A method and system for rapidly assessing and improving the quality grade of supplementary arable land

By using a comprehensive evaluation model based on arable land baseline data and an intelligent optimization technology pool, the quality grade of supplemented arable land has been rapidly and accurately improved, solving the problems of blind transformation and low efficiency in existing technologies, and ensuring the stability and controllability of the improvement effect.

CN123070801APending Publication Date: 2026-11-10ZIBO DIGITAL AGRI & RURAL DEV CENT (ZIBO AGRI TECH EXTENSION SERVICE CENT ZIBO AGRI RADIO & TELEVISION SCHOOL) +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611284661.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-24
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Existing technologies for improving the quality of supplementary arable land suffer from problems such as blind transformation, low quantitative accuracy, slow improvement speed, unstable improvement effect, and lack of systematic closed-loop management. There is a lack of technical solutions for accurate calculation and rapid implementation.

Method used

Based on the measured data of cultivated land baseline and the comprehensive evaluation model, the evaluation index weights are determined by combining the analytic hierarchy process and the entropy weight method through field surveys and data collection. Combined with multi-measure composite improvement schemes, the improvement technology units are intelligently screened and optimized to establish a systematic improvement system covering the entire process of "survey and calculation - precise policy implementation - closed-loop verification".

Benefits of technology

It has achieved rapid, accurate, and stable improvement in the quality grade of cultivated land, meeting the requirements of the supplementary cultivated land quality acceptance standards, reducing waste of improvement inputs, and improving the efficiency and controllability of improvement results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123070801A_ABST
    Figure CN123070801A_ABST
Patent Text Reader

Abstract

This invention discloses a method and system for rapidly assessing and improving the quality grade of supplementary arable land, belonging to the field of arable land quality improvement and land consolidation technology. The method includes: acquiring baseline indicator data of the arable land plots to be improved; calling a comprehensive evaluation model for arable land quality grades to quantitatively calculate the difference between each shortcoming indicator and the target grade standard, as well as improvement input parameters; calling a smart optimization technology pool for arable land improvement, using standard attainment as the objective constraint and cost minimization as the optimization goal, to intelligently select matching improvement technology units and construction combination schemes; implementing multi-measure composite and collaborative improvement and transformation construction according to the combination scheme; and conducting indicator re-testing and verification after construction and maintenance, completing the grade improvement and acceptance loop after confirming that all indicators meet the standards. This invention solves the technical problems of traditional arable land improvement and transformation being extensive and rigid, with large redundant investments and low efficiency, achieving rapid, accurate, low-cost, and stable improvement of the quality grade of supplementary arable land.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the fields of farmland quality improvement, farmland replenishment quality acceptance, and farmland improvement technology. Specifically, it relates to a method and system for rapidly assessing and improving the quality level of replenished farmland, applicable to precise level improvement and standardized acceptance scenarios in land consolidation, farmland occupation-compensation balance, and inefficient farmland improvement and transformation. Background Technology

[0002] With the development of urbanization in my country, various construction projects inevitably occupy arable land, necessitating the replenishment of arable land to address the shortage and ensure that the quantity and quality of arable land remain unchanged. Arable land is the fundamental basis for food production, and replenishing arable land is a crucial measure to strictly adhere to the 1.8 billion mu (120 million hectares) red line for arable land, implement the arable land occupation-replenishment balance system, and safeguard national food security. As various arable land protection policies are implemented, the demand for improving newly added arable land and transforming inefficient arable land is increasing, placing higher demands on the precise improvement of the quality grade of replenished arable land. However, current domestic efforts to improve the grade of replenished arable land generally adopt traditional experience-based transformation models, which have significant technical shortcomings.

[0003] First, existing methods for improving and transforming arable land mostly rely on extensive approaches, failing to develop tailored improvement plans based on the baseline indicators of the proposed replacement plots. This results in high improvement costs, poor effectiveness, and significant rework issues. Different plots exhibit significant differences in soil baseline conditions, with varying types and degrees of limitations in their load indicators. However, traditional methods often employ a "one-size-fits-all" approach, uniformly configuring the application of improvement materials and engineering measures. This leads to inadequate improvement or excessive engineering investment, severely hindering the efficiency and cost control of improving the quality of replacement arable land.

[0004] Secondly, traditional methods rely solely on manual experience to determine farmland quality deficiencies, failing to accurately quantify the required improvement levels, material inputs, and engineering work for each soil quality indicator. Grassroots technicians often estimate key operational parameters such as fertilizer application, tillage depth, and irrigation canal renovation scale based on short-term field surveys and personal experience, lacking standardized and reproducible quantitative calculation tools. This not only results in low efficiency and long cycles for improving farmland quality but also lacks unified quantitative control criteria during the renovation process, making it difficult to objectively verify and compare the renovation results, thus hindering standardized construction practices.

[0005] Third, conventional methods for improving arable land are often limited, relying heavily on chemical or organic fertilizers and failing to integrate comprehensive measures such as physical land preparation, access and irrigation, removal of soil obstructions, and biomass improvement. Single-method fertilization can only compensate for nutrient deficiencies but cannot improve soil structure, moisture conditions, or the ecological environment. Arable land improved through traditional methods often suffers from poor soil structure and weak fertility stability, making it difficult to consistently achieve the goal of "long-term stable use." In some cases, the quality grade of the land declines significantly within one or two years after acceptance.

[0006] Fourth, there is a lack of an integrated technical system encompassing "on-site surveys, quantitative calculations, precise transformation, and closed-loop verification." The transformation process lacks data support and quantitative evaluation of its effects. There is a lack of precise profiling before transformation, a lack of process control during transformation, and a lack of compliance verification after transformation. The entire process is fragmented and does not meet the current requirements for standardized, precise, and traceable acceptance of supplementary arable land quality.

[0007] Furthermore, existing technologies for improving arable land quality lack a scientific and intelligent mechanism for technology selection and combination. Various improvement technologies (such as biochar application, organic fertilizer enrichment, straw return to the field, and deep plowing) each have their applicable scenarios and cost characteristics. Traditional improvement methods often rely on empirical, subjective selection, failing to combine soil baseline deficiencies, site conditions, and cost constraints to achieve precise technology selection and optimal combination matching. This often results in the accumulation of ineffective measures and excessive redundant investment and resource waste. In actual construction, only a targeted selection of suitable technology units is needed to achieve arable land quality standards. Redundant construction not only increases project investment and wastes water, soil, material, and financial resources, but excessive human intervention also disturbs the original soil structure, disrupts the ecological balance of arable land, and hinders the accuracy, economy, and ecology of supplementary arable land improvement.

[0008] In summary, existing technologies suffer from several drawbacks, including blind transformation, low quantitative accuracy, slow improvement speed, unstable improvement effects, and lack of systematic closed-loop management. There is an urgent need for a rapid assessment and improvement technology for arable land quality grades that can be accurately calculated, quickly implemented, and with controllable effects. Summary of the Invention

[0009] This invention aims to overcome the shortcomings of existing farmland improvement and transformation technologies, which are extensive, inefficient, and lack quantitative standards. It provides a method and system for rapidly assessing and improving the quality grade of supplementary farmland. Based on the measured data of farmland baseline and a comprehensive evaluation model of grade, it accurately calculates the improvement requirements of each indicator, matches multiple measures and composite improvement schemes, and achieves rapid, accurate, and stable improvement of farmland quality grade, while meeting the requirements of official supplementary farmland quality acceptance standards. To achieve the above objectives, one or more embodiments of this specification provide a method for rapidly assessing and improving the quality grade of supplementary cultivated land, comprising the following steps: S1: Conducting on-site surveys of the supplementary cultivated land plots to be improved according to the cultivated land quality acceptance field survey specifications, and collecting cultivated land baseline index data; the cultivated land baseline index data includes agricultural production compliance evaluation indicators and cultivated land quality grade evaluation indicators; S2: Based on the cultivated land baseline index data, calling the cultivated land quality grade comprehensive evaluation model, firstly conducting an agricultural production compliance evaluation; if all agricultural production compliance evaluation indicators are qualified, then combining the preset target cultivated land quality grade standard, calculating the difference between each evaluation indicator and the target grade standard item by item, and identifying the non-compliant indicators. The system identifies three categories of indicators: those that must be improved, those that can be improved, and those that do not need improvement, based on the difficulty, cost, and contribution to the grade improvement. S3: Based on the improvement threshold, the system automatically calls upon the intelligent farmland improvement technology pool, combining the type of landfill shortcomings, soil baseline conditions, and cost control constraints to automatically calculate the corresponding input parameters required for farmland improvement. These parameters include, but are not limited to, organic fertilizer application rate, biochar application rate, straw return coverage, deep plowing depth, gravel removal workload, field road repair length, and ditch improvement scope. The system autonomously selects and outputs construction combination schemes adapted to actual working conditions. The intelligent farmland improvement technology pool contains multiple independently selectable improvement technology units. S4: According to the construction combination plan, retrieve the integrated improvement technology units selected by combination and carry out agronomic regulation and engineering remediation operations in a comprehensive manner. Through a multi-dimensional combination of agronomic and engineering measures, eliminate the limiting factors for improving the arable land grade, and promote the shortcoming indicators to meet the acceptance standards. S5: After the improvement and transformation construction is completed and stabilized, re-measure and verify the shortcoming indicators of arable land quality grade. Enter the re-measurement data into the system to recalculate the arable land quality grade, confirm that all indicators have reached the preset target grade standard, and complete the closed loop of supplementary arable land quality grade improvement and acceptance.

[0010] The agricultural production compliance evaluation indicators mentioned in step S1 include effective soil layer thickness, soil organic matter content, terrain slope and field flatness, soil intrusion and gravel content, water resource security conditions, road access conditions, and soil pollution status; the cultivated land quality grade evaluation indicators include terrain location and road access conditions, effective soil layer thickness, texture configuration, topsoil texture, soil bulk density, organic matter content, available phosphorus content, available potassium content, water resource security conditions, topsoil thickness, pH, and salinization degree.

[0011] In some embodiments, the comprehensive evaluation model for cultivated land quality grade in step S2 uses a combination of the analytic hierarchy process and the entropy weight method to determine the weight coefficients of each evaluation indicator; the weight model is constructed based on the evaluation indicator system specified in the national standard for cultivated land quality grade (GB / T 33469), and the weight coefficients of each indicator are adjusted differently according to the natural geographical conditions and land use type of the area where the supplemented cultivated land is located.

[0012] In some embodiments, the automatic calculation of the corresponding improvement input parameters in step S2 specifically includes: based on the difference between the measured values ​​of each shortcoming indicator and the target level standard value, combined with the plot area, soil type and construction conditions, calculating the material demand per unit area, engineering construction volume and construction period estimate through a preset input-output quantification model; the input-output quantification model adopts multiple linear regression or random forest regression methods and is constructed using historical farmland improvement and transformation project data as training samples.

[0013] In some embodiments, the improved technology units built into the intelligent optimization technology pool for farmland improvement in step S3 include: a biochar improvement unit, an organic fertilizer enrichment unit, a straw return to the field unit, a deep tillage and plowing unit, a mechanical land preparation unit, a gravel screening unit, a soil pH fine-tuning unit, a micro-fertilizer targeted application unit, a field micro-topography modification unit, a shallow underground pipe drainage unit, a road traffic improvement unit, an irrigation condition improvement unit, and a drainage system optimization unit; each technology unit independently stores corresponding construction process parameters, material ratio standards, applicable condition thresholds, and unit cost data.

[0014] In some embodiments, the intelligent screening and matching of improved technical units and construction combination schemes in step S3 specifically includes: using the achievement of various shortcoming indicators of the plot as the objective constraint and minimizing the transformation cost as the optimization objective, a multi-objective optimization algorithm is used to screen and optimize the technical units in the technical pool; the multi-objective optimization algorithm is the NSGA-II algorithm, which eliminates redundant construction units and excessive material input under the premise of meeting the achievement constraints, and outputs the optimal technical combination scheme and its corresponding construction sequence arrangement.

[0015] In some embodiments, the multi-measure synergistic approach in step S4 includes at least two combinations of the following: using a compound fertilization method of applying biochar and organic fertilizer to increase soil organic matter content and optimize soil aggregate structure; breaking up soil compaction and thickening the effective tillage layer through deep mechanical plowing and fine mechanical tillage; reducing soil gravel content by screening out gravel and hard debris in the field; adjusting soil pH by quantitatively applying amendments based on measured soil pH values; optimizing surface runoff conditions through fine micro-topography leveling and ridge straightening; optimizing soil water and air structure by laying shallow simple drainage pipes in heavy clay soil areas; improving the field road network system by straightening and repairing field roads; inspecting and repairing existing irrigation networks and optimizing irrigation layout and water conveyance paths; and systematically sorting out field drainage ditches and clearing silted and blocked sections to improve the field drainage network.

[0016] In some embodiments, the retesting and verification in step S5 specifically includes: conducting a full-coverage retest of the farmland quality grade evaluation indicators collected in step S1, comparing the retest data with the target grade standard values ​​item by item; if all indicators meet or exceed the target grade standard, the improvement is deemed to have met the standard; if there are indicators that do not meet the standard, a secondary reinforcement plan is automatically generated based on the difference between the indicators that do not meet the standard, and construction and retesting are carried out again until all indicators meet the standard.

[0017] In some embodiments, there are differentiated constraints between the secondary reinforcement scheme and the initial construction combination scheme: the secondary reinforcement scheme selects targeted reinforcement technology units only for the types of shortcomings corresponding to the non-compliant indicators, and the application intensity of each reinforcement technology unit is calculated based on making up the remaining difference and making the non-compliant indicator exactly reach the target value, so as to avoid over-construction and waste of resources; after the secondary reinforcement construction is completed, a re-test and verification is carried out until all non-compliant indicators meet the standards; for indicators that have met the standards in the first round of verification but have the potential for improvement, no processing is done in the secondary reinforcement stage, and only their status is recorded as a reference for subsequent farmland maintenance.

[0018] This specification also provides a system for rapidly assessing and improving the quality grade of supplemented arable land, comprising: a field data acquisition module for supporting on-site survey data entry, soil index testing data upload, plot image acquisition and location calibration, realizing standardized storage of supplemented arable land baseline data; a grade calculation and scheme generation module, which incorporates a comprehensive evaluation algorithm for arable land quality grades, an index difference calculation model, and an improvement engineering quantity calculation model, for automatically matching the optimal composite improvement scheme based on the baseline data and preset target grades, and outputting a material input list, construction parameters, and renovation period; an improvement construction management and control module for storing standardized construction processes, managing the construction procedures of multiple improvement technology units, recording progress, and retaining data, ensuring the standardized implementation of composite improvement processes; and an effect evaluation and acceptance module for supporting the entry of post-renovation index retest data, automatic grade verification, compliance determination, and automatic generation of acceptance reports, realizing the quantification, traceability, and acceptance of the entire improvement process.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] (1) For the first time, a precise grading and compensation calculation mechanism based on standardized field surveys and weighted model quantification was constructed. The comprehensive evaluation model of cultivated land quality grade automatically calculates the improvement ratio of each indicator, material input and engineering transformation work required for the plot to reach the target grade, completely abandoning the manual experience judgment mode, realizing the precise and data-driven design of improvement schemes, and effectively avoiding the waste and insufficiency of improvement input.

[0021] (2) An innovative intelligent optimization technology pool system for farmland improvement has been constructed. Abandoning the traditional fixed and one-size-fits-all comprehensive improvement model, the system intelligently selects suitable improvement technology units and optimizes the combination scheme based on the plot baseline detection data, the type of shortcoming index, construction conditions and cost thresholds. This achieves a two-way optimal balance between maximizing the improvement of farmland grade and minimizing the transformation cost, solving the industry pain points of fixed application of traditional composite improvement technologies, high ineffective investment and high improvement costs.

[0022] (3) A systematic improvement system was established, which is a whole process of "survey and calculation - precise policy implementation - closed-loop verification". Through quantitative calculation before the transformation, standardized construction management during the transformation, and full-coverage re-measurement and verification after the transformation, the whole process of improving the quality of cultivated land can be quantified, traceable and acceptable, ensuring the stability and reliability of the improvement effect.

[0023] (4) A closed-loop iterative optimization system including a secondary reinforcement mechanism was established. When the first improvement fails to meet the standard, the system automatically generates a targeted secondary reinforcement scheme to make up for the failure to meet the standard. The reinforcement strength is lower than that of the initial scheme to avoid over-construction. The iterative optimization mechanism ensures a high success rate of improvement and high efficiency of resource utilization.

[0024] (5) It can be adapted to inefficient arable land and supplementary arable land with different background conditions, and the improvement scheme is differentiated. It has wide applicability, short improvement cycle, and controllable transformation cost. It is fully compatible with the standardized acceptance work of supplementary arable land and has strong implementation and practicality. Attached Figure Description

[0025] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. The same numbers in the drawings denote the same structures or steps.

[0026] Figure 1 This is a schematic diagram illustrating an application scenario of a method for rapidly assessing and improving the quality grade of supplementary arable land, as shown in some embodiments of this specification.

[0027] Figure 2 This is an exemplary flowchart illustrating a method for rapidly assessing and improving the quality grade of supplementary arable land according to some embodiments of this specification;

[0028] Figure 3 This is a schematic diagram of the structure of the intelligent optimization technology pool for farmland improvement, as shown in some embodiments of this specification.

[0029] Figure 4 This is a schematic diagram of the workflow of the grade calculation and scheme generation module according to some embodiments of this specification;

[0030] Figure 5 This is a schematic diagram of the functional modules of a system for rapidly assessing and improving the quality grade of supplementary arable land, as shown in some embodiments of this specification. Detailed Implementation

[0031] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0032] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0033] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0034] Flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0035] Currently, the improvement of farmland quality relies mainly on the experience and judgment of technical personnel, lacking systematic quantitative calculation tools and standardized construction management systems. In practice, grassroots land consolidation agencies often adopt uniform improvement plans, applying the same types and quantities of improvement materials and implementing the same engineering measures to all plots within the same project area. This results in sandy and clayey soils, acidic and alkaline soils receiving the same treatment, causing significant resource waste and potentially leading to secondary problems in some plots due to improper material application. Furthermore, existing technologies cannot accurately predict the improvement range and required engineering volume for each deficiency index before construction, and there is a lack of scientific acceptance and verification mechanisms after construction. Most projects rely solely on subjective visual inspection or simple spot checks to determine compliance, posing significant acceptance risks. More importantly, existing technologies lack standardized classification and screening mechanisms for improvement technology units—deep tillage, organic fertilizer application, straw return to the field, and biochar improvement each have their applicable conditions and limitations, but traditional methods apply all available technologies indiscriminately to every plot of farmland, creating the misconception that "the more technologies, the better." In fact, for plots of land with only nutrient deficiency, organic fertilizer alone is sufficient to meet the standards, without the need for additional processes such as deep plowing and gravel removal. For plots with only soil compaction, deep plowing combined with straw return to the field can effectively solve the problem, without the need for expensive materials such as biochar. This redundant construction not only significantly increases the cost of land reclamation but also prolongs the construction period and reduces the overall efficiency of land consolidation.

[0036] To address the aforementioned technical problems, some embodiments of this specification provide a method and system for rapidly assessing and improving the quality grade of supplementary arable land. The typical deployment of the method and system will first be described below with reference to the accompanying drawings.

[0037] Figure 1This is a schematic diagram illustrating an application scenario of a method for rapidly assessing and improving the quality grade of supplementary arable land, as shown in some embodiments of this specification. Figure 1 As shown in System 100, in the initial stage of the supplementary arable land quality improvement project, on-site surveys and soil sampling are conducted on the plots to be improved. Survey personnel, carrying portable testing equipment and mobile terminals, conduct field surveys plot by plot according to the field survey standards of the "Detailed Rules for Acceptance of Supplementary Arable Land Quality". The survey content includes: measuring the effective soil layer thickness and topsoil layer thickness using a soil drill or profiler; collecting undisturbed soil samples using the ring cutter method to determine soil bulk density; taking mixed soil samples and packaging them for laboratory testing of chemical indicators such as organic matter content, available phosphorus, available potassium, total nitrogen, pH value, and salinization degree; determining the plot's topographic slope, field elevation difference, and area using GPS and a rangefinder; investigating the type of soil intrusion and gravel content; assessing the type of irrigation water source, water supply guarantee level, and canal system conditions; investigating the grade, accessibility, and road surface condition of field roads; and checking the distribution of pollution sources around the plots. All survey data and test results are uploaded to the system database in real time via mobile terminals to complete an accurate profile of the current status of arable land.

[0038] In some embodiments, the system 100 inputs the aforementioned baseline data into the grade calculation and scheme generation module. This module automatically calculates the current quality grade of the plot based on the national standard for "Cultivated Land Quality Grade" (GB / T 33469), and quantifies the improvement requirements of each shortcoming indicator in conjunction with the preset target grade. Finally, it generates a structured improvement scheme that includes a material input list, engineering construction parameters, and an estimated renovation period. This scheme is then passed to the technology screening submodule, which selects matching technical units and construction combination schemes from the intelligent optimal technology pool for cultivated land improvement based on the type of shortcoming indicators, soil conditions, and cost control requirements of the plot. This minimizes the renovation cost while ensuring that all shortcoming indicators meet the standards.

[0039] In some embodiments, the intelligent analysis system outputs the above-mentioned construction combination scheme as a structured construction guidance document, which is then transmitted to the improved construction management module. This module is installed on the mobile terminal of the project construction management personnel and has functions for process flow guidance, construction progress recording, and image data retention. The management personnel execute the construction tasks one by one according to the sequence of procedures prompted by the module: first, the deep tillage unit is executed, where mechanical deep tillage is performed at the depth specified by the system to break up the plow pan; then, the gravel removal unit is executed, where a vibrating screener is used to screen the topsoil, removing large gravel and construction waste; next, the organic fertilizer enrichment unit and biochar improvement unit are executed, where the fertilizer is evenly spread according to the system-calculated ratio and then rotary tilled into the tillage layer; subsequently, the soil pH fine-tuning unit and micro-fertilizer targeted application unit are executed; finally, the field micro-topography trimming unit is executed, where a laser leveler is used for fine leveling to eliminate localized waterlogging depressions. After each procedure is completed, the management personnel take and upload photos of the construction process and the completed project through the module, and enter the actual material usage and construction parameters, achieving data traceability and quality control throughout the entire construction process.

[0040] In some embodiments, after all improvement and renovation measures are completed and stabilized for one growing season (approximately 6-12 months), the system automatically triggers the effect evaluation and acceptance module. This module generates a retest task list, performing a full-coverage retest of all farmland quality grade evaluation indicators. After the retest data is entered into the system, the farmland quality grade is recalculated, and the measured values ​​of each indicator are compared item by item with the target grade standard values. If all indicators meet the standards, the improvement is deemed successful, and the system automatically generates an acceptance report; if there are indicators that do not meet the standards, the system initiates a secondary reinforcement mechanism, selecting targeted reinforcement technology units only for the type of weakness corresponding to the non-compliant indicators, and the application intensity of the reinforcement measures is lower than the application intensity of the corresponding measures in the initial construction plan, avoiding over-construction and resource waste. Through this closed-loop iterative optimization mechanism, a high success rate and high efficiency of resource utilization are achieved in improving the quality grade of supplementary farmland.

[0041] In some embodiments, Figure 2 This is an exemplary flowchart illustrating a method for rapidly assessing and improving the quality grade of supplementary arable land according to some embodiments of this specification. In some embodiments, Figure 2 The process 200 shown may include steps S1-S5.

[0042] Step S1: In accordance with the field survey specifications for farmland quality acceptance, conduct on-site surveys of the supplementary farmland plots to be upgraded, and collect baseline farmland indicator data. The baseline farmland indicator data includes agricultural production compliance evaluation indicators and farmland quality grade evaluation indicators.

[0043] In some embodiments, this step is strictly carried out in accordance with the field survey standards stipulated in the "Detailed Rules for Technical Specifications for Acceptance of Supplementary Cultivated Land Quality". The survey work is carried out by professionally trained technicians, using a combination of the "sampling point method" and the "comprehensive survey method": for plots with a small area (less than 50 mu), the comprehensive survey method is used, and each plot is investigated and recorded item by item; for plots with a large area (more than 50 mu), the grid sampling method is used, with sampling points arranged at a grid density of 50 meters × 50 meters, and no less than 5 sampling points are arranged for each plot. The average value of the data from each sampling point is taken as the representative value of the plot. The survey and collection of indicators are divided into two categories: The first category is agricultural production compliance evaluation indicators, including effective soil layer thickness (measured by soil drill method and recorded to the centimeter), soil organic matter content (detected by potassium dichromate titration method), topographic slope and field flatness (measured by GPS combined with level), soil intrusion and gravel content (measured by sieve weighing method), water resource security conditions (investigating water source type, water quantity guarantee rate and canal system supporting conditions), road traffic conditions (investigating road grade, road surface condition and accessibility), and soil pollution status (investigating surrounding pollution sources and pollutant types), totaling 7 items. The second category is the evaluation indicators for arable land quality, determined according to GB / T 33469. These include 13 basic indicators: topographic location and road access conditions, effective soil layer thickness, soil texture, topsoil texture, soil bulk density (measured by ring cutter method), organic matter content, available phosphorus content (sodium bicarbonate extraction-molybdenum antimony colorimetric method), available potassium content (ammonium acetate extraction-flame photometry method), water resource security conditions, topsoil thickness, pH, and salinization degree. Regionally specific indicators are automatically supplemented based on the arable land quality evaluation region to which the plot belongs (9 major regions including Northeast China, Huang-Huai-Hai Plain, and the middle and lower reaches of the Yangtze River). For example, "soil freeze-thaw status" is added for Northeast China, and "iron-manganese leaching index" is added for South China. All measured data are entered through standardized electronic forms on mobile terminals. Each data item includes the testing method, testing date, and operator information. After integrity verification, the data is uploaded to the system database, completing an accurate profile of the current status of arable land and providing raw data support for subsequent quantitative calculations.

[0044] Step S2: Based on the baseline data of cultivated land, call the comprehensive evaluation model of cultivated land quality level, combine it with the preset target cultivated land quality level standard, calculate the difference between each shortcoming indicator and the target level standard, quantify the required improvement ratio and improvement threshold of each indicator, and automatically calculate the corresponding improvement input parameters.

[0045] In some embodiments, after obtaining the standardized baseline data from step S1, this step invokes the comprehensive evaluation model for cultivated land quality grades in the grade calculation and scheme generation module. This model is constructed according to GB / T 33469. First, it determines the cultivated land quality grade evaluation area to which the plot belongs, and then loads the corresponding evaluation index system and index weight coefficients for that area. The weight coefficients are determined using a combination of the Analytic Hierarchy Process (AHP) and the entropy weight method. AHP is used to determine the subjective weights of each index. By constructing a judgment matrix, experts in soil science, agronomy, and land management within the region are invited to compare the importance of each evaluation index at the same level pairwise. After consistency testing, the relative weights of each index are calculated. The entropy weight method is used to determine the objective weights. Based on measured data from a large number of cultivated land samples within the evaluation area, the dispersion (information entropy) of each index data is calculated. The greater the degree of data variation, the stronger the distinguishing ability of the index in the evaluation, and the higher the corresponding objective weight. Finally, the subjective and objective weights are combined through multiplication to obtain the comprehensive weight coefficients of each evaluation index.

[0046] In the grade calculation stage, for each evaluation indicator, a corresponding membership function is selected based on its type (numerical or conceptual), mapping the measured value of the indicator to a membership value between 0 and 1. Numerical indicators (such as organic matter content, effective soil layer thickness, and soil bulk density) use fuzzy membership functions (S-shaped, parabolic, or fuzzy functions), calculating the membership degree by setting key parameters such as the upper limit, lower limit, and optimal value of the function. Conceptual indicators (such as topographic location and texture configuration) directly assign membership degrees using the Delphi method. The membership values ​​of each indicator are multiplied by their corresponding comprehensive weight coefficients and summed to calculate the Integrated Cultivated Land Quality Index (IFI). Then, based on the grade classification thresholds specified in GB / T 33469, the current cultivated land quality grade (grades one to ten) of the plot is determined.

[0047] Subsequently, based on the user's preset target level (e.g., upgrading the current eighth-grade land to fifth-grade land), the system automatically extracts the standard value ranges of each indicator corresponding to the target level from the standard database. It then compares the measured values ​​of each indicator of the land parcel with the standard values ​​of the target level item by item, and calculates the difference Δ for each indicator. i = target value i -Measured value i For Δ i Indicators with a value greater than 0 are labeled as "weakest link indicators," sorted in descending order of their differences, and the required improvement percentage (Δ) for each indicator is quantified. i / Measured value i× 100%) and absolute improvement threshold. Based on this, the system further identifies the correlation and constraints between various bottleneck indicators—for example, excessive soil bulk density may restrict the organic matter improvement effect, and pH value that is too acidic or too alkaline may affect nutrient availability—and identifies the constraints through the built-in association rule base (a "if then" production rule set built based on soil science mechanism knowledge), marks the "bottleneck indicators", and prioritizes their processing in subsequent scheme generation.

[0048] Finally, for each weak indicator, based on the difficulty, cost, and contribution to grade improvement, indicators are categorized into three groups: those requiring improvement, those that can be improved, and those that do not require improvement. Indicators requiring improvement are those with low improvement costs and high contributions to grade improvement, and are prioritized for improvement. Indicators that can be improved are those that have already met the standards but still have improvement potential, and whose improvement would further consolidate the grade or enhance farmland productivity; these will be improved if resources permit. Indicators that do not require improvement are those that have already met the standards but have limited improvement potential or excessively high improvement costs, and are not considered for improvement. The system automatically calculates the corresponding improvement input parameters using a pre-defined input-output quantification model. This model is based on measured data from no fewer than 500 land consolidation projects nationwide and uses a random forest regression method to establish a mapping relationship between the indicator improvement rate and the amount of materials applied and the amount of engineering construction. Taking organic matter content as an example, the model takes into account the current content value, target content value, soil type (sand / loam / clay), annual precipitation, and average annual temperature as input variables, and outputs the required organic fertilizer application rate (tons / acre) and biochar application rate (tons / acre), along with a 95% prediction interval to quantify the uncertainty of the estimate. For different types of bottleneck indicators, the model adopts corresponding input and output configurations: effective soil layer thickness corresponds to deep tillage depth and topsoil backfilling volume; soil bulk density corresponds to deep tillage depth, organic fertilizer application rate, and mechanical compaction parameters; gravel content corresponds to screening work volume and screening equipment selection; pH value corresponds to lime or sulfur application rate; available phosphorus / available potassium corresponds to phosphate or potash fertilizer application rate; irrigation guarantee rate / drainage capacity corresponds to channel repair length and pipeline laying length. After summing the outputs of each quantitative model, a structured improvement plan is generated, which includes a material input list (type, specifications, quantity), engineering construction parameters (depth, density, work volume), and an estimated renovation period.

[0049] Step S3: Based on the quantitatively generated improvement plan, call the preset intelligent optimization technology pool for farmland improvement, and intelligently screen and match improvement technology units and construction combination plans by combining the type of shortcoming indicators of the plot, soil conditions and cost control requirements; the intelligent optimization technology pool for farmland improvement has multiple independently selectable improvement technology units.

[0050] In some embodiments, after obtaining the structured improvement scheme output in step S2, this step transmits the various construction parameters in the scheme to the intelligent technology screening submodule. This submodule has a built-in intelligent optimization technology pool for farmland improvement, which pre-stores 13 independently selectable improvement technology units, such as... Figure 3 As shown. Figure 3 This is a schematic diagram of the structure of the intelligent optimization technology pool for farmland improvement, as shown in some embodiments of this specification. Figure 3 As shown, the technology pool adopts a layered architecture design. The top layer is the overall control interface of the technology pool, which is responsible for receiving the short-board index data and construction parameters from the level calculation and scheme generation module, and returning the screening results. The middle layer consists of 13 independently encapsulated technology units. Each technology unit is stored in the form of a standardized data packet, which includes the following information fields: (1) Unit identifier - technology name and unique code; (2) Applicable conditions - applicable soil type (sand / loam / clay), pH range, organic matter content range, terrain conditions and other threshold conditions; (3) Construction process parameters - standard application amount, depth, density, operation method, etc.; (4) Material ratio standard - if material input is involved, the material type, specifications and standard ratio are stored; (5) Unit cost data - material unit price, machine shift fee, labor cost standard; (6) Expected improvement effect curve - empirical function of the improvement of each index of the technology unit under different background conditions; (7) Construction period standard - standard working hours and maintenance cycle of a single process. The underlying layer is an indexing and matching engine for the technology pool, which is responsible for quickly retrieving technical units that meet the applicable conditions based on the input shortcoming indicator type and construction parameters, and outputting a candidate list sorted by relevance.

[0051] In some embodiments, the intelligent screening process employs the NSGA-II multi-objective optimization algorithm. Specifically, it uses "all shortcomings of the plot meeting the standards" as a hard constraint, "minimizing the transformation cost" as the primary optimization objective, and "shortening the construction period" as a secondary objective. The algorithm searches for feasible technology combinations in the technology pool, with each combination consisting of several technology units and their application intensity parameters. The algorithm iteratively evolves through crossover, mutation, and selection operations, calculating the compliance rate, total cost, and total construction period of each solution in each generation. After a preset number of generations (e.g., 200 generations) or convergence conditions, it outputs the Pareto optimal solution set. The system selects the solution with the lowest overall cost and shortest construction period from the solution set as the recommended solution. For example, for a plot with only two shortcomings—low organic matter content and high soil bulk density—the algorithm may select a combination of "organic fertilizer enrichment unit + deep tillage unit + straw return unit," while automatically excluding the biochar improvement unit (high cost, unnecessary) and the gravel removal unit (background gravel content already meets the standards). After screening, the system outputs the optimal combination of technologies and its corresponding construction sequence (such as deep plowing, application of organic fertilizer, and straw return to the field for mulching), ensuring coordination and order among the various processes. Through this intelligent screening mechanism, this invention effectively eliminates redundant construction units and excessive material inputs while ensuring that the farmland meets the standards, achieving a balance between improvement and cost control.

[0052] In some embodiments, the NSGA-II (Non-dominated Sorting Genetic Algorithm II, a fast non-dominated sorting genetic algorithm with an elitist strategy) multi-objective optimization algorithm is one of the most widely used multi-objective genetic algorithms. By introducing two core operators, non-dominated sorting and crowding distance, it can find a set of balanced Pareto optimal solutions among multiple conflicting objectives. In the farmland improvement technology unit selection problem of this invention, there are inherent conflicts among the three optimization objectives—achieving all shortcomings (hard constraint), minimizing transformation costs (primary optimization objective), and minimizing the construction period (secondary optimization objective). For example, increasing material input can usually improve the compliance rate but increase costs, while extending the construction period may reduce construction intensity but increase time costs. NSGA-II can search for a set of non-dominated Pareto optimal solutions in this multi-objective conflict space, allowing the system to flexibly select according to the actual project budget and construction period requirements.

[0053] In some embodiments, the core mechanism of the NSGA-II algorithm includes three parts: fast non-dominated sorting, crowding distance calculation, and elitist strategy. Fast non-dominated sorting is the process of dividing individuals in the population into different tiers (Pareto fronts) according to their "dominance relationships." The dominance relationship is defined as follows: In a multi-objective minimization problem, solution X dominates solution Y if and only if X is not inferior to Y on all objective functions and is superior to Y on at least one objective function; if two solutions are not mutually dominant, they belong to the same non-dominated tier. During sorting, each individual in the population is traversed, calculating the number of individuals dominated by it (dominatedCount) and the list of individuals it dominates (dominatesList). All individuals with dominatedCount=0 are assigned to the first non-dominated front F1. After removing F1 from the population, the above process is repeated for the remaining individuals to obtain F2, F3, and so on, until all individuals are stratified. After non-dominated sorting, solutions with smaller tier numbers (the earlier they appear) are better, and solutions in F1 are not inferior to all other solutions on any objective function. The crowding distance is used to further distinguish the quality of individuals within the same non-dominated level to maintain population diversity. It is calculated as follows: all individuals within the same level are sorted in ascending order according to the m-th objective function value. The crowding distance of the individuals at the edge positions after sorting (i.e., the individuals with the smallest and largest objective function values) is set to infinity. For the middle individuals, the crowding distance is the sum of the normalized differences between the two adjacent individuals on the objective function. The above calculation is repeated for all objective functions, and the total crowding distance of each individual is accumulated. The larger the crowding distance, the better the individual. Prioritizing individuals with large crowding distances can ensure that the solution is evenly distributed on the Pareto front and avoid premature convergence of the algorithm. The elite strategy merges the parent and offspring populations and then selects the best individuals to ensure that superior individuals are not lost during the evolutionary process: the parent population P (size N) and the offspring population Q (size N) are merged into R (size 2N). A fast non-dominated sort is performed on R to obtain F1, F2, F3... frontiers. Starting from F1, individuals from each frontier are sequentially filled into the new generation population P' (size N) until a frontier Fk cannot be fully accommodated. Individuals within that frontier are then sorted by crowding distance from largest to smallest and selected sequentially until P' is filled.

[0054] In some embodiments, the specific application process of the NSGA-II algorithm in this invention is as follows. First, population initialization is performed: the system randomly generates an initial parent population P0 containing N individuals, where N ranges from 100 to 200. Each individual represents a technology combination scheme, encoded as a real number vector of length equal to the total number of technology units in the technology pool (13). The value of the i-th component in the vector represents the application intensity coefficient of the i-th technology unit (a continuous value between 0 and 1): 0 indicates that the technology unit is not selected, and a positive value indicates that it is selected and applied at that intensity (for example, an intensity coefficient of 0.8 for organic fertilizer unit indicates 80% of the standard application amount, and 1.0 indicates full application). Then, the objective function is evaluated and constraints are applied: For each individual (technology combination scheme) in the population, three indicators are calculated: compliance rate (by substituting the application intensity of each technology unit of the scheme into the expected improvement effect curve, calculating the predicted improvement value of each shortcoming indicator, and counting the proportion of the number of compliance indicators to the total number of shortcoming indicators, with a hard constraint of compliance rate = 100%, and individuals that do not meet the constraints are directly eliminated in subsequent selections), total cost (based on the pre-set unit cost data of each technology unit in the technology pool, linearly converted according to the application intensity and then accumulated), and total construction period (based on the standard working hours of each technology unit, the total construction period is calculated according to the construction sequence, and the time overlap optimization of parallel operations is considered).

[0055] In some embodiments, after evaluating the objective function, non-dominated sorting and crowding calculation are performed: a fast non-dominated sort is performed on the current population (size 2N after merging parents and offspring). Individuals with a 100% success rate are given priority in the non-dominated sort, while individuals with a failure rate (<100%) are disadvantaged in the sorting. Unless all individuals fail to meet the criteria, non-compliant individuals will not be selected for the next generation. After sorting, the crowding distance between individuals within each non-dominated front is calculated. Subsequently, environmental selection is performed to generate a new generation population: N individuals are selected from the merged population to form a new generation parent population P1. Individuals from F1, F2, F3, etc., are filled in sequentially. When a front Fk cannot accommodate all individuals, individuals within that front are sorted by crowding distance from largest to smallest and selected sequentially until all N positions are filled. Next, a progeny population is generated through genetic operations: from the new generation of parent population P1, the father and mother are selected through a binary tournament (two individuals are randomly selected, with priority given to individuals with smaller non-dominant levels; if the levels are the same, individuals with greater crowding distance are selected), and a progeny population Q1 is generated using simulated binary crossover (SBX, crossover probability 0.9) and polynomial mutation (mutation probability is 1 / encoding length). This process is repeated until N progeny individuals are generated.

[0056] In some embodiments, the iterative convergence determination is as follows: merge the parent generation P1 and offspring generation Q1 of the new generation, and repeat the above non-dominated sorting, environmental selection, and genetic operation steps until the preset maximum number of iterations (e.g., 200 generations) or population convergence (no significant change in the Pareto front for multiple consecutive generations, i.e., the proportion of identical individuals in the F1 front of two adjacent generations exceeds 95%). After the iteration ends, output all individuals in the current population's F1 front, which is the Pareto optimal solution set. Each scheme in this solution set satisfies the hard constraints of meeting all bottleneck indicators, and each scheme is non-dominant in terms of the two objectives of "cost" and "time"—that is, no scheme is superior to another scheme in both cost and time. The system selects the scheme with the lowest overall cost and shortest time from the Pareto solution set as the recommended scheme. If there are multiple candidates, the entropy weight-TOPSIS method (Technique for Order Preference by Similarity to Ideal Solution, which combines the entropy weight method to objectively determine the weight of each evaluation indicator) can be used to comprehensively evaluate and rank the solution set to select the optimal scheme.

[0057] In some embodiments, the above intelligent screening process is illustrated using a specific plot of land as an example: This plot of land has only two shortcomings: low organic matter content (measured value 2.1%, target value ≥ 2.5%) and high soil bulk density (measured value 1.45 g / cm³, target value ≤ 1.30 g / cm³). After searching in the technology pool, the NSGA-II algorithm selects the Pareto optimal solution set, which includes a combination of "organic fertilizer enrichment unit + deep tillage unit + straw return unit". The total cost of this solution is 2800 yuan / mu, and the construction period is 35 days. The solution containing the biochar improvement unit costs 4200 yuan / mu. Although it meets the standard, the cost is too high, and it is judged as an inferior solution by the non-dominated sorting and eliminated. The solution containing the gravel removal unit is eliminated because the background gravel content has already met the standard, and the application intensity coefficient is compressed to close to 0 during the evolution process. After screening, the system outputs the optimal technology combination scheme and corresponding construction sequence: first, the deep tillage and plowing unit breaks up the plow pan (days 1-3); then, the organic fertilizer enrichment unit applies 2.5 tons / mu of well-rotted organic fertilizer and incorporates it through rotary tillage (days 4-6); finally, the straw return unit covers the straw and performs shallow rotary tillage (days 7-8). The total construction period is estimated at 35 days (including material transportation and machinery allocation time), with an estimated cost of 2800 yuan / mu. The system also notes that "the scheme has passed cost-effectiveness verification, and all shortcoming indicators are predicted to meet standards." Through this intelligent screening mechanism, this invention effectively eliminates redundant construction units and excessive material input while ensuring that the farmland grade meets standards, achieving optimal synergy between improvement effect, transformation cost, and construction period.

[0058] Step S4: According to the construction combination scheme, the selected improvement technology units are combined and constructed to improve and transform the supplementary arable land through a multi-pronged approach.

[0059] In some embodiments, after obtaining the optimal technology combination scheme and construction sequence arrangement selected in step S3, this step performs on-site construction according to the scheme requirements. All construction tasks are guided by the improved construction control module and the process is recorded. Specifically, for different types of short-board indicators, the construction combination scheme selects at least two of the following improved technology units for composite synergistic construction: (1) Soil fertility improvement: adopt the composite fertilization method of biochar and organic fertilizer, and evenly spread according to the ratio calculated by the system (such as applying 2.0~3.0 tons of decomposed organic fertilizer + 0.5~1.0 tons of biochar per mu) and then rotary tillage to mix into the 0~20cm tillage layer to increase the soil organic matter content, optimize the soil aggregate structure, and improve the soil water and fertilizer retention capacity. (2) Long-term soil fertility maintenance: In conjunction with straw crushing and returning technology, the straw of the previous crop is crushed to a length of 5-10cm and then evenly spread on the surface. It is then rotary tilled and compacted into the soil. The amount of straw returned to the field is controlled at 300-500kg / mu to continuously replenish soil organic matter, alleviate soil compaction, and achieve long-term stable fertility of cultivated land. (3) Soil structure optimization: Through mechanical deep tillage (depth 30-40cm), the plow pan and soil compaction layer are broken up. Combined with fine mechanical land preparation (rotary tillage depth 15-20cm, 2-3 passes), the effective cultivated layer is thickened, and the soil bulk density index is optimized to the range of 1.20-1.35g / cm³. (4) Removal of obstacles: Targeted screening of gravel, construction waste, and hard debris is carried out in the field. Vibrating screeners or drum screens are used to screen the top 0-20cm soil to remove gravel and debris with a particle size greater than 2cm, reduce the soil gravel content to ≤5%, and eliminate obstacles to cultivated land production. (5) Precise pH adjustment: Apply soil amendments quantitatively based on the measured pH value of the soil. Apply quicklime (60~150 kg / mu) when pH < 5.5, and apply sulfur powder or gypsum (50~100 kg / mu) when pH > 8.0 to adjust the soil pH value to the suitable agricultural range of 6.0~7.5, optimize the living environment of soil microorganisms, and improve the nutrient absorption and utilization rate. (6) Targeted micronutrient supplementation: Based on the baseline test data of the plot, supplement the soil with the missing micronutrients. For example, apply zinc sulfate (1~2 kg / mu) to zinc-deficient plots, apply borax (0.5~1.0 kg / mu) to boron-deficient plots, and apply chelated iron (0.5~1.0 kg / mu) to iron-deficient plots to improve the nutrient system of the cultivated land. (7) Field micro-topography modification: In response to the problems of uneven terrain, waterlogged depressions, and messy furrows in some plots, a laser leveler is used to perform fine micro-topography leveling (flatness controlled within ±3cm). Combined with ridge straightening, surface runoff conditions are optimized to avoid local waterlogging and soil erosion, and to unify the cultivation conditions of the plots. (8) Shallow underground drainage improvement: In response to the problems of heavy soil, poor air permeability, waterlogging after rain, and excessively wet topsoil in some plots, shallow simple drainage underground pipes are laid (buried depth 60~100cm, spacing 5~10m) to optimize the soil water and air structure, reduce the risk of soil waterlogging, and improve the soil and water conditions of cultivated land. (9) Road access improvement: Based on the regularization of field roads, the repair of road surface flatness (laying a gravel or sand cushion layer with a thickness of 10~15cm) and the optimization of passing nodes, the field road network system is improved, the blockage of land access is opened, and the accessibility and operation convenience of agricultural machinery are improved. (10) Improve irrigation conditions: Based on the existing irrigation network and well facilities, conduct inspections and repairs, make up for the shortcomings of irrigation facilities, optimize the irrigation layout and water conveyance path (channel lining or pipeline laying), achieve full coverage of irrigation of the plots and uniform water conveyance, and improve the irrigation water supply guarantee capacity. (11) Optimize drainage system: Systematically sort out the field drainage ditches and drainage network, dredge the silted and blocked sections (dredging depth to 20cm below the original ditch bottom elevation), standardize the ditch cross-sectional shape (bottom width ≥30cm, slope ratio 1:0.5~1:1), improve the field drainage network, effectively and quickly drain the field water, and improve the flood control and drainage capacity of cultivated land.

[0060] The specific combination of the above-mentioned technical units is determined by the intelligent screening results in step S3. During construction, the improved construction control module guides the process step by step according to the sequence of procedures. After each procedure is completed, the management personnel record the actual construction parameters (material usage, working depth, working area, etc.) through the module and take photos for record-keeping, thereby achieving data traceability and quality tracking throughout the entire construction process.

[0061] Step S5: After the improvement and renovation construction is completed and stabilized, the core indicators of the farmland quality grade are re-measured and verified. The re-measured data is entered into the system to recalculate the farmland quality grade. All indicators are confirmed to meet the preset target grade standards, and the supplementary farmland quality grade improvement and acceptance closed loop is completed.

[0062] In some embodiments, after all improvement and renovation measures are completed and stabilized for one growing season (approximately 6-12 months), this step involves performance evaluation and acceptance. During the stabilization period, normal field management (irrigation, weeding, pest and disease control, etc.) is required to ensure the improved materials fully integrate with the soil and the newly constructed field facilities undergo practical operational testing. Upon completion of the stabilization period, the system automatically generates a retesting task list, requiring full-coverage retesting of all farmland quality grade evaluation indicators collected in step S1. The retesting employs the same standard methods and quality control requirements as the initial testing to ensure data comparability—the same sampling point locations (via GPS location revisiting), the same testing methods, and the same quality control standards.

[0063] After the re-measurement data is entered into the system, the module calls the same comprehensive evaluation model and membership function as in step S2 to recalculate the Integrated Farmland Quality Index (IFI) and the corresponding quality grade, and compares the measured values ​​of each indicator with the target grade standard values ​​item by item. If all indicators meet or exceed the target grade standard, the improvement is deemed satisfactory, and the system automatically generates an acceptance report. The report includes: basic information of the plot (number, location, area), a comparison table of baseline data and re-measurement data (listing the original value, re-measurement value, improvement range, and satisfaction determination for each indicator), quality grade change (original grade → current grade), index of construction process image data (storage path of completed photos of each process), acceptance conclusion ("satisfied" or "not satisfied"), acceptance date, and electronic signature of the acceptance personnel. This report meets the standardization and traceability requirements for supplementary farmland quality acceptance and can be directly submitted as the official deliverable of the project acceptance.

[0064] If the retest reveals that some indicators fail to meet the standards, the system initiates a secondary reinforcement mechanism. The secondary reinforcement plan differs from the initial construction plan: targeted reinforcement technology units are selected only for the specific weaknesses corresponding to the failed indicators, and the application intensity of the reinforcement measures is lower than the corresponding measures in the initial construction plan (typically 40%–60% of the initial intensity). For example, if the retest shows that the organic matter content is still lower than the target value (e.g., target is 2.5%, actual measurement is 2.2%), the system only recommends supplementing with organic fertilizer, at an application rate of 50% of the organic fertilizer application rate in the initial plan (e.g., initial 2.5 tons / acre, supplement 1.25 tons / acre), to avoid over-fertilization leading to nutrient imbalance and resource waste. After the secondary reinforcement construction is completed, the retesting and verification process is repeated until all indicators meet the standards. Through this closed-loop iterative optimization mechanism, this invention achieves a high success rate in improving the quality grade of supplementary cultivated land and high efficiency in resource utilization.

[0065] Figure 4 This is a schematic diagram illustrating the workflow of the grade calculation and scheme generation module according to some embodiments of this specification. For example... Figure 4As shown, the workflow of the rating calculation and solution generation module starts from the data input layer and goes through five core processing stages in sequence: current rating assessment, target rating setting and difference calculation, weakness indicator analysis, input-output quantitative calculation, solution generation and cost-benefit verification, and finally outputs a structured improvement solution.

[0066] The data input layer receives standardized baseline data from the field data acquisition module, including basic information of the land parcel (number, location, area, and grade evaluation area), agricultural production compliance evaluation indicators (7 items), and cultivated land quality grade evaluation indicators (13 basic indicators + regional supplementary indicators). After integrity verification and outlier detection, it enters the next stage.

[0067] The first processing stage is... Figure 4 The function block numbered 410 executes, calling the built-in comprehensive evaluation model for cultivated land quality grades to determine the current grade. Function block 410 contains three parallel processing sub-modules: Sub-module 411 is the region identification sub-module, which automatically determines the cultivated land quality grade evaluation region (one of the nine major regions) to which the plot belongs based on the place name, address, and latitude and longitude coordinates, and loads the corresponding evaluation index system and index weight coefficients for that region; Sub-module 412 is the membership degree calculation sub-module, which automatically matches the corresponding membership degree function (S-type, parabolic, or conceptual assignment table) according to the membership degree function type specified in GB / T 33469 for the measured value of each evaluation indicator, and calculates the membership degree value of each indicator; Sub-module 413 is the comprehensive index aggregation sub-module, which performs a weighted summation of the membership degree value of each indicator with the corresponding comprehensive weight coefficient (obtained by combining weights using the AHP-entropy weight method) to calculate the cultivated land quality comprehensive index (IFI), and determines the current quality grade according to the grade classification threshold specified in GB / T 33469.

[0068] The second processing stage is... Figure 4 Function block 420 is executed, responsible for setting the target level and calculating the difference. Function block 420 receives the target level input by the user, automatically extracts the standard value ranges of each indicator corresponding to the target level from the standard database, compares the measured values ​​of each indicator of the land parcel with the standard values ​​of the target level item by item, and calculates the difference Δ for each indicator. i = target value i - Measured value i , will Δ i Indicators with a value greater than 0 are labeled as "weakness indicators". The list of weakness indicators is then output in descending order of the difference value.

[0069] The third processing stage is... Figure 4Function block 430 is responsible for analyzing bottleneck indicators and identifying bottlenecks. Function block 430 performs correlation analysis on the list of bottleneck indicators. It has a built-in indicator correlation rule library (stored as a "if then" production rule set) built based on soil science mechanisms. This library is used to identify the constraints and hierarchical structure between the bottleneck indicators, mark "bottleneck indicators", and output the bottleneck indicator processing priority sequence. This sequence determines the calling order and construction sequence of the subsequent input-output quantification model.

[0070] The fourth processing stage is Figure 4 Function block 440 is responsible for the quantitative calculation of input and output. Function block 440 contains three parallel input and output quantification sub-models: Sub-module 441 is the quantitative model for improving soil physical properties (built based on random forest regression), which outputs construction parameters such as deep tillage depth, organic fertilizer application rate, and screening volume to meet the needs of improving physical property indicators such as soil bulk density, effective soil layer thickness, and gravel content; Sub-module 442 is the quantitative model for improving soil chemical properties, which outputs material parameters such as organic fertilizer application rate, biochar application rate, lime / sulfur application rate, and micronutrient fertilizer type and dosage to meet the needs of improving chemical property indicators such as organic matter content, available phosphorus, available potassium, and pH value; Sub-module 443 is the quantitative model for supporting field facilities, which outputs construction parameters such as channel repair length, pipeline laying length, and road repair volume to meet the needs of improving facility condition indicators such as irrigation guarantee rate, drainage capacity, and road accessibility. Each quantification model output includes a 95% prediction interval to reflect estimation uncertainty. After the calculation is completed, all output parameters are summarized into the scheme synthesizer.

[0071] The fifth processing stage is by Figure 4Function block 450 is responsible for scheme generation and cost-benefit verification. Function block 450 contains three sequentially connected sub-modules: Sub-module 451 is the technology unit mapping sub-module, which maps the various construction parameters output from the fourth stage to the corresponding technology units in the intelligent optimal technology pool for farmland improvement (deep tillage depth → deep tillage unit, organic fertilizer application rate → organic fertilizer enrichment unit, biochar application rate → biochar improvement unit, etc.), forming an initial technology combination scheme; Sub-module 452 is the cost-benefit verification sub-module, which performs cost accounting and benefit evaluation on the initial technology combination scheme—cost accounting is based on the sum of the pre-set unit cost data of each technology unit in the technology pool and the total cost of the scheme; benefit evaluation is based on the pre-set unit cost data of each technology unit. The improvement effect curve verification process ensures that all shortcomings in the combined scheme are met. If the scheme passes the cost threshold verification and feasibility verification, it enters the output stage. If any verification fails, the scheme adjustment and optimization mechanism is triggered. Submodule 453 is the scheme adjustment and optimization submodule, which uses a greedy strategy combined with a local search algorithm to iterate the scheme—identifying high-priced technical units that cause cost overruns and reducing their application intensity or replacing them with low-cost alternatives. At the same time, it identifies non-compliant indicators and increases the application intensity of the corresponding technical units accordingly. After adjustment, the cost-benefit verification is carried out again, forming an iterative optimization closed loop until the scheme passes verification or the number of iterations reaches the upper limit. The verified scheme enters the scheme output layer, outputting the material input list, engineering construction parameters, renovation period estimate, and cost overview in a structured data format, which is then passed to the improvement construction management module as a quantitative guidance basis for subsequent construction execution.

[0072] Some embodiments of this specification also provide a system for rapidly assessing and improving the quality grade of supplementary arable land. Figure 5 This is a functional module diagram illustrating a system for rapidly assessing and improving the quality grade of supplementary cultivated land, according to some embodiments of this specification. In some embodiments, such as Figure 5 As shown, the system 500 includes a field data acquisition module 510, which supports the input of on-site survey data, the uploading of soil index testing data, the acquisition of plot images and location calibration, and realizes the standardized storage of supplementary arable land baseline data; a grade calculation and scheme generation module 520, which has built-in arable land quality grade comprehensive evaluation algorithm, index difference calculation model and improvement engineering quantity calculation model, which is used to automatically match the optimal composite improvement scheme according to the baseline data and preset target grade, and output material input list, construction parameters and renovation period; an improvement construction management and control module 530, which is used to store standardized construction technology, perform process management, progress recording and data retention for the construction procedures of multiple improvement technology units, and ensure the standardized implementation of composite improvement technology; and an effect evaluation and acceptance module 540, which supports the input of post-renovation index retest data, automatic grade verification, compliance judgment and automatic generation of acceptance reports, and realizes the quantification, traceability and acceptance of the entire improvement process.

[0073] For more information on each module, please refer to [link / reference]. Figures 2 to 4 The relevant explanations will not be repeated here. The module content of the system 500 for rapidly assessing and improving the quality of supplementary arable land corresponds to the steps of process 200.

[0074] Unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this application are not intended to limit the order of the processes and methods of this application. Although some embodiments that are currently considered useful have been discussed by way of various examples in the foregoing disclosure, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. Rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments of this application.

[0075] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the specification, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the present application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0076] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this application, their entire contents are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this application, as well as documents that limit the broadest scope of the claims of this application (currently or subsequently appended to this application). Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of this application. Other variations may also fall within the scope of this application. Therefore, alternative configurations of the embodiments of this application are considered consistent with the teachings of this application, not as examples or limitations. Accordingly, the embodiments of this application are not limited to the embodiments explicitly described and presented in this application. To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. For those skilled in the art, this application can be applied to other similar scenarios based on these drawings without creative effort. Unless obvious from the linguistic context or otherwise stated, the same reference numerals in the drawings represent the same structures or operations.

Claims

1. A method for rapidly assessing and improving the quality grade of supplementary arable land, characterized in that, Includes the following steps: S1: In accordance with the field survey specifications for farmland quality acceptance, conduct on-site surveys of the supplementary farmland plots to be upgraded and collect farmland baseline index data; the farmland baseline index data includes agricultural production compliance evaluation indicators and farmland quality grade evaluation indicators. S2: Based on the aforementioned baseline data of arable land indicators, the comprehensive evaluation model for arable land quality grades is invoked. First, an agricultural production compliance evaluation is conducted. If all agricultural production compliance evaluation indicators are qualified, then, in conjunction with the preset target arable land quality grade standard, the difference between each evaluation indicator and the target grade standard is calculated item by item to identify the non-compliant indicators. Based on the difficulty of improvement, the cost of improvement, and the contribution to grade improvement of each indicator, each indicator is divided into three categories: mandatory improvement, possible improvement, and no need for improvement. Among them, mandatory improvement indicators are those non-compliant indicators with low improvement costs and high contributions to grade improvement, and are given priority for improvement. Possible improvement indicators are those that have met the standard but still have the potential for improvement, and improvement can further consolidate the grade or enhance the arable land productivity, and are improved under the condition that resources permit. No need for improvement indicators are those that have met the standard but have limited improvement potential or excessively high improvement costs, and are not considered for improvement. S3: Based on the threshold increase, the system automatically calls the intelligent optimization technology pool for farmland improvement, and automatically calculates the corresponding input parameters required for farmland improvement by combining the type of shortcoming indicators of the plot, the soil background conditions, and cost control constraints. The parameters include, but are not limited to, the amount of organic fertilizer applied, the amount of biochar applied, the amount of straw returned to the field, the depth of deep plowing, the amount of gravel removal, the length of field road repair, and the scope of ditch improvement. The system autonomously selects and outputs construction combination schemes that are suitable for actual working conditions. The intelligent optimization technology pool for farmland improvement has multiple independently selectable improvement technology units. S4: According to the construction combination scheme, retrieve the improved technology integration unit selected by combination and carry out agronomic regulation and engineering remediation operations in a comprehensive manner. Eliminate the limiting factors of farmland grade improvement through a multi-dimensional combination of agronomic and engineering measures and promote the short-board indicators to meet the acceptance standards. S5: After the improvement and renovation construction is completed and stabilized, the shortcomings of the cultivated land quality grade indicators are re-measured and verified. The re-measured data is entered into the system to recalculate the cultivated land quality grade. All indicators are confirmed to meet the preset target grade standards, and the closed loop of supplementary cultivated land quality grade improvement and acceptance is completed.

2. The method for rapidly assessing and improving the quality grade of supplementary cultivated land according to claim 1, characterized in that, The agricultural production compliance evaluation indicators mentioned in step S1 include, but are not limited to, effective soil layer thickness, soil organic matter content, topographic slope and field flatness, soil intrusion and gravel content, water resource security conditions, road access conditions, and soil pollution status; the cultivated land quality grade evaluation indicators include, but are not limited to, topographic location and road access conditions, effective soil layer thickness, texture configuration, topsoil texture, soil bulk density, organic matter content, available phosphorus content, available potassium content, water resource security conditions, topsoil thickness, pH, and salinization degree; different provinces need to add or subtract indicators according to local conditions.

3. The method for rapidly assessing and improving the quality grade of supplementary cultivated land according to claim 1, characterized in that, The comprehensive evaluation model for cultivated land quality grade described in step S2 uses a combination of the analytic hierarchy process (AHP) and the entropy weight method to determine the weight coefficients of each evaluation indicator. The model is constructed based on the evaluation indicator system specified in the national standard for cultivated land quality grade (GB / T 33469), and the weight coefficients of each indicator are adjusted differently according to the natural geographical conditions and land use type of the supplemented cultivated land area.

4. The method for rapidly assessing and improving the quality grade of supplementary cultivated land according to claim 1, characterized in that, The automatic calculation of the corresponding improvement input parameters in step S3 specifically includes: based on the difference between the measured values ​​of each shortcoming indicator and the target level standard value, combined with the plot area, soil type and construction conditions, etc., calculating the material demand per unit area, engineering construction volume and construction period estimate through a preset input-output quantification model; the input-output quantification model adopts multiple linear regression or random forest regression methods and is constructed using historical farmland improvement and transformation project data as training samples.

5. The method for rapidly assessing and improving the quality grade of supplementary cultivated land according to claim 1, characterized in that, The technical units built into the intelligent optimization technology pool for farmland improvement in step S3 include, but are not limited to: biochar improvement unit, organic fertilizer enrichment unit, straw return to field unit, deep plowing and turning unit, mechanical land preparation unit, gravel screening unit, soil pH fine-tuning unit, micro-fertilizer targeted application unit, field micro-topography modification unit, shallow underground pipe drainage unit, road traffic improvement unit, irrigation condition improvement unit, and drainage system optimization unit; each technical unit independently stores corresponding construction process parameters, material ratio standards, applicable condition thresholds, and unit cost data.

6. The method for rapidly assessing and improving the quality grade of supplementary cultivated land according to claim 5, characterized in that, The intelligent optimization technology units and construction combination scheme for farmland improvement mentioned in step S3 specifically include: using the achievement of various shortcoming indicators of the plot as the objective constraint and minimizing the transformation cost as the optimization objective, a multi-objective optimization algorithm is used to screen and optimize the technology units in the technology pool; the multi-objective optimization algorithm is the NSGA-II algorithm, which eliminates redundant construction units and excessive material input under the premise of meeting the achievement constraints, and outputs the optimal technology combination scheme and its corresponding construction sequence arrangement.

7. The method for rapidly assessing and improving the quality grade of supplementary arable land according to claim 1, characterized in that, The multi-pronged approach described in step S4 includes at least two combinations of the following: using biochar combined with organic fertilizer to improve soil organic matter content and optimize soil aggregate structure; breaking up soil compaction and thickening the effective tillage layer through deep mechanical tillage and fine mechanical land preparation; reducing soil intrusion and gravel content by screening out gravel and hard debris in the field; adjusting soil pH by quantitatively applying amendments based on measured soil pH values; optimizing surface flatness and runoff conditions through fine micro-topography leveling and ridge shaping; optimizing soil water and salt structure by laying shallow drainage pipes in saline-alkali soil areas; improving the farmland road network system by standardizing and repairing field roads; inspecting and repairing existing irrigation networks and optimizing irrigation layout and water conveyance paths; and systematically sorting out field drainage ditches and clearing silted and blocked sections to improve the field drainage network.

8. The method for rapidly assessing and improving the quality grade of supplementary arable land according to claim 1, characterized in that, The retesting and verification in step S5 specifically includes: retesting the key shortcomings of the cultivated land quality grade evaluation indicators collected in step S1, and comparing the retested data with the target grade standard values ​​item by item; if all indicators meet or exceed the target grade standard, the improvement is deemed to have met the standard; if there are indicators that do not meet the standard, a secondary reinforcement plan is automatically generated based on the difference between the indicators that do not meet the standard, and construction and retesting are carried out again until all indicators meet the standard.

9. The method for rapidly assessing and improving the quality grade of supplementary arable land according to claim 8, characterized in that, The secondary reinforcement scheme differs from the initial construction scheme in that the secondary reinforcement scheme selects targeted reinforcement technology units only for the types of shortcomings corresponding to the non-compliant indicators. The application intensity of each reinforcement technology unit is calculated based on making up the remaining difference and ensuring that the non-compliant indicator reaches the target value, so as to avoid over-construction and waste of resources. After the secondary reinforcement construction is completed, a retest and verification are carried out until all non-compliant indicators meet the standards. For indicators that have met the standards in the first round of verification but have the potential for improvement, no action is taken in the secondary reinforcement stage, and their status is only recorded as a reference for subsequent farmland maintenance.

10. A system for rapidly assessing and improving the quality grade of supplementary arable land, the system performing the method for rapidly assessing and improving the quality grade of supplementary arable land as described in any one of claims 1-9, characterized in that, The system includes: The field data acquisition module is used to support the entry of on-site survey data, the uploading of soil index test data, the acquisition of plot images and location calibration, and to realize the standardized storage of supplementary arable land baseline data; The grade calculation and scheme generation module has a built-in comprehensive evaluation algorithm for cultivated land quality grade, index difference calculation model and improvement engineering quantity calculation model. It is used to automatically match the optimal composite improvement scheme based on the baseline data and preset target grade, and output the material input list, construction parameters and renovation period. The improved construction management module is used to store standardized construction processes, manage the construction procedures of multiple improved technical units, record progress and retain data, and ensure the standardized implementation of composite improved processes. The effect evaluation and acceptance module is used to support the input of data for retesting indicators after the transformation, automatic verification of levels, determination of compliance and automatic generation of acceptance reports, so as to realize the quantification, traceability and acceptance of the entire improvement process.