Country landscape pattern collaborative optimization method, device and equipment based on dynamic pollution assessment and multi-target constraint and medium

Abstract

The invention discloses a rural landscape pattern collaborative optimization method, device, equipment and medium based on dynamic pollution assessment and multi-target constraint, and the method comprises the steps: carrying out the multi-scale space assessment of the non-point source pollution risk of a target region through obtaining the source-sink landscape space data and dynamic pollution source strong parameters of the target region; pollution risk distribution information is generated; establishing a constraint rule base including an ecological environment target, a policy planning target and a landscape pattern target; and based on a historical landscape evolution rule, introducing the constraint rule base as a decision-making layer, carrying out multi-target comprehensive scoring and screening on state conversion of landscape cells, and simulating to generate a future landscape pattern scheme meeting the multi-target constraint. According to the method, dynamic and fine environmental impact assessment and active and multi-target spatial layout optimization can be deeply coupled, and transformation from assessment and planning separation to assessment and optimization integration is realized.

Description

Technical Field

[0001] This application relates to the interdisciplinary field of landscape ecological planning and environmental information technology. Specifically, it relates to a method, apparatus, equipment, and medium for the collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints. Background Technology

[0002] In the fields of urban and rural planning and ecological management, landscape pattern optimization is a key scientific issue in coordinating human activities with natural systems.

[0003] Traditional landscape planning methods often face two major technical disconnects: First, non-point source pollution assessment is disconnected from spatial planning. Current assessments of non-point source pollution largely rely on established watershed models (such as SWAT and AnnAGNPS). While these models are theoretically sound, their parameters are complex and difficult to calibrate, making them particularly unsuitable for small rural watersheds with complex land use types and highly heterogeneous underlying surfaces. More importantly, such assessment results are often presented in the form of reports or static maps, failing to be effectively and dynamically integrated into subsequent land use planning decisions, potentially leading to planning schemes overlooking potential pollution risks.

[0004] Second, landscape simulation models lack multi-objective collaborative decision-making capabilities. Cellular automata-Markov chain (CA-Markov) models are commonly used tools for landscape change simulation. However, traditional CA-Markov models mainly rely on historical transition probabilities and the states of neighboring pixels for prediction. In rural planning scenarios with strong policy orientation and diverse development goals, such simulations cannot proactively incorporate multiple objectives such as total pollutant control, ecological red line constraints, and industrial layout needs. Therefore, they are unlikely to generate "optimized" solutions that meet comprehensive management requirements, but rather only "possible" solutions. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and medium for collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints, which addresses the technical problems in the prior art where non-point source pollution assessment is disconnected from spatial planning and landscape simulation models lack multi-objective collaborative decision-making capabilities.

[0006] The first aspect of this application provides a method for the collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints, including: Acquire source-sink landscape spatial data and dynamic pollution source strength parameters of the target area, conduct multi-scale spatial assessment of non-point source pollution risk in the target area, and generate pollution risk distribution information; Establish a constraint rule base that includes ecological and environmental goals, policy planning goals, and landscape pattern goals, wherein the ecological and environmental goals are set at least in part based on the pollution risk distribution information; Based on the historical landscape evolution patterns, the aforementioned constraint rule base is introduced as the decision layer to perform multi-objective comprehensive scoring and screening of the state transitions of landscape cells, and simulate and generate future landscape pattern schemes that meet the multi-objective constraints.

[0007] Preferably, the acquisition of source-sink landscape spatial data and dynamic pollution source strength parameters of the target area, and the multi-scale spatial assessment of non-point source pollution risk of the target area to generate pollution risk distribution information include: identifying and extracting the spatial distribution of source landscape and sink landscape based on remote sensing images and digital elevation models. By setting moving windows of different sizes to traverse the target area, the landscape structure index within each window is calculated, and combined with the watershed division results, the optimal spatial assessment unit for pollution load calculation is determined. Within the optimal spatial assessment unit, landscape type, dynamic source strength parameters, topography and soil data are integrated to calculate non-point source pollution load and migration risk, and generate a spatial distribution map of pollution risk.

[0008] Preferably, the dynamic source strength parameter is obtained by conducting a rainfall-runoff simulation experiment for the target area, and obtaining the dynamic source strength parameter through the experiment; The dynamic source strength parameters are associated and stored in a source strength geographic information database, which is updated as land use changes.

[0009] Preferably, the establishment of a constraint rule base that includes ecological environment goals, policy planning goals, and landscape pattern goals includes: The ecological and environmental targets include pollution load reduction thresholds, water quality target values ​​for key water bodies, and vegetation coverage target values, all set based on pollution risk distribution information. The policy planning objectives include the basic farmland protection boundary, the total control index of construction land, and the land demand for the development of characteristic industries; The landscape pattern objectives include the objectives of improving the landscape diversity index and enhancing landscape spatial connectivity.

[0010] Preferably, the step of introducing the constraint rule base as a decision layer based on the historical landscape evolution pattern, performing multi-objective comprehensive scoring and screening of the state transition of landscape cells, and simulating and generating future landscape pattern schemes that meet multi-objective constraints includes: Using a cellular automaton model of local land use competition, the number of cells of each landscape type in the neighborhood is taken as the neighborhood scenario, the central landscape cell is taken as the input variable, and the central landscape cell is taken as the output landscape type. In the neighborhood transformation rules of the competing cellular automata model, the multi-objective constraint rule base is integrated as an independent decision layer; For each candidate cell state transition, calculate its comprehensive impact score on each rule in the constraint rule base; When the comprehensive impact score meets the preset threshold, the conversion is performed.

[0011] Preferably, when calculating the comprehensive impact score, differentiated weights are assigned to different constraint rules; Preferably, a random disturbance factor is introduced when calculating the comprehensive impact score.

[0012] Preferably, after simulating and generating future landscape pattern schemes that meet multi-objective constraints, the method further includes: comparing multiple landscape pattern schemes generated under different development scenarios, re-evaluating the pollution risks and ecological benefits of each scheme, and outputting a recommended optimization scheme; Preferably, the recommended optimization scheme is used to initiate a new round of optimization process for the evaluation object; Preferably, the comparison of multiple landscape pattern schemes generated under different development scenarios and the reassessment of the pollution risks and ecological benefits of each scheme includes: constructing a comprehensive evaluation index system covering ecological benefits, economic benefits and social adaptability; The aforementioned indicator system is used to quantitatively score and rank the simulated scenario solutions. The highest-scoring solution will be output as the recommended optimization solution, and the output will include at least one of the following: a spatial planning map and a supporting ecological engineering layout suggestion map.

[0013] A second aspect of this application provides a collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints, including: The pollution assessment module is used to acquire "source-sink" landscape spatial data and dynamic pollution source strength parameters of the target area, perform multi-scale spatial assessment of non-point source pollution risk in the target area, and generate pollution risk distribution information. The constraint module is used to establish a constraint rule base that includes ecological and environmental goals, policy planning goals, and landscape pattern goals, wherein the ecological and environmental goals are set at least in part based on the pollution risk distribution information; The scheme generation module is used to simulate and generate future landscape pattern schemes that meet the multi-objective constraints by introducing the constraint rule library as the decision layer based on the historical landscape evolution pattern.

[0014] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it causes the electronic device to perform the method described in the first aspect of this application.

[0015] A fourth aspect of this application provides a computer-readable storage medium for storing a computer program that, when run on a computer, causes the computer to perform the method described in the first aspect of this application.

[0016] Beneficial effects

[0017] In this embodiment, by acquiring source-sink landscape spatial data and dynamic pollution source strength parameters of the target area, a multi-scale spatial assessment of non-point source pollution risk is performed on the target area to generate pollution risk distribution information; a constraint rule base including ecological environment goals, policy planning goals, and landscape pattern goals is established, wherein the ecological environment goals are at least partially set based on the pollution risk distribution information; based on historical landscape evolution patterns, the constraint rule base is introduced as a decision layer to perform multi-objective comprehensive scoring and screening of the state transitions of landscape cells, and to simulate and generate future landscapes that meet the multi-objective constraints.

[0018] Landscape pattern scheme. This invention can deeply couple dynamic and detailed environmental impact assessment with proactive and multi-objective spatial layout optimization, realizing the transformation from the separation of assessment and planning to the integration of assessment and optimization. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation of this application. In the drawings: FIG1 is a technical roadmap according to an embodiment of this application.

[0020] Figure 2 is a study range diagram of the target area selected according to an embodiment of this application.

[0021] Figure 3 is a flowchart of a method for collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints according to an embodiment of this application.

[0022] Figure 4 is a slope map of the target area selected according to an embodiment of this application.

[0023] Figure 5 is a slope aspect diagram of the target area selected according to an embodiment of this application.

[0024] Figure 6 is a schematic diagram of the technical route for runoff analysis in the target area selected according to the embodiments of this application.

[0025] Figure 7 is a runoff analysis diagram of the target area selected according to an embodiment of this application.

[0026] Figure 8 is a schematic diagram of the selection of water environment monitoring points in the target area according to the embodiments of this application.

[0027] Figure 9 is a fusion image of the target area selected according to an embodiment of this application, using Landsat 8 remote sensing image 543.

[0028] Figure 10 is a schematic diagram of a movable window design according to an embodiment of this application.

[0029] Figure 11 is a schematic diagram of multi-plot simulation output according to an embodiment of this application.

[0030] Figure 12 is a schematic diagram of a rural landscape pattern collaborative optimization module based on dynamic pollution assessment and multi-objective constraints according to an embodiment of this application.

[0031] Figure 13 is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0033] The present application will now be described in detail with reference to the accompanying drawings and embodiments.

[0034] 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, and 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.

[0035] The technical approach of this invention, as shown in Figure 1, integrates geospatial datasets encompassing multiple dimensions such as geography, landscape, and ecology, and provides simulation models and solutions for non-point source pollution, thereby obtaining ecological protection and landscape optimization schemes. Specifically, the embodiments of this application construct a closed-loop decision-making framework that includes evaluation constraint simulation feedback, directly quantifying real-time or near-real-time environmental risk assessment results into spatial planning constraints, driving an improved landscape simulation model.

[0036] The final output is a landscape pattern optimization scheme that coordinates ecological benefits with economic development.

[0037] This application uses a landscape optimization example from a typical mountain village in Suzhou for collaborative optimization. Figure 2 shows the research scope of this embodiment; the research scope delineated in the figure is slightly larger than the village's administrative area, covering 6.8 square kilometers. Based on the mountain topography, independent watershed sub-units can be formed within the area. After rainfall, runoff flows down the mountainside from the south side and eventually drains into East Taihu Lake.

[0038] Figure 2 shows a flowchart of a method for collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints according to an embodiment of this application. As shown in Figure 2, the method for collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints includes the following steps: Step S102: Obtain the "source-sink" landscape spatial data and dynamic pollution source strength parameters of the target area, perform multi-scale spatial assessment of non-point source pollution risk in the target area, and generate pollution risk distribution information.

[0039] The above process specifically includes: The spatial distribution of "source landscape" and "converging landscape" was identified and extracted based on remote sensing imagery and digital elevation models.

[0040] Rainfall-runoff simulation experiments are conducted in the target area to obtain dynamic source strength parameters. These dynamic source strength parameters are then associated and stored in a source strength geographic information database, which is updated as land use changes.

[0041] By setting moving windows of different sizes to traverse the target area, the landscape structure index within each window is calculated, and combined with the watershed division results, the optimal spatial assessment unit for pollution load calculation is determined.

[0042] Within the optimal spatial assessment unit, landscape type, dynamic source strength parameters, topography and soil data are integrated to calculate non-point source pollution load and migration risk, and generate a spatial distribution map of pollution risk.

[0043] Specifically, for this mountain village, 0.6-meter high-resolution satellite imagery, a 30-meter resolution digital elevation model (DEM), soil type maps, and rainfall data for the past 5 years were collected. Using an object-oriented classification method, the images were interpreted, and land use was categorized into: tea gardens (primarily agricultural source), construction land (domestic source), forest land (sinkhole), and water area (sinkhole).

[0044] Specifically, the basic data obtained for this area are as follows: 1) Topographic analysis

[0045] A 30m spatial resolution DEM (Digital Elevation Model) of the target area (SR, Shuttle Radar Topography Mission) was obtained. Height, slope, and aspect analyses were performed using the ArcGIS 10.2 terrain analysis module. As shown in Figures 4 and 5, the study area slopes from north to south. Excluding mountainous areas, the elevation is approximately 5 meters, with the highest elevation in the south reaching 275 meters. The average elevation within the area is 201 meters. Slope variations are significant, with an average slope of 30%. Areas with slopes below 5% cover 2.2 km².

[0046] This area accounts for 32% of the total area, with slopes between 5% and 15% covering 1.3 km², and slopes exceeding 30% covering 1.9 km².

[0047] It accounts for 27% of the total area. The slope of the mountains is steeper on the north side, while the south side is basically flat, with an average slope of 16%. The slope aspect of the study area is mainly south-facing, with good views.

[0048] (2) Small watershed runoff analysis As shown in Figures 6 and 7, through a series of analyses such as filling depressions in the DEM, calculating the direction of water flow, the cumulative runoff, and calculating the river length, the small watershed runoff and watershed boundaries of the study area are obtained. After simulating rainfall based on natural terrain, the simulated runoff based on terrain is obtained. By comparing the simulated runoff with the actual water system, the source pollution diffusion path of the study area is obtained.

[0049] (3) Ecological and environmental monitoring data: water environment quality sampling point monitoring

[0050] Based on a detailed investigation of the region's natural hydrological conditions, as shown in Figure 8, seven water environment monitoring points are proposed. The selection primarily considers two factors: topographic conditions and catchment area characteristics, mainly considering the elevation, slope, and catchment area of ​​the water body; and the relative location of the water body to the urbanized area. Monitoring points in unaffected urban areas are selected as environmental baselines for reference, while water body monitoring in urbanized areas is used to demonstrate the impact of urbanization on the ecological environment. Downstream, two different types of monitoring points are selected: one for water bodies purified by wetlands, and the other for untreated water bodies. Comparative analysis will be used to derive water ecological protection strategies during the construction of beautiful villages.

[0051] The main monitoring indicators for water bodies include total nitrogen (TN), total phosphorus (TP), ammonia nitrogen (NH3-N), dissolved oxygen (DO), and chemical oxygen demand (CODMn).

[0052] Ecological and environmental quality monitoring: The study area was obtained by using Landsat 8 1-11 band remote sensing imagery, as shown in Figure 9. Preprocessing steps such as radiometric calibration, atmospheric correction, and geometric fine correction were completed. The imagery around the study area was cropped using a frame and color enhancement was performed. Through RS band fusion, ecological and environmental data of the study area, such as vegetation, water bodies, and surface temperature, can be quickly extracted.

[0053] Traditional methods directly cite pollution output coefficients from literature, resulting in significant errors. In implementing this invention, localized experiments are employed. Standard runoff plots are established on typical tea garden slopes and near hardened village surfaces. Runoff samples are collected simultaneously under natural or simulated rainfall conditions, and the concentrations of total nitrogen (TN) and total phosphorus (TP) are analyzed. Through monitoring multiple rainfall events, an empirical relationship between different rainfall intensities, runoff volumes, and pollutant output is established, thereby obtaining localized, dynamic "source strength" parameters.

[0054] For example, the experimentally measured TN output coefficient of tea gardens under moderate rainfall intensity was 1.2 kg / ha·mm, while the commonly used value in the literature may be 0.8-2.0 kg / ha·mm. Localized data significantly improved the accuracy.

[0055] In GIS, the attribute table of each "source" landscape patch (such as each tea garden) is associated with its corresponding dynamic source strength parameters. This database supports updates; for example, when the fertilization method of the tea garden changes, the parameters can be updated through new experiments.

[0056] Processing at different spatial scales is one of the main factors affecting the regional ecological environment. Due to the small area of ​​the study region (less than 7 square kilometers), using administrative streets as the basic unit in the calculation would not reflect the diversity of Wangshan's landscape. Therefore, a method was adopted to traverse the target area by setting moving windows of different sizes, as shown in Figure 10. Specifically, this included setting square windows with side lengths of 100m, 200m, ..., 1500m, sliding them across the entire area, and calculating the landscape Shannon within each window.

[0057] The landscape employs several indices, including diversity, dominance, patch shape, fractal dimension, sprawl, and patch cohesion. The Shannon diversity index reflects landscape heterogeneity, emphasizing the contribution of rare patch types to information. The dominance index indicates whether a landscape is controlled by a few patches. The patch shape index reflects the complexity of patch shapes; a value close to 1 indicates more regular patch shapes. A fractal dimension closer to 1 indicates stronger self-similarity and simpler patch geometry, suggesting greater disturbance. The sprawl index describes the clustering or extension trend of different patch types. The patch cohesion index reflects the connectivity of corresponding patch types; higher values ​​indicate greater clustering and better connectivity. Analysis of the curves showing how each index changes with window size reveals that the indices tend to stabilize when the window size increases to 300m. Therefore, 300m × 300m is determined as the characteristic scale reflecting the landscape heterogeneity of this region. Simultaneously, hydrological analysis is conducted based on the DEM (Digital Image Model) to delineate sub-basins. Finally, the 300m moving window is superimposed and integrated with the natural sub-basin boundary to form basic assessment units of varying sizes, all of which can well represent landscape and hydrological processes, namely the optimal spatial assessment unit.

[0058] Within each optimal spatial assessment unit, the load is calculated using the formula: Load = Σ(Area of ​​landscape type i × Its dynamic source strength parameter × Rainfall erosivity factor) × Topographic factor × Soil erodibility factor. After load calculation for all optimal spatial assessment units, a high-resolution spatial distribution map of non-point source pollution risk is generated through spatial interpolation. This map clearly shows high-risk areas (such as downstream of contiguous tea plantations and densely populated village areas) and low-risk areas (forest cover areas).

[0059] Step S104: Establish a constraint rule base that includes ecological environment goals, policy planning goals, and landscape pattern goals, wherein the ecological environment goals are set at least in part based on the pollution risk distribution information.

[0060] This step transforms multiple objectives into computable rules. Specifically, the establishment of a constraint rule base that includes ecological environment objectives, policy planning objectives, and landscape pattern objectives includes: the ecological environment objectives, which include pollution load reduction thresholds, key water quality target values, and vegetation coverage target values ​​set based on pollution risk distribution information.

[0061] For example, the ecological and environmental objectives include, but are not limited to, designing to "reduce the TN load of high-risk optimal spatial assessment units by 30% during the planning period" and "ensure that the TP concentration in water flowing into the main river does not exceed 0.2 mg / L". Simultaneously, spatial rules are set such as "forest coverage rate not less than 40%" and "the width of newly added ecological corridors not less than 50 meters".

[0062] The policy planning objectives include the protection boundaries of basic farmland, the total control indicators for construction land, and the land demand for the development of characteristic industries.

[0063] For example, the policy planning objectives include, but are not limited to, setting the "basic farmland protection area" vector layer as a non-convertible zone; setting the "total amount of newly added construction land shall not exceed 50 hectares"; and setting the "permission to convert no more than 10 hectares of forest land or farmland into tourism facility land within 500 meters of main traffic arteries".

[0064] The landscape pattern objectives include the objectives of improving the landscape diversity index and enhancing landscape spatial connectivity.

[0065] For example, the landscape pattern objectives include, but are not limited to, setting landscape index objectives such as “increasing the overall landscape Shannon Diversity Index (SHDI) by 5%” and “reducing the average distance between woodland patches”.

[0066] Step S106: Based on the historical landscape evolution pattern, the constraint rule base is introduced as the decision layer to perform multi-objective comprehensive scoring and screening of the state transition of landscape cells, and simulate and generate future landscape pattern schemes that meet the multi-objective constraints.

[0067] The above method includes the following specific steps: The basic CA-Markov model is trained using land use maps from 2015 and 2025. The standard CA-Markov model is trained in IDRISI or a similar platform to obtain the transition probability matrix between the five land use categories and appropriate neighborhood rules.

[0068] When the model runs, for each cell (center cell) to be transformed, in addition to calculating its transformation probability based on historical probability and neighborhood impact, a multi-objective decision layer is added. During decision-making, it is first assumed that the cell will be transformed from its current type A to a candidate type B; a temporary landscape state is constructed in memory, and the impact of this transformation on various rules in the "constraint rule base" is quickly calculated. For example, the changes in TN load of the parcel, forest cover in the sub-basin, and global SHDI after the transformation are calculated. Weights are preset for each rule (e.g., pollution load weight 0.4, economic development weight 0.3, landscape connectivity weight 0.3). After normalizing the above pre-assessment results, a weighted sum is performed to obtain the "comprehensive benefit score" for this transformation. Simultaneously, a small "random perturbation factor" (e.g., a random change of ±5% in the score) is introduced to prevent the algorithm from prematurely converging to a local optimum.

[0069] Next, a scoring threshold is set. The transformation will only be executed if the "overall benefit score" of the hypothesis transformation is higher than the threshold and its traditional CA transformation probability is also high. Otherwise, the model will consider other transformation types or remain unchanged.

[0070] Then, three scenarios—"ecological conservation," "tourism development," and "comprehensive balance"—are set up, mainly by adjusting the weights of each objective in the constraint rule base. The improved model is then run and iterated up to the planning target year (e.g., 2035), outputting future landscape pattern schemes under each of the three scenarios.

[0071] Therefore, in some preferred embodiments, the step of introducing the constraint rule base as a decision layer based on the historical landscape evolution law, performing multi-objective comprehensive scoring and screening of the state transition of landscape cells, and simulating the generation of future landscape pattern schemes that meet multi-objective constraints includes: using a cellular automaton model of local land use competition, taking the number of each landscape type cell in the neighborhood as the neighborhood scenario, taking the central landscape cell as the input landscape as the input variable, and simulating the output landscape type with the central landscape cell; In the neighborhood transformation rules of the competing cellular automata model, the multi-objective constraint rule base is integrated as an independent decision layer; For each candidate cell state transition, its comprehensive impact score on each rule in the constraint rule base is calculated. When calculating the comprehensive impact score, differentiated weights are assigned to different constraint rules, and a random perturbation factor is introduced. When the comprehensive impact score meets the preset threshold, the conversion is performed.

[0072] As shown in Figure 11, the input landscape type for the central landscape cell is agricultural land. In the neighboring context, there are 2 construction land landscape cells, 3 agricultural land cells, and 3 forest land cells. Influenced by the neighboring context, the output landscape type for the central landscape is construction land.

[0073] The probabilities of agricultural land and forest land are different. The probability of the central landscape land use type under different neighborhood scenarios is calculated using at least two periods of landscape types. The specific calculation method is as follows: Consider a landscape change process as Entry(), where LUi→LUj represents the process of the central landscape unit type changing from i to j, and LUk=n represents the neighborhood scenario where the number of land use type k cells in the neighborhood is n. Based on this, the input landscape, output landscape, and neighborhood scenario of all landscape units in the study area are calculated as follows: Further calculations are made to show the potential for the central landscape cell to change from landscape i to j when the number of landscape type k cells in the neighborhood is n: Finally, the probability of landscape i transforming into landscape j is calculated using a conceptual statistical model, generating a landscape land use optimization scheme based on ecological and environmental health.

[0074] The above method seamlessly integrates the previously fragmented pollution assessment with spatial planning. After planners set development goals, the system can automatically explore and recommend the optimal land space allocation scheme under environmental constraints, significantly improving the scientific rigor, precision, and operability of rural planning, and providing a powerful technical tool for the construction of beautiful villages. In some preferred embodiments, after simulating and generating a future landscape pattern scheme that satisfies multi-objective constraints, the method further includes: By comparing multiple landscape pattern schemes generated under different development scenarios, and re-evaluating the pollution risks and ecological benefits of each scheme, a recommended optimization scheme is output.

[0075] In some preferred embodiments, the comparison of multiple landscape pattern schemes generated under different development scenarios and the reassessment of the pollution risks and ecological benefits of each scheme includes: constructing a comprehensive evaluation index system covering ecological benefits, economic benefits and social adaptability; The aforementioned indicator system is used to quantitatively score and rank the simulated scenario solutions. The highest-scoring solution will be output as the recommended optimization solution, and the output will include at least one of the following: a spatial planning map and a supporting ecological engineering layout suggestion map.

[0076] In some preferred embodiments, the process further includes initiating a new round of optimization for the evaluation object based on the recommended optimization scheme.

[0077] In some preferred embodiments, the method further includes a step of linking with a real-time monitoring system: accessing online water quality monitoring data and meteorological data of the area; When monitoring data triggers early warning conditions, the dynamic evaluation steps and collaborative optimization simulation steps are automatically initiated or adjusted to achieve dynamic updating and adaptive management of the landscape optimization scheme.

[0078] In some preferred embodiments, the method further includes multi-dimensional visualization of the pollution risk spatial assessment results, multi-scenario simulation process, and final recommended solution using two-dimensional maps, three-dimensional scenes, or statistical charts.

[0079] The method described above abandons the fixed, regionalized parameters of traditional models, adopting a combination of dynamic source strength parameters and multi-scale evaluation units. It obtains more realistic "source strength" through localized experiments and determines the optimal evaluation scale by combining moving windows and small watershed analysis, significantly improving the accuracy of spatial heterogeneity assessment of small watershed non-point source pollution. Simultaneously, it transforms abstract planning objectives into concrete, spatially computable rules, providing clear instructions for computer-aided decision-making. Creatively, it incorporates the constraint rule base as an independent entity from historical probabilities and neighborhood rules in decision-making, enabling the model to proactively explore landscape configurations that meet multiple requirements.

[0080] Based on the same inventive concept as the above method embodiments, as shown in FIG. 12, an embodiment of the present application further provides a collaborative optimization device for rural landscape pattern based on dynamic pollution assessment and multi-objective constraints, including: a pollution assessment module, configured to obtain the "source-sink" landscape spatial data and dynamic pollution source intensity parameters of the target area, perform multi-scale spatial assessment of the non-point source pollution risk of the target area, and generate pollution risk distribution information; a constraint module, configured to establish a constraint rule library including ecological environment objectives, policy planning objectives and landscape pattern objectives, wherein at least part of the ecological environment objectives are set based on the pollution risk distribution information; a scheme generation module, configured to, based on the historical landscape evolution law, introduce the constraint rule library as the decision-making layer, perform multi-objective comprehensive scoring and screening on the state transition of landscape cells, and simulate and generate a future landscape pattern scheme that meets multi-objective constraints.

[0081] It should be noted that although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0082] Based on the same inventive concept as the above method embodiments, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the control method in the above embodiments.

[0083] In one embodiment, the electronic device may be a server. In this embodiment, the structure of the electronic device may be as Figure 13 shown, including a memory 2001, a communication module 2003, and one or more processors 2002.

[0084] The memory 2001 is used to store the computer program executed by the processor 2002. The memory 2001 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system and programs required to run an instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0085] Memory 2001 may be volatile memory, such as random-access memory (RAM); memory 2001 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 2001 may be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto.

[0086] Memory 2001 can be a combination of the above-mentioned memories.

[0087] Processor 2002 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 2002 is used to implement the above-mentioned audio data processing method when calling computer programs stored in memory 2001.

[0088] The communication module 2003 is used to communicate with terminal devices and other servers.

[0089] This embodiment does not limit the specific connection medium between the memory 2001, communication module 2003, and processor 2002. In Figure 13, the memory 2001 and processor 2002 are connected via a bus 2004, which is depicted by arrows. The connection methods between other components are merely illustrative and not intended to be limiting. The bus 2004 can be categorized as an address bus, data bus, control bus, etc. For ease of description, only one arrow is used in Figure 13, but this does not imply that there is only one bus or one type of bus.

[0090] Based on the same inventive concept as the above-described method embodiments, embodiments of the present invention also provide a computer-readable storage medium for storing a computer program. When the computer program is run on a computer, it enables the electronic device to implement the control method described in the above embodiments. The computer-readable storage medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0091] Based on the same inventive concept as the above-described method embodiments, embodiments of the present invention also provide a computer program product, which includes a computer program that, when run on an electronic device, causes the electronic device to perform the steps of the control methods described above according to various exemplary embodiments of this application. The program product may take the form of any combination of one or more readable media. These computer program commands can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the commands executed by the processor of the computer or other programmable data processing device generate a process for implementing... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0092] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, will understand that...

[0093] Further changes and modifications can be made to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

Claims

1. A method for collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints, characterized in that, include: Acquire "source-sink" landscape spatial data and dynamic pollution source strength parameters of the target area, conduct multi-scale spatial assessment of non-point source pollution risk in the target area, and generate pollution risk distribution information; Establish a constraint rule base that includes ecological and environmental goals, policy planning goals, and landscape pattern goals, wherein the ecological and environmental goals are set at least in part based on the pollution risk distribution information; Based on the historical landscape evolution patterns, the aforementioned constraint rule base is introduced as the decision layer to perform multi-objective comprehensive scoring and screening of the state transitions of landscape cells, and simulate and generate future landscape pattern schemes that meet the multi-objective constraints.

2. The method according to claim 1, characterized in that, The process involves acquiring "source-sink" landscape spatial data and dynamic pollution source strength parameters for the target area, conducting multi-scale spatial assessment of non-point source pollution risk in the target area, and generating pollution risk distribution information, including: identifying and extracting the spatial distribution of "source landscape" and "sink landscape" based on remote sensing images and digital elevation models. By setting moving windows of different sizes to traverse the target area, the landscape structure index within each window is calculated, and combined with the watershed division results, the optimal spatial assessment unit for pollution load calculation is determined. Within the optimal spatial assessment unit, landscape type, dynamic source strength parameters, topography and soil data are integrated to calculate non-point source pollution load and migration risk, and generate a spatial distribution map of pollution risk.

3. The method according to claim 2, characterized in that, The dynamic source strength parameters are obtained by conducting a rainfall-runoff simulation experiment for the target area, and obtaining the dynamic source strength parameters through the experiment. The dynamic source strength parameters are associated and stored in a source strength geographic information database, which is updated as land use changes.

4. The method according to claim 1, characterized in that, The establishment of a constraint rule base that includes ecological environment goals, policy planning goals, and landscape pattern goals includes: the ecological environment goals, including pollution load reduction thresholds, water quality target values ​​for key water bodies, and vegetation coverage target values ​​set based on pollution risk distribution information; The policy planning objectives include the basic farmland protection boundary, the total control index of construction land, and the land demand for the development of characteristic industries; The landscape pattern objectives include the objectives of improving the landscape diversity index and enhancing landscape spatial connectivity.

5. The method according to claim 1, characterized in that, Based on historical landscape evolution patterns, the aforementioned constraint rule base is introduced as a decision-making layer to perform multi-objective comprehensive scoring and screening of landscape cell state transitions, simulating and generating future landscape pattern schemes that meet multi-objective constraints. This includes: using a cellular automata model of local land use competition, with the number of cells of each landscape type within the neighborhood as the neighborhood scenario. The central landscape cell simulates the input landscape as the input variable, and the central landscape cell simulates the output landscape type. In the neighborhood transformation rules of the competing cellular automata model, the multi-objective constraint rule base is integrated as an independent decision layer; For each candidate cell state transition, calculate its comprehensive impact score on each rule in the constraint rule base; When the comprehensive impact score meets the preset threshold, the conversion is performed.

6. The method according to claim 5, characterized in that, When calculating the comprehensive impact score, differentiated weights are assigned to different constraint rules; Preferably, a random disturbance factor is introduced when calculating the comprehensive impact score.

7. The method according to claim 1, characterized in that, After the simulation generates a future landscape pattern scheme that satisfies multiple objective constraints, it also includes: comparing multiple landscape pattern schemes generated under different development scenarios, reassessing the pollution risks and ecological benefits of each scheme, and outputting a recommended optimization scheme; Preferably, the recommended optimization scheme is used to initiate a new round of optimization process for the evaluation object; Preferably, the comparison of multiple landscape pattern schemes generated under different development scenarios and the reassessment of the pollution risks and ecological benefits of each scheme includes: constructing a comprehensive evaluation index system covering ecological benefits, economic benefits and social adaptability; The aforementioned indicator system is used to quantitatively score and rank the simulated scenario solutions. The highest-scoring solution will be output as the recommended optimization solution, and the output will include at least one of the following: a spatial planning map and a supporting ecological engineering layout suggestion map.

8. A device for collaborative optimization of rural landscape patterns based on dynamic pollution assessment and multi-objective constraints, characterized in that: include: The pollution assessment module is used to acquire "source-sink" landscape spatial data and dynamic pollution source strength parameters of the target area, perform multi-scale spatial assessment of non-point source pollution risk in the target area, and generate pollution risk distribution information. The constraint module is used to establish a constraint rule base that includes ecological and environmental goals, policy planning goals, and landscape pattern goals, wherein the ecological and environmental goals are set at least in part based on the pollution risk distribution information; The scheme generation module is used to simulate and generate future landscape pattern schemes that meet the multi-objective constraints by introducing the constraint rule library as the decision layer based on the historical landscape evolution pattern.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the electronic device to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer. A program that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 7.

Images