Soil priority flow and influence factor real-time evaluation method and system
By acquiring various information about the soil region and combining neural networks and numerical models, the problem of inaccurate dynamic capture of soil priority flow in existing technologies has been solved, enabling accurate real-time assessment and management of soil priority flow and improving farmland management efficiency.
Patent Information
- Application Number
- CN202510995513.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-18
- Publication Date
- 2025-12-02
AI Technical Summary
Existing technologies struggle to capture soil preferential flow dynamics accurately and in real time in complex environments, and lack the ability to quantify the weights of multiple factors, resulting in low efficiency in farmland management and water resource protection.
By acquiring priority flow areas, image information, climate information, and various soil monitoring information of the target soil area, and combining neural network models and numerical models, potential priority flow risk areas and their formation probability, flow velocity, and impact area are determined. Real-time assessment is then performed using pre-trained probability prediction models and priority flow identification models.
It enables accurate and real-time assessment of soil priority flows and their influencing factors, helping farmers to rationally plan crop planting layouts, reduce negative impacts, protect soil resources, and promote sustainable use.
Smart Images
Figure CN121049474A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of soil monitoring technology, and in particular to a method and system for real-time assessment of soil preferential flow and its influencing factors. Background Technology
[0002] Preferred soil flow refers to the phenomenon where water moves more rapidly along a specific path due to the non-uniformity of the soil's pore structure. This flow pattern has a significant impact on processes such as soil moisture distribution, nutrient transport, and pollutant migration.
[0003] Currently, single-modal sensors are commonly used for soil monitoring, and the soil preferential flow path is analyzed based on the monitoring results.
[0004] However, traditional soil moisture monitoring and priority flow path analysis techniques are difficult to capture priority flow dynamics in real time and accurately in complex environments, and lack the ability to quantify the influence weights of multiple factors, resulting in low efficiency in farmland management and water resource protection. Summary of the Invention
[0005] The technical problem to be solved by the present invention is to provide a method and system for assessing soil preferential flow and its influencing factors, aiming to solve at least one of the above-mentioned technical problems.
[0006] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: Firstly, this application provides a method for real-time assessment of soil preferential flow and its influencing factors, employing the following technical solution: A method for real-time assessment of soil preferential flow and its influencing factors, comprising: The system acquires the priority flow area, image information, climate information, and soil monitoring information of the target soil area at the current moment. The soil monitoring information includes soil moisture, temperature, resistivity, soil texture, soil porosity, soil structure, and slope at monitoring points at different depths. The climate information includes temperature and precipitation. Based on the priority flow areas and soil monitoring information, potential priority flow risk zones in the target soil areas are identified; Based on the image information, crop information for the potential priority flow risk area is determined, including crop type, coverage, and crop growth. Based on the predicted time, crop information, climate information, and soil monitoring information of the potential priority flow risk zone, the probability of soil priority flow formation, flow velocity, and affected area range of the potential priority flow risk zone are determined.
[0007] The beneficial effects of this invention are as follows: By acquiring the priority flow area, image information, climate information, and soil monitoring information containing multiple parameters of the target soil area at the current moment, a rich and comprehensive data foundation is provided for assessment, reducing assessment errors caused by single or incomplete data and improving the accuracy of soil priority flow assessment. Based on the priority flow area and soil monitoring information, potential priority flow risk zones in the target soil area are identified. By understanding the crop information in this area, the formation probability, flow velocity, and affected area range of soil priority flow can be determined, enabling real-time assessment of soil priority flow and its influencing factors. This can help farmers rationally plan crop planting layouts. Based on the assessment results, corresponding measures can be taken to improve soil structure, regulate soil moisture, and control water flow, thereby reducing the negative impacts of priority flow, protecting soil resources, and promoting the sustainable use of soil.
[0008] Based on the above technical solution, the present invention can be further improved as follows.
[0009] Furthermore, obtaining the priority flow region of the target soil region at the current moment includes: Acquire radar image data of the target soil area; Based on the soil monitoring information of the target soil area, the set stratification information and the stratification interpolation processing method, the stratification difference result of the target soil area is determined, and the stratification difference result characterizes the difference in soil physical properties between soil layers at different depths; Feature recognition is performed on the radar image data and layer difference results of the target soil area to obtain the current radar feature data and the current soil feature data. Based on the current radar feature data, current soil feature data, and the preset priority flow identification model, the priority flow area is determined.
[0010] The beneficial effect of adopting the above-mentioned further scheme is that by combining the stratification difference results determined by radar image data and soil monitoring information, and performing feature recognition separately, and then using the preset priority flow recognition model, the priority flow area of the target soil area at the current moment can be determined more accurately.
[0011] Furthermore, the method for constructing the preset priority flow identification model includes: The system acquires historical radar image datasets, historical soil monitoring datasets, and surface priority flow survey data for the target soil area over a set time period. The historical radar image datasets are collected by ground penetrating radar, and the surface priority flow survey data includes the location of areas within the target soil area where priority flow phenomena are known to exist, the type of priority flow, and the water supply. Based on the ground priority flow survey data, positive sample areas are determined, and the positive sample areas represent priority flow related areas. Based on historical soil monitoring datasets, historical radar image datasets, and preset sample generation rules, regions with non-priority flow features are selected as negative sample regions. Both positive and negative sample regions are used as sample regions, and a subset of historical radar image data and a subset of historical soil monitoring data corresponding to each sample region are extracted. For each sample area, the stratification difference result of the sample area is calculated based on a subset of historical soil monitoring data, the set stratification information, and the stratification interpolation processing method; Feature recognition is performed on the stratified difference results corresponding to each sample area to obtain soil feature information corresponding to the target soil area; Radar feature identification is performed on multiple historical radar image data subsets corresponding to each sample region to obtain radar feature information corresponding to the target soil region. Based on radar and soil feature information, a feature set of the target soil area is generated, and the feature set is input into a pre-established recognition model for training until a priority flow recognition model that meets the set conditions is obtained.
[0012] The beneficial effects of adopting the above-mentioned further scheme are as follows: by constructing a priority flow identification model using historical radar image datasets, historical soil monitoring datasets, and ground priority flow survey data, and training it with feature data from positive and negative sample areas, the priority flow area of the target soil area at the current moment can be accurately obtained, thereby determining the potential priority flow risk area. This provides a more reliable basis for subsequently determining the probability of soil priority flow formation, flow velocity, and the scope of the affected area, and enables real-time assessment of soil priority flow and its influencing factors.
[0013] Furthermore, the step of selecting regions with non-priority flow features as negative sample regions based on historical soil monitoring datasets, historical radar image datasets, and preset sample generation rules includes: Based on timestamps and geographic coordinates, historical radar image datasets and historical soil monitoring datasets are matched to obtain corrected radar image datasets and corrected soil monitoring datasets. Based on the positive sample regions within the total range of the target soil region, initial negative sample candidate regions are generated. Based on the corrected soil monitoring dataset and soil texture classification algorithm corresponding to each initial negative sample candidate region, multiple initial negative sample candidate regions are screened to obtain multiple first negative sample candidate regions. Based on the corrected radar image dataset corresponding to each first negative sample candidate region, calculate the attenuation coefficient of each first negative sample candidate region. Based on the attenuation coefficient of each first negative sample candidate region, multiple second negative sample candidate regions are determined; Based on the corrected soil monitoring dataset corresponding to each second negative sample candidate region, the soil moisture content variation coefficient of each second negative sample candidate region is determined. Based on the soil moisture content variation coefficient of each second negative sample candidate area, multiple third negative sample candidate areas are determined, and each third negative sample candidate area is used as a negative sample region.
[0014] The beneficial effects of adopting the above-mentioned further scheme are as follows: by matching historical radar image datasets and historical soil monitoring datasets using timestamps and geographic coordinates, more accurate corrected data can be obtained; initial negative sample candidate regions are generated based on positive sample regions, providing a basis for subsequent screening; using a soil texture classification algorithm to screen initial negative sample candidate regions can initially filter out regions that do not meet the conditions to obtain the first negative sample candidate region; calculating the attenuation coefficient of the first negative sample candidate region can further screen to obtain the second negative sample candidate region; determining the soil moisture content variation coefficient of the second negative sample candidate region and determining the third negative sample candidate region as the negative sample region based on this can more accurately select regions with non-priority flow characteristics, improve the training accuracy and reliability of the priority flow identification model, and thus improve the accuracy of real-time assessment of soil priority flow and its influencing factors.
[0015] Furthermore, the step of determining potential priority flow risk zones within the target soil region based on the priority flow area and soil monitoring information includes: According to the preset regional division rules, the area surrounding the priority flow region is divided into multiple initial regions; Based on the climate information of each initial region, a first risk threshold is determined for each initial region; Based on soil monitoring information for each initial region, a second risk threshold is determined for each initial region; Based on the location of the priority flow region, the frequency of priority flow occurring in multiple initial regions corresponding to the historical priority flow region is obtained; Based on the frequency of occurrence in each of the initial regions, a third risk threshold is determined for each of the initial regions; Based on the first risk threshold, the second risk threshold, and the third risk threshold of each initial region, a risk threshold for each initial region is determined; Based on the location of the priority flow area, image information, climate information, and soil monitoring information, the weight of the risk threshold for each initial area is determined; Based on the risk threshold and corresponding weight of each initial region, the initial regions that meet the set score threshold are designated as potential priority flow risk regions.
[0016] The beneficial effects of adopting the above-mentioned further scheme are: by comprehensively considering the climate information, soil monitoring information and historical frequency of priority flow occurrence in the initial area surrounding the priority flow area, and combining multiple risk thresholds and corresponding weights to determine the potential priority flow risk area, the determination of the potential priority flow risk area is more accurate and comprehensive, providing a more reliable basis for the real-time assessment of soil priority flow and its influencing factors.
[0017] Furthermore, determining the crop information of the potential priority flow risk area based on the image information includes: The potential priority flow risk area is divided into multiple sub-regions; The image information is input into a neural network model to identify the crop type in each sub-region; For each sub-region, the cover of each crop is calculated based on the normalized vegetation index; For each sub-region, the growth status of each crop is determined based on its spectral characteristics, spatial characteristics, principal component analysis, and fuzzy comprehensive evaluation method.
[0018] The beneficial effects of adopting the above-mentioned further scheme are as follows: After dividing the potential priority flow risk area into multiple sub-regions, the crop types in each sub-region can be accurately identified using a neural network model. Based on the normalized vegetation index, the coverage of each crop can be calculated. Combining the spectral and spatial characteristics of each crop, the growth of the crops can be determined using principal component analysis and fuzzy comprehensive evaluation methods. This provides accurate crop information for subsequently determining the probability of soil priority flow formation, flow velocity, and affected area of the potential priority flow risk area.
[0019] Furthermore, the determination of the soil priority flow formation probability, flow velocity, and affected area range of the potential priority flow risk zone based on the predicted time, crop information, climate information, and soil monitoring information of the potential priority flow risk zone includes: The prediction time, crop information, climate information and soil monitoring information of the potential priority flow risk area are input into the pre-trained probabilistic prediction model to calculate the probability of soil priority flow formation in the priority flow risk area. The probabilistic prediction model is obtained by training a logistic regression model with historical prediction time, historical crop information, precipitation and soil moisture as prediction variables and soil priority flow formation under different conditions in historical data as dependent variables. Root resistance in each subregion is determined based on the crop type, cover, and growth status of each subregion; Based on soil monitoring information for each sub-region, the soil permeability coefficient and hydraulic gradient for each sub-region are determined; Based on the root resistance, soil permeability coefficient, and hydraulic gradient of each sub-region, the soil preferential flow velocity in the preferential flow risk zone is determined; Based on soil monitoring information, climate information, crop information, and soil moisture movement numerical models in potential priority flow risk areas, the movement process of soil priority flow is simulated, and the influence area of soil priority flow at different time steps is determined according to the simulation results.
[0020] The beneficial effects of adopting the above-mentioned further scheme are: based on the prediction time, crop information, climate information and soil monitoring information of the potential priority flow risk area, the probability of soil priority flow formation can be calculated using a pre-trained probabilistic prediction model; root resistance, soil permeability coefficient and hydraulic gradient can be determined according to the crop and soil monitoring information of the sub-region to calculate the flow velocity; and then the flow process can be simulated by combining the numerical model of soil moisture movement to determine the scope of the affected area, so as to realize the real-time assessment of the probability of soil priority flow formation, flow velocity and scope of the affected area of the potential priority flow risk area.
[0021] Secondly, this application provides a real-time assessment system for soil preferential flow and its influencing factors, employing the following technical solution: A real-time assessment system for soil preferential flow and its influencing factors includes: The acquisition module is used to acquire the priority flow area, image information, climate information, and soil monitoring information at different depths in the target soil area at the current time. The soil monitoring information includes soil moisture, temperature, resistivity, soil texture, soil porosity, soil structure, and slope at different depth monitoring points. The climate information includes temperature and precipitation. The first determining module is used to determine potential priority flow risk areas in the target soil area based on the priority flow area and soil monitoring information; The second determining module is used to determine crop information of the potential priority flow risk area based on the image information, wherein the crop information includes crop type, coverage and crop growth. The prediction module is used to determine the probability of soil priority flow formation, flow velocity, and affected area range of the potential priority flow risk area based on the prediction time, crop information, climate information, and soil monitoring information of the potential priority flow risk area.
[0022] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device includes a memory and a processor, wherein the memory stores a computer program capable of being loaded by the processor and executing a method for real-time assessment of soil priority flow and its influencing factors as described in any of the first aspects.
[0023] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program capable of being loaded by a processor and executed as described in any one of the first aspects, for real-time assessment of soil priority flow and its influencing factors.
[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description
[0025] Figure 1 A flowchart illustrating a method for real-time assessment of soil preferential flow and its influencing factors, provided as an embodiment of the present invention; Figure 2 A schematic diagram of a real-time assessment system for soil preferential flow and its influencing factors provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation
[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0027] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.
[0028] This application provides a method for real-time assessment of soil priority flow and its influencing factors. This method can be executed by an electronic device, which can be a server or a mobile terminal device. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The mobile terminal device can be a laptop computer, a desktop computer, etc., but is not limited to these.
[0029] like Figure 1 As shown, a real-time assessment method for soil preferential flow and its influencing factors mainly includes: S1, acquire the priority flow area, image information, climate information and soil monitoring information of the target soil area at the current time. The soil monitoring information includes soil moisture, temperature, resistivity, soil texture, soil porosity, soil structure and slope at different depth monitoring points. The climate information includes temperature and precipitation. In this embodiment, multiple miniature soil moisture sensors are deployed in the target soil area. Each sensor node integrates a capacitive moisture probe and a temperature compensation module. The node spacing is configured according to soil heterogeneity (default 20cm grid). Full coverage monitoring of the target soil area is achieved through LoRa wireless networking. In specific implementation, each sensor node includes a capacitive moisture probe and a temperature compensation circuit, and the nodes are connected via wireless communication modules to form a network.
[0030] When the precipitation in the climate information is greater than the set precipitation threshold, soil monitoring information of the target soil area is collected according to the first collection cycle. When the precipitation in the climate information is not greater than the set precipitation threshold, soil monitoring information of the target soil area is collected according to the second collection cycle. The first collection cycle is shorter than the second collection cycle.
[0031] Select a drone with high resolution and stable flight performance, equipped with a wide-angle or zoom high-definition camera. Plan the drone's flight path based on the size and terrain of the target soil area to ensure it covers the entire area and acquires image information of the soil surface.
[0032] In this embodiment of the application, obtaining the priority flow region of the target soil region at the current time includes: Acquire radar image data of the target soil area; Based on the soil monitoring information of the target soil area, the set stratification information and the stratification interpolation processing method, the stratification difference result of the target soil area is determined, and the stratification difference result characterizes the difference in soil physical properties between soil layers at different depths; Feature recognition is performed on the radar image data and layer difference results of the target soil area to obtain the current radar feature data and the current soil feature data. Based on the current radar feature data, current soil feature data, and the preset priority flow identification model, the priority flow area is determined.
[0033] In this embodiment, the stratification principle is determined based on factors such as soil physical properties, geological structure, and research objectives. For example, stratification can be based on soil texture variations, with sandy soil, loam, and clay layers treated as different layers; or stratification can be based on soil moisture or temperature variations, with areas exhibiting significant moisture or temperature changes treated as different layers. A stratified interpolation method is used to interpolate soil monitoring data within each stratum to obtain estimated values of soil physical properties at various locations within each stratum.
[0034] Optional, preset methods for constructing the priority flow identification model include: S11, acquire the historical radar image dataset, historical soil monitoring dataset, and surface priority flow survey data of the target soil area within a set time period. The historical radar image dataset is acquired by ground penetrating radar, and the surface priority flow survey data includes the location of areas in the target soil area where priority flow is known to exist, the type of priority flow, and the water supply. S12, Based on the ground priority flow survey data, determine the positive sample area, which represents the priority flow related area; S13, based on historical soil monitoring datasets, historical radar image datasets and preset sample generation rules, selects regions with non-priority flow features as negative sample regions; S14, both positive and negative sample regions are taken as sample regions, and a subset of historical radar image data and a subset of historical soil monitoring data corresponding to each sample region are extracted; S15, For each sample area, based on a subset of historical soil monitoring data, the set stratification information, and the stratification interpolation processing method, calculate the stratification difference result of the sample area; S16, perform feature recognition on the stratification difference results corresponding to each sample area to obtain soil feature information corresponding to the target soil area; S17, perform radar feature recognition on multiple historical radar image data subsets corresponding to each sample area to obtain radar feature information corresponding to the target soil area. S18. Based on radar feature information and soil feature information, generate a feature set of the target soil area, and input the feature set into a pre-established recognition model for training until a priority flow recognition model that meets the set conditions is obtained.
[0035] A priority flow identification model was constructed using historical radar image datasets, historical soil monitoring datasets, and ground priority flow survey data. The model was trained by combining feature data from positive and negative sample areas. It can accurately obtain the priority flow area of the target soil area at the current moment, thereby identifying potential priority flow risk areas. This provides a more reliable basis for subsequently determining the probability of soil priority flow formation, flow velocity, and the extent of the affected area, enabling real-time assessment of soil priority flow and its influencing factors.
[0036] In this embodiment, the priority flow recognition model is a Multi-Dimensional Lightweight SwinTransformer network. The Multi-Dimensional Lightweight SwinTransformer network uses lightweight one-dimensional group convolutional layers and one-dimensional separable convolutional layers to replace all multi-head self-attention linear transformations in the original Swin Transformer. The Multi-Dimensional Lightweight Swin Transformer network includes two variant architectures, each consisting of four stages. Each stage includes a parallel SwinGCNN module and a T-SwinSCNN module. The SwinGCNN module combines the SwinTransformer network with group convolutional operations, and the T-SwinSCNN module combines the SwinTransformer network with transpose operations and separable convolutions.
[0037] In this embodiment, the electronic device, based on a GIS buffer analysis tool, generates a 50m radius circular buffer for point data in the priority flow area location layer of the ground priority flow survey data, and a 20m wide strip buffer for linear data (such as priority flow paths), and outputs a polygonal layer of positive sample areas. According to the priority flow type (such as "finger flow" or "tube flow") in the ground priority flow survey data, a category label is assigned to each positive sample area, for example, Label∈{0,1,2}, where 0=finger flow, 1=tube flow, and 2=mixed flow.
[0038] Optionally, the step of selecting regions with non-priority flow features as negative sample regions based on historical soil monitoring datasets, historical radar image datasets, and preset sample generation rules includes: Based on timestamps and geographic coordinates, historical radar image datasets and historical soil monitoring datasets are matched to obtain corrected radar image datasets and corrected soil monitoring datasets. Based on the positive sample regions within the total range of the target soil region, initial negative sample candidate regions are generated. Based on the corrected soil monitoring dataset and soil texture classification algorithm corresponding to each initial negative sample candidate region, multiple initial negative sample candidate regions are screened to obtain multiple first negative sample candidate regions. Based on the corrected radar image dataset corresponding to each first negative sample candidate region, calculate the attenuation coefficient of each first negative sample candidate region. Based on the attenuation coefficient of each first negative sample candidate region, multiple second negative sample candidate regions are determined; Based on the corrected soil monitoring dataset corresponding to each second negative sample candidate region, the soil moisture content variation coefficient of each second negative sample candidate region is determined. Based on the soil moisture content variation coefficient of each second negative sample candidate area, multiple third negative sample candidate areas are determined, and each third negative sample candidate area is used as a negative sample region.
[0039] In this embodiment, the electronic device uses spatial difference operations to remove positive sample region polygons from the total range of the target soil region to generate initial negative sample candidate regions. If the area of the initial negative sample candidate region is not greater than the target sample size threshold, candidate regions are supplemented within the target soil region based on a random sampling algorithm.
[0040] Subsequently, areas with a sandy soil (sand content > 85%) or clay soil (clay content > 40%) ratio exceeding 60% or areas with soil porosity < 10% were excluded based on the soil texture classification algorithm. The corrected radar image dataset corresponding to the first negative sample candidate region is used to calculate the attenuation coefficient for each first negative sample candidate region. Finally, a sliding window analysis is invoked to calculate the coefficient of variation of soil moisture content in historical data for each candidate region, determine multiple third negative sample candidate regions, and designate each of the third negative sample candidate regions as a negative sample region.
[0041] In this embodiment of the application, feature recognition is performed on the stratified difference results corresponding to each sample area to obtain the soil feature information corresponding to the target soil area. This is achieved by extracting time-series features, such as autocorrelation coefficient, moving average, trend term, etc.
[0042] S2, Based on the priority flow area and soil monitoring information, determine the potential priority flow risk area in the target soil area; In this embodiment of the application, determining the potential priority flow risk zone in the target soil area based on the priority flow area and soil monitoring information includes: According to the preset regional division rules, the area surrounding the priority flow region is divided into multiple initial regions; Based on the climate information of each initial region, a first risk threshold is determined for each initial region; Based on soil monitoring information for each initial region, a second risk threshold is determined for each initial region; Based on the location of the priority flow region, the frequency of priority flow occurring in multiple initial regions corresponding to the historical priority flow region is obtained; Based on the frequency of occurrence in each of the initial regions, a third risk threshold is determined for each of the initial regions; Based on the first risk threshold, the second risk threshold, and the third risk threshold of each initial region, a risk threshold for each initial region is determined; Based on the location of the priority flow area, image information, climate information, and soil monitoring information, the weight of the risk threshold for each initial area is determined; Based on the risk threshold and corresponding weight of each initial region, the initial regions that meet the set score threshold are designated as potential priority flow risk regions.
[0043] In this embodiment, the terrain moisture index (TWI) is calculated by combining digital elevation model (DEM) data with preset geographical weighted regional division rules and dynamic grid technology to divide the area surrounding the priority flow area into multiple regions. The regions are further subdivided according to land use type, such as farmland, woodland, urban green space and soil type, to obtain multiple initial regions. The boundary resolution of the initial regions is automatically adjusted according to the real-time soil moisture gradient, and the grid density is increased in the priority flow high-incidence area.
[0044] Subsequently, based on high-resolution precipitation data (such as radar-retrieved precipitation), previous precipitation index and evapotranspiration data for each initial region, climate-preferred flow correlation features were trained using a random forest model to determine the first risk threshold for each initial region. The evapotranspiration data was calculated by combining the vegetation cover type of each initial region. Based on the soil moisture, temperature, electrical conductivity, aggregate stability, and fractal dimension of pore distribution in each initial region, the second risk threshold is determined by inputting the data into a support vector machine model after dimensionality reduction through principal component analysis. Based on the location of priority flow areas, the frequency of priority flow occurrence in different seasons and land use types for the corresponding initial areas is extracted from the historical database. A third risk threshold for each initial area is calculated using a Bayesian probability model. Finally, based on the location of priority flow areas, multispectral image information, climate information, and soil monitoring information, a time-series LSTM network is constructed to predict the real-time influence weights of each risk factor. The weight allocation strategy is dynamically optimized to minimize the false negative and false positive rates. Furthermore, based on the risk threshold and corresponding weight of each initial region, initial regions meeting the set score threshold are designated as potential priority flow risk zones.
[0045] By comprehensively considering climate information, soil monitoring information, and historical frequency of priority flow occurrence in the initial area surrounding the priority flow area, and combining multiple risk thresholds and corresponding weights, potential priority flow risk areas are determined, making the determination of potential priority flow risk areas more accurate and comprehensive.
[0046] S3, based on the image information, determine the crop information of the potential priority flow risk area, the crop information including crop type, coverage and crop growth; In this embodiment of the application, determining the crop information of the potential priority flow risk area based on the image information includes: The potential priority flow risk area is divided into multiple sub-regions; The image information is input into a neural network model to identify the crop type in each sub-region; For each sub-region, the cover of each crop is calculated based on the normalized vegetation index; For each sub-region, the growth status of each crop is determined based on its spectral characteristics, spatial characteristics, principal component analysis, and fuzzy comprehensive evaluation method.
[0047] In this embodiment, Geographic Information System (GIS) technology is used, combined with topographic data of the potential priority flow risk area, such as altitude, slope, and aspect, to divide the potential priority flow risk area into multiple sub-regions. For example, in mountainous areas, the area is divided into layers at certain intervals (e.g., 100 meters) according to altitude, with areas at different altitudes considered as different sub-regions; in plains areas, areas with similar slopes are grouped together based on slope variations. Soil type distribution can also be considered; through soil survey data, areas with the same or similar soil types are grouped into one sub-region. Because soil type has a significant impact on crop growth and water movement, crop information may differ between areas with different soil types.
[0048] Neural network models can employ deep convolutional neural networks (CNNs), recurrent neural networks (RNNs), etc. Deep CNNs excel in image recognition, while RNNs are suitable for processing sequential data. For each sub-region, the cover of each crop is calculated based on the normalized vegetation index (NVI). The NVI can be calculated using satellite or UAV imagery. For each sub-region, the growth status of each crop is determined based on its spectral and spatial characteristics, principal component analysis, and fuzzy comprehensive evaluation.
[0049] S4. Based on the predicted time, crop information, climate information and soil monitoring information of the potential priority flow risk area, determine the soil priority flow formation probability, flow velocity and affected area range of the potential priority flow risk area.
[0050] In this embodiment of the application, based on the predicted time, crop information, climate information, and soil monitoring information of the potential priority flow risk zone, the probability of soil priority flow formation, flow velocity, and affected area range of the potential priority flow risk zone are determined, including: S41, input the prediction time, crop information, climate information and soil monitoring information of the potential priority flow risk area into the pre-trained probability prediction model, calculate the probability of soil priority flow formation in the priority flow risk area. The probability prediction model is obtained by training a logistic regression model with historical prediction time, historical crop information, precipitation and soil moisture as prediction variables and soil priority flow formation under different conditions in historical data as dependent variables. S42, Based on the crop type, cover, and growth status of each sub-region, determine the root resistance of each sub-region; In this embodiment, for each sub-region, the impact of identified crop species, cover conditions, and growth status on soil root resistance is analyzed. Different crop species have different root structures and growth characteristics, resulting in varying levels of resistance to the soil. A mathematical model is established using regression analysis to correlate root resistance with parameters such as crop root biomass and cover, and the root resistance of each sub-region is calculated based on crop information.
[0051] S43, Based on the soil monitoring information of each sub-region, determine the soil permeability coefficient and hydraulic gradient of each sub-region; S44, Based on the root resistance, soil permeability coefficient and hydraulic gradient of each sub-region, determine the soil preferential flow velocity in the preferential flow risk zone; In this embodiment, the soil permeability coefficient of each sub-region is determined using empirical formulas or experimental data based on parameters such as soil texture and porosity. For example, the permeability coefficient is relatively large for sandy soil and relatively small for clay. Within each sub-region, the hydraulic gradient is calculated using water level heights at different locations. The soil permeability coefficient, hydraulic gradient, and root resistance of each sub-region are then substituted into the modified Darcy's law formula to calculate the preferential flow velocity in each sub-region.
[0052] S45 uses a numerical model based on soil monitoring information, climate information, crop information, and soil moisture movement in potential priority flow risk areas to simulate the movement process of soil priority flow, and determines the range of influence area of soil priority flow at different time steps based on the simulation results.
[0053] In this embodiment, a numerical model is used to simulate the movement process of preferential soil flow. Different time steps are set, and the movement of preferential soil flow at different times is simulated step-by-step, starting from the predicted time. During the simulation, processes such as soil moisture infiltration, diffusion, formation, and flow of preferential flow are considered. Based on the simulation results, the diffusion range and affected area of preferential soil flow at different time steps are analyzed.
[0054] This method provides a rich and comprehensive data foundation for assessment by acquiring priority flow areas, image information, climate information, and soil monitoring information containing multiple parameters for the target soil region at the current moment. This reduces assessment errors caused by single or incomplete data and improves the accuracy of soil priority flow assessment. Based on priority flow areas and soil monitoring information, potential priority flow risk zones in the target soil region are identified. By understanding crop information in this area, the formation probability, flow velocity, and affected area of soil priority flow are determined, enabling real-time assessment of soil priority flow and its influencing factors. This can help farmers rationally plan crop planting layouts. Based on the assessment results, corresponding measures can be taken to improve soil structure, regulate soil moisture, and control water flow, thereby reducing the negative impacts of priority flow, protecting soil resources, and promoting sustainable soil use.
[0055] Figure 2 A schematic diagram of a real-time assessment system 200 for soil preferential flow and its influencing factors is shown.
[0056] like Figure 2 As shown, a real-time assessment system 200 for soil preferential flow and its influencing factors mainly includes: The acquisition module 201 is used to acquire the priority flow area, image information, climate information, and soil monitoring information at different depths in the target soil area at the current time. The soil monitoring information includes soil moisture, temperature, resistivity, soil texture, soil porosity, soil structure, and slope at different depth monitoring points. The climate information includes temperature and precipitation. The first determining module 202 is used to determine potential priority flow risk areas in the target soil area based on the priority flow area and soil monitoring information; The second determining module 203 is used to determine crop information of the potential priority flow risk area based on the image information, wherein the crop information includes crop type, coverage and crop growth. The prediction module 204 is used to determine the probability of soil priority flow formation, flow velocity and affected area of the potential priority flow risk area based on the prediction time, crop information, climate information and soil monitoring information of the potential priority flow risk area.
[0057] In one example, the module in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
[0058] For example, when modules in a device can be implemented via a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).
[0059] In this application, various objects such as messages / information / devices / network elements / systems / apparatus / actions / operations / processes / concepts may be named. It is understood that these specific names do not constitute a limitation on the relevant objects. The names may be changed depending on the scenario, context, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from their functions and technical effects embodied / performed in the technical solution.
[0060] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0061] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0062] Figure 3 This is a structural block diagram of an electronic device 300 according to an embodiment of this application.
[0063] like Figure 3As shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.
[0064] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps in the aforementioned method for real-time assessment of soil priority flow and its influencing factors. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.
[0065] I / O interface 303 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 304 is used to test wired or wireless communication between electronic device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 304 may include a Wi-Fi component, a Bluetooth component, and an NFC component.
[0066] The communication bus 305 may include a path for transmitting information between the aforementioned components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.
[0067] The electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute a real-time assessment method for soil priority flow and its influencing factors as described in the above embodiments.
[0068] The following describes the computer-readable storage medium provided in the embodiments of this application. The computer-readable storage medium described below can be referred to in correspondence with the method for real-time assessment of soil priority flow and its influencing factors described above.
[0069] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for real-time assessment of soil priority flow and its influencing factors.
[0070] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0071] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0072] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.
Claims
1. A method for real-time assessment of soil preferential flow and its influencing factors, characterized in that, include: The system acquires the priority flow area, image information, climate information, and soil monitoring information of the target soil area at the current moment. The soil monitoring information includes soil moisture, temperature, resistivity, soil texture, soil porosity, soil structure, and slope at monitoring points at different depths. The climate information includes temperature and precipitation. Based on the priority flow areas and soil monitoring information, potential priority flow risk zones in the target soil areas are identified; Based on the image information, crop information for the potential priority flow risk area is determined, including crop type, coverage, and crop growth. Based on the predicted time, crop information, climate information, and soil monitoring information of the potential priority flow risk zone, the probability of soil priority flow formation, flow velocity, and affected area range of the potential priority flow risk zone are determined.
2. The method for real-time assessment of soil preferential flow and its influencing factors according to claim 1, characterized in that, The acquisition of the priority flow region of the target soil region at the current moment includes: Acquire radar image data of the target soil area; Based on the soil monitoring information of the target soil area, the set stratification information and the stratification interpolation processing method, the stratification difference result of the target soil area is determined, and the stratification difference result characterizes the difference in soil physical properties between soil layers at different depths; Feature recognition is performed on the radar image data and layer difference results of the target soil area to obtain the current radar feature data and the current soil feature data. Based on the current radar feature data, current soil feature data, and the preset priority flow identification model, the priority flow area is determined.
3. The method for real-time assessment of soil preferential flow and its influencing factors according to claim 2, characterized in that, The method for constructing the preset priority flow identification model includes: The system acquires historical radar image datasets, historical soil monitoring datasets, and surface priority flow survey data for the target soil area over a set time period. The historical radar image datasets are collected by ground penetrating radar, and the surface priority flow survey data includes the location of areas within the target soil area where priority flow phenomena are known to exist, the type of priority flow, and the water supply. Based on the ground priority flow survey data, positive sample areas are determined, and the positive sample areas represent priority flow related areas. Based on historical soil monitoring datasets, historical radar image datasets, and preset sample generation rules, regions with non-priority flow features are selected as negative sample regions. Both positive and negative sample regions are used as sample regions, and a subset of historical radar image data and a subset of historical soil monitoring data corresponding to each sample region are extracted. For each sample area, the stratification difference result of the sample area is calculated based on a subset of historical soil monitoring data, the set stratification information, and the stratification interpolation processing method; Feature recognition is performed on the stratified difference results corresponding to each sample area to obtain soil feature information corresponding to the target soil area; Radar feature identification is performed on multiple historical radar image data subsets corresponding to each sample region to obtain radar feature information corresponding to the target soil region. Based on radar and soil feature information, a feature set of the target soil area is generated, and the feature set is input into a pre-established recognition model for training until a priority flow recognition model that meets the set conditions is obtained.
4. The method for real-time assessment of soil preferential flow and its influencing factors according to claim 3, characterized in that, The method of selecting regions with non-priority flow features as negative sample regions based on historical soil monitoring datasets, historical radar image datasets, and preset sample generation rules includes: Based on timestamps and geographic coordinates, historical radar image datasets and historical soil monitoring datasets are matched to obtain corrected radar image datasets and corrected soil monitoring datasets. Based on the positive sample regions within the total range of the target soil region, initial negative sample candidate regions are generated. Based on the corrected soil monitoring dataset and soil texture classification algorithm corresponding to each initial negative sample candidate region, multiple initial negative sample candidate regions are screened to obtain multiple first negative sample candidate regions. Based on the corrected radar image dataset corresponding to each first negative sample candidate region, calculate the attenuation coefficient of each first negative sample candidate region. Based on the attenuation coefficient of each first negative sample candidate region, multiple second negative sample candidate regions are determined; Based on the corrected soil monitoring dataset corresponding to each second negative sample candidate region, the soil moisture content variation coefficient of each second negative sample candidate region is determined. Based on the soil moisture content variation coefficient of each second negative sample candidate area, multiple third negative sample candidate areas are determined, and each third negative sample candidate area is used as a negative sample region.
5. The method for real-time assessment of soil preferential flow and its influencing factors according to claim 3, characterized in that, The process of identifying potential priority flow risk zones within the target soil region based on the priority flow area and soil monitoring information includes: According to the preset regional division rules, the area surrounding the priority flow region is divided into multiple initial regions; Based on the climate information of each initial region, a first risk threshold is determined for each initial region; Based on soil monitoring information for each initial region, a second risk threshold is determined for each initial region; Based on the location of the priority flow region, the frequency of priority flow occurring in multiple initial regions corresponding to the historical priority flow region is obtained; Based on the frequency of occurrence in each of the initial regions, a third risk threshold is determined for each of the initial regions; Based on the first risk threshold, the second risk threshold, and the third risk threshold of each initial region, a risk threshold for each initial region is determined; Based on the location of the priority flow area, image information, climate information, and soil monitoring information, the weight of the risk threshold for each initial area is determined; Based on the risk threshold and corresponding weight of each initial region, the initial regions that meet the set score threshold are designated as potential priority flow risk regions.
6. The method for real-time assessment of soil preferential flow and its influencing factors according to claim 1, characterized in that, The step of determining crop information for the potential priority flow risk area based on the image information includes: The potential priority flow risk area is divided into multiple sub-regions; The image information is input into a neural network model to identify the crop type in each sub-region; For each sub-region, the cover of each crop is calculated based on the normalized vegetation index; For each sub-region, the growth status of each crop is determined based on its spectral characteristics, spatial characteristics, principal component analysis, and fuzzy comprehensive evaluation method.
7. The method for real-time assessment of soil preferential flow and its influencing factors according to claim 6, characterized in that, The determination of the soil priority flow formation probability, flow velocity, and affected area range of the potential priority flow risk zone based on the predicted time, crop information, climate information, and soil monitoring information of the potential priority flow risk zone includes: The prediction time, crop information, climate information and soil monitoring information of the potential priority flow risk area are input into the pre-trained probabilistic prediction model to calculate the probability of soil priority flow formation in the priority flow risk area. The probabilistic prediction model is obtained by training a logistic regression model with historical prediction time, historical crop information, precipitation and soil moisture as prediction variables and soil priority flow formation under different conditions in historical data as dependent variables. Root resistance in each subregion is determined based on the crop type, cover, and growth status of each subregion; Based on soil monitoring information for each sub-region, the soil permeability coefficient and hydraulic gradient for each sub-region are determined; Based on the root resistance, soil permeability coefficient, and hydraulic gradient of each sub-region, the soil preferential flow velocity in the preferential flow risk zone is determined; Based on soil monitoring information, climate information, crop information, and soil moisture movement numerical models in potential priority flow risk areas, the movement process of soil priority flow is simulated, and the influence area of soil priority flow at different time steps is determined according to the simulation results.
8. A real-time assessment system for soil preferential flow and its influencing factors, characterized in that, include: The acquisition module is used to acquire the priority flow area, image information, climate information, and soil monitoring information at different depths in the target soil area at the current time. The soil monitoring information includes soil moisture, temperature, resistivity, soil texture, soil porosity, soil structure, and slope at different depth monitoring points. The climate information includes temperature and precipitation. The first determining module is used to determine potential priority flow risk areas in the target soil area based on the priority flow area and soil monitoring information; The second determining module is used to determine crop information of the potential priority flow risk area based on the image information, wherein the crop information includes crop type, coverage and crop growth. The prediction module is used to determine the probability of soil priority flow formation, flow velocity, and affected area range of the potential priority flow risk area based on the prediction time, crop information, climate information, and soil monitoring information of the potential priority flow risk area.
9. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, Includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1-7.