Inefficient land identification method and system based on big data analysis

Abstract

The present invention relates to the technical field of land identification based on big data analysis, and specifically discloses a method and system for identifying low-efficiency land based on big data analysis. The method uses satellite remote sensing imagery to identify land cover types and obtains farmland as a monitoring target area. The target area is then divided into several sub-areas, and crop data and environmental status data for each sub-area are obtained through remote sensing image analysis and ground surveys. Subsequently, a One-Class SVM algorithm is used to assess the degree of crop production anomalies, and the impact of environmental status on crops is evaluated in combination with environmental interference factor analysis. Finally, through a comprehensive analysis of production anomalies and environmental interference levels in each sub-area, low-efficiency land sub-areas are identified and fed back to land managers for their decision-making on whether replanning or other intervention measures are needed.

Description

Technical Field

[0001] The present invention relates to the field of land identification technology based on big data analysis, and in particular to a method and system for identifying low-efficiency land based on big data analysis. Background Art

[0002] As the global population continues to grow, land resource scarcity is becoming increasingly prominent, especially in developing countries. The efficient use of agricultural land and the rational allocation of land resources have become crucial issues in land management and agricultural production. Traditional land use planning methods often rely on manual surveys and empirical judgment. This approach is not only labor-intensive and time-consuming, but also lacks efficient data support, making it difficult to adjust and optimize land use strategies in a rapidly changing environment.

[0003] In agricultural production, due to the impact of various factors (such as climate change, environmental pollution, and lagging agricultural technology) on the productivity of land, some farmland has become inefficiently used. Inefficient land use is often manifested as land that fails to fully realize its production potential, resulting in low yields or long-term unused land, leading to a waste of agricultural resources. In addition, environmental issues such as soil degradation and water shortages can also lead to a decline in land productivity. Traditional farmland management and planning methods have difficulty accurately identifying these inefficient areas, especially in large-scale farmland and complex environments. How to scientifically evaluate land use efficiency has become a pressing issue for land managers. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for identifying low-efficiency land based on big data analysis to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The low-efficiency land identification method based on big data analysis includes the following steps:

[0007] S1: Identify land cover types based on satellite remote sensing imagery, including forest land, farmland land, and urban built-up area land, and select farmland land as the target area for monitoring;

[0008] S2: Divide the target area into several sub-areas, obtain crop data in each sub-area, including crop yield, output value, and species, analyze the crop data in each sub-area, and evaluate the degree of abnormality in crop production in each sub-area;

[0009] S3: Obtain environmental status data in each sub-area, including air quality data and water quality data, analyze the environmental status data, and evaluate the degree of interference of the environmental status data on crops;

[0010] S4: Comprehensively analyze the abnormality of crop production in each sub-region and the degree of interference of the environmental status data of each sub-region on crops to determine whether the current sub-region is low-efficiency land;

[0011] S5: Based on the judgment result, extract the low-efficiency land sub-area, and feed the low-efficiency land sub-area back to the manager to determine whether the land in the sub-area needs to be replanned.

[0012] As a further solution of the present invention, the analysis of the crop data in each sub-region and the evaluation of the abnormality of the crop production in each sub-region specifically include:

[0013] Obtain crop yield, crop output value and crop species in each sub-region;

[0014] By constructing feature vectors for crop yield, crop output value, and crop species in each sub-region, the feature vectors are used as inputs for the One-Class SVM model, and the One-Class SVM model is trained.

[0015] According to the trained One-Class SVM model, the value of the decision function and the minimum value of the objective function are output. The sub-region anomaly coefficient is obtained by calculating the ratio of the value of the decision function to the minimum value of the objective function.

[0016] Determine whether the sub-region abnormality coefficient is greater than or equal to the preset threshold. If not, it is recorded as a normal sub-region. If so, it is recorded as an abnormal sub-region.

[0017] As a further solution of the present invention: the process of obtaining the sub-region abnormality coefficient is:

[0018] Obtain the mean and standard deviation of crop yields in the target area, calculate the difference between the crop yield in each sub-area and the mean of the crop yield in the target area, and take the absolute value to obtain the yield deviation value;

[0019] The yield deviation value is calculated by comparing it with the standard deviation of the crop yield in the target area to obtain the standardized value of the crop yield in each sub-area;

[0020] Obtain the mean and standard deviation of the crop output value in the target area, calculate the difference between the crop output value in each sub-area and the mean of the crop output value in the target area, and take the absolute value to obtain the output value deviation value;

[0021] The output value deviation value is calculated by comparing it with the standard deviation of the crop output value in the target area to obtain the standardized value of the crop output value in each sub-area;

[0022] For discrete features, including crop species, one-hot encoding is used to convert each species into a binary vector;

[0023] For discrete features, including crop species, one-hot encoding is used to convert each species into a binary vector;

[0024] Construct the feature matrix, , represents the feature vector of the i-th subregion;

[0025] Where i represents the number of sub-regions, i=1, 2, ..., n, and n represents the maximum number of sub-regions;

[0026] The feature vector Input into the One-Class SVM model for training;

[0027] The goal of the model is to distinguish normal data from abnormal data by optimizing a hyperplane, which is a decision function constructed by the normal vector w and the bias term b;

[0028] The calculation expression of the decision function is:

[0029] ;

[0030] Where, represents the decision function, x represents the input feature vector, represents the transpose of the normal vector w, and b represents the bias term;

[0031] During the optimization process, the objective function is used to maximize the distance between normal data points and the hyperplane, pull normal data points away from the hyperplane, and minimize the number of abnormal data points;

[0032] The calculation expression of the objective function is:

[0033] ;

[0034] Where, Indicates maximizing the interval between normal data points and the hyperplane, v represents the preset scale factor, represents the slack variable, represents the minimum value of the objective function;

[0035] After training is complete, the model will output the normal vector w and the bias term b, which will be used to predict new data points;

[0036] The sub-region anomaly coefficient is obtained by calculating the ratio of the decision function value to the minimum value of the objective function. .

[0037] As a further solution of the present invention, the analysis of the environmental status data and the evaluation of the degree of interference of the environmental status data on crops specifically include:

[0038] Obtain air quality and water quality data within each sub-region;

[0039] Processing the air quality and water quality data in each sub-area, and calculating the interference factor in each sub-area based on the air quality and water quality data in each sub-area;

[0040] It is determined whether the interference factor in each sub-region is greater than or equal to a preset interference factor threshold. If so, it is recorded as a high interference level sub-region; if not, it is recorded as a low interference level sub-region.

[0041] As a further solution of the present invention: the process of obtaining the interference factor is:

[0042] Perform de-meaning processing on the collected air quality and water quality data;

[0043] A zero-mean series is obtained by calculating the mean of the data and subtracting the mean from each data point;

[0044] The air quality and water quality data after de-averaging are converted into frequency domain data through discrete Fourier transform;

[0045] Through Fourier transform, the periodic fluctuations and energy components of different frequencies in the environmental state data are identified;

[0046] The Fourier transform calculation expression is:

[0047] ;

[0048] Where, Indicates frequency The corresponding Fourier coefficients are, represents the kth discrete frequency, k represents the number of frequencies, represents the data point at the mth moment, represents the data after removing the mean, m represents the number of collection time points, and M represents the maximum number of collection time points. represents the interval between two adjacent time points, and j represents the imaginary unit;

[0049] Through the Fourier coefficient, we further calculate the power spectrum density of the environmental data. The calculation expression is: ;

[0050] Where, Indicates frequency The power density at

[0051] By accumulating the power spectrum density in the entire frequency range, the total fluctuation energy of the environmental data is obtained. ;

[0052] By analyzing the power spectral density and total fluctuation energy, the interference factor is calculated by the frequency-weighted power spectrum. The calculation expression is:

[0053] ;

[0054] Where, represents the interference factor of the i-th sub-region, and E represents the maximum number of frequencies.

[0055] As a further solution of the present invention: the determination of whether the current sub-region is low-efficiency land specifically includes:

[0056] Get the sub-region anomaly coefficient within each sub-region and interference factors ;

[0057] For each sub-region, the sub-region anomaly coefficient and interference factors Perform normalization and calculate the land use score in each sub-region;

[0058] The land use score is used to determine whether each sub-region is low-efficiency land;

[0059] Determine whether the land use score in each sub-region is greater than or equal to a preset threshold. If not, the current sub-region is low-efficiency land.

[0060] As a further solution of the present invention, the determination of whether the land in the sub-region needs to be replanned specifically includes:

[0061] Feedback the identified low-efficiency land sub-areas to land managers by generating detailed GIS maps to indicate the location, size and influencing factors of low-efficiency land;

[0062] For sub-areas with high interference levels, measures are taken to reduce PM2.5 concentrations, PM10 concentrations, COD concentrations, and ammonia nitrogen concentrations, and the interference factors and land use scores are recalculated. If the land use score is less than the preset threshold, the current area will be replanned.

[0063] The low-efficiency land identification system based on big data analysis includes:

[0064] The target area determination module identifies the land cover types based on satellite remote sensing image technology, including forest land, farmland land and urban built-up area land, and obtains farmland land as the target area for monitoring.

[0065] A data collection module, wherein the data collection module is used to obtain crop data in each sub-area, including: crop yield, output value and species;

[0066] Obtain environmental status data in each sub-area, including air quality data and water quality data;

[0067] An abnormality degree assessment module, which is used to analyze the crop data in each sub-region and assess the abnormality degree of crop production in each sub-region;

[0068] An interference degree assessment module, wherein the interference degree assessment module is used to analyze the environmental status data and assess the interference degree of the environmental status data on crops;

[0069] A comprehensive analysis module, the comprehensive analysis module is used to comprehensively analyze the abnormality of crop production in each sub-region and the interference degree of the environmental status data of each sub-region on the crops;

[0070] a low-efficiency land identification module, which identifies whether each sub-region is low-efficiency land based on the analysis results of the comprehensive analysis module;

[0071] The low-efficiency land optimization module extracts low-efficiency land sub-regions based on the judgment results, feeds back the low-efficiency land sub-regions to the manager, and determines whether the land in the sub-region needs to be replanned.

[0072] Beneficial effects of the present invention:

[0073] (1) The present invention can accurately identify inefficient areas of land use through a low-efficiency land identification method based on big data analysis. Through comprehensive analysis of remote sensing imaging technology, crop data, and environmental monitoring data, the present invention can accurately evaluate each sub-region, identify these low-efficiency lands, and provide corresponding optimization solutions. Through this method, managers can accurately understand which lands are not being effectively utilized and then take replanning or intervention measures, such as improving soil quality, adjusting crop planting structures, or increasing infrastructure construction such as irrigation, thereby improving land utilization and production efficiency in these areas.

[0074] (2) By analyzing the environmental status data of each sub-region (such as air quality, ammonia nitrogen concentration, water quality indicators, etc.) and the degree of interference with crops, the invention can provide accurate risk assessment and intervention recommendations for agricultural production; crop production in many areas is affected by environmental pollution and climate change, resulting in reduced yields or damaged crop quality, and long-term reliance on traditional agricultural methods often makes it difficult to cope with these changes; through the technology of the present invention, areas with high interference levels can be identified in a timely manner, providing managers with improvement plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The present invention will be further described below with reference to the accompanying drawings.

[0076] Figure 1 This is a flowchart of the specific steps of the low-efficiency land identification method based on big data analysis of the present invention;

[0077] Figure 2 This is a flowchart of the low-efficiency land identification system based on big data analysis in the present invention. DETAILED DESCRIPTION

[0078] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0079] See also Figure 1 As shown, the present invention is a method for identifying low-efficiency land based on big data analysis, comprising the following steps:

[0080] S1: Identify land cover types based on satellite remote sensing imagery, including forest land, farmland land, and urban built-up area land, and select farmland land as the target area for monitoring;

[0081] S2: Divide the target area into several sub-areas, obtain crop data in each sub-area, including crop yield, output value, and species, analyze the crop data in each sub-area, and evaluate the degree of abnormality in crop production in each sub-area;

[0082] S3: Obtain environmental status data in each sub-area, including air quality data (such as PM2.5, PM10) and water quality data (such as COD, ammonia nitrogen), analyze the environmental status data, and evaluate the degree of interference of the environmental status data on crops;

[0083] S4: Comprehensively analyze the abnormality of crop production in each sub-region and the degree of interference of the environmental status data of each sub-region on crops to determine whether the current sub-region is low-efficiency land;

[0084] S5: Based on the judgment result, extract the low-efficiency land sub-area, and feed the low-efficiency land sub-area back to the manager to determine whether the land in the sub-area needs to be replanned.

[0085] In S1, land cover types are identified based on satellite remote sensing imagery technology, including forest land, farmland land, and urban built-up area land. Farmland land is selected as the target area for monitoring, specifically including:

[0086] Obtain image data within the monitoring area through satellite remote sensing technology, including reflection information of different ground objects, such as vegetation, soil, and water bodies;

[0087] Use remote sensing image analysis software to pre-process images, including radiation correction and geometric correction, to ensure the accuracy of image data;

[0088] Using image classification technology, different areas in satellite remote sensing images are classified according to land cover types;

[0089] The areas in the image are divided into forest land, farmland land, and urban built-up area land through the spectral characteristics of remote sensing data;

[0090] Extract the farmland area as the target area for monitoring;

[0091] Through further data screening and verification, we ensure that the extracted farmland meets the research requirements and provide an accurate geographic information basis for subsequent crop data collection and analysis;

[0092] In S2, the target area is divided into several sub-areas, and crop data in each sub-area is obtained, including: crop yield, output value, and species. The crop data in each sub-area is analyzed to evaluate the degree of abnormality in crop production in each sub-area, including:

[0093] Divide the target area into several identical sub-areas;

[0094] Through remote sensing image analysis, ground surveys, and agricultural statistical data, we can obtain the crop yields in each sub-region;

[0095] The crop output value of each sub-region is calculated based on the market price and yield of the crops;

[0096] Obtain the crop species planted in each sub-region and count the dominant crops in each sub-region;

[0097] Standardization of collected crop yields and crop output values, including:

[0098] Obtain the mean and standard deviation of crop yields in the target area, calculate the difference between the crop yield in each sub-area and the mean of the crop yield in the target area, and take the absolute value to obtain the yield deviation value;

[0099] The yield deviation value is calculated by comparing it with the standard deviation of the crop yield in the target area to obtain the standardized value of the crop yield in each sub-area;

[0100] Obtain the mean and standard deviation of the crop output value in the target area, calculate the difference between the crop output value in each sub-area and the mean of the crop output value in the target area, and take the absolute value to obtain the output value deviation value;

[0101] The output value deviation value is calculated by comparing it with the standard deviation of the crop output value in the target area to obtain the standardized value of the crop output value in each sub-area;

[0102] For discrete features, including crop species, one-hot encoding is used to convert each species into a binary vector;

[0103] Construct the feature matrix, , represents the feature vector of the i-th subregion;

[0104] Where i represents the number of sub-regions, i=1, 2, ..., n, and n represents the maximum number of sub-regions;

[0105] The feature vector Input into the One-Class SVM model for training;

[0106] The goal of the model is to distinguish normal data from abnormal data by optimizing a hyperplane, which is a decision function constructed by the normal vector w and the bias term b;

[0107] The calculation expression of the decision function is:

[0108] ;

[0109] Where, represents the decision function, x represents the input feature vector, represents the transpose of the normal vector w, and b represents the bias term;

[0110] During the optimization process, the objective function is used to maximize the distance between normal data points and the hyperplane, pull normal data points away from the hyperplane, and minimize the number of abnormal data points;

[0111] The calculation expression of the objective function is:

[0112] ;

[0113] Where, Indicates maximizing the interval between normal data points and the hyperplane, v represents the preset scale factor, represents the slack variable, represents the minimum value of the objective function;

[0114] After training is complete, the model will output the normal vector w and the bias term b, which will be used to predict new data points;

[0115] The sub-region anomaly coefficient is obtained by calculating the ratio of the decision function value to the minimum value of the objective function. , determine whether the sub-region abnormality coefficient is greater than or equal to the preset threshold. If not, it means that the crop data of the corresponding sub-region is normal and is recorded as a normal sub-region. If so, it means that the crop data of the corresponding sub-region is abnormal and is recorded as an abnormal sub-region;

[0116] It should be noted that the slack variable is used to control the proportion of outliers and penalize misclassified data points. It also allows some data points to deviate from the hyperplane, meaning that some data points may be misclassified as outliers, increasing the model's flexibility. This allows the model to not only accurately classify most data points but also tolerate some noise, resulting in stronger generalization. During the optimization process, the objective function is minimized by adjusting the normal vector, bias term, and slack variables, ultimately finding an optimal hyperplane that best distinguishes normal from outliers.

[0117] In S3, environmental status data for each sub-area is obtained, including air quality data (such as PM2.5 and PM10) and water quality data (such as COD and ammonia nitrogen). The environmental status data is analyzed and the degree of interference of the environmental status data on crops is evaluated, including:

[0118] Collect air quality data in real time through air particulate matter monitors;

[0119] The air quality data refers to the concentration of suspended particulate matter in the air, including PM2.5 concentration and PM10 concentration;

[0120] Real-time water quality data, including COD concentration and ammonia nitrogen concentration, are collected through COD meter and ammonia nitrogen meter;

[0121] Preprocess environmental status data, including processing missing values, detecting outliers, and data standardization;

[0122] By calculating the interference factor in each sub-area, it is used to evaluate the degree of interference of environmental status data on crops;

[0123] The process of obtaining the interference factor is as follows:

[0124] Perform de-meaning processing on the collected air quality and water quality data;

[0125] A zero-mean series is obtained by calculating the mean of the data and subtracting the mean from each data point;

[0126] The air quality and water quality data after de-averaging are converted into frequency domain data through discrete Fourier transform;

[0127] Through Fourier transform, we can identify periodic fluctuations and energy components of different frequencies in environmental state data;

[0128] The Fourier transform calculation expression is:

[0129] ;

[0130] Where, Indicates frequency The corresponding Fourier coefficients are, represents the kth discrete frequency, k represents the number of frequencies, represents the data point at the mth moment, represents the data after removing the mean, m represents the number of collection time points, and M represents the maximum number of collection time points. represents the interval between two adjacent time points, and j represents the imaginary unit;

[0131] Through the Fourier coefficient, we further calculate the power spectrum density of the environmental data. The calculation expression is: ;

[0132] Where, Indicates frequency The power density at

[0133] By accumulating the power spectrum density in the entire frequency range, the total fluctuation energy of the environmental data is obtained. ;

[0134] By analyzing the power spectral density and total fluctuation energy, the interference factor is calculated by the frequency-weighted power spectrum. The calculation expression is:

[0135] ;

[0136] Where, represents the interference factor of the i-th sub-region, and E represents the maximum number of frequencies. It should be noted that the power spectral density describes the energy distribution of the signal at each frequency and reflects the periodicity and volatility of the environmental state over time. The interference factor is used to evaluate the impact of the environmental state in each sub-region on crop production. The higher the interference factor, the more significant the impact of the environmental state on crop production, which may lead to a decrease in crop yield or adverse effects on quality.

[0137] comparing the interference factor of each sub-region with a preset interference factor threshold;

[0138] If the interference factor is greater than or equal to the preset interference factor threshold, it means that the environmental interference level of the corresponding sub-area is high, and it is recorded as a high-interference sub-area;

[0139] If the interference factor is less than the preset interference factor threshold, it means that the environmental interference level of the corresponding sub-area is low, and the sub-area is recorded as a low interference level sub-area.

[0140] In S4, the abnormality of crop production in each sub-region and the degree of interference of the environmental status data of each sub-region on crops are comprehensively analyzed to determine whether the current sub-region is low-efficiency land, including:

[0141] Get the sub-region anomaly coefficient within each sub-region and interference factors ;

[0142] For each sub-region, the sub-region anomaly coefficient and interference factors Perform normalization and calculate the land use score in each sub-region;

[0143] The land use score is used to determine whether each sub-region is low-efficiency land;

[0144] Determine whether the land use score in each sub-region is greater than or equal to the preset threshold. If not, the current sub-region is considered to be low-efficiency land;

[0145] The calculation expression of the land use fraction is:

[0146] ;

[0147] Where, represents the land use fraction in the i-th sub-region, and is the preset scale factor, and and All greater than 0;

[0148] Determine whether the land use score in each sub-region is greater than or equal to a preset threshold. If not, the current sub-region is low-efficiency land.

[0149] In S5, based on the judgment results, the low-efficiency land sub-regions are extracted and fed back to the manager to determine whether the land in the sub-regions needs to be replanned. Specifically, the following steps are performed:

[0150] Feedback of identified low-efficiency land sub-areas to land managers. The feedback of low-efficiency land is not just a display of data, but also through the generation of specific geographic information system (GIS) maps to indicate the location, size and influencing factors of low-efficiency land;

[0151] This provides managers with a comprehensive and intuitive basis for decision-making, facilitating land replanning, resource optimization, or precise deployment of environmental governance measures;

[0152] Exemplary:

[0153] For sub-regions with greater environmental disturbance, managers can propose measures to improve air or water quality, or adopt new crop planting strategies for areas with abnormal agricultural production;

[0154] Based on the feedback, managers conduct a comprehensive assessment of the low-efficiency land sub-areas to determine whether these lands need to be rezoned or other intervention measures are taken, including:

[0155] Determine the degree of abnormality in crop yield deviation and output value in each sub-region;

[0156] If the output deviation is too large or the output value is persistently low, it means that the agricultural production capacity of the region is seriously affected and intervention needs to be given priority;

[0157] Determine the degree to which environmental conditions interfere with agricultural production. If certain sub-areas have poor air quality (e.g., high PM2.5 and PM10 concentrations) or poor water quality (e.g., high COD and ammonia nitrogen concentrations), this may have a negative impact on crop growth and require priority intervention.

[0158] Determine whether the current area is suitable for improvement, including:

[0159] If the land area is small or restricted by geographical and climatic conditions, the possibility of replanning is low;

[0160] For larger areas of inefficient land use, adjustments can be made by improving soil and water management, introducing suitable crop varieties, and increasing irrigation facilities;

[0161] After the implementation of intervention measures, managers need to establish a long-term monitoring mechanism to regularly evaluate changes in low-efficiency land sub-areas to ensure the continued effectiveness of the intervention measures;

[0162] Through continuous collection of environmental and crop data, management strategies are dynamically adjusted and optimized, and necessary land replanning is carried out based on the latest data to ensure efficient land use and sustainable development of agricultural production.

[0163] It should be noted that through land replanning, land resources can be optimized and waste caused by irrational use can be avoided, while creating better environmental conditions for agricultural production. This process not only helps to improve agricultural production efficiency, but also promotes the sustainable development of land resources, thereby achieving the goal of maximizing land utilization benefits.

[0164] See also Figure 2 As shown in the figure, the low-efficiency land identification system based on big data analysis includes:

[0165] The target area determination module identifies the land cover types based on satellite remote sensing image technology, including forest land, farmland land and urban built-up area land, and obtains farmland land as the target area for monitoring.

[0166] A data collection module, wherein the data collection module is used to obtain crop data in each sub-area, including: crop yield, output value and species;

[0167] Obtain environmental status data in each sub-area, including air quality data and water quality data;

[0168] An abnormality degree assessment module, which is used to analyze the crop data in each sub-region and assess the abnormality degree of crop production in each sub-region;

[0169] An interference degree assessment module, wherein the interference degree assessment module is used to analyze the environmental status data and assess the interference degree of the environmental status data on crops;

[0170] A comprehensive analysis module, the comprehensive analysis module is used to comprehensively analyze the abnormality of crop production in each sub-region and the interference degree of the environmental status data of each sub-region on the crops;

[0171] a low-efficiency land identification module, which identifies whether each sub-region is low-efficiency land based on the analysis results of the comprehensive analysis module;

[0172] The low-efficiency land optimization module extracts low-efficiency land sub-regions based on the judgment results, feeds back the low-efficiency land sub-regions to the manager, and determines whether the land in the sub-region needs to be replanned.

[0173] The working principle of the present invention is as follows: land cover types are identified using satellite remote sensing imaging technology, and farmland is extracted as the monitoring area; the target area is divided into several sub-areas, and crop data (such as yield, output value, species) and environmental data (such as air quality and water quality) of each sub-area are obtained and standardized; the abnormality of crop production is evaluated using the One-Class SVM model, and the interference factors of environmental data are analyzed through Fourier transform; the abnormal coefficient and interference factor of each sub-area are comprehensively analyzed, the land use score is calculated, and the low-efficiency land sub-areas are judged. The analysis results are fed back to the manager to evaluate whether replanning or intervention measures are needed; through precise data analysis and model optimization, the system can achieve efficient utilization of land resources and sustainable development of agricultural production, and promote the optimal allocation of land resources.

[0174] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0175] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0176] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0177] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0178] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for identifying low-efficiency land use based on big data analysis, characterized by: The following steps are involved: S1: Identify land cover types based on satellite remote sensing imagery, including forest land, farmland land, and urban built-up area land, and select farmland land as the target area for monitoring; S2: Divide the target area into several sub-areas, obtain crop data in each sub-area, including crop yield, output value, and species, analyze the crop data in each sub-area, and evaluate the degree of abnormality in crop production in each sub-area; The analysis of the crop data in each sub-region and the evaluation of the abnormality of crop production in each sub-region specifically include: Obtain crop yield, crop output value and crop species in each sub-region; By constructing feature vectors for crop yield, crop output value, and crop species in each sub-region, the feature vectors are used as inputs for the One-Class SVM model, and the One-Class SVM model is trained. According to the trained One-Class SVM model, the value of the decision function and the minimum value of the objective function are output. The sub-region anomaly coefficient is obtained by calculating the ratio of the value of the decision function to the minimum value of the objective function. Determine whether the sub-region abnormality coefficient is greater than or equal to a preset threshold. If not, it is recorded as a normal sub-region; if so, it is recorded as an abnormal sub-region; S3: Obtain environmental status data in each sub-area, including air quality data and water quality data, analyze the environmental status data, and evaluate the degree of interference of the environmental status data on crops; S4: Comprehensively analyze the abnormality of crop production in each sub-region and the degree of interference of the environmental status data of each sub-region on crops to determine whether the current sub-region is low-efficiency land; S5: Based on the judgment result, extract the low-efficiency land sub-area, and feed the low-efficiency land sub-area back to the manager to determine whether the land in the sub-area needs to be replanned.

2. The method for identifying low-efficiency land based on big data analysis according to claim 1 is characterized in that: The process of obtaining the sub-region anomaly coefficient is as follows: Construct the feature matrix, , Indicates the The feature vector of each sub-region; in, represents the number of sub-regions, =1,2,......, , Indicates the maximum number of sub-regions; The feature vector Input into the One-Class SVM model for training; The goal of the model is to distinguish normal data from abnormal data by optimizing a hyperplane, which is a decision function constructed by the normal vector w and the bias term b; The calculation expression of the decision function is: ； Where, represents the decision function, x represents the input feature vector, represents the transpose of the normal vector w, and b represents the bias term; During the optimization process, the objective function is used to maximize the distance between normal data points and the hyperplane, pull normal data points away from the hyperplane, and minimize the number of abnormal data points; The calculation expression of the objective function is: ； Where, represents maximizing the distance between normal data points and the hyperplane, Indicates the preset scale factor, represents the slack variable, represents the minimum value of the objective function; After training is complete, the model will output the normal vector w and the bias term b, which will be used to predict new data points; The sub-region anomaly coefficient is obtained by calculating the ratio of the decision function value to the minimum value of the objective function. .

3. The method for identifying low-efficiency land based on big data analysis according to claim 1, characterized in that: The analysis of the environmental status data and the assessment of the degree of interference of the environmental status data on crops specifically include: Obtain air quality and water quality data within each sub-region; Processing the air quality and water quality data in each sub-area, and calculating the interference factor in each sub-area based on the air quality and water quality data in each sub-area; It is determined whether the interference factor in each sub-region is greater than or equal to a preset interference factor threshold. If so, it is recorded as a high interference level sub-region; if not, it is recorded as a low interference level sub-region.

4. The method for identifying low-efficiency land based on big data analysis according to claim 3 is characterized in that: The process of obtaining the interference factor is as follows: Perform de-meaning processing on the collected air quality and water quality data; The air quality and water quality data after de-averaging are converted into frequency domain data through discrete Fourier transform; Through Fourier transform, the periodic fluctuations and energy components of different frequencies in the environmental state data are identified; The Fourier transform calculation expression is: ； Where, Indicates frequency The corresponding Fourier coefficients are, Indicates the discrete frequencies, represents the number of frequencies, Indicates the Data points at a certain moment, represents the data after removing the mean, Indicates the number of acquisition time points, Indicates the maximum number of acquisition time points, Represents the interval between two adjacent time points. represents an imaginary unit; The power spectrum density of the environmental data is further calculated through the Fourier coefficient. The calculation expression is: ; Where, Indicates frequency The power spectral density at ; By accumulating the power spectrum density in the entire frequency range, the total fluctuation energy of the environmental data is obtained. ; By analyzing the power spectral density and total fluctuation energy, the interference factor is calculated by the frequency-weighted power spectrum. The calculation expression is: ； Where, Indicates the The interference factor of each sub-region, Indicates the maximum number of frequencies.

5. The method for identifying low-efficiency land based on big data analysis according to claim 1, characterized in that: The determining whether the current sub-region is low-efficiency land specifically includes: Get the sub-region anomaly coefficient within each sub-region and interference factors ; For each sub-region, the sub-region anomaly coefficient and interference factors Perform normalization and calculate the land use score in each sub-region; The land use score is used to determine whether each sub-region is low-efficiency land; Determine whether the land use score in each sub-region is greater than or equal to a preset threshold. If not, the current sub-region is low-efficiency land.

6. The method for identifying low-efficiency land based on big data analysis according to claim 1, characterized in that: The determination of whether the land in the sub-region needs to be replanned specifically includes: Feedback the identified low-efficiency land sub-areas to land managers by generating detailed GIS maps to indicate the location, size and influencing factors of low-efficiency land; For sub-areas with high interference levels, measures are taken to reduce PM2.5 concentrations, PM10 concentrations, COD concentrations, and ammonia nitrogen concentrations, and the interference factors and land use scores are recalculated. If the land use score is less than the preset threshold, the current area will be replanned.

7. The low-efficiency land identification system based on big data analysis is characterized by: The method for identifying low-efficiency land based on big data analysis according to any one of claims 1 to 6 comprises: a target area determination module, which identifies land cover types, including forest land, farmland land, and urban built-up area land, based on satellite remote sensing image technology, and obtains farmland land as the target area for monitoring; A data acquisition module is used to divide the target area into several sub-areas and obtain crop data in each sub-area, including: crop yield, output value and species; Obtain environmental status data in each sub-area, including air quality data and water quality data; An abnormality degree assessment module, which is used to analyze the crop data in each sub-region and assess the abnormality degree of crop production in each sub-region; An interference degree assessment module, wherein the interference degree assessment module is used to analyze the environmental status data and assess the interference degree of the environmental status data on crops; A comprehensive analysis module, the comprehensive analysis module is used to comprehensively analyze the abnormality of crop production in each sub-region and the interference degree of the environmental status data of each sub-region on the crops; A low-efficiency land identification module, which determines whether each sub-area is low-efficiency land based on the analysis results of the comprehensive analysis module; The low-efficiency land optimization module extracts low-efficiency land sub-regions based on the judgment results, feeds back the low-efficiency land sub-regions to the manager, and determines whether the land in the sub-region needs to be replanned.

Images