with a preset biological model to establish a first quantitative correlation model between pore structure and root function; The imaging parameters were adjusted based on the simulated annealing algorithm to obtain the optimized imaging parameters, the pore characteristic data set under the optimized parameters was re-obtained, and the final quantitative correlation model between pore structure and root function was output.

2. The soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging according to claim 1, characterized in that: The step of obtaining low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and preprocessing the data to obtain first correction data includes: Obtain low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of soil samples; Ensure the alignment of data from different sources in the time dimension through interpolation algorithms; The original data is adjusted using a preset temperature compensation coefficient and a preset moisture correction coefficient to obtain first corrected data.

3. The soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging according to claim 1, characterized in that: The calculating the magnetic field inhomogeneity based on the first correction data and obtaining the second correction data according to the magnetic field inhomogeneity includes: constructing a magnetic field gradient map based on the first correction data, and calculating magnetic field inhomogeneity according to the magnetic field gradient map; When the magnetic field inhomogeneity exceeds a preset inhomogeneity threshold, a uniformity optimization algorithm based on magnetic field gradient mapping is applied to process the first correction data to obtain second correction data; when the magnetic field inhomogeneity does not exceed the preset inhomogeneity threshold, the first correction data is directly used as the second correction data.

4. The soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging according to claim 1, characterized in that: The step of extracting and enhancing features from the second corrected data to generate third corrected data includes: Extracting and enhancing the second corrected data to obtain an enhanced feature set; The enhanced feature set is subjected to wavelet transformation to remove high-frequency noise, while retaining and strengthening the multi-scale low-frequency features of the pore structure, thereby generating third correction data.

5. The soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging according to claim 1, characterized in that: The step of reconstructing a high-resolution three-dimensional pore model from the third corrected data and extracting a first pore characteristic data set from the three-dimensional pore model comprises: Using voxelization and isosurface extraction techniques, a high-resolution pore 3D model is reconstructed from the third-rectified data; Multidimensional features are extracted from the three-dimensional pore model to establish a first pore feature data set; wherein the multidimensional features reflect pore size, shape, orientation and connectivity.

6. The soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging according to claim 1, characterized in that: The method of using a support vector machine algorithm to classify the pores in the first pore characteristic dataset into large, medium, and small pores, and establishing a first quantitative correlation model between pore structure and root function in combination with a preset biological model, includes: The preset biological model includes root function data of plants in soil samples; The support vector machine algorithm is used to classify the pores in the first pore characteristic data set into large, medium and small pores to obtain the pore structure category; The pore structure categories are fused with the root function data to obtain a first quantitative association model between pore structure and root function.

7. The soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging according to claim 1, characterized in that: The method adjusts the imaging parameters based on the simulated annealing algorithm to obtain optimized imaging parameters, reacquires the second pore characteristic data set under the optimized parameters, and outputs the final quantitative correlation model between pore structure and root function, including: Initializing imaging parameters, wherein the imaging parameters include echo time and sampling frequency; Optimizing the imaging parameters using a simulated annealing algorithm to minimize an objective function value; When the objective function value is lower than a preset target threshold, the imaging parameters at this time are used as optimized imaging parameters; Reacquiring optimized nuclear magnetic resonance imaging data using the optimized imaging parameters; generating a second pore characteristic data set based on the optimized MRI data; The second pore characteristic data set is integrated with the first quantitative correlation model to output a final quantitative correlation model.

8. A soil pore structure monitoring system based on low-field nuclear magnetic resonance imaging, characterized in that: include: A data acquisition and preprocessing module, configured to acquire low-field nuclear magnetic resonance imaging data, temperature data, and moisture data of a soil sample and perform preprocessing to obtain first correction data; a magnetic field correction module, configured to calculate magnetic field inhomogeneity based on the first correction data, and obtain second correction data according to the magnetic field inhomogeneity; a feature enhancement module, configured to generate third corrected data by performing wavelet transformation and nonlinear enhancement on the second corrected data; a pore feature extraction module, configured to reconstruct a high-resolution three-dimensional pore model from the third corrected data and extract a first pore feature data set from the three-dimensional pore model; a model generation module for classifying the pores in the first pore characteristic dataset into large, medium, and small pores using a support vector machine algorithm, and establishing a first quantitative association model between pore structure and root function in combination with a preset biological model; The imaging parameter optimization module is used to adjust the imaging parameters based on the simulated annealing algorithm to obtain the optimized imaging parameters, reacquire the pore characteristic data set under the optimized parameters, and output the final quantitative correlation model between pore structure and root function.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the soil pore structure monitoring method based on low-field nuclear magnetic resonance imaging as described in any one of claims 1 to 7.

Images