Chaos theory-based desertification evolution prediction method, system, equipment and medium

Abstract

The invention relates to the technical field of desertification comprehensive treatment, in particular to a desertification evolution prediction method, system, equipment and medium based on the chaos theory, and the method comprises the following steps: S1, collecting the historical and real-time data of a desertification region, and obtaining the quantification index of the desertification degree and the variation trend; s2, analyzing nonlinear characteristics of desertification monitoring observation data by using a chaos theory, identifying chaos behaviors in a system, and performing phase-space reconstruction on the quantization indexes of the desertification degree and the variation trend obtained in the S1; and S3, establishing a model based on a chaos theory, and simulating a desertification evolution process by taking the desertification monitoring data as an input boundary condition to obtain a prediction result of desertification evolution. According to the method, the chaos theory is combined to establish the regional desertification evolution network model based on the chaos theory, and the established chaos theory model well solves the problem of regional desertification trend prediction by performing phase-space reconstruction on the past regional desertification evolution characteristic indexes.

Description

Technical Field

[0001] The present invention relates to the technical field of comprehensive desertification control, and specifically to a method, system, device and medium for predicting desertification evolution based on chaos theory. Background Art

[0002] The first step in comprehensive desertification control is to accurately and scientifically judge and predict the formation process and evolution trend of desertification, so as to more accurately match the planning scheme of control facilities. Desertification is a complex natural and socio-economic process, and its evolution is affected by various factors, including climate change, human activities, etc.

[0003] CN112733587A discloses a method for monitoring the evolution of desertification process, which uses WebGis map to locate the target area and obtain the plane image of the target area, divides the plane image according to the grid-like dividing lines to obtain several grid-like areas, pre-buries remote monitoring modules at the positions of the target area corresponding to each grid-like area n to obtain various local information at these positions, and all the remote monitoring modules are communicatively interconnected with the data center. Each remote monitoring module will transmit the local information back to the data center in real time, combines the data such as soil moisture, air temperature, humidity, wind speed, wind direction, light meteorological information, and plant stem flow of key plants at the monitoring points in the desertification area, and displays it by combining the WEBGIS method, and predicts the soil moisture in the desertification area through the algorithm of BP neural network. Although BP neural network is used for prediction, its data collection and processing capabilities are easily affected by the environment itself, and traditional desertification prediction methods often based on linear models are difficult to accurately reflect the non-linear characteristics and complexity of the desertification system, thus affecting its prediction accuracy. Summary of the Invention

[0004] Aiming at the problem of low prediction accuracy of desertification in the prior art, the present invention provides a method, system, device and medium for predicting desertification evolution based on chaos theory.

[0005] The present invention is realized through the following technical solutions: A method for predicting desertification evolution based on chaos theory includes the following steps: S1, collect historical and real-time data of the desertification area, and obtain the quantization index of the desertification degree and its change trend; S2, use chaos theory to analyze the non-linear characteristics of the desertification monitoring data, identify the chaotic behavior in the system, and at the same time perform phase space reconstruction on the quantization index of the desertification degree and its change trend obtained in S1; S3, establish a model based on chaos theory, use the desertification monitoring data as the input boundary condition to simulate the desertification evolution process, and obtain the prediction result of the desertification evolution.

[0006] Preferably, in S1, the underlying surface data of desertification areas with a satellite remote sensing resolution of 1 m or more is obtained through remote sensing monitoring and ground observation.

[0007] Preferably, in S1, the quantitative index of the degree and trend of desertification is the ecological structure index.

[0008] Preferably, in S2, quantitative methods are used to analyze the chaotic characteristics of desertification monitoring and observation data, including correlation dimension, maximum Lyapunov exponent, and Kolmogorov entropy.

[0009] Preferably, in S2, the specific steps for phase space reconstruction of the quantitative index of the degree and trend of desertification are as follows: embedding the collected time series into an m-dimensional phase space with a delay time of τ, and the reconstructed m-dimensional state space is equivalent to the geometric characteristics of the original chaotic dynamic system; selecting historical data as the model input data, monitoring data as the control data, and the maximum Lyapunov exponent as the basis for verifying the chaotic characteristics of the model to verify the chaotic characteristics of the model. The maximum Lyapunov exponent algorithm can analyze the complexity of chaotic time series, and the closer its value is to 1, the stronger the chaotic characteristics of the time series.

[0010] Preferably, the delay time τ is obtained by the mutual information method, and the embedding dimension m is obtained by the false nearest neighbor method.

[0011] Preferably, in S3, numerical solution of the chaotic model is carried out, and then the obtained result is back-translated into ecological indicators that may change in desertification evolution.

[0012] Preferably, targeted treatment measures are formulated according to the ecological indicators that may change in desertification evolution.

[0013] A desertification evolution prediction system based on chaos theory includes a collection module, a preprocessing module, an analysis module, and a calculation module. The collection module is used to collect historical and real-time data of desertification areas. The preprocessing module is used to obtain the quantitative index of the degree and trend of desertification. The analysis module is used to analyze the nonlinear characteristics of desertification monitoring and observation data using chaos theory, identify the chaotic behavior in the system, and at the same time perform phase space reconstruction on the obtained quantitative index of the degree and trend of desertification. The calculation module is used to establish a model based on chaos theory, simulate the desertification evolution process with desertification monitoring data as the input boundary conditions, and obtain the prediction results of desertification evolution.

[0014] An electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method are implemented.

[0015] A storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the method are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: A method for predicting desertification evolution based on chaos theory of the present invention establishes a regional desertification evolution network model based on chaos theory by combining chaos theory. It requires less training data. By performing phase space reconstruction on the characteristic index of desertification evolution in the past in this region, the established chaos theory model better solves the problem of predicting the trend of regional desertification. The method of the present invention can comprehensively evaluate the effects of different ecological governance measures, realize the quantitative optimization of governance measures, and improve the systematicness and effectiveness of ecological governance. Through multi-objective optimization, the costs, benefits, and environmental impacts of different governance measures can be balanced, providing a scientific and reasonable governance plan for decision-makers and reducing the losses caused by desertification.

[0017] By using chaos theory to analyze the non-linear characteristics of desertification monitoring data, the present invention can more accurately identify the chaotic behavior in the system. By performing phase space reconstruction and establishing a model based on chaos theory, it can more realistically simulate the desertification evolution process, thereby improving the accuracy of prediction results.

[0018] Furthermore, the high-resolution desertification area underlying surface data obtained by remote sensing monitoring and ground observation is fully utilized, which helps to more comprehensively understand the current situation and trend of desertification. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flowchart of the method for predicting desertification evolution based on chaos theory of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following further elaborates on the present invention with specific embodiments, which are explanations rather than limitations of the present invention.

[0021] The present invention discloses a method for predicting desertification evolution based on chaos theory. Referring to Figure 1 , it includes the following steps: A method for predicting desertification evolution based on chaos theory includes the following steps: S1. Collect historical and real-time data of the desertification area, and obtain a quantitative index of the degree and change trend of desertification; S2. Use chaos theory to analyze the non-linear characteristics of desertification monitoring and observation data, identify the chaotic behavior in the system, and at the same time perform phase space reconstruction on the quantitative index of the degree and change trend of desertification obtained in S1; S3. Establish a model based on chaos theory, use the desertification monitoring data as the input boundary conditions to simulate the desertification evolution process, and obtain the prediction results of desertification evolution.

[0022] Preferably, in S1, obtain the underlying surface data of desertification areas with a satellite remote sensing resolution of 1 m or more through remote sensing monitoring and ground observation.

[0023] Preferably, in S1, the quantification index of the desertification degree and its change trend is the ecological structure index.

[0024] Preferably, in S2, adopt a quantitative method to analyze the chaotic characteristics of desertification monitoring and observation data, including correlation dimension, maximum Lyapunov exponent, and Kolmogorov entropy.

[0025] Preferably, in S2, the specific steps for phase space reconstruction of the quantification index of desertification degree and its change trend are as follows: Embed the collected time series into an m-dimensional phase space with a delay time of τ, and the reconstructed m-dimensional state space is equivalent to the geometric characteristics of the original chaotic dynamic system; Select historical data as the model input data, monitoring data as the control data, and the maximum Lyapunov exponent as the basis for verifying the chaotic characteristics of the model to verify the chaotic characteristics of the model. The maximum Lyapunov exponent algorithm can analyze the complexity of chaotic time series, and the closer its value is to 1, the stronger the chaotic characteristics of the time series.

[0026] Preferably, in S3, numerically solve the chaotic model, and then back-translate the obtained results into ecological indicators that may change in desertification evolution.

[0027] Preferably, formulate targeted control measures according to the ecological indicators that may change in desertification evolution.

[0028] A method for predicting desertification evolution based on chaos theory according to the present invention deeply explores the internal dynamic characteristics of desertification formation and evolution based on non-linear analysis methods, constructs a chaotic phase space containing rich information, provides an excellent feature space for predicting the formation and governance evolution trend of desertification, and thus can perform feature dimensionality reduction extraction on the feature space, fill the extracted dimensionality-reduced features into the training set, and use the filled training set to train a machine learning model, thereby establishing a prediction model for the formation and governance evolution trend of desertification, and using this model to accurately predict the desertification process of a certain area.

[0029] Embodiment S1. Collect historical and real-time data of desertification areas, and obtain the underlying surface data of desertification areas with a satellite remote sensing resolution of 1 km or more through remote sensing monitoring and ground observation. This data is preferably long-term data, including but not limited to the vegetation coverage of desertification areas under long time series, the number of key protected organisms, etc.

[0030] Calculate the quantitative index value reflecting the degree of desertification and its change trend - the ecological structure index (ES). The ecological structure index consists of an index library of three indicators: the vegetation coverage index, the key protected biota index, and the vegetation net primary productivity index, all of which are general-purpose indicators. The specific calculation formula for the ecological structure index is as follows: Ecological Structure Index (ES) = 0.5 × Vegetation Coverage Index + 0.2 × Key Protected Biota Index + 0.3 × Vegetation Net Primary Productivity Index.

[0031] Among them, the vegetation coverage is specifically evaluated and calculated with reference to the "Measures for the Evaluation of Regional Ecological Quality (Trial)".

[0032] In the formula: C—Vegetation Coverage Index; —Normalization coefficient of the vegetation coverage index, with a reference value of 121.16; —Average value of the monthly maximum NDVI of pixels from July to September in the evaluation year, dimensionless (where NDVI (Normalized Difference Vegetation Index) is an indicator used to quantify the growth status and vitality of vegetation, and it is calculated by comparing the intensities of red light and near-infrared light reflected by plants); n—Number of regional pixels, in pieces.

[0033] The key protected biota index is the number of species of higher plants, mammals, birds, reptiles, and amphibians recorded in the evaluation area that meet the "List of National Key Protected Wild Animals" and the "List of National Key Protected Wild Plants", and is used to characterize the protection status of biological species in the evaluation area. It is specifically evaluated and calculated with reference to the "Measures for the Evaluation of Regional Ecological Quality (Trial)".

[0034]

[0035] In the formula: —Key Protected Biota Index; —Normalization coefficient of the key protected biota index, with a reference value of 0.1510; —Number of species of higher plants, mammals, birds, reptiles, and amphibians listed in the "List of National Key Protected Wild Animals" and the "List of National Key Protected Wild Plants" in the evaluation area, in species.

[0036] The vegetation net primary productivity index represents the amount of organic matter accumulated by green plants per unit time and per unit area. It is the remaining part after subtracting autotrophic respiration (RA) from the total amount of organic matter produced by plant photosynthesis (Gross Primary Productivity, GPP), also known as net primary productivity. Unit: g•C / m 2 .

[0037] S2, using chaos theory to analyze the nonlinear characteristics of desertification data, identify chaotic behavior in the system, and simultaneously perform phase space reconstruction on the observed sequence in the time domain. Specifically, the maximum Lyapunov exponent is used for chaos identification. A Lyapunov exponent greater than zero highly depends on the initial conditions, which is a most common feature of chaotic behavior. When the Lyapunov exponent of the system is positive, the system will exhibit a chaotic state; when the Lyapunov exponent is negative, the system will exhibit a stable state. By calculating the Lyapunov exponent, it can be determined whether the system is in a chaotic state. The specific calculation is implemented by writing a Lyapunov exponent estimation algorithm using matlab code.

[0038] Phase space reconstruction: Treat the observed values at certain fixed time delay points as new dimensions, so that an equivalent phase space to the original system can be constructed through the "embedding" method. In this space, the original dynamic system can be restored and the properties of its attractor can be studied. Specifically, the phase space reconstruction can be described as follows: Let the chaotic time series be x1, x2, …, x N−1 , x N , for x t (t = 1, 2, …, N−(m−1)τ), make the following transformation: x t =(x t , x (t+τ) , x (t+2τ) , …, x [t+(m−1)τ )T In the formula: τ is the delay time; m is the embedding dimension. For N data points, by assigning the delay time τ and the embedding dimension m, N−(m−1)τ vectors or phase points can be reconstructed. Therefore, if the length of the predicted time series is L, the number of required data points is L+(m−1)τ.

[0039] According to the phase space reconstruction method, convert the chaotic time series x1, x2, …, x N−1 , x N into a new data space with a delay of τ and a dimension of m, that is

[0040] In the formula, each column represents a vector or a phase point. The mutual information method is selected to obtain the delay time. The following formula shows the functional relationship between the mutual information of the chaotic time series \(x_1, x_2, \cdots, x_{N - 1}, x\) and the delay time. The first minimum point of the mutual information function is taken as the delay time:

[0041] In the formula: \(P(x\) t ) is the probability of \(x\) t appearing in the time series \(x_1, x_2, \cdots, x\) N−1 , \(x\) N ; \(P(x\) t+τ ) is the probability of \(x\) t+τ appearing in the time series \(x\) 1+τ , \(x\) 2+τ , \(\cdots, x\) N−1+τ , \(x\) N+τ ; \(P(x\) t , \(x\) t+τ ) is the joint probability of \(x\) t and \(x\) t+τ appearing simultaneously in the time series \(x_1, x_2, \cdots, x\) N−1 , \(x\) N and \(x\) 1+τ , \(x\) 2+τ , \(\cdots, x\) N−1+τ , \(x\) N+τ .

[0042] The false nearest neighbor method is selected to obtain the embedding dimension. From a geometric perspective, the observed chaotic time series is actually the projection of the system's motion trajectory in a high-dimensional phase space onto a low-dimensional space. During the projection process, the trajectory will be distorted to some extent. Points that were not adjacent in the high-dimensional phase space may become adjacent points after being projected into the low-dimensional space, and these points are called false nearest neighbor points. The reconstruction of the phase space actually restores the chaotic motion trajectory. As the embedding dimension increases, the original system's motion trajectory will continuously unfold, and the false nearest neighbor points will gradually disappear.

[0043] After the phase space of the chaotic time series is reconstructed, for the phase point \(X(t)=(x\) t , \(x\) (t+τ) , \(x\) (t+2τ) , \(\cdots, x\) [t+(m−1)τ] ) in the space, there is a nearest neighbor point, and the distance between the two phase points is . When the dimension increases to \(m + 1\), the distance between these two points will change, and the changed distance is

[0044] If \(R\) m+1 is greater than \(R\) mIt is much larger, which can be considered to be caused by the fact that two points that were not originally adjacent in the high-dimensional phase space are projected into the low-dimensional space and become adjacent points. Thus, we have:

[0045] If S m > S, then X (t) and X j (t) is the pseudo-nearest neighbor point, where S is the threshold value.

[0046] For chaotic time series data, starting from the embedding dimension m = 2, calculate the ratio of pseudo-nearest neighbor points or the number of pseudo-nearest neighbor points. Increase the embedding dimension and recalculate until the ratio of pseudo-nearest neighbor points is less than 5% or the number of pseudo-nearest neighbor points no longer decreases. At this time, the embedding dimension can be considered to be able to fully unfold the chaotic motion trajectory, that is, the most appropriate embedding dimension.

[0047] The specific implementation of phase space reconstruction is achieved by writing a numerical calculation algorithm in Matlab.

[0048] After obtaining the optimal delay time τ and embedding dimension m of the time series, select historical data as the model input data and monitoring data as the control data, and calculate their largest Lyapunov exponents respectively using the small data method. Judge the strength of the chaotic characteristics of the time series according to the value of the largest Lyapunov exponent of the time series.

[0049] S3, abstract the current situation monitoring data and collected information of desertification in a certain area into the model input boundary conditions, and use the chaotic theory model to calculate its evolution process. For example, calculate the ecological structure index of a certain area from the remote sensing monitoring data in N years. After data training, perform phase space reconstruction and modeling, and verify the data in the following N years. Use the autocorrelation method to calculate that the delay time is 6. Since the correlation integral of the chaotic time series decays exponentially, its correlation dimension, as the power exponent of the correlation integral, gradually tends to a fixed value as the embedding dimension increases. After reaching a certain specific embedding dimension, it basically no longer increases. Therefore, it can be judged that this time series is a chaotic series.

[0050] Use the trained chaotic model to numerically solve the subsequent desertification situation in this area, analyze the change of its ecological structure index, and then translate the calculation result into the concrete result of desertification evolution, and deduce the possible changes in the vegetation coverage index and key biological protection index, so as to propose targeted control measures.

[0051] The present invention also discloses a desertification evolution prediction system based on chaos theory, which includes a collection module, a preprocessing module, an analysis module and a calculation module. The collection module is used to collect historical and real-time data of desertified areas. The preprocessing module is used to obtain a quantitative index of the degree of desertification and its change trend. The analysis module is used to analyze the nonlinear characteristics of desertification monitoring and observation data by using chaos theory, identify the chaotic behavior in the system, and at the same time perform phase space reconstruction on the obtained quantitative index of the degree of desertification and its change trend. The calculation module is used to establish a model based on chaos theory, simulate the desertification evolution process with the desertification monitoring data as the input boundary condition, and obtain the prediction result of the desertification evolution.

[0052] The present invention also discloses an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method are implemented.

[0053] The present invention also discloses a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method are implemented.

[0054] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be repeated here.

[0055] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0056] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0057] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal and method can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0058] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0059] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0060] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0061] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses, and computer program products according to embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0062] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0063] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps of the functions specified in one block or a plurality of blocks.

[0064] The foregoing are only preferred embodiments of the present invention, and are not intended to limit the technical solutions of the present invention. Those skilled in the art should understand that, without departing from the spirit and principles of the present invention, the technical solutions may be subject to several simple modifications and substitutions, and these modifications and substitutions also fall within the protection scope covered by the claims.

Claims

1. A method for predicting the evolution of desertification based on the theory of chaos, characterized in that It includes the following steps: S1. Collect historical and real-time data of desertification areas, and obtain a quantitative index of the degree and change trend of desertification; S2. Use chaos theory to analyze the nonlinear characteristics of desertification monitoring and observation data, identify chaotic behaviors in the system, and at the same time perform phase space reconstruction on the quantitative index of the degree and change trend of desertification obtained in S1; S3. Establish a model based on chaos theory, use desertification monitoring data as input boundary conditions to simulate the desertification evolution process, and obtain the prediction results of desertification evolution.

2. The desertification evolution prediction method based on chaos theory according to claim 1, characterized in that In S1, obtain the underlying surface data of desertification areas with a satellite remote sensing resolution of 1m or more through remote sensing monitoring and ground observation.

3. The desertification evolution prediction method based on the theory of chaos according to claim 1, characterized in that In S1, the quantitative index of the degree and change trend of desertification is the ecological structure index.

4. The desertification evolution prediction method based on chaos theory according to claim 1, characterized in that In S2, use quantitative methods to analyze the chaotic characteristics of desertification monitoring and observation data, including correlation dimension, maximum Lyapunov exponent, and Kolmogorov entropy.

5. The desertification evolution prediction method based on chaos theory according to claim 1, characterized in that In S2, the specific steps for performing phase space reconstruction on the quantitative index of the degree and change trend of desertification are as follows: Embed the collected time series into an m-dimensional phase space with a delay time of τ. The reconstructed m-dimensional state space is equivalent to the geometric characteristics of the original chaotic dynamic system; Select historical data as model input data, monitoring data as control data, and the maximum Lyapunov exponent as the basis for verifying the chaotic characteristics of the model to verify the chaotic characteristics of the model. The maximum Lyapunov exponent algorithm can analyze the complexity of chaotic time series. The closer its value is to 1, the stronger the chaotic characteristics of the time series.

6. The desertification evolution prediction method based on the theory of chaos according to claim 5, characterized in that The delay time τ is obtained by the mutual information method, and the embedding dimension m is obtained by the false nearest neighbor method.

7. The desertification evolution prediction method based on chaos theory according to claim 1, characterized in that In S3, perform numerical solution on the chaotic model, and then reverse translate the obtained result into ecological indicators that may change in desertification evolution.

8. A desertification evolution prediction system based on chaos theory, characterized in that, It includes a collection module, a preprocessing module, an analysis module, and a calculation module. The collection module is used to collect historical and real-time data of desertification areas. The preprocessing module is used to obtain a quantitative index of the degree and change trend of desertification. The analysis module is used to use chaos theory to analyze the nonlinear characteristics of desertification monitoring and observation data, identify chaotic behaviors in the system, and at the same time perform phase space reconstruction on the obtained quantitative index of the degree and change trend of desertification. The calculation module is used to establish a model based on chaos theory, use desertification monitoring data as input boundary conditions to simulate the desertification evolution process, and obtain the prediction results of desertification evolution.

9. An electronic device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method described in any one of claims 1 to 7.

Images