Land data processing method and device based on AI and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to an AI-based territorial data processing method and device and a storage medium. The method comprises the steps that the pH value, the organic matter content and the heavy metal concentration of a target area are collected to analyze soil attributes of the target area; the method comprises the following steps: acquiring ground surface fracture density and ground surface settlement rate of a target area to analyze a ground surface stability index, constructing topographic features of the target area based on the gradient of the target area and the ground surface stability index, and acquiring annual average precipitation data and water source data of the target area to construct hydrological features of the target area; meanwhile, the construction process of the topographic features of the target area is updated based on the hydrological features of the target area, the vegetation coverage rate of the target area is collected to determine the hydrological adjustment weight, and the target area is classified based on the soil attributes of the target area, the topographic features of the target area and the hydrological features of the target area. According to the invention, the processing efficiency of territorial data is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a land data processing method, device and storage medium based on AI. Background Art

[0002] Traditional land data processing methods mostly rely on single indicator analysis or manual experience judgment, and have limitations such as data dimension fragmentation and low processing efficiency. Existing technologies make it difficult to achieve dynamic coupling analysis of multi-source data such as soil properties, terrain characteristics, hydrological conditions and vegetation coverage, resulting in one-sided and insufficient timeliness in the evaluation results. In addition, the manual sampling process is cumbersome, professional analysis such as surface crack identification and heavy metal pollution calculation is time-consuming, and parameter adjustment lacks an adaptive mechanism and cannot cope with the dynamic changes in complex geographical environments. With the surge in the amount of remote sensing and Internet of Things data, there is an urgent need for intelligent methods to integrate multi-dimensional information and improve the automation of land data analysis and the accuracy of decision-making. Summary of the invention

[0003] The purpose of the present invention is to provide an AI-based land data processing method, device and storage medium to solve at least one of the problems existing in the prior art.

[0004] To achieve the above object, the present invention adopts the following technical solutions: A land data processing method based on AI, comprising: Collect the pH value, organic matter content and heavy metal concentration of the target area to analyze the soil properties of the target area; Collect the surface crack density and surface settlement rate of the target area to analyze the surface stability index, and construct the terrain characteristics of the target area based on the slope and surface stability index of the target area; Collect the target area's average annual precipitation data and water source data to construct the target area's hydrological characteristics, and update the target area's terrain characteristics based on the target area's hydrological characteristics and hydrological adjustment weights; The vegetation coverage of the target area is collected to construct vegetation characteristics, and the hydrological adjustment weights are determined based on the vegetation characteristics.

[0005] Optionally, a heavy metal pollution index P is constructed based on the collected copper concentration C1, lead concentration C2, and zinc concentration C3 of the target area; A pH adjustment function is constructed based on the collected pH values ​​of the target area, and the collected organic matter content of the target area is standardized to obtain the standard organic matter content. The soil properties of the target area are determined based on the pH adjustment function, the standard organic matter content and the heavy metal pollution index.

[0006] Optionally, a pH adjustment function f(pH) is constructed based on the collected pH value of the target area, and the collected organic matter content m1 of the target area is normalized to obtain a standard organic matter content M; The soil quality index SQ is constructed based on the pH adjustment function f(pH), the standard organic matter content M and the heavy metal pollution index P, and the soil quality index SQ is compared with the soil quality discriminant factor to determine the soil properties of the target area. If the soil quality index SQ is less than or equal to the soil quality discriminant factor, the soil properties of the target area are judged to be Class I soil, otherwise, the soil properties of the target area are judged to be Class II soil.

[0007] Optionally, the surface crack density Dm collected in the target area is normalized to obtain a crack density parameter Fd, the surface settlement rate Gs collected in the target area is normalized to obtain a settlement rate parameter Fc, and the crack density parameter Fd and the settlement rate parameter Fc are fused to obtain a surface stability index SSI.

[0008] Optionally, the surface stability index SSI is coupled with the slope θ of the target area to determine the terrain feature R of the target area. The expression of R is: R = (θ / θ1×SSI×β) 0.5 ; Where θ1 is the slope threshold and β is the stability adjustment factor.

[0009] Optionally, the hydrological characteristics of the target area are set to HF, and the expression of HF is HF=(js-jsmin) / (jsmax-jsmin)×g(SY)+γ×[1-1 / (1+SY)], where js is the average value of the average annual precipitation data, jsmin is the minimum value of the collected average annual precipitation, jsmax is the maximum value of the collected average annual precipitation, g(SY) is the water source weight function, and γ is the drought correction factor; The hydrological characteristic HF of the target area is compared with the hydrological discrimination factor h0 to update the construction process of the terrain characteristics of the target area. When the hydrological characteristic HF of the target area is greater than or equal to the hydrological discrimination factor h0, no update is performed. Otherwise, the stable adjustment factor is updated according to the hydrological adjustment weight.

[0010] Optionally, a ratio analysis is performed between the vegetation coverage rate zf0 and the coverage rate threshold zf1 of the target area to obtain the vegetation feature ZT, and the vegetation feature ZT is compared with the vegetation discrimination factor zt0 to determine the hydrological adjustment weight.

[0011] Optionally, the method further includes: classifying the target area based on the soil properties of the target area, the terrain features of the target area, and the hydrological features of the target area; when the soil properties of the target area are Class I soil, the target area is classified as a low potential area; when the soil properties of the target area are Class II soil, if r1×SQ+r2×(1-R)+r3×HF is less than or equal to the first category factor u1, the target area is classified as a low potential area; if r1×SQ+r2×(1-R)+r3×HF is greater than the first category factor u1 and less than or equal to the second category factor u2, the target area is classified as a medium potential area; if r1×SQ+r2×(1-R)+r3×HF is greater than the second category factor u2, the target area is classified as a high potential area; Among them, r1 is the soil attribute weight, r2 is the terrain weight, and r3 is the hydrological weight.

[0012] According to another aspect of the present application, there is provided an AI-based land data processing device, comprising: An attribute determination unit, used to analyze soil attributes of a target area based on the collected pH value, organic matter content, and heavy metal concentration of the target area; A terrain determination unit, used to analyze the surface stability index according to the collected surface crack density and surface settlement rate of the target area, and to construct the terrain characteristics of the target area based on the slope of the target area and the surface stability index; A hydrological determination unit is used to construct the hydrological characteristics of the target area based on the collected annual average precipitation data and water source data of the target area, and to update the construction process of the terrain characteristics of the target area based on the hydrological characteristics and hydrological adjustment weights of the target area; A vegetation analysis unit, used to construct vegetation characteristics according to the collected vegetation coverage of the target area, and determine the hydrological adjustment weight based on the vegetation characteristics; The classification unit is used to classify the target area according to the soil properties of the target area, the topographic characteristics of the target area, and the hydrological characteristics of the target area.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium stores a computer program, wherein the computer program is used to control the electronic device where the computer-readable storage medium is located to execute the AI-based land data processing method during runtime.

[0014] The beneficial effects of the present invention are as follows: This method builds a multi-dimensional land data collaborative analysis framework based on AI technology, significantly improving data processing efficiency. Through the automated collection and intelligent coupling of soil properties, terrain stability, hydrological characteristics and vegetation coverage, the problems of isolated data and strong manual dependence of traditional methods are solved; the AI ​​model realizes the rapid calculation of complex indicators such as heavy metal pollution index and surface stability index, and supports dynamic adjustment of parameters to enhance adaptability to different environmental conditions; through multi-feature weighted fusion, the reclamation potential level is accurately divided to provide efficient decision-making support for land consolidation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 This is a flow chart of the land data processing method based on AI in this embodiment.

[0017] Figure 2 Schematic diagram of the process of analyzing soil properties in this embodiment.

[0018] Figure 3 Schematic diagram of the process of constructing terrain features in this embodiment.

[0019] Figure 4 Schematic diagram of the flow of the method for constructing hydrological characteristics in this embodiment.

[0020] Figure 5 This is a schematic diagram of the structure of the AI-based land data processing device of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Specifically, this embodiment is applied to the processing of abandoned mining land data. Through multi-source data coupling analysis, dynamic classification of regional potential is achieved, and a four-dimensional coupling model of "soil-topography-hydrology-vegetation" is established. Accurate assessment of regional quality potential, adaptive correction of parameters and intelligent identification of reclamation levels are achieved, and finally scientific classification of low / medium / high potential areas is completed.

[0024] See also Figure 1 As shown, it is a flow chart of the land data processing method based on AI in this embodiment, including: Step S101 , collecting the pH value, organic matter content and heavy metal concentration of the target area to analyze the soil properties of the target area.

[0025] Specifically, the target area is an abandoned mining area.

[0026] Exemplarily, in this embodiment, 10 sampling points are arranged in the target area, 5 sub-samples are mixed at each point, and surface soil is collected. The pH value is determined by laboratory potentiometric method, and the mean is used as the representative value of the pH value. The organic matter content is determined by wet oxidation method (potassium dichromate-sulfuric acid method), and the mean is used as the representative value of the organic matter content. The concentrations of copper, lead and zinc are determined by atomic absorption spectroscopy, and the mean is used as the representative value of the concentrations of copper, lead and zinc. In this embodiment, there is no specific limitation on the collection method of the pH value, organic matter content and heavy metal concentration of the target area, and those skilled in the art can freely set it according to needs.

[0027] See also Figure 2 As shown, the soil property analysis method includes: Step S201, constructing a heavy metal pollution index based on the collected copper, lead and zinc concentrations of the target area.

[0028] Specifically, the heavy metal pollution index P is constructed based on the collected copper concentration C1, lead concentration C2 and zinc concentration C3 of the target area. The expression of P is: ; In the formula, i=1,2,3, S1 is the standard value of copper concentration, S2 is the standard value of lead concentration, S3 is the standard value of zinc concentration, and n=3.

[0029] Specifically, by comprehensively analyzing the square mean of the excess multiples of three heavy metals, copper, lead and zinc, a nonlinear pollution assessment model was constructed, which can identify hidden complex pollution risks, which is better than the traditional single pollution factor superposition method.

[0030] Please continue reading Figure 2 As shown, the soil property analysis method further includes: Step S202, constructing a pH adjustment function based on the collected pH value of the target area, and standardizing the collected organic matter content of the target area to obtain a standard organic matter content, and determining the soil properties of the target area based on the pH adjustment function, the standard organic matter content and the heavy metal pollution index.

[0031] Specifically, a pH adjustment function f(pH) is constructed based on the collected pH value of the target area, and is set as follows: ; Where pH is the pH value of the target area currently collected; Normalize the organic matter content m1 of the collected target area to obtain the standard organic matter content M. The expression of M is M=m1 / m2, where m2 is the organic matter content threshold; The soil quality index SQ is constructed based on the pH adjustment function f(pH), the standard organic matter content M and the heavy metal pollution index P. The expression of SQ is SQ=(f(pH)×M) / (1+k×P), where k is an adjustment factor; The soil quality index SQ is compared with the soil quality discriminant factor to determine the soil properties of the target area. If the soil quality index SQ is less than or equal to the soil quality discriminant factor, the soil properties of the target area are judged to be Class I soil. Otherwise, the soil properties of the target area are judged to be Class II soil.

[0032] Exemplarily, in this embodiment, the standard value of copper concentration, the standard value of lead concentration and the standard value of zinc concentration can be set with reference to the soil environmental quality agricultural land standard (the screening value corresponding to GB 15618-2018), the m2 can be set to 0.08, the k can be set to 0.5, and the soil quality discrimination factor can be set to 0.5; in this embodiment, no specific limitation is made to the setting of the above data, and those skilled in the art can freely set them according to needs.

[0033] Specifically, the segmented pH adjustment function is used to enhance the characterization ability of acidic or alkaline soils for the effectiveness of organic matter, and the limiting effect of pH abnormalities on fertility is scientifically reflected. At the same time, the dimensional difference is eliminated based on threshold standardization processing, and the relative contribution of organic matter content in soil quality evaluation is highlighted. The pollution index is integrated into the quality model in the form of an inhibition factor, and the dynamic offset relationship between pollution risk and soil fertility is modeled to avoid the misjudgment that high organic matter conceals the pollution risk.

[0034] Please continue reading Figure 1 As shown, the AI-based land data processing method also includes: Step S102, collecting the surface crack density and surface settlement rate of the target area to analyze the surface stability index, and constructing the terrain characteristics of the target area based on the slope of the target area and the surface stability index, and defining the surface crack density as the ratio of the total length of all surface cracks in the target area to the area of ​​the target area.

[0035] Exemplarily, in this embodiment, aerial photography can be performed by using a drone equipped with a visible light camera and a flight altitude of 80-120 meters to obtain images with a ground resolution of ≤5 cm (such as DJI Phantom 4 RTK), and cracks can be interpreted and vectorized through ArcGIS Pro / QGIS + deep learning plug-ins (such as ENVI Deep Learning or a third-party YOLOv5 model). The interpretation rule is that the actual ground width ≥0.2m (image display ≥4 pixels) is included in the statistics, and the fracture interval ≤1m is regarded as the same crack segment. The crack vector line layer is imported into QGIS and the length of each crack is calculated to obtain the crack length, and the crack length is divided by the area of ​​the target area to obtain the surface crack density Lm; data can be collected through Sentinel-1, and the collected data can be input into software tools such as GMTSAR (GMT+StaMPS) to obtain the surface settlement rate Cs of the target area. The slope of the target area can be obtained through QGIS or Google Earth Engine and other software; in this embodiment, the collection method of the surface crack density, surface settlement rate and slope of the target area is not specifically limited, and those skilled in the art can freely set it according to needs.

[0036] See also Figure 3 As shown, the method for constructing the terrain features includes: Step S301: normalize the collected surface crack density and surface settlement rate of the target area to obtain crack density parameters and settlement rate parameters, and analyze the surface stability index based on the crack density parameters and settlement rate parameters.

[0037] Specifically, the step S301 normalizes the surface crack density Dm of the collected target area to obtain a crack density parameter Fd, and the expression of Fd is Fd=1 / [1+exp(-α×Dm / Dm0)], where α is a crack restriction factor and Dm0 is a crack density threshold; The collected surface subsidence rate Gs of the target area is normalized to obtain the subsidence rate parameter Fc, the expression of Fc is Fc=min(1,Gs / Gs0), where Gs0 is the subsidence rate threshold; The crack density parameter Fd and the settlement rate parameter Fc are fused to obtain the surface stability index SSI. The expression of SSI is SSI=w1×Fd+w2×Fc, where w1 is the crack weight, w2 is the settlement weight, and w1+w2=1.

[0038] For example, in this embodiment, the crack limitation factor can be set to 0.8, the crack density threshold can be set to 3km / km², the sedimentation rate threshold can be set to 20mm / year, w1 can be set to 0.6, and w2 can be set to 0.4; in this embodiment, no specific limitation is made on the values ​​of each data, and those skilled in the art can freely set them according to needs.

[0039] Specifically, normalization processing is used to achieve a balance between the differences in low-density fracture areas and the saturation responses in high-density areas, effectively suppressing interference from extreme values. At the same time, the sedimentation rate parameters are normalized to prevent evaluation distortion caused by local sedimentation anomalies, and differentiated weight distribution is implemented for fractures and sedimentation factors to highlight the typical characteristics of the impact of fractures on the stability of mining wastelands.

[0040] Please continue reading Figure 3 As shown, the method for constructing the terrain features further includes: Step S302: constructing the terrain characteristics of the target area based on the slope of the target area and the surface stability index.

[0041] Specifically, the surface stability index SSI is coupled with the slope θ of the target area to determine the terrain characteristics R of the target area. The expression of R is: R = (θ / θ1×SSI×β) 0.5 ; Where θ1 is the slope threshold and β is the stability adjustment factor.

[0042] For example, in this embodiment, the slope threshold can be set to 45°, and the stability adjustment factor can be set to 0.6; in this embodiment, no specific limitation is imposed on the value of each data, and those skilled in the art can freely set it according to needs.

[0043] Specifically, a coupling relationship is constructed by multiplying the slope threshold standardization and the stability index to quantify the synergistic effect of terrain steepness and geological safety. A stability adjustment factor is introduced to balance the oversensitivity of large slope areas to the classification results, thereby improving the rationality of the assessment of slope reclamation potential.

[0044] Please continue reading Figure 1 As shown, the AI-based land data processing method also includes: Step S103, collecting the average annual precipitation data and water source data of the target area to construct the hydrological characteristics of the target area, and updating the construction process of the terrain characteristics of the target area based on the hydrological characteristics and hydrological adjustment weights of the target area, wherein the water source data is the Euclidean distance between the nearest river in the target area and the target area.

[0045] Illustratively, in this embodiment, the collection of the target area's average annual precipitation data should collect at least ten years of average annual precipitation from the meteorological station, and the water source data can be collected interactively; in this embodiment, no specific limitation is imposed on the collection method of each data, and those skilled in the art can freely set it according to needs.

[0046] See also Figure 4 As shown, the method for constructing the hydrological characteristics includes: Step S401, constructing the hydrological characteristics of the target area based on the collected annual average precipitation data and water source data of the target area.

[0047] Specifically, step S401 sets the hydrological characteristics of the target area to HF, and the expression of HF is HF=(js-jsmin) / (jsmax-jsmin)×g(SY)+γ×[1-1 / (1+SY)], where js is the average value of the annual average precipitation data, jsmin is the minimum value of the collected annual average precipitation, jsmax is the maximum value of the collected annual average precipitation, g(SY) is the water source weight function, γ is the drought correction factor, and SY is the Euclidean distance between the nearest river in the target area currently collected and the target area; The expression of the water source weight function g(SY) is: .

[0048] Specifically, in this embodiment, the unit of SY is km. In the calculation of hydrological characteristics and the construction of water source weight function, only its numerical value is used without considering its physical meaning. The drought correction factor is 0.5 when js≤400mm and 0.2 when js>400mm.

[0049] Specifically, the hydrological network relationship is constructed by combining the average annual precipitation and the distance to the water source, which not only reflects the total amount of regional water supply, but also reflects the characteristics of water source accessibility, accurately identifies drought vulnerability, automatically adjusts the weight of the drought correction factor according to the precipitation threshold, and specifically enhances the sensitivity of the evaluation parameters in the drought area.

[0050] Please continue reading Figure 4 As shown, the method for constructing the hydrological characteristics further includes: Step S402, a construction process of updating the terrain features of the target area based on the hydrological features of the target area.

[0051] Specifically, step S402 compares the hydrological characteristic HF of the target area with the hydrological discrimination factor h0 to update the construction process of the terrain characteristics of the target area. When the hydrological characteristic HF of the target area is greater than or equal to the hydrological discrimination factor h0, no updating is performed. Otherwise, the stable adjustment factor is updated to β1, and the expression of β1 is β1=β×{1+hydrological adjustment weight×lg[3×(h0-HF)+1] / lg4}.

[0052] Exemplarily, in this embodiment, the hydrological discrimination factor h0 can be set to 0.6; in this embodiment, the setting of the hydrological discrimination factor is not specifically limited, and those skilled in the art can freely set it according to needs.

[0053] Specifically, the areas that need to be corrected are screened through hydrological discrimination factors to avoid computational redundancy caused by parameter adjustment in the entire area. The logarithmic function is used to achieve the amplified correction effect of low hydrological characteristic values ​​to ensure the gradualness and stability of terrain parameter correction.

[0054] Please continue reading Figure 1 As shown, the AI-based land data processing method also includes: Step S104: collecting vegetation coverage of the target area to construct vegetation characteristics, and determining hydrological adjustment weights based on the vegetation characteristics.

[0055] Exemplarily, in this embodiment, the vegetation coverage rate of the target area can be obtained through a satellite remote sensing data platform.

[0056] Specifically, step S104 performs a ratio analysis on the vegetation coverage rate zf0 and the coverage rate threshold zf1 of the target area to obtain the vegetation feature ZT, and compares the vegetation feature ZT with the vegetation discrimination factor zt0 to determine the hydrological adjustment weight. When the vegetation feature ZT is greater than or equal to the vegetation discrimination factor zt0, the hydrological adjustment weight is set to T1, and T1=η1 is set. Otherwise, the hydrological adjustment weight is set to T2, and T2=η1×{1+0.2×exp[3×(zt0-ZT)-3]}, where η1 is the preset hydrological adjustment weight.

[0057] For example, in this embodiment, the coverage threshold can be set to 0.8, the vegetation discrimination factor can be set to 0.56, and the preset hydrological adjustment weight can be set to 0.3; in this embodiment, no specific limitation is imposed on the value of each data, and those skilled in the art can freely set it according to needs.

[0058] Specifically, the vegetation coverage rate is used to invert the surface ecological restoration potential, dynamically adjust the influence of hydrological characteristics, and enhance the model's ability to judge the feasibility of reclamation in ecologically fragile areas. At the same time, a vegetation-hydrological mutual feedback adjustment logic is established so that the weight parameters can be adaptively optimized with the ecological background conditions, thereby achieving precise adaptation of the microenvironment characteristics of the mining area.

[0059] Please continue reading Figure 1 As shown, the AI-based land data processing method also includes: Step S105 , classifying the target area based on the soil properties of the target area, the terrain characteristics of the target area, and the hydrological characteristics of the target area.

[0060] Specifically, when the soil property of the target area is Class I soil, the target area is divided into a low potential area. When the soil property of the target area is Class II soil, if r1×SQ+r2×(1-R)+r3×HF is less than or equal to the first category factor u1, the target area is divided into a low potential area. If r1×SQ+r2×(1-R)+r3×HF is greater than the first category factor u1 and less than or equal to the second category factor u2, the target area is divided into a medium potential area. If r1×SQ+r2×(1-R)+r3×HF is greater than the second category factor u2, the target area is divided into a high potential area. Among them, r1 is the soil attribute weight, r2 is the terrain weight, r3 is the hydrological weight, and r1+r2+r3=1.

[0061] Specifically, the low potential area is an area that needs long-term monitoring before reclamation, the medium potential area is an area that needs slight restoration before reclamation, and the high potential area is an area that can be directly reclaimed.

[0062] For example, in this embodiment, r1 can be set to 0.5, r2 can be set to 0.3, r3 can be set to 0.2, u1 can be set to 0.55, and u2 can be set to 0.75; in this embodiment, no specific limitation is made on the value of each data, and technicians in this field can freely set it according to needs.

[0063] Specifically, the nonlinear contradictory relationship among soil, topography and hydrology is balanced through a weighted combination model to improve the accuracy of target area division, thereby improving the accuracy of target area classification and the accuracy of land data processing.

[0064] See also Figure 5As shown, the AI-based land data processing device includes: The property determination unit 501 is used to analyze the soil properties of the target area according to the collected pH value, organic matter content and heavy metal concentration of the target area; A terrain determination unit 502 is used to analyze the surface stability index according to the collected surface crack density and surface settlement rate of the target area, and to construct the terrain characteristics of the target area based on the slope of the target area and the surface stability index; A hydrological determination unit 503 is used to construct the hydrological characteristics of the target area according to the collected annual average precipitation data and water source data of the target area, and to update the construction process of the terrain characteristics of the target area based on the hydrological characteristics and hydrological adjustment weights of the target area; The vegetation analysis unit 504 is used to construct vegetation features according to the collected vegetation coverage of the target area, and determine the hydrological adjustment weight based on the vegetation features; The classification unit 505 is used to classify the target area according to the soil properties of the target area, the terrain characteristics of the target area and the hydrological characteristics of the target area.

[0065] In this embodiment, the AI-based land data processing method can be implemented as an executable computer program. When the computer program is loaded into the processor, when the computer program is loaded into the memory and processed by the processor through the bus, one or more steps of the AI-based land data processing method can be executed.

[0066] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as a computer-readable program, a data structure, a program module or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, disk storage or other magnetic storage device, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media generally contain computer-readable programs, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0067] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions under the shared conditions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A land data processing method based on AI, characterized in that: include: Collect the pH value, organic matter content and heavy metal concentration of the target area to analyze the soil properties of the target area; Collect the surface crack density and surface settlement rate of the target area to analyze the surface stability index, and construct the terrain characteristics of the target area based on the slope and surface stability index of the target area; Collect the target area's average annual precipitation data and water source data to construct the target area's hydrological characteristics, and update the target area's terrain characteristics based on the target area's hydrological characteristics and hydrological adjustment weights; The vegetation coverage of the target area is collected to construct vegetation characteristics, and the hydrological adjustment weights are determined based on the vegetation characteristics.

2. The AI-based land data processing method according to claim 1 is characterized in that: The heavy metal pollution index P was constructed based on the copper concentration C1, lead concentration C2 and zinc concentration C3 collected in the target area; A pH adjustment function is constructed based on the collected pH values ​​of the target area, and the collected organic matter content of the target area is standardized to obtain the standard organic matter content. The soil properties of the target area are determined based on the pH adjustment function, the standard organic matter content and the heavy metal pollution index.

3. The AI-based land data processing method according to claim 2 is characterized in that: A pH adjustment function f(pH) is constructed based on the pH value of the target area collected, and the organic matter content m1 of the target area collected is normalized to obtain a standard organic matter content M; The soil quality index SQ is constructed based on the pH adjustment function f(pH), the standard organic matter content M and the heavy metal pollution index P, and the soil quality index SQ is compared with the soil quality discriminant factor to determine the soil properties of the target area. If the soil quality index SQ is less than or equal to the soil quality discriminant factor, the soil properties of the target area are judged to be Class I soil, otherwise, the soil properties of the target area are judged to be Class II soil.

4. The AI-based land data processing method according to claim 3 is characterized in that: The surface crack density Dm collected in the target area is normalized to obtain the crack density parameter Fd, the surface settlement rate Gs collected in the target area is normalized to obtain the settlement rate parameter Fc, and the crack density parameter Fd and the settlement rate parameter Fc are fused to obtain the surface stability index SSI.

5. The AI-based land data processing method according to claim 4 is characterized in that: The surface stability index SSI is coupled with the slope θ of the target area to determine the terrain characteristics R of the target area. The expression of R is: R = (θ / θ1×SSI×β) 0.5 ; In the formula, θ1 is the slope threshold and β is the stability adjustment factor.

6. The AI-based land data processing method according to claim 5 is characterized in that: The hydrological characteristics of the target area are set to HF, and the expression of HF is HF=(js-jsmin) / (jsmax-jsmin)×g(SY)+γ×[1-1 / (1+SY)], where js is the average value of the annual average precipitation data, jsmin is the minimum value of the collected annual average precipitation, jsmax is the maximum value of the collected annual average precipitation, g(SY) is the water source weight function, γ is the drought correction factor, and SY is the Euclidean distance between the nearest river in the target area and the target area; The hydrological characteristic HF of the target area is compared with the hydrological discrimination factor h0 to update the construction process of the terrain characteristics of the target area. When the hydrological characteristic HF of the target area is greater than or equal to the hydrological discrimination factor h0, no update is performed. Otherwise, the stable adjustment factor is updated according to the hydrological adjustment weight.

7. The AI-based land data processing method according to claim 6 is characterized in that: The vegetation coverage rate zf0 and coverage rate threshold zf1 of the target area are analyzed by ratio to obtain the vegetation feature ZT, and the vegetation feature ZT is compared with the vegetation discrimination factor zt0 to determine the hydrological adjustment weight.

8. The AI-based land data processing method according to claim 1 is characterized in that: Also includes: classifying the target area based on soil properties of the target area, topographic characteristics of the target area, and hydrological characteristics of the target area; When the soil property of the target area is Class I soil, the target area is divided into a low potential area. When the soil property of the target area is Class II soil, if r1×SQ+r2×(1-R)+r3×HF is less than or equal to the first category factor u1, the target area is divided into a low potential area. If r1×SQ+r2×(1-R)+r3×HF is greater than the first category factor u1 and less than or equal to the second category factor u2, the target area is divided into a medium potential area. If r1×SQ+r2×(1-R)+r3×HF is greater than the second category factor u2, the target area is divided into a high potential area. Among them, r1 is the soil attribute weight, r2 is the terrain weight, and r3 is the hydrological weight.

9. A land data processing device based on AI, characterized in that: include: An attribute determination unit, used to analyze soil attributes of a target area based on the collected pH value, organic matter content, and heavy metal concentration of the target area; A terrain determination unit, used to analyze the surface stability index according to the collected surface crack density and surface settlement rate of the target area, and to construct the terrain characteristics of the target area based on the slope of the target area and the surface stability index; A hydrological determination unit is used to construct the hydrological characteristics of the target area based on the collected annual average precipitation data and water source data of the target area, and to update the construction process of the terrain characteristics of the target area based on the hydrological characteristics and hydrological adjustment weights of the target area; A vegetation analysis unit is used to construct vegetation characteristics according to the collected vegetation coverage of the target area, and determine the hydrological adjustment weight based on the vegetation characteristics; The classification unit is used to classify the target area according to the soil properties of the target area, the topographic characteristics of the target area, and the hydrological characteristics of the target area.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is used to control the electronic device where the computer-readable storage medium is located to execute the AI-based land data processing method described in any one of claims 1 to 8 during runtime.

Images