Method and device for optimizing and regulating farmland pattern in arid oasis and electronic equipment

Abstract

The application provides a kind of arid region oasis farmland pattern optimization control method, device and electronic equipment, it is related to the technical field of land resource management, in the method, the water-carbon trade-off factor evaluation model is used to evaluate the driving factor of arid region oasis, and the water-carbon trade-off factor of each pixel of arid region oasis is obtained, and the water-carbon trade-off factor is embedded as an independent variable into FLUS model, and then the improved FLUS model is used to simulate the optimal farmland pattern of the data and optimal land use structure of arid region oasis, to obtain the optimal farmland pattern of arid region oasis, which provides a scientific basis for formulating sustainable development strategy of arid region oasis ecosystem, i.e. the farmland pattern optimization suitable for arid region oasis can be carried out.

Description

Technical Field

[0001] This invention relates to the technical field of land resource management, and in particular to a method, apparatus, and electronic equipment for optimizing and regulating the pattern of oasis farmland in arid regions. Background Technology

[0002] Oases in arid regions are important commodity grain production bases. The expansion of arable land has exacerbated water resource consumption, and declining groundwater levels have triggered a series of ecological and environmental problems, urgently requiring optimized arable land patterns to reduce the water-carbon tradeoff. Current research on arid oases focuses on the responses of water-carbon tradeoff changes to land use types, climate factors, and irrigation patterns. Some scholars have also optimized arable land patterns in arid oases based on different objectives. While these studies have greatly enriched the theory of ecosystem services in arid regions, they have not clarified the mechanism by which arable land expansion affects the water-carbon tradeoff, leading to continued disagreements and hindering research on arable land pattern optimization applicable to arid oases.

[0003] In summary, how to optimize the farmland pattern for oases in arid regions has become an urgent technical problem to be solved. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, and electronic device for optimizing and regulating the cultivated land pattern in arid oases, so as to alleviate the technical problem that traditional technologies cannot be used to optimize the cultivated land pattern in arid oases.

[0005] In a first aspect, the present invention provides a method for optimizing and regulating the pattern of oasis farmland in arid regions, comprising:

[0006] A multi-objective optimization model with constraints was constructed to maximize carbon sequestration and minimize evapotranspiration. The model was then solved based on data from the arid oasis to obtain the optimal land use structure.

[0007] The water-carbon balance factor assessment model was used to evaluate the driving factors of the oasis in the arid region, and the water-carbon balance factor of each pixel of the oasis in the arid region was obtained.

[0008] The water-carbon tradeoff factor is embedded as an independent variable into the FLUS model, and the improved FLUS model is used to simulate the optimal cultivated land pattern of the arid oasis data and the optimal land use structure to obtain the optimal cultivated land pattern of the arid oasis, and then the cultivated land pattern is optimized and regulated according to the optimal cultivated land pattern.

[0009] Furthermore, the objective function for maximizing the carbon sequestration amount includes: ,in, This represents the first objective function. The net primary productivity of each cell is obtained by simulation using the CASA model;

[0010] The objective function for minimizing evapotranspiration includes: ,in, This represents the second objective function. The evapotranspiration of each pixel is obtained by simulation using the CASA model;

[0011] The constraints include: the sum of the areas of all types of land use equals the total area of ​​oases in arid areas; the lower limit of cultivated land area; the total evapotranspiration not exceeding the total regional water resources; and the area of ​​ecological land not lower than the planned value.

[0012] Furthermore, the multi-objective optimization model is solved based on the data from the arid oasis, including:

[0013] A multi-objective optimization algorithm was used to solve the multi-objective optimization model with data from the arid oasis to obtain the optimal land use structure.

[0014] Furthermore, a water-carbon tradeoff factor assessment model is used to evaluate the driving factors of the arid oasis, including:

[0015] The driving factors are input into the water-carbon balance factor evaluation model to obtain the water-carbon balance factor of each pixel in the arid oasis.

[0016] Furthermore, the water-carbon tradeoff factor is embedded as an independent variable into the FLUS model, including:

[0017] The water-carbon tradeoff factor is set as a variable parallel to land use suitability, cost matrix, and restricted area in the FLUS model, thereby obtaining the improved FLUS model.

[0018] Furthermore, the optimal land use structure includes: an optimal land use structure derived from multi-scenario simulation; the method further includes:

[0019] An improved FLUS model was used to simulate the optimal cultivated land pattern of the arid oasis data and the optimal land use structure of the multi-scenario simulation, and the optimal cultivated land pattern of the arid oasis under different scenario simulations was obtained.

[0020] Based on the optimal cultivated land pattern of the arid oasis under different scenario simulations, the target optimal cultivated land pattern of the arid oasis is determined, and then cultivated land pattern optimization and regulation are carried out according to the target optimal cultivated land pattern.

[0021] Furthermore, the multi-scenario simulation includes: natural scenario simulation, economic development priority scenario simulation, ecological protection priority scenario simulation, and scenario simulation that emphasizes both economic development and ecological protection.

[0022] Secondly, the present invention also provides a device for optimizing and regulating the pattern of oasis farmland in arid areas, comprising:

[0023] A construction and solution unit is used to construct a multi-objective optimization model with constraints to maximize carbon sequestration and minimize evapotranspiration, and to solve the multi-objective optimization model based on the data of the arid oasis to obtain the optimal land use structure.

[0024] The water-carbon balance factor assessment unit is used to assess the water-carbon balance factor of the driving factors of the arid oasis using the water-carbon balance factor assessment model, and obtain the water-carbon balance factor of each pixel of the arid oasis.

[0025] The optimal cultivated land pattern simulation unit is used to embed the water-carbon trade-off factor as an independent variable into the FLUS model, and to use the improved FLUS model to simulate the optimal cultivated land pattern of the arid oasis data and the optimal land use structure, so as to obtain the optimal cultivated land pattern of the arid oasis, and then to optimize and regulate the cultivated land pattern according to the optimal cultivated land pattern.

[0026] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method described in the first aspect.

[0027] In this embodiment of the invention, a method for optimizing and regulating the cultivated land pattern of oases in arid regions is provided, comprising: constructing a multi-objective optimization model with constraints to maximize carbon sequestration, minimize evapotranspiration, and solving the multi-objective optimization model based on data from arid oases to obtain the optimal land use structure; using a water-carbon trade-off factor evaluation model to evaluate the driving factors of arid oases to obtain the water-carbon trade-off factor for each pixel of the arid oase; embedding the water-carbon trade-off factor as an independent variable into a FLUS model, and using an improved FLUS model to simulate the optimal cultivated land pattern based on the data from the arid oases and the optimal land use structure to obtain the optimal cultivated land pattern of the arid oases, and then optimizing and regulating the cultivated land pattern according to the optimal cultivated land pattern. As described above, the method for optimizing and regulating the cultivated land pattern of arid oases in this invention uses a water-carbon trade-off factor evaluation model to evaluate the driving factors of arid oases, obtaining the water-carbon trade-off factor for each pixel of the arid oase. The water-carbon trade-off factor is then embedded as an independent variable into the FLUS model. The improved FLUS model is then used to simulate the optimal cultivated land pattern of the arid oase data and optimal land use structure, obtaining the optimal cultivated land pattern of the arid oase. This provides a scientific basis for formulating sustainable development strategies for arid oase ecosystems, enabling the optimization of cultivated land patterns applicable to arid oases and alleviating the technical problem that traditional technologies cannot be used to optimize cultivated land patterns applicable to arid oases. Attached Figure Description

[0028] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0029] Figure 1 A flowchart of a method for optimizing and regulating the pattern of oasis farmland in arid areas provided in an embodiment of the present invention;

[0030] Figure 2 A technical roadmap for optimizing farmland patterns provided in embodiments of the present invention;

[0031] Figure 3 This invention provides a roadmap for optimizing arable land patterns based on a water-carbon trade-off perspective.

[0032] Figure 4 A schematic diagram of the arid oasis farmland pattern optimization and regulation device provided in an embodiment of the present invention;

[0033] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0034] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Traditional technologies are not suitable for optimizing farmland patterns in arid oases.

[0036] Based on this, in the method for optimizing and regulating the cultivated land pattern of oases in arid areas in this invention, a water-carbon trade-off factor evaluation model is used to evaluate the driving factors of oases in arid areas, obtain the water-carbon trade-off factor of each pixel of the oase, and embed the water-carbon trade-off factor as an independent variable into the FLUS model. Then, the improved FLUS model is used to simulate the optimal cultivated land pattern of the oase data and the optimal land use structure, and obtain the optimal cultivated land pattern of the oase. This provides a scientific basis for formulating sustainable development strategies for oase ecosystems in arid areas, and enables the optimization of cultivated land pattern applicable to oases in arid areas.

[0037] To facilitate understanding of this embodiment, a detailed description of the method for optimizing and regulating the pattern of oasis farmland in arid areas, as disclosed in this embodiment of the invention, will be provided first.

[0038] Example 1:

[0039] According to an embodiment of the present invention, an embodiment of a method for optimizing and regulating the pattern of oasis farmland in arid areas is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0040] Figure 1 This is a flowchart of a method for optimizing and regulating the cultivated land pattern in arid oases according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0041] Step S102: Construct a multi-objective optimization model with constraints to maximize carbon sequestration and minimize evapotranspiration, and solve the multi-objective optimization model based on data from oases in arid areas to obtain the optimal land use structure.

[0042] At present, the research on farmland pattern optimization based on ecological security perspective shows the following development trends: (1) Due to the limitations of research methods, the response of water-carbon trade-off to farmland expansion is a comprehensive effect of multiple factors. At present, the research on this aspect mainly compares the changes in WUE before and after farmland expansion, but lacks effective means to explain the impact mechanism of farmland expansion on water-carbon trade-off. Actively exploring new research methods and ideas, and comprehensively considering the multiple influences of the source, location and pattern of farmland expansion, will help to clarify the response mechanism of water-carbon trade-off to farmland expansion from a mechanistic perspective; (2) At present, the construction of farmland pattern optimization models based on ecological security perspective often aims to maximize ecosystem services. In the future, we should strengthen the attention to ecosystem service trade-off factors, improve carbon sequestration function, and reduce the negative impact on the ecosystem. This is especially important in the process of oasis land resource development and ecological management in arid areas; (3) The research on farmland pattern optimization based on water-carbon trade-off perspective involves multiple aspects such as carbon sequestration and evapotranspiration accounting, water-carbon trade-off analysis, and farmland pattern optimization. How to integrate various methods such as field research, indoor testing, statistical analysis, and model simulation to quantify the impact mechanism of arable land expansion on the water-carbon trade-off and incorporate it into the process of arable land pattern optimization remains one of the challenges currently facing land resource management research.

[0043] This invention aims to optimize the cultivated land pattern in arid oasis areas, using the expansion of cultivated land in typical arid regions as a case study, based on the perspective of water-carbon trade-offs. This research provides scientific support for land resource management in arid oasis areas. Arid oases are important commodity grain production bases in arid regions, but their ecological environments are extremely fragile. In recent years, the trade-off between food security and water scarcity has become increasingly severe. Therefore, the problem this invention seeks to solve is how to incorporate water-carbon trade-off factors into the cultivated land pattern optimization model for arid oasis areas, formulate cultivated land optimization and regulation strategies, and reduce water consumption while ensuring food security and the sustainable development of arid oasis ecosystems.

[0044] Taking arid oases as the study area, this study conducts research on the optimization of arable land patterns from the perspective of water and carbon tradeoffs, and proposes optimization and regulation strategies for arable land in arid oases. The technical approach is as follows: Figure 2 As shown:

[0045] Construction of a farmland pattern optimization model framework (including a multi-objective optimization model and an improved FLUS model): Farmland pattern optimization simulation is performed by coupling a multi-objective optimization model and an improved FLUS model. The multi-objective optimization model is used to optimize land use structure, while the improved FLUS model is used to optimize land use pattern. Simultaneously, a water-carbon tradeoff factor is incorporated into multiple steps of the model to reduce the degree of water-carbon tradeoff (i.e., the water-carbon tradeoff factor).

[0046] Based on the locational characteristics of oases in arid regions, two objective functions were set for optimizing the cultivated land pattern: First, as important grain production bases, arid oases need to ensure food security; therefore, maximizing carbon sequestration is one of the objective functions of the multi-objective optimization model. Second, arid oases suffer from water scarcity, and ecological security must be ensured during cultivated land development; therefore, minimizing evapotranspiration is the other objective function. Constraint factors for various land use types (i.e.,...) were determined by referencing regional land use planning, ecological environment protection planning, and economic development planning. Figure 3 The land area constraint (i.e., the constraint condition) is considered. Simultaneously, based on the characteristics of regional water scarcity, a total water resource constraint factor (i.e., ...) is set with reference to water resource planning. Figure 3 The water resource constraints (i.e., the constraints) in this study differ from previous research which aimed to maximize the total amount of ecosystem services. This invention sets the goals of maximizing carbon sequestration and minimizing evapotranspiration simultaneously, which to some extent reduces the trade-offs among ecosystem services and takes into account both food security and ecological security in arid oases.

[0047] The data for the oases in the arid region mentioned above includes: basic data, water and carbon parameters, and constraint data. The basic data refers to the current area of ​​various land uses in the study area (arable land, forest land, grassland, etc.), and the water and carbon parameters refer to the carbon sequestration coefficient per unit area for each type of land use. That is, the carbon sequestration coefficient per unit area for various land use types and the evapotranspiration coefficient per unit area. The above constraint data refers to the total water resources (i.e., the evapotranspiration coefficient per unit area for various land use types). ), lower limit of cultivated land area ( This includes data such as the planned area of ​​ecological land. Data sources include remote sensing data such as normalized difference vegetation index, photosynthetically active radiation absorption ratio, land use, surface temperature, roads, and population; and meteorological data such as temperature, precipitation, radiation, humidity, and wind speed.

[0048] The above-mentioned optimal land use structure can be the optimal area of ​​each type of land use (such as cultivated land area, forest land area, etc.), which must simultaneously satisfy the Pareto optimal solution of "maximum carbon sequestration" and "minimum evapotranspiration".

[0049] Step S104: The water-carbon balance factor assessment model is used to assess the driving factors of the oasis in the arid area, and the water-carbon balance factor of each pixel of the oasis in the arid area is obtained.

[0050] Specifically, the aforementioned water-carbon tradeoff factor assessment model was pre-trained. The training process will be described in detail below, and will not be repeated here.

[0051] Step S106: The water-carbon tradeoff factor is embedded as an independent variable into the FLUS model, and the improved FLUS model is used to simulate the optimal cultivated land pattern of the oasis in the arid area and the optimal land use structure to obtain the optimal cultivated land pattern of the oasis in the arid area, and then the cultivated land pattern is optimized and regulated according to the optimal cultivated land pattern.

[0052] Specifically, this invention sets the water-carbon tradeoff factor as one of the variables parallel to land use suitability, cost matrix, and restricted areas in the FLUS model, thereby improving the effectiveness of ecological indicators in the optimization of farmland patterns. Unlike traditional studies that directly use the ANN module in the FLUS model to generate farmland suitability distribution maps, this invention superimposes the water-carbon tradeoff constraint factor with farmland expansion driving factors and uses a binary logistic model to simulate the farmland suitability distribution map. Secondly, high-value areas in the overall distribution map of the water-carbon tradeoff constraint factor are directly set as restricted areas, and the cost matrix for land use type transfer is correspondingly increased. Using the improved FLUS model, farmland pattern optimization simulations based on the water-carbon tradeoff perspective are conducted to promote the goal of achieving a win-win situation for the ecology and economy of oases in arid regions.

[0053] This invention is guided by landscape ecology theory, and comprehensively uses a variety of methods to analyze the process and driving mechanism of farmland expansion in arid oasis areas, assess the resulting changes in water and carbon trade-offs, conduct research on farmland pattern optimization, and provide a scientific basis for formulating sustainable development strategies for arid oasis ecosystems.

[0054] In this embodiment of the invention, a method for optimizing and regulating the cultivated land pattern of oases in arid regions is provided, comprising: constructing a multi-objective optimization model with constraints to maximize carbon sequestration, minimize evapotranspiration, and solving the multi-objective optimization model based on data from arid oases to obtain the optimal land use structure; using a water-carbon trade-off factor evaluation model to evaluate the driving factors of arid oases to obtain the water-carbon trade-off factor for each pixel of the arid oase; embedding the water-carbon trade-off factor as an independent variable into a FLUS model, and using an improved FLUS model to simulate the optimal cultivated land pattern based on the data from the arid oases and the optimal land use structure to obtain the optimal cultivated land pattern of the arid oases, and then optimizing and regulating the cultivated land pattern according to the optimal cultivated land pattern. As described above, the method for optimizing and regulating the cultivated land pattern of arid oases in this invention uses a water-carbon trade-off factor evaluation model to evaluate the driving factors of arid oases, obtaining the water-carbon trade-off factor for each pixel of the arid oase. The water-carbon trade-off factor is then embedded as an independent variable into the FLUS model. The improved FLUS model is then used to simulate the optimal cultivated land pattern of the arid oase data and optimal land use structure, obtaining the optimal cultivated land pattern of the arid oase. This provides a scientific basis for formulating sustainable development strategies for arid oase ecosystems, enabling the optimization of cultivated land patterns applicable to arid oases and alleviating the technical problem that traditional technologies cannot be used to optimize cultivated land patterns applicable to arid oases.

[0055] The above provides a brief overview of the method for optimizing and regulating the cultivated land pattern in arid oases according to the present invention. The specific details involved are described in detail below.

[0056] In an optional embodiment of the present invention, the objective function for maximizing carbon sequestration includes: ,in, This represents the first objective function, which is the objective function for maximizing carbon sequestration. To calculate the net primary productivity of each cell using the CASA model simulation, Indicates the number of pixels. Indicates the cell number;

[0057] The objective functions for minimizing evapotranspiration include: ,in, This represents the second objective function, which is the objective function to minimize evapotranspiration. The evapotranspiration of each pixel is obtained by simulation using the CASA model. Indicates the number of pixels. Indicates the cell number;

[0058] The constraints include: the sum of the areas of all types of land use equals the total area of ​​oases in arid areas; the lower limit of arable land area; the total evapotranspiration not exceeding the total regional water resources; and the area of ​​ecological land not lower than the planned value.

[0059] Specifically, the multi-objective optimization model (optimizing land use structure (quantitative optimization)) is not a single "off-the-shelf software," but rather an algorithmic framework built upon objective functions and constraints. It needs to be independently developed or existing toolkits must be used, depending on research needs. Specific acquisition / implementation methods include:

[0060] Programming implementation: Using Python (Scipy, DEAP, PyMOO libraries), MATLAB (Optimization Toolbox), R (nsga2 package), etc., define the objective function, constraints, and optimization algorithms (such as NSGA-II, MOPSO, etc.) through code.

[0061] Commercial software such as Lingo and GAMS can solve problems by setting up multi-objective equations, making them suitable for non-programming users.

[0062] Open source frameworks, such as OpenMDAO (Multidisciplinary Optimization Platform), support modular construction of complex multi-objective problems.

[0063] The core objective is to achieve "maximum carbon sequestration of arable land" and "minimum evapotranspiration of arable land" by adjusting the area ratio of various land use types, while simultaneously meeting the constraints.

[0064] The objective functions for maximizing carbon sequestration include: ,in, This represents the first objective function. This represents the net primary productivity of each cell, simulated using the CASA model.

[0065] The objective functions for minimizing evapotranspiration include: ,in, This represents the second objective function. This represents the evapotranspiration of each pixel obtained using the CASA model simulation.

[0066] The sum of the areas of all types of land use equals the total area constraint of oases in arid regions, i.e. ;

[0067] The lower limit constraint on arable land area, namely ;

[0068] Water resource constraints: Total evapotranspiration (corresponding to total water consumption) shall not exceed the regional total water resource constraint, i.e. ;

[0069] Ecological constraints: The area of ​​ecological land such as forest land and grassland shall not be less than the planned value constraint, that is... .

[0070] Land use type constraints (i.e., land area constraints) need to be determined from three dimensions: quantitative constraints, spatial constraints, and conversion rule constraints, taking into account regional planning documents, natural conditions, and ecological and economic objectives. The specific steps are as follows:

[0071] Identify and define the rigid indicators in the plan, and determine the quantitative constraints:

[0072] The upper and lower limits of the scale of various land use types are extracted from regional land use planning, ecological environment protection planning, and economic development planning, serving as the core basis for quantitative constraints.

[0073] Cultivated land: The minimum area constraint is determined based on the "cultivated land area" and "permanent basic farmland protection area" in the overall land use plan.

[0074] Forest / Grassland (Ecological Land): The minimum area constraint is determined based on the "ecological protection red line area" and "forest area" in the ecological environment protection plan (to ensure ecological functions such as carbon sequestration and windbreak and sand fixation).

[0075] Construction land: The maximum area constraint shall be determined based on the "scale of urban construction land" and "industrial park land use indicators" in the economic development plan (to avoid encroachment on cultivated land or ecological land).

[0076] Overlaying spatial control boundaries to determine spatial constraints:

[0077] Through GIS spatial analysis, the prohibited / restricted development areas in the plan are used as spatial constraints to clarify the "non-convertible" or "limited-convertible" ranges for various land use types:

[0078] Areas prohibited from conversion: core ecological areas extracted from the ecological protection red line plan (such as desert grasslands and wetland reserves on the edge of oases) and permanent basic farmland designated by the Permanent Basic Farmland Protection Regulations are restricted from being converted into other land uses (such as construction land and unused land).

[0079] Restricted conversion areas: “Restricted construction areas” (such as buffer zones around towns) extracted from urban and rural planning are restricted to being converted only into ecological land (forest / grassland) and cannot be converted into construction land or high-intensity arable land.

[0080] Combining ecological and economic logic, the following transformation rules and constraints are determined:

[0081] Based on the ecological function and economic attributes of land use types, feasibility constraints for conversion between types are set (i.e., "which land types can be converted into arable land, and which cannot"):

[0082] Land types permitted to be converted to arable land: priority is given to unused land areas with feasible irrigation conditions (such as reserve arable land resources on the edge of oases) and low-quality grassland (non-ecological core areas), but the conversion must meet the requirement that "the amount of carbon sequestration does not decrease significantly after conversion".

[0083] Land types prohibited from being converted into arable land include: forest land (with strong carbon sequestration function), high-coverage grassland (core area for windbreak and sand fixation), and wetland (key to water resource regulation function), to avoid ecological service losses exceeding arable land benefits.

[0084] The specific method for setting the total water resource constraint factor:

[0085] In response to the core characteristic of water scarcity in arid oases, the total water resource constraint needs to be set by combining the total available water resources, water demand quotas for various land use types, and the principle of prioritizing ecological water demand. The specific steps are as follows:

[0086] Total available water resources in the accounting area:

[0087] Extract rigid data from comprehensive water resources planning to determine the constrained "total upper limit":

[0088] Total available water resources = available surface water (e.g., river runoff × development and utilization rate, usually ≤50% in arid areas to protect downstream ecology) + allowable groundwater extraction (determined based on groundwater over-extraction areas to avoid funnel expansion) + transit water allocation (e.g., inter-basin water transfer quotas).

[0089] For example: The available surface water volume of an oasis in an arid region is 1 billion cubic meters. 3 The permitted extraction volume of groundwater is 300 million cubic meters. 3 200 million cubic meters of water were allocated for transit. 3 The upper limit for the total water resources constraint is 1.5 billion cubic meters. 3 .

[0090] Allocate water demand quotas for each land use type, and clarify "type-specific constraints":

[0091] Based on the ecological / production water demand characteristics of various land uses, the total amount will be allocated according to the principle of "prioritizing ecological water demand and ensuring controllable production water demand":

[0092] Ecological water demand: Evapotranspiration water demand of forest / grassland (to maintain vegetation survival) and wetland recharge water demand are set as rigid constraints (e.g., accounting for 30% of the total, i.e., 450 million m³). 3 ), and give priority to protection.

[0093] Farmland water requirements: Based on the goal of "minimizing evapotranspiration", irrigation quotas (m³) are determined according to crop type (e.g., wheat, corn). 3 The calculation is based on the area of ​​cultivated land ( / mu) multiplied by the cultivated land area. The water requirement is ≤ 50% of the total (i.e., 750 million m³, to avoid excessive encroachment on ecological water).

[0094] Water demand for construction land: urban domestic water use + industrial water use, calculated as per capita domestic water use quota × population and water use quota per unit of industrial output value × GDP, with water demand ≤ 20% of the total (i.e. 300 million m³).

[0095] Through the above methods, the constraint factors can not only reflect the rigidity of the plan, but also connect with the core objective of "maximum carbon sequestration and minimum evapotranspiration", providing operable boundary conditions for optimizing the arable land pattern.

[0096] In an optional embodiment of the present invention, the multi-objective optimization model is solved based on data from oases in arid regions, specifically including the following steps:

[0097] A multi-objective optimization algorithm was used to solve a multi-objective optimization model with data on arid oases to obtain the optimal land use structure.

[0098] Specifically, a multi-objective optimization algorithm (such as NSGA-II) is used to generate a "Pareto optimal solution" (i.e., the optimal structural combination that cannot simultaneously increase carbon sequestration and reduce evapotranspiration) through iterative calculation. Finally, a suitable solution is selected as the optimal land use structure based on research needs (such as "ecological priority" or "balanced development" in arid areas).

[0099] In an optional embodiment of the present invention, a water-carbon tradeoff factor assessment model is used to evaluate the driving factors of oases in arid regions, specifically including the following steps:

[0100] The driving factors are input into the water-carbon balance factor evaluation model to obtain the water-carbon balance factor of each pixel in the arid oasis.

[0101] Specifically, the aforementioned water-carbon tradeoff factor assessment model was pre-trained. The training process is described below:

[0102] Step 1: Data Preparation and Preprocessing

[0103] The goal of this step is to create a clean dataset with each patch (i.e., cell) as a row.

[0104] Preparation of dependent variable (Y):

[0105] Ensure that each farmland patch has a water-carbon balance factor value. This value is calculated using the water-carbon balance factor formula.

[0106] The formula for calculating the water-carbon tradeoff factor over a preset time period can be expressed as:

[0107]

[0108] in, and The net primary productivity is defined as the initial time point (i.e., m is the first time point of the preset time period) and the end time point (i.e., n is the last time point of the preset time period), respectively. and These represent the evapotranspiration at the beginning and end of a preset time period, respectively. The water-carbon tradeoff factor is used as the target variable.

[0109] Preparation of independent variable (X):

[0110] Extract the values ​​of all driving factors for each patch. This is typically done through partition statistics or point sampling, including both continuous and categorical variables.

[0111] Continuous variables: such as annual precipitation, temperature, slope, population, GDP, groundwater depth, canal density, etc. The average value (or other statistical value that can represent the characteristics of the patch) is directly extracted from each patch.

[0112] Categorical variables, such as vegetation type, require one-hot encoding. For example, if the vegetation type includes 'forest', 'grassland', and 'shrubland', then three new binary columns (yes / no belonging to this type) should be added.

[0113] Data cleaning and preprocessing:

[0114] Handling missing values: Delete patches with too many missing values ​​or fill them with appropriate methods (such as median, mean).

[0115] Data standardization: It is strongly recommended to standardize continuous independent variables (e.g., Z-score standardization) to make the mean 0 and the standard deviation 1. This improves model performance and interpretability. You can use `sklearn.preprocessing.StandardScaler`.

[0116] Create the dataset: The final result is a structured table (such as CSV or Pandas DataFrame), where each row is a patch and the columns are the water-carbon tradeoff (Y) and all driving factors (X).

[0117] Dataset partitioning:

[0118] The data is randomly divided into a training set (e.g., 70-80%) and a test set (e.g., 20-30%). The training set is used to train the model, and the test set is used to evaluate the model's generalization ability.

[0119] Step 2: Model Training and Hyperparameter Optimization

[0120] This can be achieved using Python's scikit-learn library.

[0121] Basic model training:

[0122] Hyperparameter optimization:

[0123] Use GridSearchCV or RandomizedSearchCV to find the optimal combination of parameters to prevent overfitting and improve performance. This trains a water-carbon tradeoff factor evaluation model.

[0124] Step 3: Spatial inversion (applying the model to the entire region)

[0125] This is a crucial step in mapping statistical relationships to a spatial dimension.

[0126] Prepare full-area raster (i.e., cell) data:

[0127] Ensure you have raster files (e.g., in GeoTIFF format) containing all driving factors that match the study area. These rasters must have the same resolution, projection, and spatial extent.

[0128] All raster data are stacked into a large multi-band raster, with each band corresponding to a driving factor.

[0129] Applying models for prediction:

[0130] The best_rf_model is used to predict each cell in the entire study area.

[0131] Recommended approach: Use rasterio to read the raster, NumPy to process the array, and then perform prediction.

[0132] Step 4: Results Evaluation and Output

[0133] Model performance evaluation:

[0134] R² and RMSE: Performance on the test set is key to measuring a model's generalization ability. The closer R² is to 1 and the smaller the RMSE, the better the model's performance.

[0135] OOB Score: A built-in evaluation metric of Random Forest, roughly equivalent to R² of out-of-bag validation, which is very convenient and reliable.

[0136] Feature importance analysis:

[0137] Random forests can provide importance scores for each driving factor, which helps in interpreting the model and understanding which factors are dominant.

[0138] Output the final result:

[0139] The final predicted_water_carbon_tradeoff.tif is a map of the water-carbon tradeoff factor distributed in a continuous spatial pattern. Higher values ​​indicate a stronger tradeoff (greater constraint), while lower values ​​indicate better synergy.

[0140] Step 5: Application and Interpretation of Results

[0141] Input optimization model: The generated water-carbon tradeoff factor map is used as a cost surface or constraint in the multi-objective land use optimization model. When allocating new arable land, the optimization algorithm will tend to select areas with lower values ​​in the map (good water-carbon synergy).

[0142] Interpreting the Driving Mechanisms: By combining the results of feature importance, we can interpret which factors are the dominant factors influencing the water-carbon tradeoff. For example, if "annual precipitation" and "groundwater depth" rank highest in importance, it indicates that hydrological conditions are the key mechanism determining the water-carbon tradeoff in the study area.

[0143] In an optional embodiment of the present invention, the water-carbon tradeoff factor is embedded as an independent variable into the FLUS model, specifically including the following steps:

[0144] By setting the water-carbon tradeoff factor as a variable parallel to land use suitability, cost matrix, and restricted area in the FLUS model, an improved FLUS model is obtained.

[0145] Specifically, FLUS (Future Land Use Simulation Model) is a land use pattern simulation model developed by Li Xia's team at Sun Yat-sen University, and it is publicly available.

[0146] Official resources: Open source code (mostly C++ or Python versions) can be obtained through the author team's laboratory website (such as the relevant page of the School of Geography and Planning, Sun Yat-sen University) or research papers.

[0147] Secondary development: After obtaining the basic code, it can be improved according to the water and carbon targets (such as incorporating water and carbon tradeoff factors), which requires certain programming skills (C++ or Python).

[0148] The core objective is to allocate arable land spatially to areas with high carbon sequestration potential and low evapotranspiration, based on the "optimal land use structure" (such as total arable land area) determined by the multi-objective optimization model, while also meeting suitability conditions such as topography and soil.

[0149] Implementation path (combining improvements to water and carbon targets):

[0150] Improved suitability assessment:

[0151] Traditional FLUS uses ANN (Artificial Neural Network) to calculate the suitability of each pixel for conversion into arable land (based on driving factors such as terrain, soil, and transportation); this invention requires the addition of a "water and carbon tradeoff factor"—using the pixel's water and carbon tradeoff factor as a negative indicator (the lower the water and carbon tradeoff factor, the higher the suitability), that is:

[0152] Farmland suitability = basic driving factor suitability × (1 - standardized water and carbon tradeoff factor);

[0153] (The lower the water-carbon tradeoff factor, the less it weakens suitability, and the more suitable the pixel is to be converted into farmland. The above-mentioned basic driving factor of suitability is obtained from the ANN output.)

[0154] Set restricted areas:

[0155] Areas with high water-carbon balance factors (areas with severe water-carbon balance conflicts, such as areas with low carbon sequestration but high evapotranspiration) will be designated as restricted areas "prohibited from conversion to arable land" to prevent the expansion of arable land in these areas.

[0156] Adjusting conversion costs:

[0157] For pixels with high water-carbon tradeoff factors, increase their "conversion cost" to arable land (such as increasing ecological loss costs) so that the model will prioritize converting pixels with low water-carbon tradeoff factors to arable land during simulation.

[0158] Cellular Automata (CA) Simulation:

[0159] Based on the improved suitability, restricted areas, and conversion costs, FLUS uses CA rules (such as neighborhood influence and random perturbation) for iterative simulation, and finally outputs a spatially "high carbon sequestration and low evapotranspiration" arable land pattern, with the area of ​​various land uses conforming to the structure determined by the multi-objective optimization model.

[0160] The inputs to the improved FLUS model (i.e., the data on arid oases in step S106) include: basic geographic data, driving factor data, water and carbon factor data, structural constraints, and model parameters. The basic geographic data includes spatial data such as the study area DEM (topography), soil type, and vegetation cover (raster format, consistent cell size). The driving factor data includes spatial driving factors affecting arable land expansion such as transportation distance, urban distance, and distribution of irrigation facilities. The water and carbon factor data includes spatial distribution maps of water and carbon trade-off factors (WCTD) and the spatial distribution of carbon sequestration potential and evapotranspiration potential of each cell. The structural constraints include the land use areas of various types output by the multi-objective optimization model (such as the upper limit of the total arable land area). The model parameters include transformation rules (such as the transformation probability between different land use types), number of iterations, and neighborhood weights.

[0161] The output of the improved FLUS model includes: an optimized land use pattern map, i.e. the optimal arable land pattern of arid oases, in raster format, showing the land use type of each cell (with a focus on the spatial distribution of arable land), and the pattern meets the water and carbon target of "high carbon sequestration and low evapotranspiration".

[0162] In an optional embodiment of the present invention, the optimal land use structure includes: an optimal land use structure obtained through multi-scenario simulation; the method further includes the following steps:

[0163] (1) The improved FLUS model was used to simulate the optimal cultivated land pattern of oasis in arid areas using data and the optimal land use structure of multi-scenario simulation, and the optimal cultivated land pattern of oasis in arid areas under different scenarios was obtained.

[0164] Specifically, the multi-scenario simulation includes: natural scenario simulation, economic development priority scenario simulation, ecological protection priority scenario simulation, and scenario simulation that balances economic development and ecological protection.

[0165] (2) Determine the target optimal cultivated land pattern of arid oasis based on the optimal cultivated land pattern of arid oasis simulated under different scenarios, and then carry out cultivated land pattern optimization and regulation according to the target optimal cultivated land pattern.

[0166] Specifically, the simulation of farmland pattern optimization under different scenarios was conducted: Based on regional planning and development requirements, four scenarios were set up: natural mode, economic development priority, ecological protection priority, and a balance between economic development and ecological protection. First, using a multi-objective optimization model, the optimal range of land use demand under the four scenarios (i.e., the optimal land use structure in the multi-scenario simulation) was determined using Lingo software. Second, an improved FLUS model was used to simulate the optimal land use structure under the four scenarios. Finally, the simulation results under the four scenarios were compared and analyzed, and based on this, optimization and control strategies for oasis farmland in arid areas were proposed, providing support for regional land use planning and ecological protection and restoration.

[0167] When conducting comparative analysis, examine the core quantitative indicator system (categorized by scenario comparison dimension).

[0168] 1. Cultivated land characteristic indicators (basic attributes)

[0169] Arable land area: The total size of arable land under four scenarios (unit: hm²), reflecting the impact of different development orientations on arable land expansion / contraction (e.g., the economic priority scenario may have a larger arable land area, while the ecological priority scenario may have a smaller one).

[0170] Farmland spatial concentration: The contiguousness of farmland is measured by landscape indices (such as the clustering index). (Economic priority may lead to more contiguous farmland due to concentrated development, while ecological priority may lead to more fragmented farmland due to avoidance of ecological zones.)

[0171] Main sources of arable land expansion: Statistics on which land types (such as grassland, unused land, forest land, etc.) are mainly converted from arable land under four scenarios, reflecting the degree of encroachment on other land types under different scenarios (such as the ecological priority scenario may occupy less forest land / grassland).

[0172] 2. Water Resources Related Indicators

[0173] Total evapotranspiration: Total evapotranspiration of cultivated land under four scenarios (e.g., cubic meters or millimeters), directly reflects water consumption intensity (lower in the ecological priority scenario, possibly higher in the economic priority scenario). The higher the water consumption, the less ecologically friendly it is.

[0174] 3. Economic benefit indicators

[0175] Total carbon sequestration: The total carbon sequestration of arable land (e.g., per ton of carbon) under four scenarios reflects carbon sequestration capacity (the capacity should be higher in food security-oriented scenarios), which can be converted into grain yield and represents economic benefits.

[0176] This invention constructs a farmland optimization model framework by coupling a multi-objective optimization model with an improved FLUS model. With the objectives of maximizing carbon sequestration and minimizing evapotranspiration, it sets four development scenarios: natural development, ecological priority, economic priority, and a balance between ecology and economy (the weights of carbon sequestration and evapotranspiration differ in the objective function under different scenarios). Based on the multi-objective optimization model, the optimal solutions for land use structure under the four different development scenarios are obtained. A water-carbon tradeoff factor evaluation model is used to obtain water-carbon tradeoff limiting factors (i.e., water-carbon tradeoff factors), which are then incorporated into the FLUS model to simulate farmland patterns under the four different scenarios. By comparing the differences in farmland patterns under different scenarios, farmland optimization and regulation strategies are proposed, providing a scientific basis for land use planning and ecological protection in arid oasis areas.

[0177] This invention has the following innovations:

[0178] (1) Geographically, this invention takes the ecologically fragile oasis in arid regions as the research object. Based on the background of the impact of farmland expansion on ecological security, it conducts research on the optimization of farmland pattern. Therefore, this invention has distinct regional characteristics and is also a basic and hot research closely related to the forefront of geography and ecology.

[0179] (2) In terms of content, this invention employs various methods such as field surveys, indoor testing, statistical analysis, and model simulation to optimize the oasis farmland pattern in arid areas from the perspective of mitigating the water-carbon tradeoff. This invention addresses the deficiency in land use pattern optimization research regarding the limited attention paid to the water-carbon tradeoff and demonstrates a certain degree of innovation in its research content.

[0180] (3) In terms of methodology, the water-carbon trade-off factor is incorporated into the farmland optimization model, so that the simulation results can simultaneously achieve the goals of food security and ecological security. Therefore, this invention has certain methodological innovations.

[0181] Example 2:

[0182] This invention also provides a device for optimizing and regulating the cultivated land pattern of oases in arid regions. This device is mainly used to execute the method for optimizing and regulating the cultivated land pattern of oases in arid regions provided in Embodiment 1 of this invention. The following is a detailed description of the device for optimizing and regulating the cultivated land pattern of oases in arid regions provided in this invention.

[0183] Figure 4 This is a schematic diagram of a device for optimizing and regulating the cultivated land pattern in arid oasis areas according to an embodiment of the present invention, as shown below. Figure 4 As shown, the device mainly includes: a construction and solution unit 10, a water-carbon tradeoff factor evaluation unit 20, and an optimal arable land pattern simulation unit 30, wherein:

[0184] The construction and solution unit is used to construct a multi-objective optimization model that maximizes carbon sequestration, minimizes evapotranspiration, and has constraints. The multi-objective optimization model is solved based on data from oases in arid areas to obtain the optimal land use structure.

[0185] The water-carbon balance factor assessment unit is used to assess the water-carbon balance factor of the driving factors of arid oases using the water-carbon balance factor assessment model, and obtain the water-carbon balance factor of each pixel of the arid oasis.

[0186] The optimal cultivated land pattern simulation unit is used to embed water and carbon trade-off factors as independent variables into the FLUS model, and to simulate the optimal cultivated land pattern using the improved FLUS model on data of arid oases and optimal land use structure, so as to obtain the optimal cultivated land pattern of arid oases, and then to optimize and regulate the cultivated land pattern according to the optimal cultivated land pattern.

[0187] In this embodiment of the invention, a device for optimizing and regulating the cultivated land pattern of oases in arid regions is provided, comprising: constructing a multi-objective optimization model with constraints to maximize carbon sequestration, minimize evapotranspiration, and solving the multi-objective optimization model based on data from arid oases to obtain the optimal land use structure; using a water-carbon trade-off factor evaluation model to evaluate the driving factors of arid oases to obtain the water-carbon trade-off factor for each pixel of the arid oase; embedding the water-carbon trade-off factor as an independent variable into a FLUS model, and using an improved FLUS model to simulate the optimal cultivated land pattern based on the data from the arid oases and the optimal land use structure to obtain the optimal cultivated land pattern of the arid oases, and then optimizing and regulating the cultivated land pattern according to the optimal cultivated land pattern. As described above, the arid oasis farmland pattern optimization and control device of the present invention uses a water-carbon trade-off factor evaluation model to evaluate the driving factors of arid oasis, obtains the water-carbon trade-off factor of each pixel of arid oasis, and embeds the water-carbon trade-off factor as an independent variable into the FLUS model. Then, the improved FLUS model is used to simulate the optimal farmland pattern of arid oasis data and optimal land use structure, and obtains the optimal farmland pattern of arid oasis. This provides a scientific basis for formulating sustainable development strategies for arid oasis ecosystems, and can carry out farmland pattern optimization applicable to arid oasis, alleviating the technical problem that traditional technologies cannot carry out farmland pattern optimization applicable to arid oasis.

[0188] Optionally, the objective function for maximizing carbon sequestration includes: ,in, This represents the first objective function. The objective function for minimizing evapotranspiration is as follows: (The net primary productivity of each cell is obtained using the CASA model simulation.) ,in, This represents the second objective function. The evapotranspiration of each pixel is obtained by simulating using the CASA model; the constraints include: the sum of the areas of all types of land use equals the total area of ​​oases in arid areas, the lower limit of cultivated land area, the total evapotranspiration not exceeding the total amount of regional water resources, and the ecological land area not being lower than the planned value.

[0189] Optionally, the construction and solution unit is also used to: solve a multi-objective optimization model with data on arid oases using a multi-objective optimization algorithm to obtain the optimal land use structure.

[0190] Optionally, the water-carbon tradeoff factor assessment unit is also used to: input driving factors into the water-carbon tradeoff factor assessment model to obtain the water-carbon tradeoff factor for each pixel of the arid oasis.

[0191] Optionally, the optimal farmland pattern simulation unit can also be used to: set the water-carbon tradeoff factor as a variable parallel to land use suitability, cost matrix, and restricted area in the FLUS model, thereby obtaining an improved FLUS model.

[0192] Optionally, the optimal land use structure includes: the optimal land use structure simulated under multiple scenarios; the device is also used to: simulate the optimal cultivated land pattern using the data of the arid oasis and the optimal land use structure simulated under multiple scenarios using an improved FLUS model, to obtain the optimal cultivated land pattern of the arid oasis under different scenarios; determine the target optimal cultivated land pattern of the arid oasis based on the optimal cultivated land pattern of the arid oasis under different scenarios, and then optimize and regulate the cultivated land pattern according to the target optimal cultivated land pattern.

[0193] Optionally, the multi-scenario simulation includes: natural scenario simulation, economic development priority scenario simulation, ecological protection priority scenario simulation, and scenario simulation that balances economic development and ecological protection.

[0194] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0195] like Figure 5 As shown in the embodiment of this application, an electronic device 600 includes a processor 601, a memory 602, and a bus. The memory 602 stores machine-readable instructions that can be executed by the processor 601. When the electronic device is running, the processor 601 and the memory 602 communicate via the bus. The processor 601 executes the machine-readable instructions to perform the steps of the above-described method for optimizing and regulating the oasis farmland pattern in arid areas.

[0196] Specifically, the aforementioned memory 602 and processor 601 can be general-purpose memory and processor, without any specific limitations. When the processor 601 runs the computer program stored in the memory 602, it can execute the aforementioned method for optimizing and regulating the oasis farmland pattern in arid areas.

[0197] The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 601 or by instructions in software form. The processor 601 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 602, and processor 601 reads the information from memory 602 and, in conjunction with its hardware, completes the steps of the above method.

[0198] Corresponding to the above-mentioned method for optimizing and regulating the arable land pattern of oases in arid areas, this application also provides a computer-readable storage medium storing machine-executable instructions. When the machine-executable instructions are called and run by a processor, the machine-executable instructions cause the processor to perform the steps of the above-mentioned method for optimizing and regulating the arable land pattern of oases in arid areas.

[0199] The arid oasis farmland pattern optimization and control device provided in this application embodiment can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0200] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0201] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0202] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0203] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0204] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the arid oasis farmland pattern optimization and control method described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0205] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0206] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for optimizing and regulating the pattern of oasis farmland in arid regions, characterized in that, include: A multi-objective optimization model with constraints was constructed to maximize carbon sequestration and minimize evapotranspiration. The model was then solved based on data from the arid oasis to obtain the optimal land use structure. A water-carbon balance factor assessment model was used to evaluate the driving factors of the arid oasis, obtaining the water-carbon balance factor for each pixel of the arid oasis. The calculation formula for the water-carbon balance factor over a preset time period is expressed as follows: , Indicates the initial time point of the preset time period. Net primary productivity, Indicates the end time of the preset time period. Net primary productivity, Indicates the initial time point of the preset time period. Evaporation amount, Indicates the end time of the preset time period. The evapotranspiration rate, the water-carbon tradeoff factor evaluation model is obtained by pre-training the water-carbon tradeoff factor and the corresponding driving factor sample for a preset time period. The water-carbon tradeoff factor is embedded as an independent variable into the FLUS model, and the improved FLUS model is used to simulate the optimal cultivated land pattern of the arid oasis data and the optimal land use structure to obtain the optimal cultivated land pattern of the arid oasis, and then the cultivated land pattern is optimized and regulated according to the optimal cultivated land pattern. The water-carbon tradeoff factor is embedded as an independent variable in the FLUS model, including: The water-carbon tradeoff factor is set as a variable parallel to land use suitability, cost matrix, and restricted area in the FLUS model, thereby obtaining the improved FLUS model.

2. The method according to claim 1, characterized in that, The objective function for maximizing carbon sequestration includes: ,in, This represents the first objective function. The net primary productivity of each cell is obtained by simulation using the CASA model. Indicates the number of pixels. Indicates the cell number; The objective function for minimizing evapotranspiration includes: ,in, This represents the second objective function. The evapotranspiration of each pixel is obtained by simulation using the CASA model. Indicates the number of pixels. Indicates the cell number; The constraints include: the sum of the areas of all types of land use equals the total area of ​​oases in arid areas; the lower limit of cultivated land area; the total evapotranspiration not exceeding the total regional water resources; and the area of ​​ecological land not lower than the planned value.

3. The method according to claim 1, characterized in that, The multi-objective optimization model is solved based on the data from the arid oasis, including: A multi-objective optimization algorithm was used to solve the multi-objective optimization model with data from the arid oasis to obtain the optimal land use structure.

4. The method according to claim 1, characterized in that, The water-carbon tradeoff factor assessment model was used to evaluate the driving factors of the oases in the arid region, including: The driving factors are input into the water-carbon balance factor evaluation model to obtain the water-carbon balance factor of each pixel in the arid oasis.

5. The method according to claim 1, characterized in that, The optimal land use structure includes: an optimal land use structure simulated under multiple scenarios; the method further includes: An improved FLUS model was used to simulate the optimal cultivated land pattern of the arid oasis data and the optimal land use structure of the multi-scenario simulation, and the optimal cultivated land pattern of the arid oasis under different scenario simulations was obtained. Based on the optimal cultivated land pattern of the arid oasis under different scenario simulations, the target optimal cultivated land pattern of the arid oasis is determined, and then cultivated land pattern optimization and regulation are carried out according to the target optimal cultivated land pattern.

6. The method according to claim 5, characterized in that, The multi-scenario simulations include: natural scenario simulation, economic development priority scenario simulation, ecological protection priority scenario simulation, and scenario simulation that balances economic development and ecological protection.

7. A device for optimizing and regulating the pattern of cultivated land in oases in arid regions, characterized in that, include: A construction and solution unit is used to construct a multi-objective optimization model with constraints to maximize carbon sequestration and minimize evapotranspiration, and to solve the multi-objective optimization model based on the data of the arid oasis to obtain the optimal land use structure. The water-carbon balance factor assessment unit is used to assess the water-carbon balance factor of the driving factors of the arid oasis using a water-carbon balance factor assessment model, and to obtain the water-carbon balance factor of each pixel of the arid oasis. The calculation formula for the water-carbon balance factor over a preset time period is expressed as follows: , Indicates the initial time point of the preset time period. Net primary productivity, Indicates the end time of the preset time period. Net primary productivity, Indicates the initial time point of the preset time period. Evaporation amount, Indicates the end time of the preset time period. The evapotranspiration rate, the water-carbon tradeoff factor evaluation model is obtained by pre-training the water-carbon tradeoff factor and the corresponding driving factor sample for a preset time period. The optimal cultivated land pattern simulation unit is used to embed the water-carbon trade-off factor as an independent variable into the FLUS model, and to use the improved FLUS model to simulate the optimal cultivated land pattern of the arid oasis data and the optimal land use structure, so as to obtain the optimal cultivated land pattern of the arid oasis, and then to optimize and regulate the cultivated land pattern according to the optimal cultivated land pattern. The optimal farmland pattern simulation unit is further used to: set the water-carbon tradeoff factor as a variable parallel to land use suitability, cost matrix, and restricted area in the FLUS model, thereby obtaining the improved FLUS model.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

Images