Land and resources data management method and system

Abstract

The present invention discloses a land and resources data management method and system, and relates to the technical field of land and resources data management. It includes collecting periodic event data and land and resources use data of the target area; using time series analysis methods to extract the fluctuation law of periodic events and generate characteristic parameters; according to the periodic characteristic parameters, calculating the time window adjustment coefficient, dynamically constructing a resource management prediction model, so that the resource management prediction model can capture the short-term and long-term impacts of periodic events on land use; based on the prediction results, combining the land and resources data set to design a resource allocation optimization strategy, and visualize the output through a GIS system. The present invention provides a comprehensive, dynamic and efficient land and resources management method, which can collect and analyze the short-term and long-term impacts of periodic events on land use, and provide technical support for the scientific management of land resources.

Description

Technical Field

[0001] The present invention relates to the technical field of land and resources data management, in particular to a land and resources data management method and system. Background Art

[0002] Current land and resources data management technology mainly predicts land use through single historical data or static models, failing to fully consider the impact of periodic events (such as seasonal precipitation, freeze-thaw cycles, periodic floods, etc.), resulting in insufficient adaptability and accuracy of the prediction model.

[0003] Especially in areas prone to geological disasters and agricultural production areas, the impact of periodic events is significant, and existing methods are difficult to meet the requirements of dynamic management and optimal resource allocation. Summary of the invention

[0004] In view of the problem of neglecting the impact of periodic events on land use prediction and resource management in the above-mentioned background technology, the land and resources data management method and system of the present invention are proposed.

[0005] Therefore, the problem to be solved by the present invention is how to improve prediction accuracy and optimize resource allocation strategy.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides a land and resources data management method, which includes collecting periodic event data and land and resources use data of the target area from a geographic information system, a sensor network and a historical database, and fusing multi-source heterogeneous data through data cleaning and normalization technology; using a time series analysis method to extract the fluctuation law of periodic events, generate characteristic parameters, and use the basic period, fluctuation amplitude and trend change rate as the final output of the periodic characteristic parameters; according to the periodic characteristic parameters, calculating the time window adjustment coefficient, dynamically constructing a resource management prediction model, so that the resource management prediction model can capture the short-term and long-term impacts of periodic events on land use; based on the prediction results, combining the land and resources data set to design a resource allocation optimization strategy, and visualize the output through the GIS system to assist decision makers in formulating scientific land and resources management plans.

[0008] As a preferred solution of the land and resources data management method described in the present invention, after fusing multi-source heterogeneous data through data cleaning and normalization technology, the data from different sources are aligned and integrated according to time and space indexes to form a multidimensional data table.

[0009] As a preferred solution of the land and resources data management method described in the present invention, the method of extracting the fluctuation law of periodic events using the time series analysis method and generating characteristic parameters includes the following steps: denoising the original time series data, using wavelet decomposition and reconstruction to extract the main periodic characteristic parameters; performing frequency domain analysis on the processed time series data using fast Fourier transform to extract the frequency and amplitude of the main periodic components.

[0010] As a preferred solution of the land resources data management method of the present invention, wherein: the frequency domain analysis of the processed time series data using fast Fourier transform includes: using fast Fourier transform to analyze the dominant period and fluctuation amplitude of the data as follows:

[0011] ,

[0012] in, is the Fourier transform result at frequency f, is the power spectrum density at frequency f, which is used to determine the dominant period, is the total length of the time series data, f is the frequency variable, is the time series data after noise reduction, is the time index; is an imaginary unit, Represents the time domain signal time points; according to the basic cycle, an improved SARIMA model, namely a seasonal autoregressive integrated moving average model, is constructed, and the periodic event characteristic data is used as input, wherein the seasonal autoregressive integrated moving average model is as follows:

[0013] ,

[0014] in, is the periodic characteristic time series of the input, B is the lag operator, is the seasonal autoregressive coefficient polynomial, which represents the autoregressive effect of the long-term trend. It is a seasonal difference operation to eliminate the seasonal effect in the cyclical trend. is the seasonal moving average coefficient polynomial, which represents the average effect of short-term fluctuations, is the residual term, and s is the cycle length.

[0015] As a preferred solution of the land and resources data management method described in the present invention, wherein: according to the periodic characteristic parameters, calculating the time window adjustment coefficient includes the following steps: dividing the predicted time series into several time windows based on the periodic characteristic parameters; for each time window, calculating the time window adjustment coefficient.

[0016] As a preferred solution of the land resources data management method of the present invention, the time window adjustment coefficient is calculated as follows:

[0017] ,

[0018] in, is the adjustment factor, between 0 and 1, is the residual variance of the base period output by the SARIMA model, Assign weights to each time window, The basic cycle.

[0019] As a preferred solution of the land and resources data management method of the present invention, wherein: the design of resource allocation optimization strategy in combination with the land and resources data set includes: clarifying the goal of resource allocation optimization according to the generated resource management prediction model and the impact of periodic events on land use;

[0020] The objectives include: optimization of agricultural planting planning; rational allocation of disaster prevention resources; and adjustment of land use planning.

[0021] In the second aspect, the present invention provides a land and resources data management system, which includes: a data acquisition and fusion module, which is used to collect periodic event data and land and resources usage data of the target area from geographic information systems, sensor networks and historical databases, and fuse multi-source heterogeneous data through data cleaning and normalization technology; a feature extraction module, which is used to extract the fluctuation law of periodic events using time series analysis methods, generate characteristic parameters, and use the basic period, fluctuation amplitude and trend change rate as the final output of periodic characteristic parameters; a prediction model construction module, which is used to calculate the time window adjustment coefficient according to the periodic characteristic parameters, and dynamically construct a resource management prediction model, so that the resource management prediction model can capture the short-term and long-term impacts of periodic events on land use; a decision support module, which is used to design resource allocation optimization strategies based on prediction results and in combination with land and resources data sets, and output them through GIS system visualization to assist decision makers in formulating scientific land and resources management plans.

[0022] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the land and resources data management method as described in the first aspect of the present invention are implemented.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the land and resources data management method as described in the first aspect of the present invention are implemented.

[0024] The beneficial effects of the present invention are as follows: the present invention extracts periodic characteristic parameters through the fusion processing of multi-source heterogeneous data and time series analysis, and introduces the time window adjustment coefficient to dynamically construct a resource management prediction model, thereby effectively capturing the short-term and long-term impacts of periodic events on land use, solving the problem that traditional prediction methods are difficult to balance short-term fluctuations and long-term trends, and making the prediction model more flexible and accurate. In addition, based on the resource management prediction model, the present invention proposes targeted strategies for the optimal allocation of land resources, such as optimization of agricultural planting planning, rational allocation of disaster prevention resources, and dynamic adjustment of land use, and uses the GIS system to visualize the output of the optimization plan, which significantly improves the decision-making efficiency and scientificity. The present invention provides a comprehensive, dynamic and efficient land and resources management method that can collect and analyze the short-term and long-term impacts of periodic events on land use, and provide technical support for the scientific management of land resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 This is a flow chart of the land and resources data management method.

[0027] Figure 2 This is the structural diagram of the land and resources data management system. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0030] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0031] Example 1, reference Figure 1~Figure 2, which is the first embodiment of the present invention, and provides a land resources data management method, such as Figure 1 As shown, including,

[0032] S1: Collect periodic event data (such as precipitation, temperature, freeze-thaw cycle, etc.) and land and resources use data of the target area from geographic information systems (GIS), sensor networks and historical databases, and integrate multi-source heterogeneous data through data cleaning and normalization techniques to ensure data quality and consistency.

[0033] Specifically, first, it is necessary to clarify the main types of data that need to be collected, including periodic event data (precipitation, temperature, freeze-thaw cycles, etc.) and land and resources use data (land type, use distribution, geological information, etc.).

[0034] Among them, data sources include geographic information systems (GIS), sensor networks and historical databases.

[0035] For real-time sensor data, set the data collection frequency (such as once every hour or once a day) and use time stamps, and batch download relevant historical data from historical databases and GIS systems to ensure integrity.

[0036] All collected data are stored in a unified database (such as PostGIS or Hadoop HDFS), and a multidimensional data structure indexed by time and region is established to facilitate subsequent query and analysis.

[0037] After preprocessing and normalizing the collected data, the data from different sources are aligned and integrated according to time and space indexes to form a multidimensional data table. For example, the precipitation, temperature and land use data at a specific time point and region are associated.

[0038] Finally, the processed data set is divided into two categories:

[0039] Periodic event dataset: contains indicators such as precipitation, temperature, freeze-thaw cycles, etc.

[0040] Land and resources dataset: Contains information such as land use distribution and resource attributes for use in optimizing management strategies.

[0041] S2: Use time series analysis methods to extract the fluctuation patterns of periodic events and generate characteristic parameters.

[0042] S2.1: De-noise the original time series data, use wavelet decomposition and reconstruction, and extract the main periodic characteristic parameters.

[0043] Specifically, the periodic event data obtained in step S1 is subjected to noise reduction processing, and the original data is decomposed by wavelet transform to separate the high-frequency noise signal from the low-frequency trend signal to retain the main fluctuation information of the periodic characteristics. The specific formula is as follows:

[0044] ,

[0045] in, is the time series data after noise reduction, is the coefficient of wavelet decomposition, the coefficient of the jth layer and the kth position; is the wavelet basis function, the basis function of the jth layer and the kth position; J is the highest layer of the selected wavelet decomposition (corresponding to the different frequency components of the signal), Is the time index.

[0046] The denoised data is smoothed using the sliding average method to reduce the interference of short-term data fluctuations on the analysis of periodic patterns and ensure the stability and continuity of time series data.

[0047] S2.2: Use fast Fourier transform (FFT) to perform frequency domain analysis on the time series data processed in step S2.1, extract the frequency and amplitude of the main periodic components, and use this to determine the basic period of the time series.

[0048] Among them, the dominant period and fluctuation amplitude of the data analyzed using Fast Fourier Transform (FFT) are as follows:

[0049] ,

[0050] in, is the Fourier transform result at frequency f, is the power spectrum density at frequency f, which is used to determine the dominant period, is the total length of the time series data, f is the frequency variable, is an imaginary unit, , 2π is a constant, representing a complete cycle Represents the time domain signal a point in time.

[0051] Furthermore, according to the basic cycle, an improved SARIMA model, namely the seasonal autoregressive integrated moving average model, is constructed, and the characteristic data of periodic events are used as input to generate characteristic parameters of the basic cycle, amplitude and trend.

[0052] Preferably, the seasonal autoregressive integrated moving average model is as follows:

[0053] ,

[0054] in, is the periodic characteristic time series of the input, B is the lag operator, is the seasonal autoregressive coefficient polynomial, which represents the autoregressive effect of the long-term trend. It is a seasonal difference operation to eliminate the seasonal effect in the cyclical trend. is the seasonal moving average coefficient polynomial, which represents the average effect of short-term fluctuations, is the residual term, and s is the period length (the dominant period determined by FFT).

[0055] It can be seen that by introducing the dominant cycle length s extracted by FFT and dynamically adjusting the seasonal difference and autoregressive model parameters, the flexibility of model fitting can be improved.

[0056] S2.3: The basic period, fluctuation amplitude and trend change rate are taken as the final output of the periodic characteristic parameters, expressed as ,in, As the basic cycle, is the fluctuation range, It is the trend change rate, which is calculated by the long-term trend coefficient of the SARIMA model. The output data format adopts a structured form (such as JSON or tabular data) to facilitate seamless integration with other subsequent models or systems.

[0057] S3: Based on the periodic characteristic parameters, the time window adjustment coefficient is calculated and the resource management prediction model is dynamically constructed so that the resource management prediction model can capture the short-term and long-term impacts of periodic events on land use.

[0058] S3.1: Based on the periodic characteristic parameters output from step S2 , divide the predicted time series into several time windows, each time window length is , defined as follows:

[0059] ,

[0060] in, is the number of windows in a period (specified by the application scenario).

[0061] Assign initial weights to each time window. According to the characteristic parameters and trend rate of change Dynamic Adjustment:

[0062] ,

[0063] It can be seen that by combining the amplitude of periodic events and the trend change rate, dynamically determining window division and weight allocation, the combined impact of short-term fluctuations and long-term trends can be captured.

[0064] S3.2: For each time window, calculate the time window adjustment coefficient , the formula is:

[0065] ,

[0066] in, is the adjustment factor (between 0 and 1), The residual variance of the base period output by the SARIMA model.

[0067] S3.3: Build a dynamic resource management prediction model.

[0068] Using the time window adjustment coefficient calculated in step S3.2 and the traditional resource management prediction model output, dynamically build a resource management prediction model , so that it can reflect the impact of periodic events on land use:

[0069] ,

[0070] in, For the initial resource management forecast model output (which can be a preliminary model built based on traditional data analysis methods), the adjusted forecast values ​​will more accurately capture the dynamic impact of periodic events on land use.

[0071] S3.4: Revised resource management forecast results Integrate outputs for subsequent land use optimization and decision support.

[0072] S4: Based on the prediction results, combined with the land and resources dataset, design resource allocation optimization strategies, such as adjusting agricultural planting plans, allocating disaster prevention resources, or improving land use planning, and visualize the output through the GIS system to assist decision makers in formulating scientific land and resources management plans.

[0073] Specifically, according to the dynamic resource management prediction model generated in step S3 and the impact of periodic events on land use, the goal of resource allocation optimization is clarified. The goals may include:

[0074] Optimization of agricultural planting planning;

[0075] Rational allocation of disaster prevention resources;

[0076] Adjustment of land use planning, etc.

[0077] For example, crop type and distribution optimization: combining information such as land use distribution, soil quality, and climate data to dynamically adjust crop planting areas. For example, based on predicted seasonal precipitation changes, if a region is expected to experience longer periods of drought in the future, drought-tolerant crops can be recommended or irrigation resource allocation in the region can be improved.

[0078] Optimal allocation of agricultural resources: Optimize the use of water resources according to water resource distribution and climate change, improve water use efficiency, and avoid planting water-intensive crops in water-scarce areas.

[0079] Disaster risk area identification: Identify high-risk areas through land use data and climate forecast data. For example, if the precipitation and freeze-thaw cycles in a certain area show extreme changes, the area will need more disaster response resources such as flood control and freeze-thaw prevention.

[0080] Spatial allocation of resource configuration: Based on the GIS system, disaster prevention resources (such as emergency supplies, facilities, personnel, etc.) can be allocated to disaster-prone areas as needed and optimized spatially to ensure efficient use of resources and rapid response.

[0081] Dynamically adjust land use: By combining land quality data, resource availability, and environmental forecasts, land use can be adjusted dynamically. For example, if some agricultural land can no longer be cultivated efficiently due to climate change or land degradation, the land can be adjusted to ecological protection areas, urban expansion areas, or other uses.

[0082] Balance between ecological protection and land development: Optimize the distribution of ecological protection areas and development areas to ensure the sustainability of the ecological environment while taking into account the economic development needs of the region. The optimal allocation of resources can be achieved through flexible adjustment of land use.

[0083] Furthermore, this embodiment also provides a land and resources data management system, including:

[0084] Data collection and fusion module, which is used to collect periodic event data and land resource use data of the target area from geographic information systems, sensor networks and historical databases, and fuse multi-source heterogeneous data through data cleaning and normalization technology;

[0085] The feature extraction module is used to extract the fluctuation law of periodic events by using the time series analysis method, generate characteristic parameters, and use the basic period, fluctuation amplitude and trend change rate as the final output of the periodic characteristic parameters;

[0086] A prediction model building module, used to calculate the time window adjustment coefficient according to the periodic characteristic parameters, and dynamically build a resource management prediction model so that the resource management prediction model can capture the short-term and long-term impacts of periodic events on land use;

[0087] The decision support module is used to design resource allocation optimization strategies based on prediction results and combined with land and resources data sets, and to assist decision makers in formulating scientific land and resources management plans through GIS system visualization output.

[0088] This embodiment also provides a computer device suitable for the land and resources data management method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the land and resources data management method proposed in the above embodiment.

[0089] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.

[0090] The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0091] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for managing land and resources data as proposed in the above embodiment is implemented.

[0092] In summary, the present invention extracts periodic characteristic parameters through the fusion processing of multi-source heterogeneous data and time series analysis, and introduces the time window adjustment coefficient to dynamically construct a resource management prediction model, thereby effectively capturing the short-term and long-term impacts of periodic events on land use, solving the problem that traditional prediction methods are difficult to balance short-term fluctuations and long-term trends, and making the prediction model more flexible and accurate. In addition, based on the resource management prediction model, the present invention proposes targeted strategies for the optimal allocation of land resources, such as optimization of agricultural planting planning, rational allocation of disaster prevention resources, and dynamic adjustment of land use, and uses the GIS system to visualize the output of the optimization plan, which significantly improves the decision-making efficiency and scientificity. The present invention provides a comprehensive, dynamic and efficient land and resources management method that can collect and analyze the short-term and long-term impacts of periodic events on land use, and provide technical support for the scientific management of land resources.

[0093] Example 2, referring to Table 1 and Table 2, is the second example of the present invention. This example provides a land and resources data management method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0094] To verify the present invention, an experiment on land and resources management optimization based on periodic event data was carried out in a coastal area (target area). The selected periodic events include precipitation, temperature and freeze-thaw cycle, and the land and resources use data include land type, use distribution and geological information.

[0095] The specific steps used in this experiment are as follows:

[0096] The precipitation, temperature, freeze-thaw cycle, and land use data of the target area over the past 10 years were collected through a geographic information system (GIS), a regional sensor network, and a historical database. Real-time sensor data was collected on a daily basis, and historical data was downloaded in batches and stored in a PostGIS database.

[0097] The collected data are cleaned to remove outliers and missing values, and multi-source heterogeneous data are fused through normalization technology, and integrated into multidimensional data tables by time and regional indexes.

[0098] Wavelet transform was used to denoise the precipitation and temperature time series and separate high-frequency noise signals from low-frequency trend signals. Subsequently, the frequency and amplitude of the main periodic components were extracted by fast Fourier transform (FFT) to generate characteristic parameters, including the basic period (3 months), fluctuation amplitude (20%) and trend change rate (2%).

[0099] Based on the extracted periodic characteristic parameters, an improved SARIMA model is constructed, and the time window adjustment coefficient is calculated to reflect the combined impact of short-term and long-term periodic events. The forecast results show that the precipitation in the target area will decrease by 15% in the second and third months in the next 6 months, and the temperature fluctuation rate will increase by 10%.

[0100] According to the prediction results, combined with land use distribution and resource attribute data, a resource allocation optimization plan is designed. Some experimental data are as follows:

[0101] Table 1 Periodic event data

[0102] Parameter name Precipitation (mm) Air temperature (°C) Freeze-thaw cycle (days) Basic cycle (month) Fluctuation range (%) Trend change rate (%) Month 1 120 25 10 3 15 1.5 Month 2 100 27 12 3 20 2.0 Month 3 80 30 15 3 25 2.5 Month 4 90 28 14 3 18 1.8 Month 5 110 26 11 3 12 1.2 Month 6 130 24 9 3 10 1.0

[0103] Table 2 Resource allocation optimization results

[0104] Optimization goals Original Configuration Optimized configuration Improvement Applicable areas Main Function Irrigation resource allocation (tons) 500 750 +50% High risk areas Mitigating the effects of drought Drought-tolerant crop planting area (mu) 2000 3000 +50% High risk areas Improve agricultural planting efficiency Disaster prevention material reserves (unit) 100 150 +50% Frequent freeze-thaw areas Improving disaster response capabilities Area of ​​ecological protection area (mu) 1000 1200 +20% Inefficient land use Promote ecological environment restoration

[0105] As can be seen from Table 1, the main characteristic parameters of periodic events are accurately extracted by the method of the present invention. For example, the basic period of precipitation is 3 months, and the fluctuation amplitude shows a trend of increasing month by month. This shows that the combination of time series analysis and SARIMA model can effectively predict the characteristics of future climate fluctuations. At the same time, the time window adjustment coefficient enables the model to dynamically capture the combined impact of short-term fluctuations (such as a sharp drop of 15% in precipitation in the third month) and long-term trends (the temperature trend change rate is stable at 2%).

[0106] As can be seen from Table 2, the resource allocation optimized based on the prediction results significantly improved the efficiency of resource utilization. For example, increasing irrigation resources by 50% in high-risk areas effectively alleviated the threat of drought to agricultural planting; the planting area of ​​drought-resistant crops was expanded by 50%, further improving the agricultural output efficiency of the target area. In addition, the ecological environment was also improved by converting inefficient land into ecological protection areas. These optimization effects are clearly visualized through the GIS system, providing regional managers with intuitive and scientific decision-making basis.

[0107] Compared with the existing technology, the method of the present invention has significant advantages in data fusion, feature extraction and dynamic prediction. In particular, the introduction of the time window adjustment coefficient breaks through the limitation of the traditional model that it cannot dynamically balance short-term fluctuations and long-term trends, making the prediction results more timely and accurate, thus providing more efficient technical support and optimization solutions for land and resources management in complex environments.

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A land and resources data management method, characterized in that: include: S1: Collect periodic event data and land resource use data of the target area from geographic information systems, sensor networks and historical databases, and fuse multi-source heterogeneous data through data cleaning and normalization technology; then align and integrate data from different sources according to time and space indexes to form a multidimensional data table; S2: Use time series analysis methods to extract the fluctuation patterns of periodic events, generate characteristic parameters, and use the basic period, fluctuation amplitude and trend change rate as the final output of periodic characteristic parameters; The following steps are involved: S2.1: De-noise the original time series data, use wavelet decomposition and reconstruction to extract periodic characteristic parameters; The specific formula for denoising the original time series data is as follows: ， in, is the time series data after noise reduction, is the coefficient of wavelet decomposition, the coefficient of the jth layer and the kth position; is the wavelet basis function, the basis function of the jth layer and the kth position; J is the highest layer of the selected wavelet decomposition, is the time index; S2.2: Perform frequency domain analysis on the time series data processed in step S2.1 using fast Fourier transform, extract the frequency and amplitude, and use this to determine the basic period of the time series; Among them, the dominant period and fluctuation amplitude of the data analyzed using fast Fourier transform are as follows: ， in, is the Fourier transform result at frequency f, is the power spectrum density at frequency f, which is used to determine the dominant period, is the total length of the time series data, f is the frequency variable, is an imaginary unit, , 2π is a constant, representing a complete cycle Represents the time domain signal time point; According to the basic cycle, the SARIMA model is constructed, and the characteristic data of periodic events are used as input to generate the basic cycle, fluctuation amplitude and trend change rate; The SARIMA model is as follows: ， in, is the periodic characteristic time series of the input, B is the lag operator, is the seasonal autoregressive coefficient polynomial, which represents the autoregressive effect of the long-term trend. It is a seasonal difference operation to eliminate the seasonal effect in the cyclical trend. is the seasonal moving average coefficient polynomial, which represents the average effect of short-term fluctuations, is the residual term, s is the cycle length; S2.3: The basic period, fluctuation amplitude and trend change rate are taken as the final output of the periodic characteristic parameters, expressed as ,in, As the basic cycle, is the fluctuation range, is the trend change rate, which is calculated by the long-term trend coefficient of the SARIMA model; the output data format adopts a structured form to facilitate seamless connection with other subsequent models or systems; S3: According to the periodic characteristic parameters, the time window adjustment coefficient is calculated, and the resource management prediction model is dynamically constructed so that the resource management prediction model can capture the short-term and long-term impacts of periodic events on land use; including the following steps: S3.1: Based on the periodic characteristic parameters output from step S2 , divide the predicted time series into several time windows, each time window length is , defined as follows: ， in, is the number of windows in the period; Assign initial weights to each time window. According to the characteristic parameters and trend rate of change Dynamic Adjustment: ； S3.2: For each time window, calculate the time window adjustment coefficient , the formula is: ， in, is the regulating factor, The residual variance of the base period output by the SARIMA model; S3.3: Build a dynamic resource management prediction model; Using the time window adjustment coefficient calculated in step S3.2 and the traditional resource management prediction model output, dynamically build a resource management prediction model , so that it can reflect the impact of periodic events on land use: ， in, Provides initial resource management forecast model output; S3.4: Revised resource management forecast results Integrate outputs for subsequent land use optimization and decision support; S4: Based on the prediction results, combined with the land and resources data set, design resource allocation optimization strategies, adjust agricultural planting plans, allocate disaster prevention resources or improve land use planning, and visualize the output through the GIS system to assist decision makers in formulating scientific land and resources management plans.

2. A land and resources data management system, based on the land and resources data management method according to claim 1, characterized in that: Also includes: Data collection and fusion module, which is used to collect periodic event data and land resource use data of the target area from geographic information systems, sensor networks and historical databases, and fuse multi-source heterogeneous data through data cleaning and normalization technology; The feature extraction module is used to extract the fluctuation law of periodic events by using the time series analysis method, generate characteristic parameters, and use the basic period, fluctuation amplitude and trend change rate as the final output of the periodic characteristic parameters; A prediction model building module, used to calculate the time window adjustment coefficient according to the periodic characteristic parameters, and dynamically build a resource management prediction model so that the resource management prediction model can capture the short-term and long-term impacts of periodic events on land use; The decision support module is used to design resource allocation optimization strategies based on prediction results and combined with land and resources data sets, and to assist decision makers in formulating scientific land and resources management plans through GIS system visualization output.

3. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the land and resources data management method described in claim 1 are implemented.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the land and resources data management method according to claim 1 are implemented.

Images