A method and system for identifying low-efficiency areas of a saline-alkali soil hole-disk seedling flower sea

Abstract

This invention belongs to the field of data processing technology and proposes a method and system for identifying inefficient areas in saline-alkali land flower fields using seedling trays. Specifically, the method involves: first, acquiring the spatial boundary information of the flower field area; then, dividing the area into grids based on the spatial boundary information; periodically collecting multi-temporal remote sensing data for each grid; and constructing a time-series measurement of saline-alkali land corresponding to each grid using the multi-temporal remote sensing data; finally, determining whether there is a risk of salinity accumulation and water stagnation imbalance based on the time-series measurement of saline-alkali land. Based on multi-source remote sensing data, a dynamic imbalance risk identification model is established, effectively solving the management problems of accurately identifying potential inefficient areas and making irrigation decisions unsuitable for local conditions when flower fields are deployed over large areas in saline-alkali land. This significantly improves the landscape stability, resource utilization efficiency, and management accuracy of saline-alkali land flower systems, providing effective support for achieving large-scale, intelligent, and low-intervention landscape ecosystem operation.

Description

Technical Field

[0001] This invention belongs to the field of defect recognition and image processing technology, specifically relating to a method and system for identifying inefficient areas of saline-alkali soil seedling tray flower fields. Background Technology

[0002] In current practices of flower cultivation in saline-alkali land, plug seedlings are widely used in the construction of large-scale flower fields as a cultivation method that facilitates transplanting and centralized management. This is combined with drip irrigation and sprinkler irrigation to improve plant survival rates and enhance landscape balance. However, due to the natural defects of saline-alkali land, such as loose soil structure, weak water retention capacity, and the tendency of salt to migrate with water and accumulate in evaporation areas, even with a uniformly deployed irrigation system initially, it is difficult to achieve long-term effective water-salt dynamic balance. Existing technologies mostly rely on regular manual inspections for irrigation adjustments and replanting assessments, identifying potential problem areas based on visual observation of growth or soil moisture sampling. More advanced methods utilize intelligent means such as multispectral remote sensing and low-altitude drone image analysis for regional diagnosis, identifying abnormal growth areas by analyzing plant reflectance or NDVI growth index. This improves monitoring efficiency to some extent, but it ignores the unique characteristics of saline-alkali land, such as highly reflective soil, localized alkaline patches, and low seedling biomass. Ultimately, the identification scheme is prone to misjudgment, especially in accurately depicting regional areas of inefficient growth caused by micro-topography and water-salt coupling.

[0003] In the practical application of these solutions, the main technical problem is the inability to accurately identify localized inefficient areas caused by uneven water and salt migration and slight differences in seed tray placement—that is, the risk of salt accumulation and water retention imbalance. Because salt migrates in the soil under the influence of irrigation water and is controlled by evaporation, groundwater level, and micro-topographic slope, its redistribution in vertical and horizontal space often forms salt accumulation points or water retention zones. These areas may appear identical to normal areas initially, making them difficult to quickly identify using single image features. Salt accumulation and water retention problems lead to imbalanced irrigation resource allocation, prolonged manual replanting cycles, and even damage to the visual continuity and ecological stability of the entire flower field, ultimately increasing maintenance costs and reducing the utilization efficiency of saline-alkali land. Especially during important festivals or exhibitions, a concentrated outbreak of wilting in inefficient areas can cause macro-landscape disruptions or failure of ecological demonstrations. Summary of the Invention

[0004] The purpose of this invention is to propose a method and system for identifying inefficient areas of saline-alkali soil seedling tray flower fields, so as to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions.

[0005] To achieve the above objectives, according to one aspect of the present invention, a method for identifying inefficient areas of saline-alkali soil seedling tray flower fields is provided, the method comprising the following steps:

[0006] S100: Obtain spatial boundary information of the flower sea area;

[0007] S200: Grid division of the region based on spatial boundary information;

[0008] S300: Regularly collect multi-temporal remote sensing data from each grid;

[0009] S400: Construct time-series data of alkaline land corresponding to each grid using multi-temporal remote sensing data;

[0010] S500: Determines the risk of saline accumulation and water stagnation imbalance based on time-series measurements of alkaline land.

[0011] Furthermore, in step S100, the method for obtaining the spatial boundary information of the flower sea area is as follows: the spatial boundary information includes data based on field surveying and mapping data, remote sensing images, or geographic information system data, which is used to determine the external boundary range of the flower sea planting area.

[0012] Spatial boundary information serves as the foundation of the entire inefficient area identification process. This includes, but is not limited to, high-resolution remote sensing imagery, on-site drone aerial photography data, ground-measured geographic coordinate data, or plot boundary data obtained from existing GIS geographic information systems. Specifically, using multispectral imagery acquired by drones, the outer contour of the actual planting area is extracted through image recognition or annotation. Furthermore, NDVI vegetation index, soil reflectance, and historical planting data should be combined to plan layers, achieving precise delineation of the actual cultivation area. This is because irregular transition zones often exist at the boundaries in saline-alkali environments, such as saline-alkali bare land, non-vegetated areas, or mixed vegetation zones.

[0013] The significance of determining spatial boundary information in the ecological environment of saline-alkali land is that salt accumulates along the low-lying areas of the surface micro-topography, which makes it easy for salt accumulation dead zones to form at the edge. At the same time, the water permeability and wind erosion of the boundary area may be significantly different from those of the central area, which will have an edge effect on the overall water and salt migration pattern.

[0014] Furthermore, in step S200, the method for dividing the region into grids based on spatial boundary information is as follows: a two-dimensional regular grid with equal spacing or adaptive scale is constructed within the spatial boundary range, and each grid cell has a unique spatial identifier.

[0015] The target area is divided using a regular two-dimensional grid. Typically, a grid structure can be generated based on an equal-spacing division method under a projected coordinate system. Alternatively, an adaptive non-uniform scale grid system can be constructed based on topographic relief, known vegetation distribution density, or soil heterogeneity to better adapt to the natural differences within the region.

[0016] Each grid cell, serving as the smallest spatial unit for subsequent time-series analysis, must possess a clear geographic reference, including its center point latitude and longitude, range coordinates, and identification number, to facilitate spatial alignment and indexing operations during subsequent data acquisition, analysis, and result mapping. This gridding process can be implemented using GIS software, remote sensing image processing platforms, or custom scripts, and can be dynamically adjusted based on the scale and resolution requirements of the flower field during actual deployment.

[0017] The purpose of this step is to provide a data framework for the processing steps of multi-temporal image overlay, pixel attribution management, and local time series extraction. A unified spatial division standard enables remote sensing data acquired at different time points to establish a one-to-one correspondence in the time dimension under the same grid system, effectively improving the accuracy and robustness of subsequent time series modeling and anomaly identification.

[0018] Furthermore, in step S300, the method for periodically collecting multi-temporal remote sensing data of each grid is as follows: multispectral image data collected by a multispectral remote sensing imager mounted on a UAV is used as multi-temporal remote sensing data, and vegetation index enhancement preprocessing is performed on the multi-temporal remote sensing data, that is, NDVI layer of multi-temporal remote sensing data is constructed based on red light and near-infrared bands.

[0019] The multi-temporal remote sensing data refers to a collection of remote sensing images acquired periodically at multiple time points in the same spatial area using the same remote sensing device during the flower planting cycle. The multispectral image data covers at least the near-infrared (760–900 nm) and visible light (450–700 nm) bands.

[0020] In multi-temporal remote sensing data, an NDVI layer is constructed based on red and near-infrared bands and used as a vegetation activity index, providing highly sensitive physiological state observation variables for time-series modeling. NDVI (Normalized Difference Vegetation Index) is a common vegetation cover index in spectral images; its calculation process will not be elaborated further.

[0021] Multi-temporal remote sensing data is stored in the computer in the GeoTIFF three-dimensional array format, and its preprocessing also includes registration, radiometric correction and cloud cover removal.

[0022] The goal of this step is to construct a time-series-based system that gradually accumulates historical spectral data at different seedling stages to capture early change signals and build a normalized vegetation index to correlate regional growth trends over time. This will serve as a key basis for subsequently determining the risk of salinity accumulation and water retention imbalance.

[0023] Further, in step S400, the method for constructing the time-series of alkali land corresponding to each grid using multi-temporal remote sensing data is as follows: In any multi-temporal remote sensing data obtained, the average pixel values ​​of red light, blue light and infrared light within the grid are recorded as R_red, R_blue and R_nir respectively, the moisture parameter is recorded as the ratio of R_nir to R_red, and the alkali return parameter is recorded as the Euclidean norm of R_red and R_blue. The time point of each acquisition of multi-temporal remote sensing data is recorded as a measurement point, and the time-series of alkali land is constructed by the moisture parameter, alkali return parameter and NDVI layer corresponding to each time-series continuous measurement point.

[0024] The specific calculation method for the alkali return parameter is as follows: SBIdx = sqrt(R_red) 2 +R_blue 2 The expression sqrt represents the square root function. The efflorescence parameter is used to detect highly reflective areas, such as exposed efflorescence on the ground surface. In saline-alkali environments, salts are often dissolved in groundwater or irrigation water. Furthermore, under conditions of strong sunlight and high evaporation, water migrates upwards from underground or within the soil. After evaporation, the salts remaining on the surface form efflorescence patches. Therefore, the efflorescence parameter in saline-alkali environments shows significant and uncertain changes over time or with irrigation. The moisture parameter, on the other hand, reflects the suppressive effect of surface soil moisture content on near-infrared reflectance and is a sensitive indicator for monitoring waterlogged areas.

[0025] From a microscopic perspective, the fundamental principle behind the need for time-series analysis lies in the significant nonlinearity, hysteresis, and local feedback inherent in the water-salt migration process within saline-alkali soils. Once the seedlings in plug trays have established themselves in the planting area, root activity alters local water channels, while irrigation further disrupts the original salt redistribution pathways, leading to rapid salt accumulation or impaired water penetration, ultimately resulting in slow seedling growth or even death. This heterogeneity is not statically generated but rather arises from the dynamic evolution of the soil-water-seedling coupling, making it difficult to accurately characterize using image recognition at a single moment, thus forming the current technical bottleneck.

[0026] Further, in step S500, the method for determining whether the risk of salinity accumulation and water stagnation imbalance has occurred based on the time-series measurement of alkaline land is as follows: the average value of the pixel value of the NDVI layer corresponding to any measuring point is defined as the ecological parameter, the average value of the ecological parameter corresponding to a measuring point and the previous 3-7 measuring points is defined as the previous value of the ecological parameter, and the difference between the state parameter of the measuring point and the previous value of the ecological parameter is defined as the ecological parameter anomaly D_NDVI. If the ecological parameter anomaly is negative, the current measuring point is marked as a negative ecological measuring point.

[0027] The difference in moisture parameters between any monitoring point and the previous monitoring point is denoted as D_MIdx, and the difference in alkali return parameters is denoted as D_SBIdx. The focusing time interval is defined as 15-20 days. The imbalance risk index is calculated based on the ecological parameter anomalies, D_MIdx, and D_SBIdx of each negative ecological monitoring point within the focusing time interval. The sub-scores of the imbalance risk index corresponding to all grids in the same monitoring point are used as the index threshold. Grids with imbalance risk indices less than the index threshold are marked as imbalanced at the monitoring point. If more than half of the grids are marked as imbalanced within the focusing time interval, it is determined that there is a risk of salinity accumulation and water stagnation imbalance.

[0028] The mathematical expression for calculating the imbalance risk index is IR_Value = D_NDVI × mean < W_i1 × (a1·D_MIdx(i1) + a2·D_SBIdx(i1))>, where a1 and a2 are the weight values ​​of the moisture parameter and the alkali return parameter, respectively, with a default value of 0.5. W_i1 is the time distance weight, which is mathematically expressed as W_i1 = 1 + exp(-i1), where i1 is the sequence number of the negative ecological measurement point in the focused time interval, and a sequence number of 1 represents the current natural day. D_MIdx(i1) and D_SBIdx(i1) represent the D_MIdx and D_SBIdx corresponding to the i1th natural day in the focused time interval, respectively, and mean is the sign of the average value function.

[0029] The principle behind the judgment process is that, due to the dual constraints of water supply and salt accumulation on plant growth in saline-alkali environments, the root system exhibits a significant lag response to microenvironmental changes. Therefore, when local soil salt accumulation or water retention occurs, the NDVI ecological parameter of plants often does not fluctuate drastically immediately, but rather shows a gradual decline or a persistently low value. Thus, this method uses previous values ​​of ecological parameters to identify whether the flower sea plants in the area are in a degenerative trend of disrupted equilibrium. The quantification process of the imbalance risk index utilizes the high values ​​of previous water and salt disturbances and the high values ​​of current ecological decline. When both are simultaneously established, the risk index increases significantly, effectively filtering out misjudgments caused by non-critical disturbances or short-term fluctuations. The structure of ecological triggers and water and salt accumulation drives reflects the strength of the causal relationship between water and salt migration imbalance leading to plant decline in the saline-alkali plug seedling system, constituting a dynamic imbalance judgment mechanism with sensitivity, directionality, and lag tolerance. The occurrence of salt accumulation and water retention imbalance risk indicates that the area corresponding to that grid is an inefficient area of ​​saline-alkali plug seedling flower sea.

[0030] Further, in step S600, the risk identification result is fed back to the terminal for decision support, including the irrigation amount or preferred irrigation method. In this invention, all undefined variables, if not explicitly defined, can be manually set thresholds.

[0031] This invention also provides a system for identifying inefficient areas of saline-alkali soil seedling tray flower fields. This system includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for identifying inefficient areas of saline-alkali soil seedling tray flower fields. This system can run on computing devices such as desktop computers, laptops, handheld computers, and cloud data centers. The runnable system may include, but is not limited to, processors, memory, and server clusters. The processor executes the computer program within the following system units:

[0032] Boundary recognition unit, used to obtain spatial boundary information of the flower sea area;

[0033] Meshable cells are used to divide a region into grids based on spatial boundary information.

[0034] The spectral data acquisition unit is used to periodically acquire multi-temporal remote sensing data from each grid.

[0035] The time-series construction unit is used to construct time-series data of alkaline land corresponding to each grid using multi-temporal remote sensing data.

[0036] The salt accumulation and water stagnation imbalance risk assessment unit is used to determine whether a salt accumulation and water stagnation imbalance risk has occurred based on the time-series measurement of alkaline land.

[0037] The beneficial effects of this invention are as follows: This invention provides a method and system for identifying inefficient areas in saline-alkali land flower fields using tray seedlings. Based on multi-source remote sensing data, it constructs a time-series analytical framework oriented towards the ecological response mechanism of saline-alkali land. By abstractly expressing the coupling relationship between vegetation growth status and water-salt dynamics, it establishes a risk identification model for dynamic imbalance, effectively solving the management problems of "difficulty in accurately identifying potential inefficient areas and inability to make irrigation decisions according to local conditions" when flower fields are deployed on a large scale in saline-alkali land. In the existing model, uniform irrigation often causes water shortages, waterlogging, or salt accumulation in some areas, wasting water resources and causing local degradation of the flower landscape, forming visual faults and reducing the overall display effect. The judgment results not only support the generation of regional irrigation control strategies, but also form a hierarchical early warning layer to assist operation and maintenance personnel in adjusting replanting and intervention plans in a timely manner, avoiding the concentrated outbreak of catastrophic losses, and improving the foresight and response efficiency of management. Compared with the traditional method that relies on manual inspection and static image judgment, this invention significantly improves the landscape stability, resource utilization efficiency, and management accuracy of saline-alkali land flower systems, providing effective support for the realization of large-scale, intelligent, and low-intervention landscape ecosystem operation. Attached Figure Description

[0038] The above and other features of the present invention will become more apparent from the detailed description of the embodiments shown in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals denote the same or similar elements. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort. In the drawings:

[0039] Figure 1 The diagram shows a flowchart of a method for identifying inefficient areas of saline-alkali soil seedling tray flower fields.

[0040] Figure 2 The diagram shows the structure of a system for identifying inefficient areas of saline-alkali soil seedling trays for flower fields. Detailed Implementation

[0041] The following will provide a clear and complete description of the concept, specific structure, and technical effects of the present invention in conjunction with the embodiments and accompanying drawings, so as to fully understand the purpose, solution, and effects of the present invention. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0042] like Figure 1 The diagram shows a flowchart of a method for identifying inefficient areas of saline-alkali soil seedling planting sites. The following section will combine... Figure 1 This invention describes a method for identifying inefficient areas of saline-alkali soil seedling planting beds, comprising the following steps:

[0043] S100: Obtain spatial boundary information of the flower sea area;

[0044] S200: Grid division of the region based on spatial boundary information;

[0045] S300: Regularly collect multi-temporal remote sensing data from each grid;

[0046] S400: Construct time-series data of alkaline land corresponding to each grid using multi-temporal remote sensing data;

[0047] S500: Determines the risk of saline accumulation and water stagnation imbalance based on time-series measurements of alkaline land.

[0048] Furthermore, in step S100, the method for obtaining the spatial boundary information of the flower sea area is as follows: the spatial boundary information includes data based on field surveying and mapping data, remote sensing images, or geographic information system data, which is used to determine the external boundary range of the flower sea planting area.

[0049] Spatial boundary information serves as the foundation of the entire inefficient area identification process. This includes, but is not limited to, high-resolution remote sensing imagery, on-site drone aerial photography data, ground-measured geographic coordinate data, or plot boundary data obtained from existing GIS geographic information systems. Specifically, using multispectral imagery acquired by drones, the outer contour of the actual planting area is extracted through image recognition or annotation. Furthermore, NDVI vegetation index, soil reflectance, and historical planting data should be combined to plan layers, achieving precise delineation of the actual cultivation area. This is because irregular transition zones often exist at the boundaries in saline-alkali environments, such as saline-alkali bare land, non-vegetated areas, or mixed vegetation zones.

[0050] Furthermore, in step S200, the method for dividing the region into grids based on spatial boundary information is as follows: a two-dimensional regular grid with equal spacing or adaptive scale is constructed within the spatial boundary range, and each grid cell has a unique spatial identifier.

[0051] The target area is divided using a regular two-dimensional grid. Typically, a grid structure can be generated based on an equal-spacing division method under a projected coordinate system. Alternatively, an adaptive non-uniform scale grid system can be constructed based on topographic relief, known vegetation distribution density, or soil heterogeneity to better adapt to the natural differences within the region.

[0052] Each grid cell, serving as the smallest spatial unit for subsequent time-series analysis, must possess a clear geographic reference, including its center point latitude and longitude, range coordinates, and identification number, to facilitate spatial alignment and indexing operations during subsequent data acquisition, analysis, and result mapping. This gridding process can be implemented using GIS software, remote sensing image processing platforms, or custom scripts, and can be dynamically adjusted based on the scale and resolution requirements of the flower field during actual deployment.

[0053] Furthermore, in step S300, the method for periodically collecting multi-temporal remote sensing data of each grid is as follows: multispectral image data collected by a multispectral remote sensing imager mounted on a UAV is used as multi-temporal remote sensing data, and vegetation index enhancement preprocessing is performed on the multi-temporal remote sensing data, that is, NDVI layer of multi-temporal remote sensing data is constructed based on red light and near-infrared bands.

[0054] The multi-temporal remote sensing data refers to a collection of remote sensing images acquired periodically at multiple time points in the same spatial area using the same remote sensing device during the flower planting cycle. The multispectral image data covers at least the near-infrared (760–900 nm) and visible light (450–700 nm) bands.

[0055] In multi-temporal remote sensing data, an NDVI layer is constructed based on red and near-infrared bands and used as a vegetation activity index, providing highly sensitive physiological state observation variables for time-series modeling. NDVI (Normalized Difference Vegetation Index) is a common vegetation cover index in spectral images; its calculation process will not be elaborated further.

[0056] Multi-temporal remote sensing data is stored in the computer in the GeoTIFF three-dimensional array format, and its preprocessing also includes registration, radiometric correction and cloud cover removal.

[0057] Further, in step S400, the method for constructing the time-series of alkali land corresponding to each grid using multi-temporal remote sensing data is as follows: In any multi-temporal remote sensing data obtained, the average pixel values ​​of red light, blue light and infrared light within the grid are recorded as R_red, R_blue and R_nir respectively, the moisture parameter is recorded as the ratio of R_nir to R_red, and the alkali return parameter is recorded as the Euclidean norm of R_red and R_blue. The time point of each acquisition of multi-temporal remote sensing data is recorded as a measurement point, and the time-series of alkali land is constructed by the moisture parameter, alkali return parameter and NDVI layer corresponding to each time-series continuous measurement point.

[0058] The specific calculation method for the alkali return parameter is as follows: SBIdx = sqrt(R_red) 2 +R_blue 2 The expression sqrt represents the square root function. The efflorescence parameter is used to detect highly reflective areas, such as exposed efflorescence on the ground surface. In saline-alkali environments, salts are often dissolved in groundwater or irrigation water. Furthermore, under conditions of strong sunlight and high evaporation, water migrates upwards from underground or within the soil. After evaporation, the salts remaining on the surface form efflorescence patches. Therefore, the efflorescence parameter in saline-alkali environments shows significant and uncertain changes over time or with irrigation. The moisture parameter, on the other hand, reflects the suppressive effect of surface soil moisture content on near-infrared reflectance and is a sensitive indicator for monitoring waterlogged areas.

[0059] Further, in step S500, the method for determining whether the risk of salinity accumulation and water stagnation imbalance has occurred based on the time-series measurement of alkaline land is as follows: the average value of the pixel value of the NDVI layer corresponding to any measuring point is defined as the ecological parameter, the average value of the ecological parameter corresponding to a measuring point and the previous 3-7 measuring points is defined as the previous value of the ecological parameter, and the difference between the state parameter of the measuring point and the previous value of the ecological parameter is defined as the ecological parameter anomaly D_NDVI. If the ecological parameter anomaly is negative, the current measuring point is marked as a negative ecological measuring point.

[0060] The difference in moisture parameters between any monitoring point and the previous monitoring point is denoted as D_MIdx, and the difference in alkali return parameters is denoted as D_SBIdx. The focusing time interval is defined as 15-20 days. The imbalance risk index is calculated based on the ecological parameter anomalies, D_MIdx, and D_SBIdx of each negative ecological monitoring point within the focusing time interval. The sub-scores of the imbalance risk index corresponding to all grids in the same monitoring point are used as the index threshold. Grids with imbalance risk indices less than the index threshold are marked as imbalanced at the monitoring point. If more than half of the grids are marked as imbalanced within the focusing time interval, it is determined that there is a risk of salinity accumulation and water stagnation imbalance.

[0061] The mathematical expression for calculating the imbalance risk index is IR_Value = D_NDVI × mean < W_i1 × (a1·D_MIdx(i1) + a2·D_SBIdx(i1))>, where a1 and a2 are the weight values ​​of the moisture parameter and the alkali return parameter, respectively, with a default value of 0.5. W_i1 is the time distance weight, which is mathematically expressed as W_i1 = 1 + exp(-i1), where i1 is the sequence number of the negative ecological measurement point in the focused time interval, and a sequence number of 1 represents the current natural day. D_MIdx(i1) and D_SBIdx(i1) represent the D_MIdx and D_SBIdx corresponding to the i1th natural day in the focused time interval, respectively, and mean is the sign of the average value function.

[0062] Further, in step S600, the risk identification result is fed back to the terminal for decision support, including the irrigation amount or preferred irrigation method. In this invention, all undefined variables, if not explicitly defined, can be manually set thresholds.

[0063] An embodiment of the present invention provides a system for identifying inefficient areas of saline-alkali soil seedling tray flower fields, such as... Figure 2 The diagram shows a structural diagram of a system for identifying inefficient areas of saline-alkali land seedling trays for flower fields according to the present invention. This embodiment of the system includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the above-described embodiment of the method for identifying inefficient areas of saline-alkali land seedling trays for flower fields.

[0064] The system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program in units of the following system:

[0065] Boundary recognition unit, used to obtain spatial boundary information of the flower sea area;

[0066] Meshable cells are used to divide a region into grids based on spatial boundary information.

[0067] The spectral data acquisition unit is used to periodically acquire multi-temporal remote sensing data from each grid.

[0068] The time-series construction unit is used to construct time-series data of alkaline land corresponding to each grid using multi-temporal remote sensing data.

[0069] The salt accumulation and water stagnation imbalance risk assessment unit is used to determine whether a salt accumulation and water stagnation imbalance risk has occurred based on the time-series measurement of alkaline land.

[0070] The aforementioned system for identifying inefficient areas of saline-alkali land seedling trays for flower fields can run on computing devices such as desktop computers, laptops, handheld computers, and cloud servers. The system that can run on this system may include, but is not limited to, processors and memory. Those skilled in the art will understand that the example described is merely an illustration of a system for identifying inefficient areas of saline-alkali land seedling trays for flower fields and does not constitute a limitation on such a system. It may include more or fewer components, or a combination of certain components, or different components. For example, the system may also include input / output devices, network access devices, buses, etc.

[0071] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the operating system of the inefficient saline-alkali land seedling planting and flower field identification system, connecting various parts of the operating system through various interfaces and lines.

[0072] The memory can be used to store the computer program and / or modules. The processor implements various functions of the inefficient area identification system for saline-alkali land seedling flower fields by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0073] Although the invention has been described in considerable detail and particularly with regard to several of the described embodiments, it is not intended to limit itself to any of these details or embodiments or any particular embodiment, thereby effectively covering the intended scope of the invention. Furthermore, the invention has been described above with respect to embodiments foreseeable by the inventors in order to provide a useful description, and non-substantial modifications to the invention that have not yet been foreseen may still represent equivalent modifications.

Claims

1. A method for identifying inefficient areas of saline-alkali soil seedling tray flower fields, characterized in that, The method includes the following steps: S100: Obtain spatial boundary information of the flower sea area; S200: Grid division of the region based on spatial boundary information; S300: Regularly collect multi-temporal remote sensing data from each grid; S400: Construct time-series data of alkaline land corresponding to each grid using multi-temporal remote sensing data; S500: Determines the risk of salinity accumulation and water stagnation imbalance based on time-series measurements of alkaline land. The method for periodically collecting multi-temporal remote sensing data of each grid in S300 is as follows: multispectral image data collected by a multispectral remote sensing imager mounted on an UAV is used as multi-temporal remote sensing data. The multi-temporal remote sensing data is preprocessed with vegetation index enhancement, that is, an NDVI layer of multi-temporal remote sensing data is constructed based on red light and near-infrared bands. The method for constructing the time-series of alkali land corresponding to each grid in step S400 using multi-temporal remote sensing data is as follows: In any multi-temporal remote sensing data obtained, the average pixel values ​​of red light, blue light and infrared light in the grid are recorded as R_red, R_blue and R_nir respectively, the moisture parameter is recorded as the ratio of R_nir to R_red, and the alkali return parameter is recorded as the Euclidean norm of R_red and R_blue. The time point of each acquisition of multi-temporal remote sensing data is recorded as a measurement point. The time-series of alkali land is constructed by the moisture parameter, alkali return parameter and NDVI layer corresponding to each measurement point that is consecutive in time. In step S500, the method for determining whether the risk of salinity accumulation and water stagnation imbalance has occurred based on the time-series measurement of alkaline land is as follows: the average value of the pixel value of the NDVI layer corresponding to any measuring point is defined as the ecological parameter, the average value of the ecological parameter corresponding to a measuring point and the previous 3-7 measuring points is defined as the previous value of the ecological parameter, and the difference between the state parameter of the measuring point and the previous value of the ecological parameter is defined as the ecological parameter anomaly D_NDVI. If the ecological parameter anomaly is negative, the current measuring point is marked as a negative ecological measuring point. The difference in moisture parameters between any monitoring point and the previous monitoring point is denoted as D_MIdx, and the difference in alkali return parameters is denoted as D_SBIdx. The focusing time interval is defined as 15-20 days. The imbalance risk index is calculated based on the ecological parameter anomalies, D_MIdx, and D_SBIdx of each negative ecological monitoring point within the focusing time interval. The sub-scores of the imbalance risk index corresponding to all grids in the same monitoring point are used as the index threshold. Grids with imbalance risk indices less than the index threshold are marked as imbalanced at the monitoring point. If more than half of the grids are marked as imbalanced within the focusing time interval, it is determined that there is a risk of salinity accumulation and water stagnation imbalance.

2. The method for identifying inefficient areas of saline-alkali soil seedling planting beds according to claim 1, characterized in that, In step S100, the method for obtaining the spatial boundary information of the flower sea area is as follows: the spatial boundary information includes data based on field surveying and mapping data, remote sensing images or geographic information system data, which is used to determine the external boundary range of the flower sea planting area.

3. The method for identifying inefficient areas of saline-alkali soil seedling planting beds according to claim 1, characterized in that, In step S200, the method for dividing the region into grids based on spatial boundary information is as follows: within the spatial boundary range, construct a two-dimensional regular grid with equal spacing or adaptive scale, and each grid cell has a unique spatial identifier.

4. The method for identifying inefficient areas of saline-alkali soil seedling planting beds according to claim 1, characterized in that, It also includes step S600, which feeds back the risk identification results to the terminal for decision support, including changes to irrigation amount or irrigation frequency, and sends grid location information of grids at risk of salt accumulation and water stagnation imbalance to the administrator client.

5. A system for identifying inefficient areas of saline-alkali soil seedling tray flower fields, characterized in that, The system for identifying inefficient areas of saline-alkali land seedling tray flower fields includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for identifying inefficient areas of saline-alkali land seedling tray flower fields according to any one of claims 1-4. The system for identifying inefficient areas of saline-alkali land seedling tray flower fields runs on a desktop computer, a laptop computer, a handheld computer, or a cloud data center computing device.

Images