A regional-scale intelligent and precise improvement system and method for strongly acidic arable land
By constructing a soil acidification information perception layer and an intelligent diagnosis layer that integrates multi-source data, combined with an improvement scheme optimization decision layer and a variable precision operation execution layer, the problem of lack of systematicness and precision in the improvement of strongly acidic farmland at the regional scale has been solved. This has enabled precise characterization of the degree of soil acidification and precise application of soil amendments, achieving the effect of intelligent improvement.
Patent Information
- Application Number
- CN202611245363.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-17
- Publication Date
- 2026-11-10
AI Technical Summary
Existing technologies lack a systematic understanding and precise characterization of the spatial heterogeneity of acidification in regionally strongly acidic farmland. Improvement schemes lack specificity and systematicity, and the application of amendments is inaccurate, resulting in insufficient or excessive improvement in some areas, making it difficult to achieve intelligent decision-making and dynamic optimization.
A regional soil acidification information sensing layer is constructed. Through multi-source data fusion and spatial interpolation, a continuous spatial distribution map of soil pH, organic matter content and texture is generated. Combined with an intelligent acidification degree diagnosis layer and an improvement scheme optimization decision layer, annual improvement targets are dynamically set to achieve precise calculation and application of conditioners and organic fertilizers. A variable precision operation execution layer is established to form a closed-loop management mechanism.
It enables precise identification and grading of strongly acidic farmland at the regional scale, and differentiated and precise calculation and intelligent recommendation of soil amendment dosage, ensuring the accessibility, safety and economy of the improvement effect. It solves the problem of the lack of pertinence and systematicness of improvement schemes in traditional methods, and realizes dynamic closed-loop management with annual iterative optimization.
Smart Images

Figure CN123058130A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of soil improvement technology, and in particular relates to a regional-scale intelligent and precise improvement system and method for strongly acidic arable land. Background Technology
[0002] Soil acidification is a global soil degradation problem that has become a major obstacle to sustainable agricultural development and national food security. In my country, acidified arable land is widely distributed and covers a large area, exhibiting a trend of increasing acidity, rapid acidification, and potential acidification. Soil acidification exacerbates soil fertility degradation, ecological function decline, and increased risks of heavy metal pollution, severely restricting regional grain production capacity and sustainable agricultural development. Acidification leads to a sharp increase in the concentration of harmful aluminum and manganese ions in the soil, producing toxic effects on crops and affecting crop yield and quality; in strongly acidic areas, crop yields can decrease by more than 20%. Simultaneously, soil acidification also leads to a decrease in microbial diversity and abundance, exacerbating soil-borne diseases and pests.
[0003] Therefore, existing technologies for the remediation of acidified farmland still have the following prominent problems: First, traditional methods for remediating acidified farmland mainly rely on the field application of chemical amendments such as lime and dolomite, and organic fertilizers. Remediation decisions are often based on experience or local spot monitoring data, lacking a systematic understanding and precise characterization of the spatial heterogeneity of farmland acidification at the regional scale. The distribution characteristics of strongly acidic farmland and the spatial variation patterns of acidification levels at the regional scale are difficult to effectively depict, resulting in a lack of targeted and systematic remediation plans. Second, the level of intelligence in acidification remediation decisions in existing technologies is low, with remediation plans largely relying on human experience or simple rules. Although some studies in recent years have explored combining remote sensing monitoring and geographic information systems with soil remediation, most have remained at the level of monitoring and visualizing soil acidification, failing to form a complete chain from precise regional-scale acidification diagnosis to intelligent decision-making for remediation plans. There is a lack of effective data communication and intelligent transformation mechanisms between the decision-making and execution levels. Third, existing technologies struggle to achieve precise application of amendments. Because soil acidification is spatially unevenly distributed, with significant differences in acidification levels across different regions, traditional methods often employ uniform or experience-based application of conditioners. This fails to consider the spatial heterogeneity of soil pH buffering capacity or the dynamic characteristics of conditioner utilization rates varying with soil type and environmental conditions. This leads to insufficient improvement in some areas and excessive conditioner application in others, affecting improvement effectiveness and potentially causing secondary environmental problems. Furthermore, the lack of regionally differentiated characterization of organic fertilizer mineralization loss rates hinders precise optimization of organic fertilizer application. Fourth, current technologies lack a complete closed-loop system encompassing "perception-diagnosis-decision-execution." Currently, the processes from acquiring soil acidification information, diagnosing acidification levels, formulating improvement plans, to precise application of conditioners are fragmented, lacking an integrated system solution. Moreover, there is a lack of dynamic setting mechanisms for progressively increasing improvement targets each year and a closed-loop management capability for iterative correction year by year, preventing the improvement process from adaptively optimizing based on actual results. In conclusion, there is an urgent need to develop a system and method capable of intelligent and precise improvement of strongly acidic farmland at the regional scale. Summary of the Invention
[0004] To address the aforementioned technical problems, this invention provides a regional-scale intelligent and precise improvement system and method for severely acidic arable land. Specifically, the regional-scale intelligent and precise improvement system for severely acidic arable land includes: The regional soil acidification information sensing layer is used to acquire multi-source soil acidification and fertility-related data of the target area, and obtain multi-source sensing data of the target area. An intelligent acidification degree diagnosis layer is connected to the regional soil acidification information sensing layer. It is used to receive the multi-source sensing data and perform acidification degree classification diagnosis through a spatial interpolation model based on the multi-source sensing data to obtain the acidification diagnosis results of each spatial unit in the target area. The improvement scheme optimization decision layer is connected to the acidification degree intelligent diagnosis layer. It is used to receive the acidification diagnosis results and, based on the acidification diagnosis results, combined with the crop types and suitable growth parameters of each spatial unit, dynamically set the annual improvement targets for each spatial unit, calculate the recommended dosage of the improver for each year, and generate annual and differentiated regional improvement schemes. The variable precision operation execution layer is connected to the improvement scheme optimization decision layer. It is used to receive the regional improvement scheme, and based on the regional improvement scheme, combined with the global positioning system and variable operation technology, generate the annual variable operation prescription map, and control the operation machinery to perform variable precision application of the improvement agent.
[0005] Preferably, the regional soil acidification information sensing layer includes: The actual data acquisition module is used to set up monitoring points in the target area according to the preset deployment density, collect mixed soil samples of the topsoil and conduct laboratory tests to obtain the latitude and longitude coordinates and soil physicochemical property test data of each monitoring point; wherein, the soil physicochemical property test data includes soil pH value, organic matter content, mechanical composition, bulk density and topsoil thickness. The historical and survey data integration module is used to access historical soil survey data, soil testing and fertilizer recommendation historical data, arable land quality monitoring historical data and the results of the third national soil census of the target area. After standardization and quality control, it is spatiotemporally matched with the monitoring point data obtained by the actual data acquisition module to obtain historical supplementary data in a unified format. The planting information acquisition module is used to acquire information on the types of crops planted and the crop rotation system in each spatial unit of the target area, and obtain planting information data. The meteorological and auxiliary data module is used to acquire meteorological data such as precipitation, temperature and acid rain frequency of the target area, and obtain meteorological auxiliary data.
[0006] Preferably, the intelligent diagnostic layer for acidification level includes: The multi-source data fusion module is used to perform spatiotemporal registration and standardization on the monitoring point data obtained by the actual data acquisition module, the historical supplementary data obtained by the historical and survey data integration module, and the meteorological auxiliary data obtained by the meteorological and auxiliary data module, and unify them into the same spatial grid system to obtain a fused standardized spatial dataset. The spatial interpolation and mapping module is connected to the multi-source data fusion module. It is used to receive the standardized spatial dataset and use co-kriging or random forest spatial prediction methods, with monitoring point data as the main data and historical data as the auxiliary data, combined with soil type, topography and land use auxiliary covariates to perform spatial interpolation to generate a continuous spatial distribution map of soil pH, organic matter content and soil texture in the target area. The acidification degree grading module is connected to the spatial interpolation and mapping module. It is used to receive the spatial distribution map of soil pH value, and classify the acidification degree according to the preset grading standard, and count the area and spatial distribution of each level to obtain the acidification degree grading result. The acidification and fertility comprehensive assessment module is connected to the acidification degree classification module and the spatial interpolation and mapping module, respectively. It is used to receive the acidification degree classification results and the spatial distribution maps of organic matter content and soil texture, overlay the acidification classification results with organic matter content and texture information, identify the combined obstacle areas of acidification and infertility, and obtain the comprehensive assessment results of acidification and fertility.
[0007] Preferably, the improved scheme optimizes the decision-making layer, which includes: The Crop Suitable pH and Nutrient Requirements Database Module is used to store the suitable soil pH range, suitable organic matter content reference value, and minimum organic matter requirement threshold for crops. The dynamic improvement target setting module is connected to the acidification degree classification module, the acidification and fertility comprehensive assessment module, and the crop suitable pH and nutrient requirement database module, respectively. It is used to receive the acidification diagnosis results and the acidification and fertility comprehensive assessment results of each spatial unit, and retrieve the suitable pH range and organic matter requirements of the currently planted crops in each spatial unit from the crop suitable pH and nutrient requirement database module. It sets the long-term target pH value and long-term target organic matter content of each spatial unit, and decomposes the long-term target into the phased targets of each year according to the improvement cycle and annual improvement safety threshold, so as to obtain the annual improvement target data of each spatial unit. The soil acid-base buffer capacity and texture correction module is connected to the spatial interpolation and mapping module. It is used to receive soil texture and organic matter content data of each spatial unit, and calculate the actual soil acid-base buffer capacity of each spatial unit based on the soil clay content and organic matter content to obtain buffer capacity correction data. The conditioner dosage calculation module is connected to the dynamic improvement target setting module and the soil acid-base buffer capacity and texture correction module, respectively. It is used to receive the annual improvement target data and buffer capacity correction data of each spatial unit, and calculate the theoretical recommended dosage of conditioner for each year based on the soil bulk density, topsoil thickness, conditioner acid neutralization capacity and conditioner utilization coefficient of each spatial unit, so as to obtain the conditioner dosage data of each spatial unit for each year. The organic fertilizer usage calculation module is connected to the dynamic improvement target setting module. It is used to receive the annual improvement target data of each spatial unit and calculate the theoretical recommended usage of organic fertilizer for each year based on the soil bulk density, topsoil thickness, organic matter content in the selected organic fertilizer, seasonal mineralization rate of organic fertilizer and annual mineralization loss rate of soil organic matter in each spatial unit, so as to obtain the organic fertilizer usage data of each spatial unit for each year. The comprehensive improvement scheme generation module is connected to the conditioner dosage calculation module and the organic fertilizer dosage calculation module, respectively. It is used to receive conditioner dosage data and organic fertilizer dosage data of each spatial unit for each year, and to integrate them spatially and temporally to generate annual and differentiated regional improvement schemes that include the types of improvers, recommended application rates, application periods and application sequences of each spatial unit for each year.
[0008] Preferably, the improved scheme further includes the following optimization decision layer: The improvement effect pre-evaluation module, connected to the comprehensive improvement scheme generation module, is used to receive differentiated regional improvement schemes by year, and to perform year-by-year virtual simulation pre-evaluation of the improvement schemes for each spatial unit using a soil acidification buffer model and an organic matter balance model. It predicts the pH value and organic matter content of each spatial unit at the end of each year, and verifies whether the annual improvement amount does not exceed the annual safety threshold and the single application limit, and obtains the pre-evaluation results. The pre-evaluation results are output in the form of visual charts for users to review and adjust.
[0009] Preferably, the variable precision job execution layer includes: The annual work prescription map generation module is connected to the improvement scheme optimization decision layer. It is used to receive the regional improvement scheme and convert the recommended dosage of conditioner and organic fertilizer for each spatial unit into a variable work prescription map containing information on the independent application of conditioner and organic fertilizer. The variable work prescription map is in raster or vector format. The GPS positioning and navigation module is used to obtain the precise location of the operating machinery in real time and generate positioning and navigation information; The variable application control module is connected to the annual operation prescription map generation module and the GPS positioning and navigation module respectively. It is used to receive the variable operation prescription map and the positioning and navigation information, and adjust the discharge rate of conditioner and organic fertilizer in real time according to the target application amount of the current grid in the prescription map and the travel speed of the operating machinery, so as to control the operating machinery to perform variable precise application. The operation quality monitoring module is connected to the variable application control module. It is used to record the actual application amount, operation trajectory and coverage area in real time, generate an operation quality report, and feed the actual application amount data back to the system database.
[0010] Preferably, the variable application control module includes a dual-variable hopper, a controller, and an actuator; The dual-variable hoppers respectively contain conditioner and organic fertilizer; The controller is connected to the annual work prescription map generation module and the GPS positioning and navigation module, and is used to calculate the discharge rate of conditioner and organic fertilizer according to the target application amount and mechanical travel speed of the current grid, respectively. The actuator is connected to the controller and is used to control the opening of the discharge ports of the conditioner hopper and the organic fertilizer hopper according to the discharge rate, so as to realize the combined variable application or independent variable application of conditioner and organic fertilizer.
[0011] This invention also provides a method for intelligent and precise improvement of strongly acidic farmland at the regional scale, comprising: Based on the multi-source soil acidification and fertility data of the target area, the soil pH value, organic matter content and texture data of each spatial unit of the target area were obtained; Based on the soil pH, organic matter content and texture data of each spatial unit, combined with the types of crops planted in each spatial unit and their suitable pH range and organic matter requirements, and by introducing the improvement cycle parameter, the phased soil pH improvement targets and phased organic matter improvement targets for each spatial unit are obtained for each year. Based on the phased soil pH improvement targets for each spatial unit in different years, combined with the soil acid-base buffer capacity of each spatial unit and the acid neutralization capacity and utilization coefficient of the conditioner, the recommended dosage of conditioner for each spatial unit in each year is obtained. Based on the phased organic matter improvement targets for each spatial unit in different years, and combined with the soil bulk density, topsoil thickness, annual soil organic matter mineralization loss rate, organic matter content of organic fertilizer and seasonal mineralization rate of each spatial unit, the recommended amount of organic fertilizer for each spatial unit in each year is obtained. Based on the recommended dosage of conditioner and organic fertilizer for each spatial unit in each year, generate differentiated regional improvement plans for each year; Based on the regional improvement plan, an annual work prescription map is generated for precise variable-based operations.
[0012] Preferably, the process of obtaining the recommended dosage of conditioner for each space unit in each year includes: The acid neutralizing capacity of the conditioner was determined; Based on the soil type of the target area, the utilization rate coefficient of the conditioner in each spatial unit was determined through field incubation experiments; Based on the initial soil pH value in year n, the phased soil pH improvement target in year n, soil bulk density, topsoil thickness, soil acid-base buffer capacity, and the acid neutralization capacity and utilization coefficient of the conditioner for each spatial unit, calculate the theoretical recommended dosage of conditioner for year n for the corresponding spatial unit. Set an annual limit for the use of the conditioner. If the theoretically recommended dosage of the conditioner exceeds the limit, the dosage for the current year will be cut off at the limit and the excess will be carried over to the following year.
[0013] Preferably, the process of obtaining the recommended amount of organic fertilizer for each spatial unit in each year includes: Based on the geographical location, climate conditions, soil type, and farming system of the target area, determine the annual soil organic matter mineralization loss rate of each spatial unit; Based on the initial organic matter content in year n, the phased organic matter improvement target in year n, soil bulk density, topsoil thickness, annual soil organic matter mineralization loss rate, organic matter content in organic fertilizer and seasonal mineralization rate of each spatial unit, calculate the theoretical recommended amount of organic fertilizer for year n of the corresponding spatial unit. Set an upper limit for the application of organic fertilizer in a single year. If the theoretically recommended amount of organic fertilizer exceeds the upper limit, the amount used in the current year will be cut off to the upper limit and the excess will be carried over to the following year.
[0014] Compared with the prior art, the present invention has the following advantages and technical effects: This invention constructs a regional soil acidification information sensing layer, integrates multi-source information such as field monitoring point data, historical soil survey data, the results of the Third National Soil Census, and meteorological data, and combines co-kriging or random forest spatial interpolation methods to generate a continuous spatial distribution map of soil pH, organic matter content, and texture in the target area. This enables a systematic understanding and precise characterization of the spatial heterogeneity of farmland acidification at the regional scale, allowing for targeted and differentiated remediation solutions.
[0015] This invention constructs an intelligent diagnostic layer for acidification levels and an optimization decision-making layer for improvement schemes, realizing a complete intelligent decision-making chain from multi-source data fusion, spatial interpolation mapping, acidification level classification to dynamic setting of improvement targets and precise dosage calculation. In particular, by introducing improvement cycle parameters and annual pH / organic matter improvement safety thresholds, a dynamic constraint mechanism for progressively increasing improvement targets each year is established. This scientifically decomposes long-term improvement goals into actionable and verifiable phased goals for each year, solving the problem of traditional experience-based decision-making lacking scientific quantitative basis.
[0016] This invention proposes several innovative and precise calculation methods. Regarding conditioner dosage calculation, it for the first time incorporates the spatial heterogeneity of soil acid-base buffering capacity, the variety-specific differences in conditioner acid-neutralizing capacity, and the dynamic characteristics of conditioner utilization coefficients varying with soil type and environmental conditions into a unified calculation framework, achieving precise calculation of conditioner dosage based on spatially differentiated attributes. Regarding organic fertilizer dosage calculation, it innovatively introduces regional differences in the annual soil organic matter mineralization loss rate and the seasonal mineralization rate parameter of organic fertilizer, and considers the accelerating effect of conditioner application on organic matter mineralization, achieving precise optimization of organic fertilizer dosage. Simultaneously, by setting a single annual application cap and a safety cutoff and extension mechanism, it effectively avoids secondary environmental problems such as soil compaction, secondary salinization, and nutrient leaching caused by excessive application of conditioners.
[0017] This invention transforms the differentiated improvement plans output from the decision-making level into variable-operation prescription maps through a variable-precision operation execution layer. Combined with GPS navigation and variable-application control technology, it achieves spatially precise application of conditioners, establishing a data connection and intelligent transformation channel from decision-making to execution. More importantly, this invention establishes a closed-loop management mechanism of "annual effect tracking—parameter back-calculation correction—scheme iterative optimization." Through periodic field sampling and testing, it obtains updated data on actual pH and organic matter in each unit, back-calculates the actual conditioner utilization rate coefficient and organic matter mineralization loss rate, and updates the system parameter database. Based on this, it optimizes the phased targets and dosage calculations for the next year, achieving year-by-year iterative and dynamically adaptive closed-loop optimization management, thereby ensuring the attainability, safety, and economy of the improvement effect throughout the entire cycle.
[0018] In summary, this invention, through its integrated system architecture design of "perception-diagnosis-decision-execution" and the synergistic effect of the aforementioned key technologies, effectively overcomes the shortcomings of existing technologies, such as the lack of systematic regional scale, low level of intelligent decision-making, insufficient application precision, and lack of a complete closed loop. It achieves precise identification and classification of strongly acidic arable land at the regional scale, differentiated and precise calculation and intelligent recommendation of amendment dosage, precise variable-based operations based on spatial positioning, and dynamic closed-loop management with year-by-year iterative optimization. This results in improved systematicness, scientific rigor, precision, and adaptability in regional acidification control, providing a complete system solution for the scientific management and intelligent improvement of strongly acidic arable land at the regional scale. Attached Figure Description
[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of the system structure according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the method flow according to an embodiment of the present invention. Detailed Implementation
[0020] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0021] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0022] Example 1 like Figure 1As shown, this embodiment provides a regional-scale intelligent and precise improvement system for highly acidic arable land, including: The regional soil acidification information sensing layer is used to acquire multi-source soil acidification and fertility-related data of the target area, and obtain multi-source sensing data of the target area. The intelligent acidification level diagnosis layer is connected to the regional soil acidification information sensing layer. It is used to receive multi-source sensing data and perform acidification level classification diagnosis through a spatial interpolation model based on the multi-source sensing data to obtain the acidification diagnosis results of each spatial unit in the target area. The improvement scheme optimizes the decision-making layer and connects with the intelligent diagnosis layer of acidification level. It is used to receive acidification diagnosis results and, based on the acidification diagnosis results, combined with the crop types and suitable growth parameters of each spatial unit, dynamically set the annual improvement targets for each spatial unit, calculate the recommended dosage of improver for each year, and generate annual and differentiated regional improvement schemes. The variable precision operation execution layer connects with the improvement plan optimization decision layer. It is used to receive regional improvement plans and, based on the regional improvement plans, combine the global positioning system and variable operation technology to generate the annual variable operation prescription map, and control the operation machinery to perform variable precision application of the improvement agent.
[0023] This embodiment constructs a four-in-one intelligent improvement closed-loop system by building a regional soil acidification information perception layer based on multi-source data fusion, an intelligent diagnosis layer for acidification degree based on machine learning and mechanism models, an improvement scheme optimization decision layer for regional spatial heterogeneity, and a variable-based precise operation execution layer. This system can achieve accurate identification and classification of regionally strongly acidic arable land, differentiated and accurate calculation and intelligent recommendation of amendment dosage, and variable-based precise operation based on spatial positioning. It effectively overcomes the shortcomings of existing technologies, such as the lack of regional-scale systematic features, low level of decision-making intelligence, insufficient application accuracy, and lack of a complete closed loop, and provides a systematic solution for the scientific management and intelligent improvement of regionally strongly acidic arable land.
[0024] Furthermore, the regional soil acidification information sensing layer includes: The actual data acquisition module is used to set up monitoring points in the target area according to the preset deployment density, collect mixed soil samples from the topsoil layer and conduct laboratory tests to obtain the latitude and longitude coordinates and soil physicochemical property test data of each monitoring point; among which, the soil physicochemical property test data includes soil pH value, organic matter content, mechanical composition, bulk density and topsoil thickness. The historical and survey data integration module is used to access historical soil survey data, soil testing and fertilizer recommendation historical data, arable land quality monitoring historical data and the results of the Third National Soil Census of the target area. After standardization and quality control, it is spatiotemporally matched with the monitoring point data obtained by the actual data acquisition module to obtain historical supplementary data in a unified format. The planting information acquisition module is used to acquire information on the types of crops planted and the crop rotation system in each spatial unit of the target area, and obtain planting information data. The meteorological and auxiliary data module is used to acquire meteorological data such as precipitation, temperature and acid rain frequency of the target area, and obtain meteorological auxiliary data.
[0025] Furthermore, the regional soil acidification information sensing layer involved in this embodiment is used to acquire multi-source soil acidification and fertility-related data for the target area, including but not limited to sampling and testing data from on-site monitoring points in the project area, historical soil survey data, results of the Third National Soil Census, meteorological data, and information on crop types and crop rotation systems. The intelligent acidification degree diagnosis layer is used to generate spatial distribution maps of soil pH, organic matter, and acidification degree classification maps for the target area based on the sensing layer data and through a spatial interpolation model. The improvement scheme optimization decision layer is used to dynamically set annual soil pH and organic matter improvement targets for each unit based on the basic data such as soil pH, organic matter, and texture of each spatial unit output by the diagnosis layer, combined with the crop type, its suitable pH range, and organic matter requirements, and by introducing improvement cycle parameters. It also calculates the safe recommended dosage of soil conditioners and organic fertilizers for each year, generating differentiated regional improvement schemes for each year. The variable precision operation execution layer is used to achieve precise annual application of conditioners and organic fertilizers based on the annual improvement scheme output by the decision layer, combined with the Global Positioning System (GPS) and variable operation technology.
[0026] Specifically, the regional soil acidification information sensing layer includes the following modules: Actual data acquisition module: responsible for obtaining basic physicochemical properties data of cultivated soil in the target area through field system sampling and laboratory testing, serving as the core and most reliable data source for system diagnosis and decision-making.
[0027] More specifically, the principles for the deployment of monitoring points include the following aspects: Deployment density: Based on the area of the project area, the number of basic monitoring points is determined according to the principle of deploying no less than one monitoring point per 1,000 mu (approximately 66.7 hectares).
[0028] Conditions for increasing the number of monitoring points: In the following situations, the number of monitoring points should be increased appropriately to ensure that the monitoring data can fully reflect the spatial heterogeneity of regional soil properties: areas with complex topography (such as hills, mountains and plains transition zones); areas with diverse or interspersed soil types; fields with significant differences in land use patterns or planting systems; sensitive areas with significant differences in acidification levels in the past or known acidification barriers.
[0029] The density of encrypted monitoring points can be increased to 500 mu or even higher. The specific density is automatically recommended by the system based on indicators such as terrain undulation, soil type, and map complexity, and is implemented after user confirmation.
[0030] More specifically, sampling and detection methods include the following aspects: Sampling time: Select the time after crop harvest or before the next season's sowing (autumn or spring), avoiding periods of interference such as fertilization and irrigation.
[0031] Sampling method: At each monitoring point, an "S" or quincunx pattern sampling method is used to collect mixed soil samples from the topsoil layer (0-20 cm). Each mixed sample consists of 5-10 subsamples mixed in equal amounts to ensure representativeness.
[0032] The detection indicators and methods are shown in Table 1 below.
[0033] Table 1 Data entry and spatialization: The latitude and longitude coordinates of each monitoring point and the detection results are entered into the system's spatial database to form a monitoring point location attribute dataset. This dataset serves as the core input for subsequent spatial interpolation mapping.
[0034] Historical and Survey Data Integration Module: This module integrates historical soil survey data, soil testing and fertilizer recommendation data, farmland quality monitoring data, and interim results from the Third National Soil Census for the target area. It extracts basic attributes such as soil pH, organic matter content, cation exchange capacity, and particle composition from each field or historical sampling point. After standardization and quality control, the historical data is spatiotemporally matched with data from newly added monitoring points and incorporated into a unified regional spatial database, serving as a supplementary data source for acidification diagnosis and fertilizer application calculation.
[0035] Planting Information Acquisition Module: This module is used to acquire information on crop types and crop rotation systems for each field within the target area. It connects with the agricultural data system of the relevant agricultural authorities or is based on field survey records, and supports annual updates.
[0036] Meteorological and Auxiliary Data Module: Used to acquire meteorological data such as precipitation, temperature, and acid rain frequency in the target area, serving as auxiliary information for acidification driving factor analysis and organic matter mineralization rate estimation.
[0037] Furthermore, the intelligent diagnostic layer for acidification levels includes: The multi-source data fusion module is used to perform spatiotemporal registration and standardization on the monitoring point data obtained by the actual data acquisition module, the historical supplementary data obtained by the historical and survey data integration module, and the meteorological auxiliary data obtained by the meteorological and auxiliary data module, and unify them into the same spatial grid system to obtain a fused standardized spatial dataset. The spatial interpolation and mapping module, connected to the multi-source data fusion module, is used to receive standardized spatial datasets and employ co-kriging or random forest spatial prediction methods. It uses monitoring point data as the main source and historical data as a supplement, combined with soil type, topography and land use auxiliary covariates to perform spatial interpolation, generating continuous spatial distribution maps of soil pH, organic matter content and soil texture in the target area. The acidification degree classification module, connected to the spatial interpolation and mapping module, is used to receive the spatial distribution map of soil pH value, classify the acidification degree according to the preset classification standard, count the area and spatial distribution of each level, and obtain the acidification degree classification result. The acidification and fertility comprehensive assessment module is connected to the acidification degree classification module and the spatial interpolation and mapping module, respectively. It is used to receive the acidification degree classification results and the spatial distribution maps of organic matter content and soil texture. It overlays the acidification classification results with organic matter content and texture information to identify the combined obstacles of acidification and infertility and obtain the comprehensive assessment results of acidification and fertility.
[0038] Furthermore, the intelligent acidification level diagnostic layer involved in this embodiment includes the following modules: The multi-source data fusion module is used to perform spatiotemporal registration and standardization processing on the multi-source data (actual monitoring point data, historical survey data, and meteorological data) acquired by the sensing layer, unifying them under the same spatial grid (such as 30 m × 30 m or field-level system). For historical data, different weights are assigned according to the reliability and timeliness of their sampling points, with priority given to recent actual monitoring data.
[0039] The spatial interpolation and mapping module employs co-kriging or random forest spatial prediction methods, primarily using actual monitoring point data supplemented by historical data, and incorporating auxiliary covariates such as soil type, topography, and land use. It generates continuous spatial distribution maps of soil pH and organic matter content in the target area, as well as spatial distribution maps of soil texture (sand, silt, and clay content). The uncertainty of the interpolation results is evaluated through cross-validation, and confidence intervals are marked on the output maps.
[0040] The acidification level classification module, based on the spatial distribution map of soil pH, classifies soil into the following categories: strongly acidic (pH<5.0), acidic (5.0 ≤ pH<5.5), slightly acidic (5.5 ≤ pH<6.5), and neutral and above (pH ≥ 6.5), and calculates the area and spatial distribution of each category.
[0041] The acidification and fertility comprehensive assessment module overlays acidification grading results with organic matter content and texture information to identify areas with combined acidification and infertility obstacles, providing a basis for subsequent comprehensive improvement plans.
[0042] Furthermore, the improved plan optimizes the decision-making level by including: The Crop Suitable pH and Nutrient Requirements Database Module is used to store the suitable soil pH range, suitable organic matter content reference value, and minimum organic matter requirement threshold for crops. The dynamic improvement target setting module is connected to the acidification degree classification module, the acidification and fertility comprehensive assessment module, and the crop suitable pH and nutrient requirement database module, respectively. It is used to receive the acidification diagnosis results and the acidification and fertility comprehensive assessment results of each spatial unit, and retrieve the suitable pH range and organic matter requirements of the currently planted crops in each spatial unit from the crop suitable pH and nutrient requirement database module. It sets the long-term target pH value and long-term target organic matter content of each spatial unit, and decomposes the long-term target into the phased targets of each year according to the improvement cycle and annual improvement safety threshold, so as to obtain the annual improvement target data of each spatial unit. The soil acid-base buffer capacity and texture correction module is connected to the spatial interpolation and mapping module. It is used to receive soil texture and organic matter content data of each spatial unit, and calculate the actual soil acid-base buffer capacity of each spatial unit based on the soil clay content and organic matter content to obtain buffer capacity correction data. The conditioner dosage calculation module is connected to the dynamic improvement target setting module and the soil acid-base buffer capacity and texture correction module, respectively. It is used to receive the annual improvement target data and buffer capacity correction data of each spatial unit, and calculate the theoretical recommended dosage of conditioner for each year based on the soil bulk density, topsoil thickness, conditioner acid neutralization capacity and conditioner utilization coefficient of each spatial unit, so as to obtain the conditioner dosage data of each spatial unit for each year. The organic fertilizer usage calculation module is connected to the dynamic improvement target setting module. It is used to receive the annual improvement target data of each spatial unit and calculate the theoretical recommended amount of organic fertilizer for each year based on the soil bulk density, topsoil thickness, organic matter content in the selected organic fertilizer, seasonal mineralization rate of organic fertilizer and annual mineralization loss rate of soil organic matter in each spatial unit, thus obtaining the organic fertilizer usage data for each spatial unit in each year. The comprehensive improvement scheme generation module is connected to the conditioner dosage calculation module and the organic fertilizer dosage calculation module, respectively. It is used to receive conditioner dosage data and organic fertilizer dosage data of each spatial unit for each year, and to integrate them spatially and temporally to generate annual and differentiated regional improvement schemes that include the types of improvers, recommended application rates, application periods and application sequences of each spatial unit for each year.
[0043] Furthermore, the improved decision-making layer involved in this embodiment specifically includes the following modules: The Crop Suitable pH and Nutrient Requirements Database Module stores the suitable soil pH ranges and reference values for suitable organic matter content for major food crops, cash crops, and vegetable crops. For example, the suitable pH for rice is 5.5–6.5, wheat 6.0–7.5, corn 6.0–7.0, peanuts 5.5–7.0, citrus 5.5–6.5, and vegetables (leafy vegetables) 6.0–7.0. The database also includes the minimum threshold requirements for soil organic matter for crops (e.g., ≥15 g / kg for rice, ≥20 g / kg for vegetables).
[0044] Dynamic improvement target setting module: For each spatial unit (field or grid), based on the type of crop currently planted in the unit, the suitable pH range of the crop is retrieved from the database, and the long-term target pH value (pHtarget) is set as the median or optimal value of the suitable range (e.g., 6.0 for rice). At the same time, the long-term target organic matter content (OMtarget) is set as the lower limit of the suitable range required by the crop or the recommended value corresponding to the regional arable land quality grade (e.g., ≥20 g / kg).
[0045] Based on this, this embodiment introduces an improvement cycle parameter T (T = 3-5 years, set by the user based on the degree of regional acidification, budget, and farming system). To avoid risks such as soil compaction, anaerobic environment, secondary soil salinization, or nutrient leaching caused by excessive application of soil conditioners or organic fertilizers in a single year, this module sets the following annual target setting rules: Annual pH increase safety threshold: The annual increase in soil pH should not exceed 0.3 to 0.5 units (the lower limit should be taken for sandy soils and the upper limit for clay soils) to avoid the concentrated release of aluminum ions due to drastic pH changes, which may cause acute toxicity to crops, or excessive lime may cause soil sticking and a sharp drop in the availability of trace elements (iron, manganese, zinc, etc.).
[0046] Annual organic matter increase safety threshold: The annual increase in the organic matter content of the topsoil should not exceed 3-5 g / kg (the lower limit is taken for high fertility soils) to prevent the risk of soil pore blockage, anaerobic environment and non-point source nitrogen and phosphorus leaching caused by the input of large amounts of organic fertilizer.
[0047] Progressive annual target setting: If the annualized average improvement after dividing the difference between the long-term target and the current value by the improvement period T does not exceed the aforementioned safety threshold, then the phased targets for each year are set according to the principle of uniform distribution. If the annualized average improvement exceeds the safety threshold, then the safety threshold is used as the maximum annual improvement, the improvement period is automatically extended, or the long-term target value is adjusted, and the user is prompted for confirmation in the system. At the same time, the system allows the adoption of a "heavy in the first year, light in the second" strategy (40% to 50% of the total demand in the first year, decreasing year by year) to adapt to the law of diminishing marginal benefits in actual production, but the absolute improvement in any year must still not exceed the aforementioned safety threshold.
[0048] Soil pH Buffer Capacity and Texture Correction Module: This module calculates the actual soil pH buffer capacity (BC, unit: cmol / kg / pH) based on the soil texture (clay content) and organic matter content of each unit, using empirical models or laboratory measurement data. The following correction relationship is used: Wherein, BC0 is the basic buffer capacity, Clay is the clay content (%), OM is the organic matter content (g / kg), and k1 and k2 are regional correction coefficients. These correction coefficients can be locally calibrated based on the measured buffer capacity data at the monitoring points.
[0049] The module for accurately calculating the annual usage of soil conditioners includes methods for determining and evaluating the acid neutralization capacity (ANC) of conditioners, the determination and dynamic updating mechanism of the utilization coefficient (η), and accurate calculation of the annual usage based on these two factors.
[0050] Specifically, the determination of the conditioner's acid neutralization capacity (ANC) includes: The acid neutralizing capacity (ANC) of a conditioner refers to its ability to neutralize soil acidity per unit mass, expressed as the amount of acid neutralized per kilogram of conditioner (cmol / kg). ANC is an inherent chemical property of the conditioner, determined by the content and form of its main alkaline components. This example uses a method of consulting a product standard parameter database: for commercially available conditioners, the neutralization value parameters can be directly consulted in the product instructions or quality inspection reports. The theoretical ANC reference values for common conditioners are shown in Table 2 below. Table 2 Specifically, the determination and dynamic updating of the conditioner utilization coefficient (η) includes: The conditioner utilization coefficient η refers to the proportion of effective components that actually participate in neutralizing soil acidity after application (0 < η ≤ 1). η is not an inherent property of the conditioner, but a dynamic parameter influenced by multiple factors such as soil properties, application method, environmental conditions, and time scale. In the target area, representative soil types are selected, and field micro-plots or pot culture experiments are conducted with gradient conditioner application rates (e.g., 0, 0.5, 1.0, 2.0, 3.0 t / ha). Soil pH is measured at different time points (7 days, 30 days, 60 days, 90 days) after application. Using the pH increase after 90 days of stabilization as a baseline, the actual η value is calculated using the following formula: Among them, pH 实测 The measured pH value of the soil after the conditioner has been applied and stabilized is given. Q_actual represents the actual amount applied.
[0051] Specifically, the annual dosage calculation for conditioning agents includes: Based on the above methods for determining ANC and η, for each spatial unit, the theoretical recommended dosage of conditioner (Qadj,n, tons / hectare) is calculated according to the initial soil pH value (pHn) in year n and the phased target pH value (pHtarget,n) in year n, combined with soil bulk density (ρ, obtained from actual monitoring), topsoil thickness (H, obtained from actual monitoring), and actual buffer capacity (BC): If pH target,n ≤ pH n If so, no conditioning agent needs to be used in that year.
[0052] Meanwhile, the annual application limit for quicklime is set at 200 kg / mu (equivalent to 3.0 tons / hectare); other types of conditioners such as dolomite powder have corresponding application limits set based on their acid neutralization capacity and the conversion relationship with quicklime (calculated in equivalent amounts based on acid neutralization capacity). If the calculated Q... adj,n If the corresponding upper limit is exceeded, the system will automatically cut off the usage for the current year to the upper limit and carry over the excess to the following year, readjusting the improvement cycle and annual targets to ensure safety and reasonableness throughout the entire cycle.
[0053] The annual recommended organic fertilizer application optimization module is used to calculate the theoretical recommended organic fertilizer application rate (Qom,n, tons / hectare) for the nth year based on the initial organic matter content (OMn) and the phased target organic matter content (OMtarget,n) for the nth year, combined with soil bulk density (ρ, obtained from actual monitoring), topsoil thickness (H, obtained from actual monitoring), organic matter content in the selected organic fertilizer (OMfer, %), mineralization rate of organic fertilizer in the current season (k, generally 0.3-0.5), and annual soil organic matter mineralization loss rate (δ). The coefficient 10 is used for unit conversion (converting g / kg to t / ha). If OM n ≥ OM target,n If so, no maintenance organic fertilizer may be applied or only maintenance organic fertilizer may be applied (the amount should be supplemented according to the amount of mineralization loss).
[0054] Specifically, the methods for determining the annual soil organic matter mineralization loss rate (δ) include: The annual soil organic matter mineralization loss rate δ refers to the percentage of soil organic matter consumed annually due to microbial mineralization. In my country, the annual soil organic matter mineralization rate generally ranges from 1% to 4%. The specific value is significantly influenced by climate, soil type, and farming system. This embodiment establishes a reference value system based on different regional characteristics, as shown in Table 3. Table 3 Similarly, the annual application limit for commercial organic fertilizer is set at 500 kg / mu (equivalent to 7.5 tons / hectare). If the calculated Q... om,n If the limit is exceeded, the system will automatically truncate the data and carry it over to the next year.
[0055] Meanwhile, this module also considers the accelerated mineralization effect of organic matter caused by the application of conditioners on soil pH increase, and introduces a correction coefficient (1 + α×ΔpH) to fine-tune the amount of organic fertilizer, where α is an empirical coefficient (0.05~0.10).
[0056] The comprehensive improvement plan generation module is used to spatially and temporally integrate the dosage of conditioner and organic fertilizer in each unit and each year, forming an annual, differentiated regional improvement plan that includes the following elements: Types of conditioners, recommended application rates, and application times (e.g., before winter planting or before sowing) for each spatial unit and each year. The types of organic fertilizers, recommended application rates, and application periods for each spatial unit in each year; The annual order of application of conditioner and organic fertilizer (e.g., apply conditioner first and then till, and apply organic fertilizer 10-15 days later). Total input cost estimate for the whole cycle (T years) and expected improvement effects in each year (annual pH increase, increase in organic matter and crop yield potential).
[0057] The pre-evaluation module for improvement effects is used to conduct virtual simulation pre-evaluation of the annual improvement plan using soil acidification buffer model and organic matter balance model. It predicts the pH value and organic matter content of each unit at the end of each year, verifies whether they do not exceed the annual safety threshold and the upper limit of single application (quicklime ≤ 200 kg / mu, commercial organic fertilizer ≤ 500 kg / mu), and outputs the results in the form of visual charts for users to review and adjust.
[0058] Furthermore, the improved plan for optimizing the decision-making level also includes: The pre-assessment module for improvement effect is connected to the comprehensive improvement scheme generation module. It is used to receive differentiated regional improvement schemes by year and to conduct year-by-year virtual simulation pre-assessment of the improvement schemes for each spatial unit using soil acidification buffer model and organic matter balance model. It predicts the pH value and organic matter content of each spatial unit at the end of each year and verifies whether the annual improvement amount does not exceed the annual safety threshold and the upper limit of single application amount. The pre-assessment results are output in the form of visual charts for users to review and adjust.
[0059] Furthermore, the variable-precision job execution layer includes: The annual work prescription map generation module is connected to the improvement plan optimization decision-making layer. It is used to receive regional improvement plans and convert the recommended dosage of conditioner and organic fertilizer for each spatial unit into variable work prescription maps containing information on the independent application of conditioner and organic fertilizer. The variable work prescription map is in raster or vector format. The GPS positioning and navigation module is used to obtain the precise location of the operating machinery in real time and generate positioning and navigation information; The variable application control module is connected to the annual operation prescription map generation module and the GPS positioning and navigation module respectively. It is used to receive the variable operation prescription map and positioning and navigation information, and adjust the discharge rate of conditioner and organic fertilizer in real time according to the target application amount of the current grid in the prescription map and the travel speed of the operating machinery, so as to control the operating machinery to perform variable precise application. The operation quality monitoring module, connected to the variable application control module, is used to record the actual application amount, operation trajectory and coverage area in real time, generate operation quality reports, and feed the actual application amount data back to the system database.
[0060] Furthermore, the variable precision operation execution layer involved in this embodiment includes the following modules: The annual application prescription map generation module is used to convert the recommended dosage of conditioner and organic fertilizer for each spatial unit output by the decision-making level into variable application prescription maps (raster or vector format), which contain independent application amount information for the two materials.
[0061] The GPS positioning and navigation module is used to obtain the precise location of the operating machinery in real time, ensuring accurate navigation according to the spatial grid of the prescription map.
[0062] The variable application control module includes a controller and an actuator. The controller adjusts the dispensing rate of conditioner and organic fertilizer in real time based on the target application rate of the current grid and the machine's travel speed in the prescription map. If a combined application operation is adopted, two variable hoppers can be set up for separate control; if the operation is carried out in stages, the corresponding prescription map is called up separately for each stage.
[0063] The operation quality monitoring module is used to record the actual application amount, operation trajectory and coverage area in real time, generate operation quality reports, and feed the actual application amount data back to the system database as the basis for adjusting the plan in the following year.
[0064] Furthermore, the variable application control module includes a dual-variable hopper, a controller, and an actuator; The dual-variable hoppers hold conditioner and organic fertilizer separately; The controller is connected to the annual work prescription map generation module and the GPS positioning and navigation module to calculate the discharge rate of conditioner and organic fertilizer based on the target application amount and mechanical travel speed of the current grid, respectively. The actuator is connected to the controller and is used to control the opening of the discharge ports of the conditioner hopper and the organic fertilizer hopper according to the discharge rate, so as to realize the combined variable application or independent variable application of conditioner and organic fertilizer.
[0065] Example 2 like Figure 2 As shown, based on the same inventive concept, this embodiment also provides a method for intelligent and precise improvement of regionally-scale strongly acidic arable land, including: Based on the multi-source soil acidification and fertility data of the target area, the soil pH value, organic matter content and texture data of each spatial unit in the target area were obtained; Based on the soil pH, organic matter content and texture data of each spatial unit, combined with the types of crops planted in each spatial unit and their suitable pH range and organic matter requirements, and by introducing the improvement cycle parameter, the phased soil pH improvement targets and phased organic matter improvement targets for each spatial unit are obtained for each year. Based on the phased soil pH improvement targets for each spatial unit in different years, combined with the soil acid-base buffer capacity of each spatial unit and the acid neutralization capacity and utilization coefficient of the conditioner, the recommended dosage of conditioner for each spatial unit in each year is obtained. Based on the phased organic matter improvement targets for each spatial unit in different years, and combined with the soil bulk density, topsoil thickness, annual soil organic matter mineralization loss rate, organic matter content of organic fertilizer and seasonal mineralization rate of each spatial unit, the recommended amount of organic fertilizer for each spatial unit in each year is obtained. Based on the recommended dosage of conditioner and organic fertilizer for each spatial unit in each year, generate differentiated regional improvement plans for each year; Based on the regional improvement plan, an annual work prescription map is generated, and precise variable-based operations are carried out.
[0066] Furthermore, the process of obtaining the recommended dosage of conditioner for each space unit in each year includes: Determine the acid neutralizing capacity of the conditioner; Based on the soil type of the target area, the utilization rate coefficient of the conditioner in each spatial unit was determined through field incubation experiments; Based on the initial soil pH value in year n, the phased soil pH improvement target in year n, soil bulk density, topsoil thickness, soil acid-base buffer capacity, and the acid neutralization capacity and utilization coefficient of the conditioner for each spatial unit, calculate the theoretical recommended dosage of conditioner for year n for the corresponding spatial unit. Set an annual limit for the use of the conditioner. If the theoretically recommended dosage of the conditioner exceeds the limit, the dosage for the current year will be cut off at the limit and the excess will be carried over to the following year.
[0067] Furthermore, the process of obtaining the recommended amount of organic fertilizer for each spatial unit in each year includes: Based on the geographical location, climate conditions, soil type and farming system of the target area, determine the annual soil organic matter mineralization loss rate of each spatial unit; Based on the initial organic matter content in year n, the phased organic matter improvement target in year n, soil bulk density, topsoil thickness, annual soil organic matter mineralization loss rate, organic matter content in organic fertilizer and seasonal mineralization rate of each spatial unit, calculate the theoretical recommended amount of organic fertilizer for year n of the corresponding spatial unit. Set an upper limit for the application of organic fertilizer in a single year. If the theoretically recommended amount of organic fertilizer exceeds the upper limit, the amount used in the current year will be cut off to the upper limit and the excess will be carried over to the following year.
[0068] As an optional implementation, this embodiment provides a method for intelligent and precise improvement of regionally-scale strongly acidic arable land, including the following steps: Step S1: Setting up monitoring points and collecting and testing samples.
[0069] Following the principle of having at least one monitoring point per 1000 mu (approximately 66.7 hectares), soil monitoring points were appropriately densified in the project area, taking into account factors such as topography, soil type, and cropping system. After crop harvest or before sowing, mixed soil samples from the topsoil layer (0–20 cm) were collected and sent to the laboratory for testing of soil pH, organic matter content, mechanical composition (sand / silt / clay content), bulk density, and topsoil thickness. The coordinates of the monitoring points were also recorded.
[0070] Step S2: Multi-source data integration and spatialization.
[0071] The actual monitoring data obtained in step S1 is standardized and coordinate matched with historical soil survey data, the results of the Third National Soil Census, and historical data on soil testing and fertilizer application. Continuous spatial distribution maps of soil pH, organic matter content, and texture are generated using co-kriging or random forest spatial interpolation methods.
[0072] Step S3: Comprehensive diagnosis of acidification and fertility.
[0073] The degree of acidification was classified based on the spatial distribution map, and the complex barrier zone of strong acidity and low organic matter was identified.
[0074] Step S4: Dynamically improve target setting (including periodicity and safety constraints).
[0075] For each spatial unit, the suitable pH range and organic matter requirements are retrieved based on the crop type, and long-term target pH value and target organic matter content are set. The improvement period T (3–5 years) is set according to the regional acidification level. Combined with the annual pH increase safety threshold (0.3–0.5 units) and the annual organic matter increase safety threshold (3–5 g / kg), the long-term goal is broken down into annual phased goals. If the annualized requirement exceeds the safety threshold, the period is automatically extended or the goal is adjusted, and the user is prompted for confirmation.
[0076] Step S5: Determination and assignment of conditioner ANC and η.
[0077] For the conditioner to be selected for the target area, its ANC value is determined by laboratory standard titration (ISO 20978) or obtained by consulting the product standard parameter library; according to the distribution of soil types in the target area, initial η is assigned to each spatial unit by field incubation experiment or empirical reference value method.
[0078] Step S6: Calculation of annual soil conditioner usage.
[0079] Using the initial pH of each unit in year n, the phased target pH, the soil bulk density (ρ) and topsoil thickness (H) obtained from monitoring data, and the measured ANC and η values, calculate the recommended amount of conditioner for that year according to the conditioner calculation formula, and verify whether it exceeds the single-year application limit of 200 kg / mu of quicklime (or other conditioners converted to an equivalent amount). If it exceeds, the application will be cut off and carried forward.
[0080] Step S7: Assigning a value to the annual soil organic matter mineralization loss rate δ.
[0081] Based on the geographical location, climate conditions, soil type, and farming system of the target area, initial δ values are assigned to each spatial unit from the regional experience reference value system; if long-term location monitoring data is available, field measured values are used first.
[0082] Step S8: Calculate the recommended annual amount of organic fertilizer.
[0083] Using the initial organic matter, phased target organic matter, ρ and H obtained from monitoring data, organic fertilizer parameters and mineralization rate, and the assigned δ for each unit in year n, calculate the recommended amount of organic fertilizer for that year according to the organic fertilizer calculation formula, and check whether it exceeds the single annual application limit of 500 kg / mu of commercial organic fertilizer (or other organic fertilizers converted to the same amount). If it exceeds, the application will be cut off and carried forward.
[0084] Step S9: Generate and pre-evaluate the comprehensive improvement plan.
[0085] The results of S6 and S8 were integrated to form differentiated regional plans for each year and spatial unit, including the combined application of conditioners and organic fertilizers. Annual effect pre-evaluation was conducted to ensure that the annual improvement amount meets the safety threshold.
[0086] Step S10: Generate the annual work prescription map.
[0087] The amount of conditioner and organic fertilizer used in the current year is converted into variable operation prescription charts.
[0088] Step S11: Precise variable operation.
[0089] Based on the prescription map, GPS navigation and variable application control equipment are used to complete the precise application of conditioner and organic fertilizer separately or simultaneously.
[0090] Step S12: Annual performance tracking and parameter calibration.
[0091] Each year, after crop harvest or before the next planting season, periodic field sampling and testing are conducted at monitoring points in the project area (the original locations can be reused or appropriately increased) to obtain updated data on actual pH and organic matter in each unit, which is then fed back to the decision-making level. The system compares the measured values with the estimated values for the year, reverse-engineers the actual η and δ values, updates the system parameter library and corrects the buffer capacity model, and optimizes the phased targets and dosage calculations for the next year, achieving iterative, dynamic, and closed-loop management year by year.
[0092] The regional-scale intelligent and precise improvement method for strongly acidic arable land provided in this embodiment has all the advantages of the regional-scale intelligent and precise improvement system for strongly acidic arable land provided in Embodiment 1.
[0093] Example 3 This embodiment also discloses a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in Embodiment 1.
[0094] Example 4 This embodiment also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in Embodiment 1.
[0095] Example 5 This embodiment also discloses a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in Embodiment 1.
[0096] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A regional-scale intelligent and precise improvement system for highly acidic arable land, characterized in that, include: The regional soil acidification information sensing layer is used to acquire multi-source soil acidification and fertility-related data of the target area, and obtain multi-source sensing data of the target area. An intelligent acidification degree diagnosis layer is connected to the regional soil acidification information sensing layer. It is used to receive the multi-source sensing data and perform acidification degree classification diagnosis through a spatial interpolation model based on the multi-source sensing data to obtain the acidification diagnosis results of each spatial unit in the target area. The improvement scheme optimization decision layer is connected to the acidification degree intelligent diagnosis layer. It is used to receive the acidification diagnosis results and, based on the acidification diagnosis results, combined with the crop types and suitable growth parameters of each spatial unit, dynamically set the annual improvement targets for each spatial unit, calculate the recommended dosage of the improver for each year, and generate annual and differentiated regional improvement schemes. The variable precision operation execution layer is connected to the improvement scheme optimization decision layer. It is used to receive the regional improvement scheme, and based on the regional improvement scheme, combined with the global positioning system and variable operation technology, generate the annual variable operation prescription map, and control the operation machinery to perform variable precision application of the improvement agent.
2. The system according to claim 1, characterized in that, The regional soil acidification information sensing layer includes: The actual data acquisition module is used to set up monitoring points in the target area according to the preset deployment density, collect mixed soil samples of the topsoil and conduct laboratory tests to obtain the latitude and longitude coordinates and soil physicochemical property test data of each monitoring point; wherein, the soil physicochemical property test data includes soil pH value, organic matter content, mechanical composition, bulk density and topsoil thickness. The historical and survey data integration module is used to access historical soil survey data, soil testing and fertilizer recommendation historical data, arable land quality monitoring historical data and the results of the third national soil census of the target area. After standardization and quality control, it is spatiotemporally matched with the monitoring point data obtained by the actual data acquisition module to obtain historical supplementary data in a unified format. The planting information acquisition module is used to acquire information on the types of crops planted and the crop rotation system in each spatial unit of the target area, and to obtain planting information data. The meteorological and auxiliary data module is used to acquire meteorological data such as precipitation, temperature and acid rain frequency of the target area, and obtain meteorological auxiliary data.
3. The system according to claim 1, characterized in that, The intelligent diagnostic layer for acidification level includes: The multi-source data fusion module is used to perform spatiotemporal registration and standardization on the monitoring point data obtained by the actual data acquisition module, the historical supplementary data obtained by the historical and survey data integration module, and the meteorological auxiliary data obtained by the meteorological and auxiliary data module, and unify them into the same spatial grid system to obtain a fused standardized spatial dataset. The spatial interpolation and mapping module is connected to the multi-source data fusion module. It is used to receive the standardized spatial dataset and use co-kriging or random forest spatial prediction methods, with monitoring point data as the main data and historical data as the auxiliary data, combined with soil type, topography and land use auxiliary covariates to perform spatial interpolation to generate a continuous spatial distribution map of soil pH, organic matter content and soil texture in the target area. An acidification degree grading module, connected to the spatial interpolation and mapping module, is used to receive the spatial distribution map of soil pH value, grade the acidification degree according to a preset grading standard, and statistically analyze the area and spatial distribution of each grade to obtain the acidification degree grading result. The acidification and fertility comprehensive assessment module is connected to the acidification degree classification module and the spatial interpolation and mapping module, respectively. It is used to receive the acidification degree classification results and the spatial distribution maps of organic matter content and soil texture, overlay the acidification classification results with organic matter content and texture information, identify the combined obstacle areas of acidification and infertility, and obtain the comprehensive assessment results of acidification and fertility.
4. The system according to claim 1, characterized in that, The improved scheme optimizes the decision-making layer, including: The Crop Suitable pH and Nutrient Requirements Database Module is used to store the suitable soil pH range, suitable organic matter content reference value, and minimum organic matter requirement threshold for crops. The dynamic improvement target setting module is connected to the acidification degree classification module, the acidification and fertility comprehensive assessment module, and the crop suitable pH and nutrient requirement database module, respectively. It is used to receive the acidification diagnosis results and the acidification and fertility comprehensive assessment results of each spatial unit, and retrieve the suitable pH range and organic matter requirements of the currently planted crops in each spatial unit from the crop suitable pH and nutrient requirement database module. It sets the long-term target pH value and long-term target organic matter content of each spatial unit, and decomposes the long-term target into the phased targets of each year according to the improvement cycle and annual improvement safety threshold, so as to obtain the annual improvement target data of each spatial unit. The soil acid-base buffer capacity and texture correction module is connected to the spatial interpolation and mapping module. It is used to receive soil texture and organic matter content data of each spatial unit, and calculate the actual soil acid-base buffer capacity of each spatial unit based on the soil clay content and organic matter content to obtain buffer capacity correction data. The conditioner dosage calculation module is connected to the dynamic improvement target setting module and the soil acid-base buffer capacity and texture correction module, respectively. It is used to receive the annual improvement target data and buffer capacity correction data of each spatial unit, and calculate the theoretical recommended dosage of conditioner for each year based on the soil bulk density, topsoil thickness, conditioner acid neutralization capacity and conditioner utilization coefficient of each spatial unit, so as to obtain the conditioner dosage data of each spatial unit for each year. The organic fertilizer usage calculation module is connected to the dynamic improvement target setting module. It is used to receive the annual improvement target data of each spatial unit and calculate the theoretical recommended usage of organic fertilizer for each year based on the soil bulk density, topsoil thickness, organic matter content in the selected organic fertilizer, seasonal mineralization rate of organic fertilizer and annual mineralization loss rate of soil organic matter in each spatial unit, so as to obtain the organic fertilizer usage data of each spatial unit for each year. The comprehensive improvement scheme generation module is connected to the conditioner dosage calculation module and the organic fertilizer dosage calculation module, respectively. It is used to receive conditioner dosage data and organic fertilizer dosage data of each spatial unit for each year, and to integrate them spatially and temporally to generate annual and differentiated regional improvement schemes that include the types of improvers, recommended application rates, application periods and application sequences of each spatial unit for each year.
5. The system according to claim 1, characterized in that, The improved decision-making layer also includes: The improvement effect pre-evaluation module, connected to the comprehensive improvement scheme generation module, is used to receive differentiated regional improvement schemes by year, and to perform year-by-year virtual simulation pre-evaluation of the improvement schemes for each spatial unit using a soil acidification buffer model and an organic matter balance model. It predicts the pH value and organic matter content of each spatial unit at the end of each year, and verifies whether the annual improvement amount does not exceed the annual safety threshold and the single application limit, and obtains the pre-evaluation results. The pre-evaluation results are output in the form of visual charts for users to review and adjust.
6. The system according to claim 1, characterized in that, The variable-precision job execution layer includes: The annual work prescription map generation module is connected to the improvement scheme optimization decision layer. It is used to receive the regional improvement scheme and convert the recommended dosage of conditioner and organic fertilizer for each spatial unit into a variable work prescription map containing information on the independent application of conditioner and organic fertilizer. The variable work prescription map is in raster or vector format. The GPS positioning and navigation module is used to obtain the precise location of the operating machinery in real time and generate positioning and navigation information; The variable application control module is connected to the annual operation prescription map generation module and the GPS positioning and navigation module respectively. It is used to receive the variable operation prescription map and the positioning and navigation information, and adjust the discharge rate of conditioner and organic fertilizer in real time according to the target application amount of the current grid in the prescription map and the travel speed of the operating machinery, so as to control the operating machinery to perform variable precise application. The operation quality monitoring module is connected to the variable application control module. It is used to record the actual application amount, operation trajectory and coverage area in real time, generate an operation quality report, and feed the actual application amount data back to the system database.
7. The system according to claim 6, characterized in that, The variable application control module includes a dual-variable hopper, a controller, and an actuator; The dual-variable hoppers respectively contain conditioner and organic fertilizer; The controller is connected to the annual work prescription map generation module and the GPS positioning and navigation module, and is used to calculate the discharge rate of conditioner and organic fertilizer according to the target application amount and mechanical travel speed of the current grid, respectively. The actuator is connected to the controller and is used to control the opening of the discharge ports of the conditioner hopper and the organic fertilizer hopper according to the discharge rate, so as to realize the combined variable application of conditioner and organic fertilizer or the independent variable application in multiple times.
8. A method for intelligent and precise improvement of strongly acidic arable land at a regional scale, characterized in that, include: Based on the multi-source soil acidification and fertility data of the target area, the soil pH value, organic matter content and texture data of each spatial unit of the target area were obtained; Based on the soil pH, organic matter content and texture data of each spatial unit, combined with the types of crops planted in each spatial unit and their suitable pH range and organic matter requirements, and by introducing the improvement cycle parameter, the phased soil pH improvement targets and phased organic matter improvement targets for each spatial unit are obtained for each year. Based on the phased soil pH improvement targets for each spatial unit in different years, combined with the soil acid-base buffer capacity of each spatial unit and the acid neutralization capacity and utilization coefficient of the conditioner, the recommended dosage of conditioner for each spatial unit in each year is obtained. Based on the phased organic matter improvement targets for each spatial unit in different years, and combined with the soil bulk density, topsoil thickness, annual soil organic matter mineralization loss rate, organic matter content of organic fertilizer and seasonal mineralization rate of each spatial unit, the recommended amount of organic fertilizer for each spatial unit in each year is obtained. Based on the recommended dosage of conditioner and organic fertilizer for each spatial unit in each year, generate differentiated regional improvement plans for each year; Based on the regional improvement plan, an annual work prescription map is generated for precise variable-based operations.
9. The method according to claim 8, characterized in that, The process of obtaining the recommended dosage of conditioning agents for each space unit for each year includes: The acid neutralizing capacity of the conditioner was determined; Based on the soil type of the target area, the utilization rate coefficient of the conditioner in each spatial unit was determined through field incubation experiments; Based on the initial soil pH value in year n, the phased soil pH improvement target in year n, soil bulk density, topsoil thickness, soil acid-base buffer capacity, and the acid neutralization capacity and utilization coefficient of the conditioner for each spatial unit, calculate the theoretical recommended dosage of conditioner for year n for the corresponding spatial unit. Set an annual limit for the use of the conditioner. If the theoretically recommended dosage of the conditioner exceeds the limit, the dosage for the current year will be cut off at the limit and the excess will be carried over to the following year.
10. The method according to claim 8, characterized in that, The process of obtaining the recommended amount of organic fertilizer for each spatial unit in each year includes: Based on the geographical location, climate conditions, soil type, and farming system of the target area, determine the annual soil organic matter mineralization loss rate of each spatial unit; Based on the initial organic matter content in year n, the phased organic matter improvement target in year n, soil bulk density, topsoil thickness, annual soil organic matter mineralization loss rate, organic matter content in organic fertilizer and seasonal mineralization rate of each spatial unit, calculate the theoretical recommended amount of organic fertilizer for year n of the corresponding spatial unit. Set an upper limit for the application of organic fertilizer in a single year. If the theoretically recommended amount of organic fertilizer exceeds the upper limit, the amount used in this year will be cut off to the upper limit and the excess will be carried over to the following year.
