Optimization analysis system for agricultural land use efficiency based on multi-source data fusion

Abstract

The application relates to the technical field of optimization analysis systems, in particular to an agricultural land utilization efficiency optimization analysis system based on multi-source data fusion, which comprises a land block parameter integration module, a land block suitability evaluation module, an adjacent relationship correction module and a utilization efficiency optimization module.In the application, multi-source data such as slope, soil organic matter and water accessibility are standardized and integrated as land block basic parameters, a multi-factor comprehensive evaluation is realized by combining an analytic hierarchy process, land block suitability changes are reflected in detail, water and fertilizer migration and crop competition are dynamically simulated by using a cellular automaton based on land block adjacent relationships and crop compatibility parameters, the problems of uneven resource distribution and unreasonable combination are avoided, and genetic algorithm optimization is introduced after water and fertilization parameters are weighted and adjusted, so that efficient configuration of agricultural land and maximization of output benefits are realized, the scientificity of resource allocation and the spatial coordination effect are strengthened, and actual demands and resource rationality are considered.

Description

Technical Field

[0001] This invention relates to the field of optimization analysis system technology, and in particular to an optimization analysis system for farmland use efficiency based on multi-source data fusion. Background Technology

[0002] The field of optimization analysis systems involves the analysis and evaluation of efficiency, resource allocation, and utilization rates through data collection, modeling, calculation, and comparison of specific objects or processes. Its core aspects include data input and storage, parameter setting, computational logic construction, and result output. This field is widely applied in resource management, energy allocation, production scheduling, and land use. The overall technology aims to provide quantitative analysis and systematic support for the utilization efficiency of various resources or processes. Among these, the traditional agricultural land use efficiency optimization analysis system refers to a data processing tool for agricultural land resource allocation and utilization. It primarily addresses technical issues such as low agricultural land utilization rates, uneven resource distribution, and unreasonable input-output ratios. Traditional methods typically involve statistical analysis of land survey data, comparison of crop planting area and yield data, and organization of land nutrient and input indicators. Computers are used to collect and comprehensively process relevant data to form a basic analytical system for agricultural land use efficiency.

[0003] Traditional methods mainly rely on single data sources such as land survey data statistics and crop area and yield comparisons. The analysis process cannot fully reflect comprehensive environmental factors such as soil and water, which limits the assessment of land suitability. In practical applications, it is easy to have problems such as one-sided resource allocation and monotonous crop combinations and spatial layouts. When there are diversified and dynamic changes in land use, it is difficult to effectively respond to complex environments and the coupling of multiple factors, which can easily lead to uneven resource distribution and imbalance of input and output ratios. For example, in the case of crop rotation or mixed cropping, traditional methods cannot accurately simulate the interaction between different crops, which affects the scientific nature of resource allocation and the improvement of agricultural land use efficiency. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a farmland use efficiency optimization analysis system based on multi-source data fusion.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a farmland use efficiency optimization analysis system based on multi-source data fusion includes:

[0006] The plot parameter integration module is used to collect plot slope, soil organic matter and water accessibility data, and after normalization, construct a standardized set of basic plot parameters, which is then transmitted to the plot suitability evaluation module.

[0007] The land suitability evaluation module is used to receive the basic parameter set of the land plot, input slope data, soil organic matter data, and water accessibility data as evaluation factors into the analytic hierarchy process model, calculate the land suitability evaluation value of each plot in combination with crop growth parameters, and transmit it to the adjacency correction module.

[0008] The adjacency correction module is used to receive the suitability evaluation value of the plot, identify the adjacency relationship of the plot, and input the evaluation value difference and crop compatibility parameter into the cellular automata model. Through iterative calculation, it simulates the migration of water and fertilizer resources and the effect of crops, identifies combinations with resource competition, generates adjacency correction coefficients, and transmits them to the utilization efficiency optimization module.

[0009] An efficiency optimization module is used to receive the adjacency correction coefficient, and to perform weighted adjustments on the water use parameters and fertilization parameters of the crop combination. The adjusted parameters are then input into a genetic algorithm, which searches for the crop spatial layout scheme with the highest fitness value determined by a preset fitness function through crossover and mutation operations.

[0010] As a further aspect of the present invention, the basic parameter set of the plot specifically includes normalized slope value, normalized soil organic matter value, and normalized water accessibility value; the plot suitability evaluation value includes crop growth suitability, environmental compatibility, and production potential; the adjacency correction coefficient specifically refers to resource competition intensity, crop compatibility impact, and resource migration efficiency; and the crop spatial layout scheme includes crop zoning configuration, water use configuration, and fertilization optimization strategy.

[0011] As a further aspect of the present invention, the plot parameter integration module specifically includes: a data acquisition submodule, used to acquire slope, soil organic matter and moisture accessibility data of each plot through remote sensing image interpretation and sensor monitoring, and generate original plot data;

[0012] The data processing submodule is used to call the original plot data and perform maximum and minimum normalization processing on the slope, soil organic matter and water accessibility data respectively to generate a normalized parameter matrix;

[0013] The parameter construction submodule is used to integrate the normalized values ​​of slope, soil organic matter, and water accessibility in the normalized parameter matrix to establish a structured dataset associated with the spatial location information of the plot, thereby obtaining the standardized set of basic parameters for the plot.

[0014] As a further embodiment of the present invention, the land suitability evaluation module specifically includes: a factor weight calculation submodule, which is used to receive the basic parameter set of the land, construct a hierarchical analysis judgment matrix based on the slope data, the soil organic matter data and the water accessibility data, calculate the weight of each evaluation factor, and generate an evaluation factor weight set;

[0015] The growth suitability evaluation submodule is used to call the evaluation factor weight set, combine it with the preset crop growth parameters, and perform a weighted summation operation on the parameter values ​​in the basic parameter set of the plot to obtain the plot suitability evaluation value for each plot for a specific crop.

[0016] As a further embodiment of the present invention, the adjacency relationship correction module specifically includes: an adjacency relationship identification submodule, used to analyze and determine the spatial adjacency relationship between plots based on the geospatial coordinate data of each plot, and generate a plot adjacency matrix;

[0017] The iterative simulation calculation submodule is used to call the adjacency matrix of the plot and the suitability evaluation value of the plot, and use the difference in evaluation value and crop compatibility parameters as the initial state and transformation rules of the cellular automata model. Through multiple iterations, the simulation calculation of the water and fertilizer resource migration process between plots and the interaction between crops is carried out to obtain the resource competition simulation results.

[0018] The correction coefficient generation submodule is used to analyze the resource competition simulation results, quantify the competition intensity and crop compatibility impact between combinations of land parcels with resource competition, and obtain the adjacency correction coefficient.

[0019] As a further embodiment of the present invention, the utilization efficiency optimization module specifically includes: a parameter weighting adjustment submodule, used to receive the adjacency correction coefficient, and to perform weighted adjustment on the water use parameters and fertilization parameters of the preset crop combination according to the adjacency correction coefficient, thereby generating a weighted optimization parameter set;

[0020] The genetic algorithm optimization submodule is used to take the weighted optimization parameter set as the input constraint of the genetic algorithm, and iteratively generate a candidate crop layout population with higher fitness values ​​by initializing the population, performing selection, crossover and mutation operations.

[0021] The optimal solution selection submodule is used to evaluate the fitness value of each individual in the candidate crop layout population based on the fitness function with the total output of farmland and the efficiency of resource utilization as optimization indicators, select and output the individual with the highest fitness value, and obtain the crop spatial layout scheme.

[0022] As a further aspect of the present invention, the maximum and minimum normalization processing performed on the slope, soil organic matter, and water accessibility data in the data processing submodule specifically involves obtaining the maximum and minimum values ​​of the corresponding parameters in all plots, and calculating the normalized value based on the original parameter values ​​of any plot as follows: First, obtain the original parameter values ​​of the plot; second, calculate the difference between the original parameter value and the minimum value of the parameter in all plots; then, calculate the difference between the maximum and minimum values ​​of the parameter in all plots; finally, divide the two differences to obtain the normalized value of the parameter for the plot, and combine the normalized values ​​of all parameters in all plots to generate the normalized parameter matrix.

[0023] As a further aspect of the present invention, after calculating the weights of each evaluation factor, the factor weight calculation submodule also performs a consistency check, which is achieved by calculating the consistency ratio. Completed, the calculation formula is as follows: ;

[0024] in, For consistency ratio, As a consistency indicator, its calculation method is as follows:

[0025] , To determine the largest eigenvalue of a matrix using the analytic hierarchy process (AHP), To evaluate the number of factors, The average random consistency index;

[0026] After obtaining the consistency ratio, it is determined whether the consistency ratio is less than a preset consistency threshold. If it is less, the evaluation factor weight set that has passed the consistency test is used for subsequent calculations. If it is greater, the analytic hierarchy process judgment matrix is ​​adjusted and recalculated until the consistency test is passed.

[0027] As a further aspect of the present invention, in the correction coefficient generation submodule, the adjacent correction coefficient... The specific calculation formula is as follows: ;

[0028] in, For the plot of land Adjacent plots Adjacency correction factor between them and plots of land With the plot of land The suitability evaluation value of the aforementioned land parcel, The maximum suitability score among all plots. As a resource competition weighting factor, The resource competition weight factor and the crop compatibility weight factor are combined to form a weighting factor of 1. A crop type compatibility function used to determine crop type compatibility based on plot size. Crop types With the plot of land Crop types The compatibility relationship returns a preset compatibility rating.

[0029] As a further aspect of the present invention, in the optimal solution selection submodule, the fitness function is specifically used to calculate the fitness value of any crop spatial layout scheme. The calculation formula is as follows:

[0030] ;

[0031] in, This represents the fitness value of the crop spatial layout scheme. This is the total output weighting coefficient. This is a weighting coefficient for resource utilization efficiency. The total number of land parcels. For land parcel indexing, For the first Predicted yield per unit area of ​​crops planted on each plot of land For the first The area of ​​each plot of land, For the first Planned water use for each plot of land For the first Planned fertilizer application amount for each plot of land.

[0032] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0033] In this invention, multi-source data such as slope, soil organic matter, and water accessibility are standardized and integrated as basic parameters for plot analysis. Combined with the analytic hierarchy process (AHP), a multi-factor comprehensive evaluation is introduced, which can meticulously reflect changes in plot suitability. Simultaneously, based on plot adjacency relationships and crop compatibility parameters, cellular automata are used to dynamically simulate water and fertilizer resource migration and crop competition, effectively avoiding problems of uneven resource distribution and unreasonable crop combinations. Furthermore, after weighted adjustments to water and fertilizer parameters, a genetic algorithm is introduced to optimize spatial layout, contributing to efficient allocation of agricultural land resources and maximizing crop output benefits. This significantly improves agricultural land utilization efficiency, strengthens the scientific nature of resource allocation and the spatial synergy of crops, and balances actual planting needs with the rationality of resource utilization. Attached Figure Description

[0034] Figure 1This is a schematic diagram of the overall process of the farmland use efficiency optimization analysis system based on multi-source data fusion of the present invention;

[0035] Figure 2 This is a schematic diagram of the internal process of the land parcel parameter integration module of the present invention;

[0036] Figure 3 This is a schematic diagram of the internal process of the land suitability evaluation module of the present invention;

[0037] Figure 4 This is a schematic diagram of the internal process of the adjacency relationship correction module of the present invention;

[0038] Figure 5 This is a schematic diagram of the internal process of the efficiency optimization module in this invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the software-based technical solution is described in detail below with reference to system architecture diagrams and embodiments. It should be understood that the specific embodiments described herein are only for explaining the technical solutions of this invention and do not constitute a limitation on the scope of protection.

[0040] In the description of this invention, the system architecture relationships or data processing flows indicated by terms such as "layer," "module," "interface," "data flow," "client," and "server" are all defined based on the architecture diagram or flowchart corresponding to the embodiments. This way of describing is only used to clearly illustrate the logical relationships between the elements in the technical solution, and not to limit the physical deployment form. The term "multiple" includes two or more technical units, including but not limited to multiple data nodes, processing threads, service instances, or functional components and other scalable elements. The specific number is determined according to the actual business scenario and needs to be specifically specified.

[0041] Please see Figure 1 and Figure 2 This invention provides a technical solution: a farmland use efficiency optimization analysis system based on multi-source data fusion, comprising:

[0042] The plot parameter integration module is used to collect plot slope, soil organic matter and water accessibility data, and after normalization, construct a standardized set of basic plot parameters, which is then transmitted to the plot suitability evaluation module.

[0043] The basic parameter set for the plot specifically includes normalized values ​​for slope, soil organic matter, and water accessibility.

[0044] The plot parameter integration module specifically includes: a data acquisition submodule, which is used to collect slope, soil organic matter and moisture accessibility data of each plot through remote sensing image interpretation and sensor monitoring, and generate raw plot data;

[0045] The data processing submodule is used to call the original plot data and perform maximum and minimum normalization processing on the slope, soil organic matter and water accessibility data respectively to generate a normalized parameter matrix;

[0046] In the data processing submodule, the maximum and minimum normalization processing performed on the slope, soil organic matter, and moisture accessibility data is as follows: First, obtain the maximum and minimum values ​​of the corresponding parameters in all plots, and calculate the normalized value of any plot based on its original parameter values. The logic is as follows: First, obtain the original parameter values ​​of the plot; second, calculate the difference between the original parameter value and the minimum value of the parameter in all plots; third, calculate the difference between the maximum and minimum values ​​of the parameter in all plots; finally, divide the two differences to obtain the normalized value of the parameter for that plot, and combine the normalized values ​​of all parameters in all plots to generate a normalized parameter matrix.

[0047] The parameter construction submodule is used to integrate the normalized values ​​of slope, soil organic matter, and water accessibility in the normalized parameter matrix to establish a structured dataset associated with the spatial location information of the plot, thereby obtaining a standardized set of basic parameters for the plot.

[0048] First, the data acquisition submodule was executed. For the target farmland, such as a 10-hectare experimental farm comprising five plots (numbered A01 to A05), remote sensing imagery was acquired using a DJI Mavic 3M drone equipped with a multispectral sensor at 10:00 AM on August 28, 2025. The flight altitude was set to 100 meters, with a forward overlap of 80% and a lateral overlap of 70%. After acquisition, the average slope of each plot was interpreted using a Digital Elevation Model (DEM). Simultaneously, at five sampling points—the center point and four corner points of each plot—the organic matter content of the topsoil (0-20 cm) was measured using a soil nutrient rapid tester (model: TRF-5X). The average of the five measurements was taken as the soil organic matter data for that plot. For water accessibility, the Euclidean distance between the geometric center of each plot and the nearest water source (such as a river or irrigation canal) was calculated using Geographic Information System (GIS) software (version: ArcGIS Pro 3.1), and this distance was used as the water accessibility data.

[0049] For example, the specific values ​​of the original plot data collected for the five plots are as follows: Plot A01 has a slope of 5 degrees, a soil organic matter content of 25.1 g / kg, and a water accessibility of 150 meters. Plot A02 has a slope of 8 degrees, a soil organic matter content of 18.5 g / kg, and a water accessibility of 300 meters. Plot A03 has a slope of 2 degrees, a soil organic matter content of 35.8 g / kg, and a water accessibility of 80 meters. Plot A04 has a slope of 12 degrees, a soil organic matter content of 15.2 g / kg, and a water accessibility of 450 meters. Plot A05 has a slope of 6 degrees, a soil organic matter content of 28.9 g / kg, and a water accessibility of 220 meters.

[0050] Next, the data processing submodule is executed. The original plot data generated in the preceding steps is called, and maximum-minimum normalization is performed on the three parameters: slope, soil organic matter, and water accessibility. This process first identifies the maximum and minimum values ​​of each parameter across all plots. Taking the slope parameter as an example, the maximum value across all plots is 12 degrees for plot A04, and the minimum value is 2 degrees for plot A03. Subsequently, the normalized value of the parameter for any plot is calculated according to specific logic. Specifically, the original parameter value for that plot is obtained, the difference between the original value and the minimum value of the parameter is calculated, then the difference between the maximum and minimum values ​​of the parameter is calculated, and finally, the previous difference is divided by the next difference.

[0051] Taking the normalized slope value of plot A01 as an example: its original parameter value is 5 degrees, the minimum parameter value is 2 degrees, and the maximum parameter value is 12 degrees. First, calculate the difference between the original parameter value and the minimum value, i.e., 5 - 2 = 3. Second, calculate the difference between the maximum value and the minimum value, i.e., 12 - 2 = 10. Third, divide the two differences, obtaining 3 / 10 = 0.3. Therefore, the normalized slope value of plot A01 is 0.3. For negative indicators like slope (lower values ​​are better), the normalized value remains unchanged. For positive indicators like soil organic matter (higher values ​​are better), the normalized value also remains unchanged. However, for water accessibility (distance, a negative indicator), to unify its numerical meaning with other indicators (i.e., higher values ​​are better), the normalized value is subtracted from 1 after normalization. Taking the water accessibility of plot A01 as an example: the original value is 150 meters, the minimum value is 80 meters, and the maximum value is 450 meters. Its initial normalized value is... The corrected value is 1 - 0.189 = 0.811.

[0052] Following this method, the normalized values ​​of all parameters for all plots are calculated, and these normalized values ​​are combined to generate a normalized parameter matrix.

[0053] Table 1. Original Data and Normalized Parameters of Agricultural Land Plots

[0054]

[0055] As shown in Table 1, this table lists the original collected data of five example plots and the parameter values ​​after max-min normalization.

[0056] Finally, the parameter construction submodule integrates all data in the normalized parameter matrix, namely the normalized values ​​of slope, soil organic matter, and water accessibility, and associates them with the geospatial coordinates of each plot (e.g., the latitude and longitude coordinates of the plot's center point determined by GPS). For example, the spatial location information of plot A01 is (longitude 116.3975, latitude 39.9080), and the associated dataset is... After integrating the data from all land parcels, a structured dataset is created, which is a standardized set of basic parameters for the land parcels, and then transmitted to the land parcel suitability evaluation module.

[0057] Please see Figure 1 and Figure 3 The plot suitability evaluation module is used to receive the basic parameter set of the plot, input the slope data, soil organic matter data, and water accessibility data as evaluation factors into the analytic hierarchy process model, calculate the plot suitability evaluation value of each plot in combination with crop growth parameters, and transmit it to the adjacency correction module.

[0058] The suitability evaluation value of a plot includes crop growth suitability, environmental compatibility, and production potential.

[0059] The land suitability evaluation module specifically includes: a factor weight calculation submodule, which receives the basic parameter set of the land plot, constructs a analytic hierarchy process judgment matrix based on slope data, soil organic matter data and water accessibility data, calculates the weight of each evaluation factor, and generates an evaluation factor weight set;

[0060] After calculating the weights of each evaluation factor, the factor weight calculation submodule also performs a consistency check, which is done by calculating the consistency ratio. Completed, the calculation formula is as follows: ;

[0061] in, For consistency ratio, As a consistency indicator, its calculation method is as follows: , To determine the largest eigenvalue of a matrix using the analytic hierarchy process (AHP), To evaluate the number of factors, The average random consistency index;

[0062] After obtaining the consistency ratio, it is determined whether the consistency ratio is less than the preset consistency threshold. If it is less, the weight set of evaluation factors that have passed the consistency test will be used for subsequent calculations. If it is greater, the analytic hierarchy process judgment matrix will be adjusted and recalculated until the consistency test is passed.

[0063] The growth suitability evaluation submodule is used to call the evaluation factor weight set, combine it with the preset crop growth parameters, and perform a weighted summation operation on the parameter values ​​in the basic parameter set of the plot to obtain the plot suitability evaluation value for each plot for a specific crop.

[0064] First, the factor weight calculation submodule receives the standardized set of basic plot parameters generated in the preceding steps. Based on three evaluation factors—slope, soil organic matter, and water accessibility—it constructs a judgment matrix for the analytic hierarchy process (AHP). The judgment matrix is ​​constructed based on the experience-based scoring of agricultural experts for the growth requirements of specific crops (e.g., maize). The scoring uses a 1-9 scale, where 1 indicates that two factors are equally important, and 9 indicates that one factor is more important than the other.

[0065] To determine the weights of each evaluation factor, a panel of 10 senior agricultural experts was organized to conduct pairwise comparisons and scoring of the three factors: slope (C1), soil organic matter (C2), and water accessibility (C3). The scoring process involved three rounds of independent back-to-back scoring, and the arithmetic mean of the results was used to construct the final judgment matrix A.

[0066] ;

[0067] Subsequently, the weights of each evaluation factor are calculated based on this judgment matrix. The weights of each factor are obtained by calculating the largest eigenvalue of the judgment matrix and its corresponding eigenvector, and then normalizing the eigenvector. The largest eigenvalue is then calculated. The corresponding feature vector is After normalization, the evaluation factor weight set is obtained. Among them, the slope weight is 0.132, the soil organic matter weight is 0.545, and the water accessibility weight is 0.323.

[0068] After obtaining the weights, a consistency check is performed. This check is conducted by calculating the consistency ratio. Completed, the calculation formula is as follows: .

[0069] In this formula, Represents the consistency ratio, used to measure the degree of logical consistency of the judgment matrix. It is a consistency index, and its calculation logic is as follows: First, obtain the largest eigenvalue of the judgment matrix. and obtain the number of evaluation factors. Secondly, calculation and The difference; finally, divide this difference by The purpose of this operation is to quantify the degree to which the matrix deviates from perfect consistency. It is the average random consistency index, whose value is calculated by a large number of randomly generated judgment matrices. The average value is obtained, and depends on the order of the matrix. In this example, the number of evaluation factors... The value is 3.

[0070] To set a consistency threshold, 1000 Monte Carlo simulations were performed, generating random 3rd-order positive reciprocal matrices, and their... The average random consistency index is obtained by averaging the values. The value is 0.58. Meanwhile, based on practical standards, the consistency threshold is preset to 0.1.

[0071] Example Demonstration: 1. Calculate the consistency index by substituting parameter values. : .

[0072]

[0073] 2. Calculate the consistency ratio 3. Consistency assessment: The calculated results The value is 0.0079, which is less than the preset consistency threshold of 0.1. This result indicates that the judgment matrix meets the consistency requirements and passes the consistency test. Therefore, the weight set of this evaluation factor is... For use in subsequent calculations. If If the value is greater than 0.1, return to the step of adjusting the judgment matrix, invite experts to review and revise the score, until the test is passed.

[0074] Next, the growth suitability evaluation submodule calls the evaluation factor weight set that passed the consistency test in the previous steps. In conjunction with preset corn growth parameters, a weighted summation operation is performed on the normalized parameter values ​​of each plot in the plot basic parameter set.

[0075] Taking plot A01 as an example, its normalized parameter values ​​are: slope 0.300, soil organic matter 0.481, and moisture accessibility 0.811. Its plot suitability evaluation value is... The calculation process is as follows:

[0076]

[0077] Similarly, calculate the suitability evaluation values ​​for other plots: the evaluation value of plot A02.

[0078]

[0079] Evaluation value of plot A03

[0080]

[0081] Evaluation value of plot A04

[0082]

[0083] Evaluation value of plot A05

[0084]

[0085] After the calculation is completed, the land suitability evaluation values ​​for corn plots are obtained, and this set of evaluation values ​​is obtained. It comprehensively reflects crop growth suitability, environmental compatibility, and production potential, and is then transmitted to the adjacency correction module.

[0086] Please see Figure 1 and Figure 4 The adjacency correction module is used to receive the suitability evaluation value of the plot, identify the adjacency relationship of the plot, and input the difference in evaluation value and crop compatibility parameters into the cellular automata model. Through iterative calculation, it simulates the migration of water and fertilizer resources and the effect of crops, identifies combinations with resource competition, generates adjacency correction coefficients, and passes them to the utilization efficiency optimization module.

[0087] The adjacency correction coefficient specifically refers to the intensity of resource competition, the impact of crop compatibility, and the efficiency of resource migration.

[0088] The adjacency correction module specifically includes: an adjacency identification submodule, which is used to analyze and determine the spatial adjacency relationship between plots based on the geospatial coordinate data of each plot, and generate a plot adjacency matrix;

[0089] The iterative simulation calculation submodule is used to call the plot adjacency matrix and plot suitability evaluation value, and use the evaluation value difference and crop compatibility parameter as the initial state and transformation rule of the cellular automata model. Through multiple iterations, it simulates and calculates the water and fertilizer resource migration process between plots and the interaction between crops to obtain the resource competition simulation results.

[0090] The correction coefficient generation submodule is used to analyze the resource competition simulation results, quantify the competition intensity and crop compatibility impact between combinations of land parcels with resource competition, and obtain the adjacency correction coefficient.

[0091] In the correction coefficient generation submodule, adjacent correction coefficients The specific calculation formula is as follows:

[0092] ;

[0093] in, For the plot of land Adjacent plots Adjacency correction factor between them and plots of land With the plot of land The suitability evaluation value of the land parcel, The maximum suitability score among all plots. As a resource competition weighting factor, The weighting factor is the crop compatibility factor, and the sum of the resource competition weighting factor and the crop compatibility weighting factor is 1. A crop type compatibility function used to determine crop type compatibility based on plot size. Crop types With the plot of land Crop types The compatibility relationship returns a preset compatibility rating.

[0094] First, the adjacency identification submodule is executed. Based on the geospatial coordinate data of each plot, such as by analyzing the plot boundary vector data using GIS software, the spatial adjacency relationships between plots are determined. Assume the spatial layout of the five plots is as follows: A01 is adjacent to A02 and A05; A02 is adjacent to A01, A03, and A05; A03 is adjacent to A02 and A04; A04 is adjacent to A03 and A05; and A05 is adjacent to A01, A02, and A04. Based on this analysis, a 5x5 plot adjacency matrix is ​​generated. In the matrix, if plot i is adjacent to plot j, the corresponding element is 1; otherwise, it is 0.

[0095] Next, the iterative simulation calculation submodule calls the land parcel adjacency matrix and the previously calculated set of land parcel suitability evaluation values. The differences in evaluation values ​​and crop compatibility parameters were used as the initial state and transition rules for the cellular automata model. The model simulated the migration of water and fertilizer resources between plots due to agricultural activities such as irrigation and fertilization, as well as root competition or allelopathy between different crops, through multiple iterations. For example, it was assumed that plots with higher evaluation values ​​(such as A03) would have a "siphoning effect" on adjacent plots with lower evaluation values ​​(such as A02), simulating the process of resources concentrating from lower to higher evaluation values. After 20 iterations, the simulation results of resource competition were obtained, quantifying the net flux of resource flow between plots.

[0096] The transformation rule of the above cellular automata model is as follows: In each iteration, for any plot of land... In the next moment ( Simulated resource quantity From its current moment ( ) resource quantity With all adjacent plots The amount of resources transferred is jointly determined. Specifically, the calculation formula is as follows:

[0097] .in, For the plot of land exist Simulated resource quantity at any given time. For the plot of land exist Simulated resource quantity at any given time. Indicates the land parcel The set of all adjacent plots Summation, The preset resource migration coefficient is determined through regression analysis of historical irrigation data; in this embodiment, it is set to 0.05. and plots of land and plot of land The suitability evaluation value of the land parcel, Adjacent plots exist Simulated resource quantity at any given time. This formula quantifies the net outflow of resources from high-suitability-value plots to low-suitability-value plots, and the net inflow of resources from low-suitability-value plots to high-suitability-value plots.

[0098] Subsequently, the correction coefficient generation submodule analyzes the resource competition simulation results, quantifying the intensity of competition and the impact of crop compatibility among plot combinations with resource competition. Adjacency correction coefficient. The specific calculation formula is as follows: .

[0099] In this formula, It is a plot of land Adjacent plots The adjacency correction coefficient between them is used to quantify the mutual influence between them. and These are the suitability evaluation values ​​for the two plots of land. This is the highest suitability assessment value among all plots. (Symbol) This indicates taking the absolute value. Part 1 The calculation is based on the resource competition intensity based on the difference in evaluation values. The logic is: the greater the difference in evaluation values ​​between two adjacent plots, the more intense the resource competition, and the smaller the value of this item; conversely, the smaller the difference, the closer the value of this item is to 1. It is a resource competition weighting factor. It is a crop compatibility weighting factor. It is a crop type compatibility function that depends on the plot. Crop types and plot of land Crop types It returns a compatibility evaluation value. The entire formula combines physical resource competition and biological inter-crop interactions through a weighted summation.

[0100] Weighting factors and (and The optimal crop mix was determined through a three-year field comparative experiment. The experiment included 200 plots, each planted with different crop combinations (e.g., corn-soybean, corn-wheat), and compared with monocultures. By measuring changes in crop yield and soil water and fertilizer content, multiple linear regression analysis was used to determine the weights of the impact of differences in evaluation values ​​on yield and the weights of the impact of crop compatibility on yield. The final determination... It is 0.6. It is 0.4.

[0101] Crop type compatibility functions The evaluation values ​​were determined by combining pot experiments with literature data. For example, corn ( ) and soybeans ( There is a nitrogen-fixing symbiotic effect between them, and the evaluation value is set at 1.2 (promoting); maize ( ) and wheat ( Crop rotation, with neutral compatibility, is rated at 1.0 (neutral); corn ( ) and sunflower ( There is allelopathic interaction and intense nutrient competition among the cells, with an evaluation value set at 0.7 (inhibition). These non-numerical data were quantified through the experimental process described above.

[0102] Example demonstration: Assume that corn is planted on plot A01 ( The adjacent plot A02 is planted with soybeans. 1. Obtain the parameter values ​​required for the calculation: (Based on the aforementioned calculations) (Based on the aforementioned calculations) (Highest evaluation value among all plots) (Corn-soybean compatibility evaluation value) 2. Substitute into the formula to calculate the adjacency correction coefficient. :

[0103] ;

[0104] The result 0.8958 is the adjacency correction coefficient for plot A01 to A02. This value is less than 1, indicating that although there is a compatibility-promoting effect between crops, the resource competition effect caused by the difference in plot suitability evaluation values ​​is more significant, resulting in a slight overall inhibitory effect. If the value is greater than 1, it indicates an overall promoting effect. After calculating the correction coefficients between all adjacent plots, the adjacency correction coefficient set is obtained and passed to the utilization efficiency optimization module.

[0105] Please see Figure 1 and Figure 5 The efficiency optimization module is used to receive the adjacency correction coefficient and adjust the water use parameters and fertilization parameters of the crop combination. The adjusted parameters are then input into the genetic algorithm, which searches for the crop spatial layout scheme with the highest fitness value determined by the preset fitness function through crossover and mutation operations.

[0106] Crop spatial layout schemes include crop zoning configuration, water use configuration, and fertilization optimization strategies.

[0107] The efficiency optimization module specifically includes: a parameter weighting adjustment submodule, which receives the adjacency correction coefficient and adjusts the water use parameters and fertilization parameters of the preset crop combination according to the adjacency correction coefficient to generate a weighted optimization parameter set;

[0108] The genetic algorithm optimization submodule is used to take the weighted optimization parameter set as the input constraint of the genetic algorithm, and iteratively generate a candidate crop layout population with higher fitness values ​​by initializing the population, performing selection, crossover and mutation operations.

[0109] The optimal solution selection submodule is used to evaluate the fitness value of each individual in the candidate crop layout population based on the fitness function with the total output of farmland and the efficiency of resource utilization as optimization indicators, select and output the individual with the highest fitness value, and obtain the crop spatial layout scheme.

[0110] In the optimal solution selection submodule, the fitness function is specifically used to calculate the fitness value of any crop spatial layout scheme. The calculation formula is as follows: ;

[0111] in, This represents the fitness value of the crop spatial layout scheme. This is the total output weighting coefficient. This is a weighting coefficient for resource utilization efficiency. The total number of land parcels. For land parcel indexing, For the first Predicted yield per unit area of ​​crops planted on each plot of land For the first The area of ​​each plot of land, For the first Planned water use for each plot of land For the first Planned fertilizer application amount for each plot of land.

[0112] First, the parameter weighted adjustment submodule receives the adjacency correction coefficient generated in the preceding steps and adjusts the water use parameters and fertilization parameters of the preset crop combination according to this coefficient. For example, if the initial planned fertilization rate for a plot is 100 kg / ha, and its average adjacency correction coefficient with all adjacent plots is 0.8958, then the adjusted fertilization rate is 100 * 0.8958 = 89.58 kg / ha. This adjustment quantifies the mutual influence between plots in terms of water and fertilizer input. After adjusting the parameters for all plots, a weighted optimization parameter set is generated.

[0113] Next, the genetic algorithm optimization submodule uses the weighted optimization parameter set as input constraints for the genetic algorithm. The algorithm first initializes a population, for example, containing 100 individuals. Each individual (chromosome) represents a complete crop spatial layout scheme, encoded as a sequence containing the crop type, adjusted water use, and adjusted fertilizer application for each plot. Subsequently, through selection (e.g., roulette wheel selection), crossover (e.g., single-point crossover), and mutation (e.g., basic position mutation), iteratively generating candidate crop layout populations with higher fitness values. This process is repeated, for example, for 200 generations.

[0114] Finally, the optimal solution selection submodule evaluates the fitness value of each individual in the candidate crop layout population based on a specific fitness function, and selects and outputs the individual with the highest fitness value. Fitness function The specific calculation formula is as follows: .

[0115] Where F is the fitness value of the crop spatial layout scheme. This is the total output weighting coefficient. Here, N is the resource utilization efficiency weighting coefficient, N is the total number of land parcels, and k is the land parcel index. Predict the yield per unit area of ​​crops planted on the k-th plot. Let be the area of ​​the k-th plot. The total resource input cost for the k-th plot is obtained by multiplying the planned water utilization and planned fertilizer application for the plot by their corresponding unit cost prices and then summing the results.

[0116] Weighting coefficient and The setup is based on an economic benefit analysis of historical data on agricultural product market prices and resource costs such as water and fertilizer over the past five years. By constructing a linear programming model, the objective function that maximizes the farm's total profit under different market and cost scenarios is solved. The ratio of the output term to the cost term coefficients is used as... and The basis for this setting. Determined through calculation. , .

[0117] Table 2 Example of parameters for a crop spatial layout scheme

[0118]

[0119] Example demonstration (calculating the fitness value F of this layout scheme based on the data in Table 2): 1. Calculate each parameter: To standardize the units of measurement, resource unit cost is introduced for calculation. The unit price for irrigation water is set at 1.5 yuan / cubic meter, and the unit price for fertilizer is 4.0 yuan / kg. 2. Calculate total output.

[0120] 3. Calculate the total resource input cost.

[0121]

[0122]

[0123]

[0124] Substitute into the formula to calculate the fitness value

[0125] The fitness value of 68.45346 represents the overall evaluation score of this specific layout scheme. The genetic algorithm calculates the fitness values ​​of all 100 individuals (layout schemes) in the population and, based on these fitness values, uses roulette wheel selection to determine the individuals used to generate the next generation of the population. After 200 generations of iteration, the individual with the highest fitness value is the final output crop spatial layout scheme, which defines in detail the types of crops to be planted, the amount of water to be allocated, and the fertilization strategy for each plot.

[0126] The above embodiments illustrate preferred embodiments of the present invention. Any equivalent adjustments to the technical solution based on software engineering methods are within the scope of protection, including but not limited to: implementing algorithm logic using different programming languages, refactoring functional modules into services, adjusting data interaction protocols, and optimizing resource scheduling strategies. Any implementation scheme derived from reasonable modifications to the data processing flow, service call chain, or system architecture layer without departing from the core technology of the present invention should be considered within the scope of protection defined by the claims of the present invention.

Claims

1. A system for optimizing and analyzing farmland use efficiency based on multi-source data fusion, characterized in that, The system includes: a plot parameter integration module, which is used to collect plot slope, soil organic matter and water accessibility data, and after normalization processing, construct a standardized set of basic plot parameters, which is then transmitted to the plot suitability evaluation module; The land suitability evaluation module is used to receive the basic parameter set of the land plot, input slope data, soil organic matter data, and water accessibility data as evaluation factors into the analytic hierarchy process model, calculate the land suitability evaluation value of each plot in combination with crop growth parameters, and transmit it to the adjacency correction module. The adjacency correction module is used to receive the suitability evaluation value of the plot, identify the adjacency relationship of the plot, and input the evaluation value difference and crop compatibility parameter into the cellular automata model. Through iterative calculation, it simulates the migration of water and fertilizer resources and the effect of crops, identifies combinations with resource competition, generates adjacency correction coefficients, and transmits them to the utilization efficiency optimization module. The efficiency optimization module is used to receive the adjacency correction coefficient, and to perform weighted adjustment on the water use parameters and fertilization parameters of the crop combination. The adjusted parameters are then input into the genetic algorithm, and the crop spatial layout scheme with the highest fitness value is searched through crossover and mutation operations. The adjacency correction coefficient The specific calculation formula is as follows: ; in, For the plot of land Adjacent plots Adjacency correction factor between them and plots of land With the plot of land The suitability evaluation value of the aforementioned land parcel, The maximum suitability score among all plots. As a resource competition weighting factor, The resource competition weight factor and the crop compatibility weight factor are combined to form a weighting factor of 1. A crop type compatibility function used to determine crop type compatibility based on plot size. Crop types With the plot of land Crop types The compatibility relationship returns a preset compatibility evaluation value; The fitness function is specifically used to calculate the fitness value of any crop spatial layout scheme. The calculation formula is as follows: ; in, The fitness value of the crop spatial layout scheme. This is the total output weighting coefficient. This is a weighting coefficient for resource utilization efficiency. The total number of land parcels. For land parcel indexing, For the first Predicted yield per unit area of ​​crops planted on each plot of land For the first The area of ​​each plot of land, For the first Planned water use for each plot of land For the first Planned fertilizer application amount for each plot of land.

2. The farmland use efficiency optimization analysis system based on multi-source data fusion according to claim 1, characterized in that, The basic parameter set of the plot specifically includes the normalized value of slope, the normalized value of soil organic matter, and the normalized value of water accessibility. The plot suitability evaluation value includes crop growth suitability, environmental compatibility, and production potential. The adjacency correction coefficient specifically refers to the intensity of resource competition, the impact of crop compatibility, and the efficiency of resource migration. The crop spatial layout scheme includes crop zoning configuration, water use configuration, and fertilization optimization strategy.

3. The farmland use efficiency optimization analysis system based on multi-source data fusion according to claim 1, characterized in that, The plot parameter integration module specifically includes: a data acquisition submodule, which is used to collect slope, soil organic matter and moisture accessibility data of each plot through remote sensing image interpretation and sensor monitoring, and generate raw plot data; The data processing submodule is used to call the original plot data and perform maximum and minimum normalization processing on the slope, soil organic matter and water accessibility data respectively to generate a normalized parameter matrix; The parameter construction submodule is used to integrate the normalized values ​​of slope, soil organic matter, and water accessibility in the normalized parameter matrix to establish a structured dataset associated with the spatial location information of the plot, thereby obtaining the standardized set of basic parameters for the plot.

4. The farmland use efficiency optimization analysis system based on multi-source data fusion according to claim 1, characterized in that, The land suitability evaluation module specifically includes: a factor weight calculation submodule, which is used to receive the basic parameter set of the land, construct a hierarchical analysis judgment matrix based on the slope data, the soil organic matter data and the water accessibility data, calculate the weight of each evaluation factor, and generate an evaluation factor weight set; The growth suitability evaluation submodule is used to call the evaluation factor weight set, combine it with the preset crop growth parameters, and perform a weighted summation operation on the parameter values ​​in the basic parameter set of the plot to obtain the plot suitability evaluation value for each plot for a specific crop.

5. The farmland use efficiency optimization analysis system based on multi-source data fusion according to claim 1, characterized in that, The adjacency correction module specifically includes: an adjacency identification submodule, used to analyze and determine the spatial adjacency relationship between plots based on the geospatial coordinate data of each plot, and generate a plot adjacency matrix; The iterative simulation calculation submodule is used to call the adjacency matrix of the plot and the suitability evaluation value of the plot, and use the difference in evaluation value and crop compatibility parameters as the initial state and transformation rules of the cellular automata model. Through multiple iterations, the simulation calculation of the water and fertilizer resource migration process between plots and the interaction between crops is carried out to obtain the resource competition simulation results. The correction coefficient generation submodule is used to analyze the resource competition simulation results, quantify the competition intensity and crop compatibility impact between combinations of land parcels with resource competition, and obtain the adjacency correction coefficient.

6. The farmland use efficiency optimization analysis system based on multi-source data fusion according to claim 1, characterized in that, The utilization efficiency optimization module specifically includes: a parameter weighting adjustment submodule, used to receive the adjacency correction coefficient, and adjust the water use parameters and fertilization parameters of the preset crop combination according to the adjacency correction coefficient to generate a weighted optimization parameter set; The genetic algorithm optimization submodule is used to take the weighted optimization parameter set as the input constraint of the genetic algorithm, and iteratively generate a candidate crop layout population with higher fitness values ​​by initializing the population, performing selection, crossover and mutation operations. The optimal solution selection submodule is used to evaluate the fitness value of each individual in the candidate crop layout population based on the fitness function with the total output of farmland and the efficiency of resource utilization as optimization indicators, select and output the individual with the highest fitness value, and obtain the crop spatial layout scheme.

7. The farmland use efficiency optimization analysis system based on multi-source data fusion according to claim 3, characterized in that, In the data processing submodule, the maximum and minimum normalization processing performed on the slope, soil organic matter, and water accessibility data specifically involves obtaining the maximum and minimum values ​​of the corresponding parameters in all plots, and calculating the normalized value based on the original parameter values ​​of any plot as follows: First, obtain the original parameter values ​​of the plot; second, calculate the difference between the original parameter value and the minimum value of the parameter in all plots; then, calculate the difference between the maximum and minimum values ​​of the parameter in all plots; finally, divide the two differences to obtain the normalized value of the parameter for that plot, and combine the normalized values ​​of all parameters in all plots to generate the normalized parameter matrix.

8. The farmland use efficiency optimization analysis system based on multi-source data fusion according to claim 4, characterized in that, After calculating the weights of each evaluation factor, the factor weight calculation submodule also performs a consistency check, which is achieved by calculating the consistency ratio. Completed, the calculation formula is as follows: ; in, For consistency ratio, As a consistency indicator, its calculation method is as follows: , To determine the largest eigenvalue of the matrix using the analytic hierarchy process, To evaluate the number of factors, The average random consistency index; After obtaining the consistency ratio, it is determined whether the consistency ratio is less than a preset consistency threshold. If it is less, the evaluation factor weight set that has passed the consistency test is used for subsequent calculations. If it is greater, the analytic hierarchy process judgment matrix is ​​adjusted and recalculated until the consistency test is passed.

Images