Ecological monitoring data integration analysis method and system

Abstract

The invention relates to the technical field of ecological data monitoring and analysis, and particularly discloses an ecological monitoring data integrated analysis method and system. Soil moisture content and pH value data of each sub-region are collected in real time through a capacitive soil humidity sensor and an electrode pH value sensor, a soil moisture content abnormal index and a pH value abnormal index are calculated by using fast Fourier transform and a K-Means clustering algorithm, and a soil degradation coefficient is obtained by combining weighted normalization processing; and evaluating the soil health condition of each sub-region, constructing a machine learning model based on the data features to predict the future soil degradation level, further analyzing the relationship between precipitation and soil degradation for the region predicted to be seriously degraded, and starting a dynamic precipitation treatment scheme if it is found that precipitation increase can prevent soil degradation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ecological data monitoring and analysis, and particularly relates to an ecological monitoring data integration analysis method and system. BACKGROUND

[0002] Soil degradation is one of the major threats to global ecosystems, which not only affects agricultural productivity, but also has a profound impact on biodiversity and water resource management. In order to effectively address this problem, ecological monitoring data integration analysis methods have gradually become an important tool in research and practice.

[0003] The prior art has the following disadvantages: Although the existing ecological monitoring data integration analysis method has significant advantages in theory, it still faces many challenges in practical application. First, traditional monitoring systems usually only focus on a single or a few indicators, lacking the ability to comprehensively assess soil health conditions, resulting in the inability to accurately capture complex soil change patterns. Secondly, the existing early warning system mostly relies on historical data and experience judgment, failing to fully utilize real-time data and advanced data analysis technology, limiting the sensitivity and accuracy of the early warning system. For example, traditional soil degradation prediction models are often based on static data, which cannot adapt to dynamic changes in natural environmental conditions, resulting in unreliable prediction results. In addition, the existing irrigation management system is mostly fixed, lacking the ability to dynamically adjust according to real-time soil health conditions, easily causing water resource waste or soil over-wetting and other problems. More importantly, in the face of the complex relationship between precipitation and soil degradation, the existing technology often fails to provide effective dynamic precipitation management solutions, making it difficult to prevent and control potential soil degradation. These problems jointly restrict the effectiveness and efficiency of soil degradation prevention and control measures, and there is an urgent need for a more integrated and intelligent ecological monitoring data integration analysis method to achieve accurate prediction and dynamic management of soil degradation, thereby improving the efficiency of sustainable use of land resources and the level of ecological protection. The present application is aimed at the above problems and proposes an innovative ecological monitoring data integration analysis method, which realizes comprehensive monitoring and efficient management of soil degradation through systematic data collection, in-depth analysis and intelligent control. SUMMARY

[0004] The purpose of the present application is to provide an ecological monitoring data integration analysis method and system to solve the problems in the above background.

[0005] The purpose of the present application can be achieved by the following technical solutions: An ecological monitoring data integration analysis method, comprising the following steps: S1: uniformly dividing a target ecological monitoring area into a plurality of identical ecological sub-regions; S2: In the monitoring period, real-time acquisition of soil moisture content data and pH value data in each ecological sub-region, according to the change degree of soil moisture content and pH value in the monitoring period, the soil quality of each ecological sub-region is evaluated; S3: According to the evaluation result, each ecological sub-region is divided into three levels of normal area, slight degradation area and serious degradation area; S4: Based on the ecological sub-region of the slight degradation area, a machine learning model is constructed to predict the future soil degradation degree; S5: According to the prediction result, for the ecological sub-region which is predicted to develop into serious degradation, the influence degree of precipitation on soil degradation is analyzed, and the ecological sub-region is dynamically treated according to the analysis result.

[0006] As a further scheme of the application: the evaluation of the soil quality of each ecological sub-region specifically includes: The soil moisture content data in each ecological sub-region is obtained, the soil moisture content anomaly index of each ecological sub-region in the current period is calculated according to the change degree of soil moisture content in the monitoring period, the soil pH value data in each ecological sub-region is obtained, the soil pH value anomaly index of each ecological sub-region is calculated according to the deviation degree of soil pH value in the monitoring period, the soil moisture content anomaly index and the soil pH value anomaly index in each ecological sub-region are comprehensively calculated and processed to obtain the soil degradation coefficient, and the soil degradation coefficient of each ecological sub-region is compared with the preset first threshold and the preset second threshold, and the soil degradation degree of each ecological sub-region is judged according to the comparison result.

[0007] As a further scheme of the application: the acquisition process of the soil moisture content anomaly index is: In the monitoring period, the soil moisture content data in each ecological sub-region is real-time collected in time sequence by the capacitive soil humidity sensor network to obtain several groups of time sequence data of soil moisture content; The time sequence data of normalized soil moisture content in each ecological sub-region is subjected to fast Fourier transform to convert time domain data into frequency domain representation form to obtain complex frequency components; The energy spectrum density of each frequency component is calculated, the main frequency component of soil moisture content change under normal circumstances and the corresponding energy level are determined based on historical data as a baseline; The baseline is the long-term average energy spectrum density distribution; The deviation degree of the energy spectrum density of the soil moisture content data of the current period from the baseline is calculated to obtain the soil moisture content anomaly index.

[0008] As a further scheme of the application: the acquisition process of the soil pH value anomaly index is: In the monitoring period, the soil pH data in each ecological sub-region is collected in real time in time sequence using an electrode type pH sensor, The K-Means clustering algorithm is used for clustering analysis of the standardized pH data: randomly initialize a cluster center, assign each sample to the nearest cluster center, update the cluster center to the average of all samples in the cluster, and repeat the assignment and update until the cluster center no longer changes; According to the clustering results, the cluster containing the most samples is regarded as the "normal" category, and the samples of other clusters are regarded as potential abnormal points; For each time point of the pH value, the distance of the pH value to the nearest cluster center is calculated to obtain the pH abnormality index of the corresponding time point, and the mean value of the pH abnormality index of all time collection points in the monitoring period is calculated to obtain the soil pH abnormality index of the corresponding ecological sub-region.

[0009] As a further scheme of the application: according to the evaluation results, each ecological sub-region is divided into three levels of normal region, slight degradation region and serious degradation region, specifically including: If the soil degradation coefficient of each ecological sub-region is greater than or equal to a preset first threshold, it is recorded as a serious degradation region, if not, it is judged whether the soil degradation coefficient is greater than a preset second threshold, if yes, it is recorded as a slight degradation region, if not, it is recorded as a normal region.

[0010] As a further scheme of the application: the future soil degradation degree is predicted, specifically including: Based on the ecological sub-region of the slight degradation region, the soil water content abnormality index and the soil pH abnormality index in each ecological sub-region are extracted, the soil water content abnormality index and the soil pH abnormality index are constructed into a comprehensive feature vector, which is used as the input of the machine learning model, and the model output is the soil degradation level of each monitoring period in the future, including normal, slight degradation and serious degradation.

[0011] As a further scheme of the application: the construction process of the machine learning model is: The soil water content abnormality index and the soil pH abnormality index are constructed into a comprehensive feature vector, which is used as the input of the machine learning model, to minimize the error between the predicted soil degradation level of each monitoring period in the future and the actual soil degradation level, and the model is trained, according to the trained machine learning model, the soil degradation level of each monitoring period in the future is output, corresponding to the ecological sub-region, the machine learning model is a multi-source linear regression model.

[0012] As a further scheme of the present application: according to the prediction result, for the ecological sub-region predicted to develop into severe degradation, the rainfall and the influence degree on soil degradation are analyzed, and according to the analysis result, the ecological sub-region is subjected to dynamic rainfall treatment, specifically including: According to the prediction result, the ecological sub-region that will develop into severe degradation in the future is marked, the time from the current time to the ecological sub-region developing into severe degradation in the future is obtained, and the rainfall change curve in the corresponding time is obtained, whether the ecological sub-region developing into severe degradation and the rainfall change curve with time are in a linear relationship is judged, if the rainfall promotes soil degradation, if the rainfall can prevent soil degradation, the ecological sub-region predicted to develop into severe degradation is subjected to dynamic rainfall treatment.

[0013] As a further scheme of the present application: the judgment of whether the rainfall promotes soil degradation specifically includes: The time period in which the rainfall shows an upward trend is identified, and the corresponding soil degradation condition in these time periods is obtained, if the soil is not further degraded during the increase of rainfall, the soil degradation condition in the time period in which the rainfall shows a downward trend is continuously analyzed, if the soil is also not further degraded during the decrease of rainfall, it indicates that the rainfall does not have a significant impact on the current soil degradation; if the soil is further degraded during the decrease of rainfall, it indicates that the increase of rainfall can prevent the further degradation of soil; If the soil is further degraded in the time period in which the rainfall shows an upward trend, the soil degradation condition in the time period in which the rainfall shows a downward trend is further analyzed, if the soil is also further degraded during the decrease of rainfall, it indicates that the rainfall does not have a significant impact on the current soil degradation; otherwise, if the soil is not further degraded during the decrease of rainfall, it indicates that the increase of rainfall fails to prevent soil degradation.

[0014] An ecological monitoring data integration analysis system, comprising: A region division module, the region division module uniformly divides a target ecological monitoring area into a plurality of identical ecological sub-regions; A data analysis module, the data analysis module collects soil moisture content data and pH data in each ecological sub-region in real time within a monitoring period, and evaluates the soil quality in each ecological sub-region according to the change degree of the soil moisture content and the pH within the monitoring period; A regional soil degradation degree division module, the regional soil degradation degree division module divides each ecological sub-region into three grades of normal region, slight degradation region and severe degradation region according to the evaluation result; A model establishment module, the model establishment module constructs a machine learning model based on the ecological sub-regions of the slight degradation region to predict the future soil degradation degree; The impact degree analysis and dynamic adjustment module analyzes the precipitation and its impact on soil degradation for ecological sub-regions predicted to develop into severely degraded areas based on the prediction results, and performs dynamic precipitation treatment on the ecological sub-regions based on the analysis results.

[0015] The beneficial effects of this invention are: (1) This invention improves the accuracy of predicting soil degradation trends and management efficiency through integrated data acquisition and in-depth analysis methods. High-precision capacitive soil moisture sensors and electrode-type pH sensors are used to monitor soil moisture and pH changes in each ecological sub-region in real time, ensuring that the acquired data has high temporal resolution and accuracy. To further explore the deeper information behind these data, this invention uses Fast Fourier Transform (FFT) technology to convert time-domain data into frequency-domain representation, identifying the main frequency components and their energy spectral density of soil moisture changes, thereby calculating the soil moisture anomaly index. Simultaneously, the K-Means clustering algorithm is used to perform cluster analysis on the standardized soil pH data, determining the "normal" category and identifying potential anomalies, thus obtaining the soil pH anomaly index. Based on the above two key indicators, combined with weighted normalization processing, a soil degradation coefficient that comprehensively reflects the soil health status is calculated. Based on these detailed and multi-dimensional data features, this invention further constructs a machine learning model. Through learning and training on historical data, it can accurately predict the soil degradation level (including normal, slight degradation, and severe degradation) in each future monitoring cycle. This data-driven, multi-dimensional fusion analysis strategy not only greatly improves the accuracy and reliability of prediction, but also enables timely detection and early warning of potential soil degradation risks. This allows land managers to take targeted protection measures based on scientific evidence, effectively prevent soil degradation, promote the sustainable use of land resources, and provide strong technical support for achieving precision agriculture and ecological environmental protection.

[0016] (2) Another core advantage of the invention lies in its innovative dynamic precipitation treatment scheme, which is specifically optimized for ecological sub-regions that are predicted to develop into severe degradation in the future. By deeply analyzing the relationship between precipitation and soil degradation, the invention can accurately determine whether precipitation plays a promoting or preventive role in soil degradation. Once it is determined that an increase in precipitation helps prevent further soil degradation, the dynamic precipitation treatment scheme is activated: first, real-time monitoring of precipitation and soil health indicators in these high-risk areas is conducted to ensure the timeliness and accuracy of the data. When the monitoring data shows that the precipitation is below the set safety threshold and the soil health indicators are close to the degradation threshold, the system will automatically trigger a series of response measures, such as implementing artificial rain enhancement or optimizing the existing irrigation system configuration, to dynamically adjust the precipitation and ensure that the soil moisture content remains within the appropriate range, effectively inhibiting the progress of soil degradation. In addition, to achieve long-term soil health management, the invention also introduces a continuous monitoring and feedback mechanism to continuously assess soil health conditions and dynamically adjust precipitation management strategies based on the latest data feedback, achieving precise regulation and efficient resource utilization. This method not only significantly improves the efficiency of sustainable use of land resources, but also promotes the recovery of damaged ecosystems and enhances the self-healing ability of ecosystems. Compared with traditional fixed irrigation methods, the dynamic precipitation treatment scheme provided by the invention is more flexible and adaptable, better able to cope with complex natural environmental changes and variable climate conditions, providing strong technical support for precision agriculture and environmental protection. This method based on real-time data analysis and intelligent control not only improves the effectiveness of soil management and ecological protection, but also sets an example for the scientific management and rational use of other natural resources. BRIEF DESCRIPTION OF DRAWINGS

[0017] The invention will be further described below with reference to the accompanying drawings.

[0018] Figure 1 is a specific step flowchart of the ecological monitoring data integration analysis method of the invention; Figure 2 is a flowchart of the soil degradation degree in the ecological sub-region in the invention; Figure 3 is a flowchart of an ecological monitoring data integration analysis system in the invention. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the invention. Obviously, the described embodiments are only a part of the embodiments of the invention, not all embodiments. Based on the embodiments in the invention, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the invention.

[0020] Embodiment 1, please refer to Figure 1 As shown in the figure, the present application is an ecological monitoring data integration analysis method, comprising the following steps: S1: uniformly divide the target ecological monitoring area into multiple identical ecological sub-regions; S2: in the monitoring period, real-time collection of soil moisture content data and pH data in each ecological sub-region, according to the degree of change of soil moisture content and pH in the monitoring period, to evaluate the soil quality in each ecological sub-region; S3: according to the evaluation results, divide each ecological sub-region into three levels of normal area, slight degradation area and serious degradation area; S4: based on the ecological sub-region of slight degradation area, construct a machine learning model to predict the future soil degradation degree; S5: according to the prediction results, for the ecological sub-region predicted to develop into serious degradation, analyze the influence degree of precipitation and soil degradation, and according to the analysis results, carry out dynamic precipitation treatment on the ecological sub-region.

[0021] Embodiment 2, please refer to Figure 2 As shown in the figure, in S1, the target ecological monitoring area is uniformly divided into multiple identical ecological sub-regions, which specifically includes: First, collect the high-resolution geographic information system (GIS) data of the target ecological monitoring area, including the key information of terrain, vegetation coverage and soil type. Then, according to the monitoring purpose and research demand, determine the appropriate partition scale to ensure that each ecological sub-region is consistent in size while maintaining the uniformity of internal environmental characteristics as much as possible. Then, use the grid division tool in GIS software to cut the entire monitoring area into regular grid sub-regions according to the predetermined scale, for example, square or rectangular grid, each grid represents an ecological sub-region. In order to ensure the effectiveness and scientificity of the partition, the generated sub-regions need to be checked for reasonableness, and the boundaries need to be adjusted to avoid dividing significantly different ecological environmental characteristics into the same sub-region, and to ensure that the transition between all sub-regions is as smooth and natural as possible. In this way, through the systematic partition method, the uniform division of the target ecological monitoring area is realized, laying a foundation for subsequent data collection and analysis.

[0022] In S2, in the monitoring period, real-time collection of soil moisture content data and pH data in each ecological sub-region, according to the degree of change of soil moisture content and pH in the monitoring period, to evaluate the soil quality in each ecological sub-region, which specifically includes: Soil moisture content data for each ecological sub-region is acquired. Based on the degree of change in soil moisture content within the monitoring period, the soil moisture content anomaly index for each ecological sub-region in the current period is calculated. Soil pH data for each ecological sub-region is acquired. Based on the degree of deviation in soil pH within the monitoring period, the soil pH anomaly index for each ecological sub-region is calculated. The soil moisture content anomaly index and the soil pH anomaly index for each ecological sub-region are comprehensively calculated and processed to obtain the soil degradation coefficient. The soil degradation coefficient for each ecological sub-region is compared with a preset first threshold and a preset second threshold. Based on the comparison results, the degree of soil degradation for each ecological sub-region is determined. During the monitoring period, soil moisture content data in each ecological sub-region is collected in real time according to the time series through a capacitive soil moisture sensor network, resulting in several sets of time series data of soil moisture content; and the collected time series data of soil moisture content are normalized to eliminate the influence of dimensions on the calculation. The capacitive soil moisture sensor is deployed at a depth of 30 cm in the specific area being monitored. The normalized soil moisture content time series data in each ecological sub-region is subjected to fast Fourier transform to convert the time domain data into frequency domain representation, and the frequency components in complex form are obtained. The energy spectral density of each frequency component is calculated using the following expression: ; In the formula, Indicates the first Energy spectral density of each frequency component Indicates the first One frequency component, Indicates the number of frequency components; Based on historical data, the main frequency components of soil moisture content changes under normal conditions and their corresponding energy levels are identified as baselines. Preset thresholds are set, and frequency components exceeding these thresholds are considered abnormal.

[0023] The baseline is the long-term average energy spectral density distribution; For the data of the current period, the degree of deviation from the baseline is calculated to obtain the soil moisture content anomaly index. The calculation expression is as follows: ; In the formula, This indicates an abnormal soil moisture content index. This represents the total number of data collection points. Indicates the current period number Energy spectral density of each frequency component Indicates the baseline number The energy spectrum density of a frequency component; It should be noted that: by adopting the Fourier transform technology, not only the time-varying characteristics of soil moisture content can be accurately captured, but also potential abnormal fluctuation patterns can be identified, thereby providing strong technical support for precision agriculture and environmental protection. The smaller the value of the soil moisture content anomaly index is, the closer the current period of soil moisture content change is to the baseline, indicating that the soil moisture content is in a normal state. The larger the value of the soil moisture content anomaly index is, the more the current period of soil moisture content change deviates from the normal range, indicating that there may be abnormal conditions such as excessive drought or flood.

[0024] The acquisition process of the soil pH abnormality index is: During the monitoring period, the soil pH data in each ecological sub-region is collected in real time according to the time sequence using an electrode type pH sensor, The electrode type pH sensor is deployed in the specific area of 30cm depth for monitoring; The collected soil pH data is normalized to ensure that data of different dimensions can be compared; The K-Means clustering algorithm is used to perform clustering analysis on the standardized pH data: randomly initialize a cluster center, assign each sample to the nearest cluster center, update the cluster center to the average value of all samples in the cluster, and repeat the assignment and update until the cluster center no longer changes; According to the clustering result, the cluster containing the most samples is regarded as the "normal" category, and the samples of other clusters are regarded as potential abnormal points; For each time point of pH value, the distance from the pH value to the nearest cluster center is calculated, wherein the distance is calculated using the Euclidean distance; The pH abnormality index corresponding to the time point is obtained, and the pH abnormality index of all time collection points in the monitoring period is averaged to obtain the soil pH abnormality index of the corresponding ecological sub-region.

[0025] It should be noted that: by adopting the clustering analysis technology, not only the time-varying characteristics of soil pH can be accurately captured, but also potential abnormal fluctuation patterns can be identified, thereby providing strong technical support for precision agriculture and environmental protection. The smaller the value of the soil pH abnormality index is, the more the soil pH values at most time points are concentrated in the "normal" cluster, indicating that the soil pH is in a normal state. The larger the value of the soil pH abnormality index is, the more data points deviate from the normal range, indicating that there may be abnormal conditions.

[0026] The calculation expression of the soil degradation coefficient is: ; wherein, represents a soil degradation coefficient, and is a preset proportion factor, and and are both greater than 0, represents a soil water content anomaly index, represents a soil pH anomaly index. It should be noted that the soil degradation coefficient is obtained through the calculation process of weighted normalization, and the smaller the value of the soil degradation coefficient, the lower the corresponding soil degradation degree, and the larger the value of the soil degradation coefficient, the higher the corresponding soil degradation degree.

[0027] In S3, according to the evaluation result, each ecological sub-region is divided into three levels of normal area, slight degradation area and serious degradation area, which specifically includes: determining whether the soil degradation coefficient of each ecological sub-region is greater than or equal to a preset first threshold value, if yes, it is recorded as a serious degradation area, if not, it is determined whether the soil degradation coefficient is greater than a preset second threshold value, if yes, it is recorded as a slight degradation area, if not, it is recorded as a normal area.

[0028] In S4, based on the ecological sub-region of the slight degradation area, a machine learning model is constructed to predict the future soil degradation degree, which specifically includes: Based on the ecological sub-region of the slight degradation area, the soil water content anomaly index and the soil pH anomaly index in each current ecological sub-region are extracted, and the soil water content anomaly index and the soil pH anomaly index are constructed into a comprehensive feature vector as the input of the machine learning model. The model output is the soil degradation level of each monitoring period in the future, including normal, slight degradation and serious degradation.

[0029] The construction process of the machine learning model is: The soil water content anomaly index and the soil pH anomaly index are constructed into a comprehensive feature vector as the input of the machine learning model. In order to prepare the training data set, we need the soil degradation level label (normal, slight degradation, serious degradation) in the historical record, and this step requires labeling processing on the existing data. Start training the multi-source linear regression model. In this process, the model finds the best fitting relationship between the input features and the output categories, although traditional linear regression is mainly used for continuous value prediction, but it can be realized through appropriate adjustment or combination with other classification techniques. Classification task.

[0030] Specific to the training process, first initialize the multi-source linear regression model parameters, and then use historical data to train the model. In each iteration, the model calculates the prediction error according to the current parameters, and adjusts the parameters to minimize the error.

[0031] To improve the prediction accuracy, cross-validation techniques are introduced to further optimize the model. After the initial training is completed, the performance of the model is estimated by k-fold cross-validation methods (such as 5-fold or 10-fold cross-validation), and overfitting is prevented. In addition, removing redundant information through principal component analysis also helps to improve the efficiency and accuracy of the model. Finally, the trained multi-source linear regression model is used to predict the soil degradation level of each monitoring period in the future.

[0032] In S5, according to the prediction result, for the ecological sub-region that is predicted to develop into severe degradation, the influence degree of precipitation on soil degradation is analyzed, and according to the analysis result, dynamic precipitation treatment is carried out on the ecological sub-region, which specifically includes: According to the prediction result, the ecological sub-region that will develop into severe degradation in the future is marked, the time from the current time to the ecological sub-region developing into severe degradation in the future is obtained, and the change curve of the precipitation with time in the corresponding time is obtained. It is judged whether the ecological sub-region developing into severe degradation and the change curve of the precipitation with time are in a linear relationship. If they are in a linear relationship, it is judged whether the precipitation promotes soil degradation. If the precipitation can prevent soil degradation, dynamic precipitation treatment is carried out on the ecological sub-region predicted to develop into severe degradation, which specifically includes: For each ecological sub-region marked as developing into severe degradation in the future, the time interval from the current time to the predicted severe degradation is calculated. This can be achieved by comparing the time sequence given by the prediction model with the current time; For each ecological sub-region predicted to develop into severe degradation in the future, the change curve of the precipitation with time in the determined time period is collected, the time period in which the precipitation shows an upward trend is identified, and the corresponding soil degradation condition in these time periods is obtained. If the soil does not further degrade during the period of increasing precipitation, the soil degradation condition in the time period of decreasing precipitation is analyzed. If the soil does not further degrade during the period of decreasing precipitation, it indicates that the precipitation does not significantly affect the current soil degradation. If the soil further degrades during the period of decreasing precipitation, it indicates that the increase in precipitation can prevent further soil degradation; If the soil further degrades during the period of increasing precipitation, the soil degradation condition in the time period of decreasing precipitation is further analyzed. If the soil also further degrades during the period of decreasing precipitation, it indicates that the precipitation does not significantly affect the current soil degradation. Otherwise, if the soil does not further degrade during the period of decreasing precipitation, it indicates that the increase in precipitation does not prevent soil degradation; If the soil degradation can be prevented based on the increase of precipitation, a dynamic precipitation treatment scheme is started: real-time monitoring of precipitation and soil health index changes in these areas; when the precipitation is detected to be lower than the set threshold and the soil health index is less than the degradation threshold, the precipitation is dynamically adjusted by artificial rain and optimization of irrigation system to ensure that the soil moisture content is maintained within the appropriate range, preventing soil degradation; at the same time, the soil health status is continuously monitored and the precipitation management strategy is adjusted according to the feedback to achieve precise regulation and efficient resource utilization, so as to protect and restore the health of the ecological system.

[0033] Embodiment 3, please refer to Figure 3 An ecological monitoring data integration analysis system, comprising: A region division module, which uniformly divides the target ecological monitoring area into a plurality of identical ecological sub-regions; A data analysis module, which collects soil moisture content data and pH data in each ecological sub-region in real time within a monitoring period, and evaluates the soil quality in each ecological sub-region according to the change degree of soil moisture content and pH within the monitoring period; A regional soil degradation degree division module, which divides each ecological sub-region into three grades of normal area, slight degradation area and severe degradation area according to the evaluation results; A model establishment module, which constructs a machine learning model based on the ecological sub-regions of the slight degradation area to predict the future soil degradation degree; An influence degree analysis and dynamic adjustment module, which analyzes the influence degree of precipitation and soil degradation for the ecological sub-regions predicted to develop into severe degradation according to the prediction results, and dynamically adjusts the precipitation of the ecological sub-regions according to the analysis results.

[0034] The working principle of the present application is as follows: the target ecological monitoring area is divided into multiple identical ecological sub-regions, and the soil moisture content and pH data of each sub-region are collected in real time within the monitoring period. By analyzing the degree of change in these data, the soil moisture content anomaly index and the soil pH anomaly index are calculated, and the soil degradation coefficient is obtained by combining the weighted normalization method, so as to evaluate the soil quality of each ecological sub-region and classify it into normal, slightly degraded or severely degraded areas. Based on the data of the slightly degraded area, a machine learning model is constructed to predict the future soil degradation level. For the areas predicted to be severely degraded, the relationship between precipitation and land degradation is further analyzed. If it is found that the increase of precipitation can effectively prevent soil degradation, then dynamic precipitation treatment scheme is implemented for these areas: real-time monitoring of precipitation and soil health index changes, when insufficient precipitation and soil health index close to degradation threshold are detected, artificial rain or optimized irrigation system is taken to adjust the precipitation, so as to ensure that the soil moisture content is maintained within the appropriate range. In addition, continuous monitoring and feedback adjustment of the precipitation management strategy are carried out to realize precise regulation and efficient resource utilization, so as to protect and restore the health of the ecological system. This method not only can accurately capture the time-varying characteristics of soil health status, but also can identify potential abnormal fluctuation patterns, providing strong technical support for precision agriculture and environmental protection. Through data-driven decision-making, the present application emphasizes the importance of dynamic adjustment and personalized response, which helps to realize more efficient resource management and ecological protection. This method is particularly suitable for soil health management under complex environmental conditions, and improves the efficiency of sustainable utilization of land resources.

[0035] The above formulas are dimensionless values calculated, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the latest real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0036] The above-described embodiments can be implemented in part or in whole through software, hardware, firmware or any combination thereof. When implemented in software, the above-described embodiments can be implemented 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 programs are loaded into a computer, all or part of the processes described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired or wireless (such as infrared, wireless, microwave, etc.) manner. 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, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0037] It should be understood that the term "and / or" herein only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents that the front and rear associated objects are in an "or" relationship, but can also represent an "and / or" relationship, which can be understood in the context.

[0038] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of the processes should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0039] The above describes one embodiment of the present application in detail, but the content described is only the preferred embodiment of the present application, and cannot be considered as limiting the scope of the implementation of the present application. Any equivalent changes and improvements made within the scope of the present application are still within the scope of the patent coverage of the present application.

Claims

1. A method for integrated analysis of ecological monitoring data, characterized in that, Includes the following steps: S1: Divide the target ecological monitoring area evenly into multiple identical ecological sub-regions; S2: During the monitoring period, real-time data on soil moisture content and pH level are collected for each ecological sub-region. Based on the changes in soil moisture content and pH level during the monitoring period, the soil quality of each ecological sub-region is assessed. S3: Based on the assessment results, each ecological sub-region is divided into three levels: normal region, slightly degraded region, and severely degraded region; S4: Based on the ecological sub-regions of slightly degraded areas, construct machine learning models to predict the future degree of soil degradation; S5: Based on the prediction results, for ecological sub-regions predicted to develop into severely degraded areas, analyze the precipitation and its impact on soil degradation, and implement dynamic precipitation management for the ecological sub-regions based on the analysis results.

2. The ecological monitoring data integration and analysis method according to claim 1, characterized in that, The assessment of soil quality within each ecological sub-region specifically includes: Soil moisture content data for each ecological sub-region is acquired. Based on the degree of change in soil moisture content within the monitoring period, the soil moisture content anomaly index for each ecological sub-region in the current period is calculated. Soil pH data for each ecological sub-region is acquired. Based on the degree of deviation in soil pH within the monitoring period, the soil pH anomaly index for each ecological sub-region is calculated. The soil moisture content anomaly index and the soil pH anomaly index for each ecological sub-region are comprehensively calculated and processed to obtain the soil degradation coefficient. The soil degradation coefficient for each ecological sub-region is compared with a preset first threshold and a preset second threshold. Based on the comparison results, the degree of soil degradation for each ecological sub-region is determined.

3. The ecological monitoring data integration and analysis method according to claim 2, characterized in that, The process for obtaining the soil moisture content anomaly index is as follows: During the monitoring period, soil moisture content data in each ecological sub-region is collected in real time according to the time series through a capacitive soil moisture sensor network, resulting in several sets of time series data of soil moisture content. The normalized soil moisture content time series data in each ecological sub-region is subjected to fast Fourier transform to convert the time domain data into frequency domain representation, and the frequency components in complex form are obtained. Calculate the energy spectral density of each frequency component, and based on historical data, determine the main frequency components and corresponding energy levels of soil moisture content changes under normal conditions, as a baseline. The baseline is the long-term average energy spectral density distribution; The soil moisture anomaly index is obtained by calculating the deviation between the energy spectral density of the soil moisture data for the current period and the baseline.

4. The method for integrated analysis of ecological monitoring data according to claim 2, characterized in that, The process for obtaining the soil pH anomaly index is as follows: During the monitoring period, soil pH data for each ecological sub-region was collected in real time using electrode-type pH sensors according to the time series. Cluster analysis was performed on the standardized pH data using the K-Means clustering algorithm: random initialization. Given a cluster center, assign each sample to the nearest cluster center, update the cluster center to the average of all samples in its cluster, and repeat the assignment and update until the cluster center no longer changes; Based on the clustering results, the cluster containing the most samples is considered the "normal" category, and samples from other clusters are considered potential outliers. For each time point, the distance from the pH value to the nearest cluster center is calculated to obtain the corresponding pH anomaly index. The average of the pH anomaly indices of all time points collected during the monitoring period is calculated to obtain the soil pH anomaly index of the corresponding ecological sub-region.

5. The ecological monitoring data integration and analysis method according to claim 1, characterized in that, Based on the assessment results, each ecological sub-region is divided into three levels: normal region, slightly degraded region, and severely degraded region, specifically including: Determine whether the soil degradation coefficient of each ecological sub-region is greater than or equal to a preset first threshold. If so, it is recorded as a severely degraded region. If not, determine whether the soil degradation coefficient is greater than a preset second threshold. If so, it is recorded as a slightly degraded region. If not, it is recorded as a normal region.

6. The method for integrated analysis of ecological monitoring data according to claim 1, characterized in that, The prediction of future soil degradation specifically includes: Based on the ecological sub-regions of slightly degraded areas, the soil moisture content anomaly index and soil pH anomaly index are extracted in each current ecological sub-region. The soil moisture content anomaly index and soil pH anomaly index are constructed into a comprehensive feature vector, which is used as the input of the machine learning model. The model output is the soil degradation level for each future monitoring period, including normal, slightly degraded and severely degraded.

7. The ecological monitoring data integration and analysis method according to claim 6, characterized in that, The process of constructing the machine learning model is as follows: Soil moisture content anomaly index and soil pH anomaly index are constructed into a comprehensive feature vector, which is used as input to a machine learning model to minimize the error between the predicted soil degradation level for each future monitoring period and the actual soil degradation level. The model is trained, and based on the trained machine learning model, the soil degradation level in the corresponding ecological sub-region for each future monitoring period is output. The machine learning model is a multi-source linear regression model.

8. The method for integrated analysis of ecological monitoring data according to claim 1, characterized in that, Based on the prediction results, for ecological sub-regions predicted to develop into severely degraded areas, the impact of precipitation on soil degradation is analyzed. Based on the analysis results, dynamic precipitation management is implemented for these ecological sub-regions, specifically including: Based on the prediction results, ecological sub-regions that are likely to develop into severely degraded areas in the future are marked. The time taken from the current moment to the future development into a severely degraded ecological sub-region is obtained, and the precipitation change curve over time is obtained for the corresponding time. It is determined whether there is a linear relationship between the ecological sub-regions that develop into severely degraded areas and the precipitation change curve over time. If there is a linear relationship, it is determined whether precipitation promotes soil degradation. If precipitation can prevent soil degradation, dynamic precipitation treatment is applied to the ecological sub-regions predicted to be severely degraded.

9. The method for integrated analysis of ecological monitoring data according to claim 8, characterized in that, The determination of whether precipitation promotes soil degradation specifically includes: Identify periods of increasing precipitation and obtain the corresponding soil degradation data for these periods. If the soil does not degrade further during periods of increasing precipitation, continue analyzing soil degradation during periods of decreasing precipitation. If the soil does not degrade further during periods of decreasing precipitation, it indicates that precipitation does not have a significant impact on current soil degradation. If the soil degrades further during periods of decreasing precipitation, it indicates that increasing precipitation can prevent further soil degradation. If soil degradation continues during periods of increasing precipitation, further analysis should be conducted on soil degradation during periods of decreasing precipitation. If soil degradation continues during periods of decreasing precipitation, it indicates that precipitation does not have a significant impact on current soil degradation. Otherwise, if soil degradation does not continue during periods of decreasing precipitation, it indicates that the increase in precipitation has failed to prevent soil degradation.

10. An ecological monitoring data integration and analysis system, characterized in that, An ecological monitoring data integration and analysis method as described in any one of claims 1-9, comprising: A region division module, which uniformly divides the target ecological monitoring area into multiple identical ecological sub-regions; The data analysis module collects soil moisture content and pH data in real time within each ecological sub-region during the monitoring period, and evaluates the soil quality within each ecological sub-region based on the degree of change in soil moisture content and pH during the monitoring period. The regional soil degradation degree classification module divides each ecological sub-region into three levels: normal region, slightly degraded region, and severely degraded region based on the assessment results. The model building module constructs a machine learning model based on the ecological sub-regions of the slightly degraded area to predict the future degree of soil degradation. The impact degree analysis and dynamic adjustment module analyzes the precipitation and its impact on soil degradation for ecological sub-regions predicted to develop into severely degraded areas based on the prediction results, and performs dynamic precipitation treatment on the ecological sub-regions based on the analysis results.

Images