Method and system for simulating and predicting habitat suitability of lake wetland migrant birds based on CA-Markov model

Abstract

The invention belongs to the technical field of ecological environment and water conservancy, and particularly provides a lake wetland migrant bird habitat suitability simulation and prediction method and system based on a CA-Markov model.The method comprises the steps that lake wetland migrant bird habitat element types, lake terrain data and daily scale site water level data are obtained; hydrological situation indexes of the lake wetland are obtained through an inverse distance weight space interpolation method; screening main hydrological situation indexes influencing the habitat elements of the migrant birds, and establishing a fitting relationship between the hydrological situation indexes and the habitat elements of the migrant birds; a CA-Markov model is adopted to simulate and predict habitat elements of the migrant birds at the next moment, simulated plant types and rest land types are used as habitat elements of habitat suitability, and the habitat suitability of the migrant birds is obtained by calculating HSI indexes. The method provides important technical support for evaluation of the suitable habitat of the migrant birds in the lake wetland and protection of biodiversity.

Description

Technical Field

[0001] This invention belongs to the field of ecological environment and water conservancy technology, specifically, it relates to a method and system for simulating and predicting the suitability of migratory bird habitats in lake wetlands based on the CA-Markov model. Background Technology

[0002] Lake wetlands are crucial habitats for migratory birds, but their ecosystems are vulnerable to threats from climate change and human activities. In recent years, the shrinking of global wetland area, water quality deterioration, and habitat fragmentation have intensified, directly impacting the survival environment of migratory bird populations and destroying suitable habitats for them. Therefore, conducting habitat simulation and prediction for migratory birds in lake wetlands is of great significance for maintaining wetland biodiversity.

[0003] The suitability of migratory bird habitats in lake wetlands is influenced by multiple factors, exhibiting significant spatiotemporal heterogeneity. Generally, migratory bird habitat elements include foraging plant types and resting site types. However, for lake wetlands, both plant types and resting site types are affected by hydrological conditions. Traditional research methods (such as field surveys and statistical models) struggle to capture complex spatial dynamics and long-term evolutionary trends, and are ineffective in considering the impact of hydrological conditions on migratory bird habitats. Therefore, there is an urgent need to introduce simulation and prediction tools that integrate hydrological conditions and spatiotemporal characteristics. The CA-Markov model combines the spatial self-organizing properties of cellular automata (CA) with the time-series predictive capabilities of Markov chains, effectively simulating land use cover change and its ecological effects, and providing a new technical approach for migratory bird habitat suitability research. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for simulating and predicting the suitability of migratory bird habitats in lake wetlands based on the CA-Markov model, which provides important technical support for the assessment of suitable habitats for migratory birds in lake wetlands and the protection of biodiversity.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a method for simulating and predicting the suitability of migratory bird habitats in lake wetlands based on the CA-Markov model, comprising the following steps: Step 1: Obtain the types of migratory bird habitat elements in lake wetlands, lake topographic data, and daily-scale station water level data. Obtain the hydrological situation indicators of lake wetlands through the inverse distance weighted spatial interpolation method. Step 2: Screen the main hydrological situation indicators that affect migratory bird habitats and establish the fitting relationship between hydrological situation indicators and migratory bird habitat elements; Step 3: Use the CA-Markov model to simulate and predict the migratory bird habitat elements at the next moment. Use the simulated plant type and rest area type as habitat elements for habitat suitability, and obtain the migratory bird habitat suitability by calculating the HSI index.

[0006] In the preferred embodiment, in step one, the habitat elements of lake wetlands for migratory birds include food source plant types and resting area types.

[0007] In a preferred embodiment, step one includes the following steps: S101. Acquisition of migratory bird habitat elements: Acquire satellite remote sensing images of lakes and wetlands, as well as land use and plant type data, and obtain the spatial distribution of migratory bird food source plant types and resting place types in lakes and wetlands through satellite remote sensing interpretation; S102. Calculation of Hydrological Situation Indicators: Collect topographic data and daily station water level data of lakes and wetlands, and use inverse distance weighted interpolation to obtain the spatial distribution map of daily water levels. The formula for inverse distance weighted interpolation is as follows: ; in, z ( x , y ) is an unknown point ( x , y (Predicted water level value) z i It is the first i Values ​​for a known water level station; d i It is an unknown point to the number i Distance to a known water level station; p This is a power parameter that controls the weight of the distance's influence; n represents the number of known water level stations. Based on the difference between the spatial distribution map of daily water levels and the topographic data of lakes and wetlands, we can identify whether each image grid is submerged, count the daily submersion status, and obtain hydrological situation indicators.

[0008] In a preferred embodiment, the hydrological situation indicators include the inundation time, inundation depth, and water patch distance for each image grid.

[0009] In the preferred embodiment, in step two, the relationship between hydrological situation indicators and migratory bird food source plant types and resting place types is fitted based on Gaussian or exponential models, respectively. The main hydrological situation indicators that affect food source plant types and resting place types are selected, where the independent variable is the hydrological situation and the dependent variable is the area statistics of each food source plant type or resting place type.

[0010] In the preferred embodiment, in step two, a suitability map of the selected main hydrological situation indicators affecting food source plant types and recreational area types is generated using the Sigmoid fuzzy membership function.

[0011] In the preferred embodiment, step three includes the following steps: S301, CA-Markov Model Construction: CA-Markov models corresponding to food plant type and rest area type were constructed respectively. Square grids were used to set the cell size, and the cell state was set to food plant type and rest area type respectively. Based on the principle of cellular automata, the transition function of the cell is constructed as shown in the following equation: ; In the formula, , The central cells are respectively in t and t The state result at time +1 N For the cell's neighborhood, f A state transition rule function representing the interaction between neighboring cell units; For food source plant type and rest area type respectively, the Markov transition matrix is ​​calculated using data from the previous time step and the current time step, and the result of the next time step is predicted by combining the suitability atlas of hydrological situation. The formula for calculating the Markov transition matrix is ​​shown below: ; ; In the formula, 0≤ P ij <1; ; P ij ( i , j =1, 2,..., n () represents the current time type i Transform into j The probability of; P This is the overall state transition probability matrix; n For the number of types; S303. Habitat Suitability Index (HSI) Calculation: Simulated and predicted food source plant types and resting place types are used as habitat elements in the HSI method. Suitability types are categorized for both habitat elements, and values ​​are assigned to each category. The analytic hierarchy process (AHP) is used to determine the weights of each habitat element. The HSI method is then used to calculate the habitat suitability for migratory birds. The calculation formula is as follows: ; In the formula, w i and f i These are habitat elements. i The weights and values; k It refers to the quantity of habitat elements.

[0012] In the preferred embodiment, the two types of habitat elements are classified into suitable, relatively suitable, relatively unsuitable, and unsuitable categories.

[0013] In the preferred embodiment, the values ​​for suitable, relatively suitable, relatively unsuitable, and unsuitable are 5, 3, 1, and 0, respectively.

[0014] This invention also provides a lake wetland plant type prediction system that integrates a two-dimensional hydrodynamic model and CA-Markov, comprising: a memory and a processor, wherein the memory and the processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the above-mentioned method for simulating and predicting the suitability of lake wetland migratory bird habitats based on the CA-Markov model.

[0015] This invention provides a method and system for simulating and predicting the suitability of migratory bird habitats in lake wetlands based on the CA-Markov model, which has the following beneficial effects: 1. By combining daily-scale water level data with inverse distance weighted spatial interpolation technology, a refined spatial distribution calculation of hydrological situation indicators was achieved, overcoming the limitation of insufficient spatial representativeness of traditional station data, and providing high-precision hydrological driving data for the simulation of migratory bird habitat elements.

[0016] 2. By combining the spatial dynamic simulation capability of cellular automata with the time series prediction advantage of Markov chains through the CA-Markov model, the spatiotemporal evolution patterns of food source plant types and recreational types can be accurately captured, solving the problem that traditional statistical models are unable to characterize the dynamic changes of habitat elements.

[0017] 3. Key hydrological indicators affecting migratory bird habitats (such as inundation time, water depth, and distance between water patches) were selectively screened, and quantitative fitting relationships were established using Gaussian or exponential models. This clarified the driving mechanism of hydrological processes on the distribution of food plants and resting place types, providing a scientific basis for wetland hydrological regulation.

[0018] 4. By introducing the Sigmoid fuzzy membership function to construct a suitability atlas of hydrological indicators, the continuous and quantitative expression of the impact of hydrological conditions on habitat suitability is realized, thereby improving the ecological interpretability of the simulation results.

[0019] 5. Based on the HSI index, this study integrates two core habitat elements: food plants and rest areas. Weights are rationally allocated using the analytic hierarchy process (AHP), and a four-level classification (suitable, relatively suitable, relatively unsuitable, unsuitable) and a value system (5, 3, 1, 0) are employed to achieve intuitive quantification and spatial visualization of migratory bird habitat suitability. The assessment results directly reflect the carrying capacity of different regions for migratory birds, providing precise spatial guidance for the delineation of wetland protection priority areas and the restoration of migratory bird habitats. Attached Figure Description

[0020] The present invention will be further described below with reference to the accompanying drawings and embodiments: Figure 1 This is a flowchart illustrating an embodiment of the present invention; Figure 2 This is a schematic diagram showing the fitting relationship between migratory bird habitat element types and hydrological situation indicators; Figure 3 This is a schematic diagram of the Sigmoid fuzzy membership function; Figure 4 This is a schematic diagram of the results of habitat suitability for migratory birds. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0022] like Figure 1 As shown, a method for simulating and predicting the suitability of migratory bird habitats in lake wetlands based on the CA-Markov model includes the following steps: Step 1: Obtain the types of migratory bird habitat elements in lake wetlands, lake topographic data, and daily-scale station water level data. Obtain the hydrological situation indicators of lake wetlands through the inverse distance weighted spatial interpolation method.

[0023] In this embodiment, the habitat elements of migratory birds in lake wetlands include food source plant types and resting area types.

[0024] Specifically, the following steps are included: S101. Acquisition of migratory bird habitat elements: Acquire satellite remote sensing images of lakes and wetlands, as well as land use and plant type data. Obtain the spatial distribution of food source plant types and resting place types for migratory birds in lakes and wetlands through satellite remote sensing interpretation.

[0025] In this example, the food source plants of migratory birds in lake wetlands are divided into sedges, sedges, reeds, water bodies with Vallisneria natans growth areas (water depth less than 1.5 m) and water bodies without Vallisneria natans growth areas (water depth greater than 1.5 m). Resting areas are divided into deep water (water depth greater than 2 m), shallow water (water depth less than 2 m), soft mud, hard mud, and grassy areas, thus fully reflecting the foraging and habitat needs of migratory birds.

[0026] S102. Calculation of hydrological situation indicators: Collect topographic data and daily station water level data of lakes and wetlands, and use the inverse distance weighted interpolation method to obtain the spatial distribution map of daily water level, ensuring that it is consistent with the spatial resolution of the topographic data.

[0027] The formula for inverse distance weighted interpolation is shown below: ; in, z ( x , y ) is an unknown point ( x , y (Predicted water level value) z i It is the first i Values ​​for a known water level station; d i It is an unknown point to the number i Distance to a known water level station; p It is a power parameter that controls the influence weight of distance, and is usually taken as 2; n represents the number of known water level stations.

[0028] Based on the difference between the spatial distribution map of daily water levels and the topographic data of lakes and wetlands, we can identify whether each image grid is submerged, count the daily submersion status, and obtain hydrological situation indicators.

[0029] The hydrological situation indicators include the inundation time, inundation depth, and distance between water patches for each image grid.

[0030] The descriptions and ecological meanings of each hydrological condition index are shown in Table 1.

[0031]

[0032] Step 2: Screen the main hydrological situation indicators that affect migratory bird habitats and establish the fitting relationship between hydrological situation indicators and migratory bird habitat elements.

[0033] Specifically, the following steps are included: S201. Function Fitting: Fit the relationship between hydrological situation indicators and migratory bird food source plant types and resting place types based on Gaussian or exponential models respectively. Select the main hydrological situation indicators that affect food source plant types and resting place types. The independent variable is the hydrological situation, and the dependent variable is the area statistics of each food source plant type or resting place type.

[0034] like Figure 2 As shown, in this example, the main hydrological factor influencing the type of food source plants is the annual inundation time, and the main hydrological factor influencing the type of recreation area is the distance between water patches.

[0035] S202. Suitability Map Production: For the selected main hydrological indicators affecting food source plant types and recreational site types, suitability maps for these indicators are produced using the Sigmoid fuzzy membership function. (See...) Figure 3 .

[0036] Specifically, an increasing Sigmoid function was used for hydrological situation factors that had a positive impact on habitat adaptability indicators, while a decreasing Sigmoid function was used for hydrological situation factors that had a negative impact on habitat adaptability indicators. The suitability results for each hydrological situation factor were obtained based on the fitting results.

[0037] Step 3: Use the CA-Markov model to simulate and predict the migratory bird habitat elements at the next moment. Use the simulated plant type and rest area type as habitat elements for habitat suitability, and obtain the migratory bird habitat suitability by calculating the HSI index.

[0038] Specifically, the following steps are included: S301, CA-Markov Model Construction: CA-Markov models corresponding to food plant type and rest area type were constructed respectively. Square grids were used to set the cell size, and the cell state was set to food plant type and rest area type respectively. Based on the principle of cellular automata, the transition function of the cell is constructed as shown in the following equation: ; In the formula, , The central cells are respectively in t and t The state result at time +1 N For the cell's neighborhood, f The state transition rule function represents the interaction between cell units within the neighborhood; in this example, a 5×5 filter is used to define the cell neighborhood.

[0039] For food source plant type and rest area type respectively, the Markov transition matrix is ​​calculated using data from the previous time step and the current time step, and the result of the next time step is predicted by combining the suitability atlas of hydrological situation. The formula for calculating the Markov transition matrix is ​​shown below: ; ; In the formula, 0≤ P ij <1; ; P ij ( i , j =1, 2,..., n () represents the current time type i Transform into j The probability of; P This is the overall state transition probability matrix; n Number of types.

[0040] In this example, the types of food plants and recreational areas in the lake wetland at the next time point were predicted.

[0041] S303. Habitat Suitability Index (HSI) Calculation: The simulated and predicted food source plant types and recreational site types are used as habitat elements in the HSI method. The two types of habitat elements are classified into suitable, relatively suitable, relatively unsuitable, and unsuitable categories. Values ​​are assigned to each category, with suitable, relatively suitable, relatively unsuitable, and unsuitable being assigned values ​​of 5, 3, 1, and 0, respectively.

[0042] The Analytic Hierarchy Process (AHP) was used to determine the weights of each habitat element. With migratory bird habitat suitability as the objective level and plant type and rest area type as primary indicators, a judgment matrix was constructed to calculate the weights of plant type and rest area type. Furthermore, the HSI method was used to calculate migratory bird habitat suitability, using the following formula: ; In the formula, w i and f i These are habitat elements. i The weights and values; k It refers to the quantity of habitat elements.

[0043] In this example, different suitability types were defined for food source plant types and resting place types, and corresponding scores were assigned to quantify the values ​​of each habitat element. Specific types and their assigned values ​​are shown in Table 2. Finally, the final distribution map of migratory bird habitat suitability in lake wetlands was obtained by calculating the HSI index, as shown below. Figure 4 As shown.

[0044]

[0045] This embodiment also provides a simulation and prediction system for the suitability of migratory bird habitats in lake wetlands based on the CA-Markov model, including: a memory and a processor, wherein the memory and the processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the above-described simulation and prediction method for the suitability of migratory bird habitats in lake wetlands based on the CA-Markov model.

[0046] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for simulating and predicting the habitat suitability of lake wetland migratory birds based on a CA-Markov model, characterized in that, The method comprises the following steps: Step one, obtaining lake wetland bird habitat element type, lake terrain data and daily scale site water level data, and obtaining the hydrological regime index of the lake wetland by inverse distance weighted spatial interpolation method; Step two, screening the main hydrological regime index affecting the bird habitat element, and establishing the fitting relationship between the hydrological regime index and the bird habitat element; Step three, simulating and predicting the bird habitat element at the next time by using the CA-Markov model, taking the simulated plant type and resting place type as the habitat element of habitat suitability, and obtaining the bird habitat suitability by calculating the HSI index. 2.The method of simulating and predicting the habitat suitability of migratory birds in a lake wetland based on a CA-Markov model according to claim 1, characterized in that, In step one, the lake wetland bird habitat element type includes food source plant type and resting place type.

3. The method of claim 2, wherein the method is characterized by, The step one comprises the following steps: S101, bird habitat element type acquisition: satellite remote sensing image of lake wetland and land use and plant type data are acquired, and the spatial distribution of lake wetland bird food source plant type and resting place type is obtained by satellite remote sensing interpretation; S102, calculation of hydrological regime index: the terrain data and daily scale site water level data of the lake wetland are collected, the spatial distribution map of daily scale water level is obtained by using inverse distance weighted interpolation method, and the formula of inverse distance weighted interpolation is as follows: ； wherein, z x y is the water level prediction value of the unknown point x y z i is the value of the i th known water level site; d i is the distance from the unknown point to the i th known water level site; p is the power parameter, which controls the influence weight of the distance; n represents the number of known water level sites;​​​​ According to the difference between the spatial distribution map of daily scale water level and the terrain data of the lake wetland, it is identified whether each image grid is flooded, the flooding condition of each day is counted, and the hydrological regime index is obtained.

4. The method of claim 3, wherein the method is characterized by, The hydrological regime index includes the flooding time, flooding water depth and water body patch distance of each image grid.

5. The method of claim 2, wherein the method is characterized by: In step two, the relationship between the hydrological regime index and the bird food source plant type and resting place type is fitted based on Gaussian model or exponential model, and the main hydrological regime index affecting the food source plant type and resting place type is selected, wherein the independent variable is the hydrological regime, and the dependent variable is the area statistics result of each food source plant type or resting place type.

6. The method of claim 5, wherein the method is based on a CA-Markov model. In step two, for the selected main hydrological regime index affecting the food source plant type and resting place type, the suitability map of the hydrological regime index is made by using Sigmoid fuzzy membership function.

7. The method of claim 6, wherein the method is a method for simulating and predicting the habitat suitability of migratory birds in a lake wetland based on a CA-Markov model. The step three comprises the following steps: S301, CA-Markov model construction: the CA-Markov model corresponding to the food source plant type and the resting place type is constructed respectively, the square grid is used for setting the cell size, and the cell state is set as the food source plant type and the resting place type respectively; According to the principle of cellular automata, the transition function of the cell is constructed, as shown in the following formula: ； wherein, , are the state results of the central cell at time t and t +1, respectively, N is the neighborhood of the cell, f denotes the state transition rule function of the cell units in the neighborhood. For the food source plant type and the resting place type respectively, the Markov transition matrix is calculated by using the data of the previous time and the current time, and the suitability map of the hydrological regime is combined to predict the result at the next time; The calculation formula of Markov transition matrix is as follows: ； ； In the formula, 0≤ P ij <1; ; P ij ( i , j =1, 2,..., n () represents the current time type i Transform into j The probability of; P This is the overall state transition probability matrix; n Number of types; S303, habitat suitability index HSI calculation: taking the simulation prediction of food source plant type and resting place type as habitat elements of HSI method, dividing the two habitat element types into suitable types, assigning values to each type, determining the weight of each habitat element using analytic hierarchy process, and calculating the habitat suitability of the migratory bird using the HSI method, the calculation formula is as follows: ； wherein w i and f i are the weight and value, respectively, of the habitat element i ; k is the number of habitat elements.

8. The method according to claim 7, wherein the method is characterized in that, The two habitat element types are divided into suitable types, which are divided into suitable, more suitable, less suitable and unsuitable.

9. The method of claim 8, wherein the method is based on a CA-Markov model. The corresponding values of suitable, more suitable, less suitable and unsuitable are 5, 3, 1 and 0 respectively.

10. A system for simulating and predicting the habitat suitability of migratory birds in a lake wetland based on a CA-Markov model, characterized in that, It comprises: A memory and a processor, which are connected in communication with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the lake wetland migratory bird habitat suitability simulation prediction method based on the CA-Markov model according to any one of claims 1 to 9.

Images