Agricultural waste resource distribution simulation method and system based on big data analysis

Abstract

The application discloses a kind of based on big data analysis's agricultural waste resourceization layout simulation method and system, belong to agricultural waste processing field, including: according to dynamic distribution characteristics, using geographic information system analysis terrain undulation and road condition, construct space constraint model, determine the feasibility range of transport path;If terrain undulation exceeds preset threshold, then obtain optimized path cost set by adjusting transport path through weighted distance algorithm;Through candidate facility site selection point set, using K means clustering algorithm, divide service radius range, determine the service coverage area of each facility;According to service coverage area and dynamic distribution characteristics, calculate the waste treatment capacity demand of each region, obtain facility scale configuration scheme;If processing capacity demand exceeds preset threshold, then obtain final resourceization facility layout scheme by adjusting site selection point set and coverage area through iterative optimization algorithm.The application can carry out reasonable agricultural waste recovery layout.

Description

Technical Field

[0001] This invention belongs to the field of agricultural waste treatment technology, and in particular relates to a method and system for simulating the resource utilization layout of agricultural waste based on big data analysis. Background Technology

[0002] Agricultural waste recycling is a crucial pathway to achieving sustainable agricultural development and environmental protection, directly impacting rural ecological balance and resource recycling efficiency. Improperly handled agricultural waste, such as crop straw and livestock manure, not only wastes resources but can also lead to soil pollution and eutrophication. Scientifically planning the layout of waste recycling facilities is essential for improving treatment efficiency and reducing environmental risks. However, existing methods have significant shortcomings in integrating multi-source information and dynamic optimization. Many solutions rely on single data sources or static analysis, making it difficult to address the spatiotemporal variations in agricultural waste distribution and effectively balance transportation costs and processing capacity requirements, resulting in a lack of precision in site selection and service area planning for recycling facilities. In practical applications, the core challenges of agricultural waste recycling stem from two interrelated technical factors: the dynamic nature of waste generation and distribution, and the complexity of spatial constraints. Waste generation is influenced by season, crop type, and livestock scale, exhibiting significant spatiotemporal heterogeneity. For example, in a region, straw generation is concentrated in spring, while livestock manure may dominate in autumn. This dynamic change requires site selection models to adapt to the waste distribution at different times in real time. However, the dynamic nature of waste distribution further complicates spatial constraints. Factors such as topographic relief, road conditions, and environmentally sensitive areas (e.g., water source protection zones) limit facility site selection and transportation route choices. For example, in mountainous areas, steep terrain can lead to soaring transportation costs, while flat areas may be unsuitable for building treatment plants due to environmental sensitivity restrictions. This interaction between dynamic distribution and spatial constraints makes the site selection and service radius optimization of resource recovery facilities exceptionally complex. Therefore, how to construct an accurate resource recovery facility layout optimization model that comprehensively considers multi-dimensional spatial constraints such as topography, transportation routes, and environmentally sensitive areas under dynamically changing agricultural waste distribution has become a key issue in the field of agricultural waste resource recovery layout simulation. Summary of the Invention

[0003] This invention proposes a method and system for simulating the layout of agricultural waste resource utilization based on big data analysis, in order to solve the problems existing in the above-mentioned prior art.

[0004] To achieve the above objectives, this invention provides a method for simulating the layout of agricultural waste resource utilization based on big data analysis, comprising the following steps:

[0005] Acquire spatiotemporal distribution data of agricultural waste, determine the types, quantities, and seasonal variation patterns of waste based on the spatiotemporal distribution data, and obtain dynamic distribution characteristics;

[0006] Based on the dynamic distribution characteristics, a geographic information system is used to analyze the terrain undulations and road conditions, construct a spatial constraint model, and obtain the feasibility range of transportation routes.

[0007] When the terrain undulations exceed a preset threshold, the transportation route is adjusted using a weighted distance algorithm to obtain an optimized set of route costs.

[0008] Based on the optimized path cost set and combined with the distribution data of environmentally sensitive areas, spatial overlay analysis is used to screen out a set of candidate facility site selection points that meet environmental constraints.

[0009] Based on the set of candidate facility sites, the service radius range is divided using the K-means clustering algorithm to determine the service coverage area of ​​each facility;

[0010] Based on the service coverage area and dynamic distribution characteristics, the waste treatment capacity requirements of each region are calculated to obtain a facility scale configuration plan.

[0011] When the processing capacity demand exceeds the preset threshold, the site selection point set and coverage area are adjusted through iterative optimization algorithms to obtain the final resource-based facility layout scheme.

[0012] Optionally, the obtained dynamic distribution characteristics include:

[0013] Remote sensing image data and agricultural production records related to agricultural waste were acquired through a multi-source data acquisition system, and a spatiotemporal distribution dataset containing timestamps and geographic coordinates was constructed.

[0014] By employing a data fusion analysis method, remote sensing image data is matched with agricultural production records to generate preliminary classification results of the types and quantities of agricultural waste;

[0015] If the confidence level of the classification result is lower than the preset threshold, the remote sensing image data is used to extract features through the support vector machine algorithm to obtain the distribution characteristics of agricultural waste types.

[0016] Based on the distribution characteristics of different types and combined with time series data in agricultural production records, analyze the seasonal variation patterns of agricultural waste and determine the seasonal variation trend.

[0017] By modeling seasonal variation trends using the random forest algorithm, the dynamic distribution characteristics of agricultural waste are predicted, generating spatiotemporal distribution prediction results.

[0018] Based on the spatiotemporal distribution prediction results, the spatiotemporal distribution pattern of generated agricultural waste is obtained, and a distribution characteristic description is obtained.

[0019] Optionally, the feasibility range of determining the transportation route includes:

[0020] Topographic relief data is obtained from a high-resolution digital elevation model using a geographic information system, and combined with road network data to generate a topographic constraint dataset that includes slope and road type.

[0021] By using a weighted overlay analysis method, combining terrain relief data and road condition data, the spatial constraint weights of transportation routes are calculated to obtain the route feasibility distribution.

[0022] Based on the distribution of path feasibility and combined with the distribution characteristics of agricultural waste, a spatial matching relationship between the path and the waste distribution is generated to obtain the matched path distribution data.

[0023] The matched path distribution data is smoothed using spatial interpolation to generate a continuous transportation path feasibility distribution.

[0024] Optionally, the optimized path cost set includes:

[0025] When the slope value of the terrain constraint dataset exceeds the preset threshold, the transport path weights are adjusted by the least squares method to obtain the optimized path weight set.

[0026] Based on the optimized set of path weights, the Dijkstra algorithm is used to calculate the shortest path in the road network, generating a preliminary set of transportation paths.

[0027] By using spatial analysis methods, the preliminary set of transportation routes is spatially overlaid with agricultural waste distribution data to obtain a spatially matched dataset of routes and waste distribution.

[0028] If the matching degree of the spatial matching dataset is lower than the preset threshold, the kernel density estimation method is used to smooth the path distribution and generate continuous path distribution features.

[0029] Based on the continuous path distribution characteristics and combined with the road network capacity data, a set of transportation path costs is generated.

[0030] Optionally, the selection of a set of candidate facility sites that meet environmental constraints includes:

[0031] Spatial constraint features are extracted from the distribution data of environmentally sensitive areas. The environmentally sensitive areas are divided into discrete spatial units using a rasterization method to obtain an environmental constraint raster dataset.

[0032] Based on the environmental constraint raster dataset and the path cost set, spatial overlay analysis is used to calculate the spatial correlation degree between each spatial unit and the path cost, and the spatial correlation degree distribution is obtained.

[0033] If there are areas in the spatial correlation distribution that are below the preset threshold, a weighted distance algorithm is used to preliminarily screen the candidate facility site selection point set to obtain a preliminary site selection point set.

[0034] Based on the preliminary set of site selection points and combined with the terrain constraint factors in the geospatial data, the least squares method is used to optimize the location weights of the site selection points, resulting in the optimized set of site selection point weights.

[0035] Based on the optimized set of site selection point weights, spatial clustering analysis is used to determine the spatial distribution characteristics of the site selection point set, and the clustered candidate site selection point set is obtained.

[0036] Based on the clustered candidate site selection point set and combined with the path capacity data, the spatial network analysis method is used to calculate the connectivity between the site selection points and the path network, and obtain the connectivity distribution of facility site selection.

[0037] Based on the connectivity distribution of facility sites and combined with environmental impact factors, a weighted overlay analysis is used to select the final set of facility sites that meet environmental constraints and accessibility requirements.

[0038] Optionally, determining the service coverage area of ​​each facility includes:

[0039] Based on the candidate facility site selection point set, the K-means clustering algorithm is used to cluster and group the facility site selection point set. According to the preset service radius threshold, the service coverage area of ​​each facility site selection point is divided to obtain a preliminary service coverage area set.

[0040] Traffic capacity data is obtained from the path network data. Based on the preliminary service coverage area set, spatial network analysis method is used to calculate the connectivity between each service coverage area and the path network. If the connectivity is lower than a preset threshold, the service radius range is adjusted to obtain an optimized service coverage area set.

[0041] Based on the optimized service coverage area set, combined with terrain factors and environmental impact data, a weighted overlay analysis is used to calculate the comprehensive weight of terrain factors and environmental impact in each service coverage area. If the comprehensive weight is lower than a preset threshold, the service coverage area is removed to obtain the final service coverage area set.

[0042] Optionally, the obtained facility scale configuration scheme includes:

[0043] By using service coverage area and waste distribution data, a weighted analysis method is employed to predict the amount of waste generated in each region, thereby obtaining the regional waste distribution characteristics.

[0044] Based on the regional waste distribution characteristics and combined with waste type data, a classification algorithm is used to determine the processing capacity requirements of each region.

[0045] If the processing capacity requirement exceeds the preset threshold, then by combining the facility location distribution data and using spatial analysis methods, the facility scale configuration is adjusted to obtain a preliminary facility scale plan.

[0046] Based on the preliminary facility scale plan and combined with transportation route planning data, network analysis methods are used to calculate the transportation efficiency of each facility, resulting in an optimized facility scale plan.

[0047] By using the optimized facility scale plan and combining environmental carrying capacity data, a weighted overlay analysis is adopted to calculate the environmental impact weight of each region and determine whether the environmental carrying capacity meets the requirements.

[0048] If the environmental carrying capacity is lower than the preset threshold, the transportation route planning will be adjusted, the facility scale configuration will be recalculated, and the final facility scale configuration scheme will be obtained.

[0049] Optionally, the final resource utilization facility layout scheme includes:

[0050] By using regional waste generation data and cluster analysis, the waste distribution density of each region is determined, and the regional waste distribution characteristics are obtained.

[0051] If the distribution characteristics of waste in the region show that the density is higher than the preset threshold, the genetic algorithm is used to adjust the site selection point set and coverage area to obtain a preliminary resource recovery facility layout plan.

[0052] Based on the preliminary resource utilization facility layout plan, network analysis method is used to calculate the transportation path efficiency between facilities and obtain the optimized transportation path plan.

[0053] By optimizing the transportation route planning and combining it with environmental carrying capacity data, a weighted overlay analysis is used to calculate the environmental impact weight of each region and determine whether the environmental carrying capacity meets the requirements.

[0054] If the environmental carrying capacity is lower than the preset threshold, the site selection point set and coverage area are readjusted through the simulated annealing algorithm to obtain an updated resource recovery facility layout scheme.

[0055] Based on the updated resource recovery facility layout plan, spatial analysis methods are used to verify the matching degree between the facility distribution and the regional waste distribution characteristics, and the final resource recovery facility layout plan is obtained.

[0056] This invention also provides a simulation system for the layout of agricultural waste resource utilization based on big data analysis, comprising:

[0057] The data acquisition module is used to acquire remote sensing images of agricultural waste and agricultural production records through a multi-source data acquisition system, determine the types, quantities, and seasonal variation patterns of waste, and obtain dynamic distribution characteristics;

[0058] The spatial constraint modeling module is used to construct a spatial constraint model based on dynamic distribution characteristics, using a geographic information system to analyze terrain undulations and road conditions, and to determine the feasibility range of transportation routes.

[0059] The route optimization module is used to adjust the transportation route using a weighted distance algorithm if the terrain undulation exceeds a preset threshold, thereby obtaining an optimized set of route costs.

[0060] The environmental constraint screening module is used to screen out a set of candidate facility site selection points that meet environmental constraints based on the optimized path cost set and the distribution data of environmentally sensitive areas, using spatial overlay analysis.

[0061] The service area division module is used to divide the service radius range and determine the service coverage area of ​​each facility by using the K-means clustering algorithm based on the candidate facility site selection point set.

[0062] The demand calculation module is used to calculate the waste treatment capacity requirements of each region based on the service coverage area and dynamic distribution characteristics, and to obtain a facility scale configuration plan.

[0063] The layout optimization module is used to adjust the set of site selection points and coverage area through iterative optimization algorithms if the processing capacity demand exceeds a preset threshold, so as to obtain the final resource-based facility layout scheme.

[0064] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0065] Compared with the prior art, the present invention has the following advantages and technical effects:

[0066] This invention discloses a big data analysis-based simulation method for the resource utilization layout of agricultural waste. Addressing the challenges of dynamic spatiotemporal distribution of agricultural waste, transportation routes constrained by terrain and environment, and difficulties in optimizing facility site selection and service coverage, this invention integrates remote sensing imagery, agricultural production records, and a geographic information system (GIS) to construct a comprehensive solution from data acquisition to facility layout. First, this invention acquires the types, quantities, and seasonal variations of waste through multi-source data collection, generating dynamic distribution characteristics. Next, combining terrain undulations and road conditions, a spatial constraint model is constructed using a GIS, and a weighted distance algorithm is used to optimize transportation routes and reduce costs. Subsequently, spatial overlay analysis is used to screen candidate site locations that meet environmental constraints, and a K-means clustering algorithm is used to divide the service radius, determining the coverage area and processing capacity requirements. If the requirements exceed the limits, an iterative optimization algorithm is used to adjust the site selection and coverage area, ultimately generating an efficient facility layout scheme. This invention achieves high efficiency and environmental friendliness in the resource utilization of agricultural waste, significantly improving the scientific nature of facility site selection and operational efficiency. Attached Figure Description

[0067] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0068] Figure 1 This is a flowchart of a method according to an embodiment of the present invention;

[0069] Figure 2 This is a system structure diagram of an embodiment of the present invention. Detailed Implementation

[0070] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0071] 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.

[0072] like Figure 1 As shown, this embodiment provides a method for simulating the layout of agricultural waste resource utilization based on big data analysis, including the following steps:

[0073] Acquire spatiotemporal distribution data of agricultural waste, determine the types, quantities, and seasonal variation patterns of waste based on the spatiotemporal distribution data, and obtain dynamic distribution characteristics;

[0074] Based on the dynamic distribution characteristics, a geographic information system is used to analyze the terrain undulations and road conditions, construct a spatial constraint model, and obtain the feasibility range of transportation routes.

[0075] When the terrain undulations exceed a preset threshold, the transportation route is adjusted using a weighted distance algorithm to obtain an optimized set of route costs.

[0076] Based on the optimized path cost set and combined with the distribution data of environmentally sensitive areas, spatial overlay analysis is used to screen out a set of candidate facility site selection points that meet environmental constraints.

[0077] Based on the set of candidate facility sites, the service radius range is divided using the K-means clustering algorithm to determine the service coverage area of ​​each facility;

[0078] Based on the service coverage area and dynamic distribution characteristics, the waste treatment capacity requirements of each region are calculated to obtain a facility scale configuration plan.

[0079] When the processing capacity demand exceeds the preset threshold, the site selection point set and coverage area are adjusted through iterative optimization algorithms to obtain the final resource-based facility layout scheme.

[0080] Specifically, the following steps are included:

[0081] Step S101: Obtain the spatiotemporal distribution data of agricultural waste through a multi-source data acquisition system, and combine it with remote sensing images and agricultural production records to determine the types, quantities, and seasonal variation patterns of waste, thereby obtaining dynamic distribution characteristics.

[0082] Specifically, remote sensing imagery data and agricultural production records related to agricultural waste are acquired through a multi-source data acquisition system to construct a spatiotemporal distribution dataset containing timestamps and geographic coordinates. A data fusion analysis method is used to match the remote sensing imagery data with the agricultural production records, generating preliminary classification results for the types and quantities of agricultural waste. If the confidence level of the classification results is lower than a preset threshold, a support vector machine algorithm is used to extract features from the remote sensing imagery data to obtain the type distribution characteristics of agricultural waste. Based on the type distribution characteristics and combined with time-series data from the agricultural production records, the seasonal variation patterns of agricultural waste are analyzed to determine the seasonal variation trend. A random forest algorithm is used to model the seasonal variation trend, predicting the dynamic distribution characteristics of agricultural waste and generating spatiotemporal distribution prediction results. If the deviation between the predicted results and the actual collected spatiotemporal distribution data exceeds a preset threshold, a convolutional neural network is used to perform deep analysis on the remote sensing imagery data to adjust the dynamic distribution characteristics. Based on the adjusted dynamic distribution characteristics, the spatiotemporal distribution patterns of agricultural waste are generated, resulting in the final distribution characteristic description.

[0083] For example, agricultural waste-related data acquired through a multi-source data acquisition system can be combined with satellite remote sensing imagery and ground-based agricultural production records to form a spatiotemporally distributed dataset containing timestamps and geographic coordinates. Remote sensing imagery, acquired via Landsat or Sentinel-2 satellites, has a spatial resolution of 10-30 meters, covers farmland areas, and records crop planting and waste disposal information. Agricultural production records include crop type, planting time, and harvest quantity, sourced from farmer reports or agricultural IoT devices. The dataset is stored in time-series format, such as monthly data from March 2024 to February 2025, with each record containing latitude and longitude, a timestamp, and waste type.

[0084] In this embodiment, the data fusion analysis method uses weighted overlay technology to match the spectral features of remote sensing images with agricultural production records.

[0085] For example, rice straw has high near-infrared reflectivity, which can be used to initially classify waste types and estimate quantities, such as approximately 2 tons of straw per hectare. If the classification confidence level is below the threshold of 0.8, a support vector machine is used to extract image texture and spectral features to generate species distribution characteristics, such as distinguishing between piles of corn stalks and fruit tree branches. This method improves classification accuracy and reduces misclassification.

[0086] Specifically, seasonal variation pattern analysis can be combined with time series data in agricultural production records to observe changes in waste distribution.

[0087] For example, rice straw is mainly produced in autumn (September-October), with a decrease in its accumulation during winter. Using a random forest algorithm, with input features including crop type, season, and rainfall, the algorithm predicts the dynamic distribution characteristics of waste, such as predicting that the amount of waste accumulated in a certain area in autumn will be 500 tons, decreasing to 100 tons in spring. If the prediction deviation exceeds 10%, a convolutional neural network is used to perform deep analysis on remote sensing imagery, extracting deep spatial features and adjusting the dynamic distribution characteristics.

[0088] For example, networks can identify the boundaries and density of waste dumping sites in images and optimize prediction models.

[0089] For example, the adjusted dynamic distribution characteristics can generate the spatiotemporal distribution patterns of agricultural waste, describing the distribution trends of waste in different seasons and regions, such as waste being concentrated in the northeastern part of farmland in autumn and dispersed in the south in spring. This distribution pattern helps to accurately formulate waste treatment plans, such as optimizing composting site selection or planning transportation routes, thereby improving resource utilization efficiency and reducing environmental pollution.

[0090] In this embodiment, the spatiotemporal distribution prediction results can be used to guide agricultural waste management.

[0091] For example, if forecasts indicate a surge in waste accumulation in a region during the fall, advance deployment of treatment facilities can reduce the risk of incineration. The final distribution characteristics provide data support for agricultural waste management, optimize resource allocation, and contribute to sustainable development.

[0092] Step S102: Based on the dynamic distribution characteristics, use a geographic information system to analyze the terrain undulations and road conditions, construct a spatial constraint model, and determine the feasibility range of the transportation route.

[0093] Specifically, a Geographic Information System (GIS) is used to acquire terrain relief data from a high-resolution digital elevation model (DEM), which is then combined with road network data to generate a terrain constraint dataset containing slope and road type. A weighted overlay analysis method is used to fuse terrain relief data and road condition data to calculate the spatial constraint weights of transportation routes, resulting in a preliminary distribution of route feasibility. If the weights of the preliminary route feasibility distribution are lower than a preset threshold, the shortest path algorithm is used to optimize the road network data and determine a set of highly feasible transportation routes. Based on the set of highly feasible transportation routes and the distribution characteristics of agricultural waste, a spatial matching relationship between routes and waste distribution is generated, resulting in matched route distribution data. Spatial interpolation is used to smooth the matched route distribution data, generating a continuous transportation route feasibility distribution and determining the smoothed route distribution characteristics. If the deviation between the smoothed route distribution characteristics and the actual road condition data exceeds a preset threshold, a random forest algorithm is used to adjust the route distribution characteristics, resulting in an optimized transportation route distribution.

[0094] In this embodiment, the process of the geographic information system obtaining terrain undulation data from the high-resolution digital elevation model can be understood as extracting features such as slope and aspect through three-dimensional terrain modeling.

[0095] For example, using a 30-meter resolution digital elevation model, the terrain of an agricultural area can be analyzed to extract terrain data with slope values ​​ranging from 0° to 45°, generating a raster dataset containing slope information. This dataset can reflect the limitations of terrain on transportation routes; for instance, areas with steep slopes may not be suitable for heavy vehicles. Combined with road network data, the constraints on transportation routes can be further clarified.

[0096] For example, an agricultural waste collection point is located on a hillside with a slope of 10°. There are tertiary highways and rural roads nearby. Through geographic information system analysis, the rural roads are more suitable for transportation due to their gentle slope.

[0097] For example, the weighted overlay analysis method integrates terrain relief data and road condition data by assigning weights to slope, road type, and road surface condition.

[0098] Optionally, slope weight accounts for 40%, road type for 30%, and road surface condition for 30%. In an agricultural area, assuming a Class III highway has a slope of 5° and an asphalt surface, the calculated route feasibility is relatively high. However, another rural dirt road has a slope of 15° and a poor road surface, resulting in a weight below the threshold of 0.7, requiring further optimization. This method can clearly distinguish the feasibility of routes, providing a basis for subsequent analysis.

[0099] It should be noted that if the path feasibility weight is lower than the threshold, the shortest path algorithm can be used to optimize the road network.

[0100] For example, for rural dirt roads with a weight below 0.7, the Dijkstra algorithm is used to replan the route, combining road length and travel time, to find an alternative route that is 10% longer but has a gentler slope. This route is more suitable for agricultural waste transport vehicles, ensuring transportation efficiency.

[0101] In this embodiment, the spatial matching relationship between the generated path and the distribution of agricultural waste can be achieved through spatial overlay analysis.

[0102] For example, if 1,000 tons of agricultural waste in a certain area are distributed across 10 collection points, matching analysis can be used to determine the set of closest paths, prioritizing roads with a slope of less than 8 degrees. This matching method can effectively reduce transportation costs and improve efficiency.

[0103] For example, when using spatial interpolation methods to smooth path distribution data, Kriging interpolation can be employed. Suppose that the path distribution data for a certain area is discontinuous at some nodes; interpolation can generate a continuous feasibility distribution map, with the slope smoothly transitioning from 5° to 10°, facilitating the planning of continuous transportation routes. This smooth distribution can more intuitively demonstrate path feasibility.

[0104] Optionally, if the smoothed path distribution deviates significantly from the actual road conditions, it can be adjusted using a random forest algorithm.

[0105] For example, some sections of actual roads may be flooded due to seasonal rainfall, exceeding a 10% deviation from the target. By analyzing historical road condition data and terrain features using a random forest algorithm, the route distribution can be adjusted, flooded sections can be removed, and more realistic transportation routes can be generated. This adjustment can improve the accuracy of route planning and adapt to dynamically changing transportation demands.

[0106] In this embodiment, the optimized transportation route distribution, combined with the distribution characteristics of agricultural waste, can provide a more efficient solution for waste collection.

[0107] For example, in a certain region where straw waste is mainly generated in autumn, optimizing route planning and prioritizing gently sloping asphalt roads can reduce transportation time and costs. This approach can effectively support the efficient collection and treatment of agricultural waste.

[0108] Step S103: If the terrain undulation exceeds a preset threshold, the transportation route is adjusted using a weighted distance algorithm to obtain an optimized set of route costs.

[0109] Specifically, if the slope value of the terrain-constrained dataset exceeds a preset threshold, the transport path weights are adjusted using the least squares method to obtain an optimized set of path weights. Based on the optimized set of path weights, the Dijkstra algorithm is used to calculate the shortest path in the road network, generating a preliminary set of transport paths. Using spatial analysis methods, the preliminary set of transport paths is spatially overlaid with agricultural waste distribution data to obtain a spatial matching dataset of paths and waste distribution. If the matching degree of the spatial matching dataset is lower than a preset threshold, kernel density estimation is used to smooth the path distribution, generating continuous path distribution features. Based on the continuous path distribution features, combined with the road network's capacity data, the final set of transport path costs is generated.

[0110] For example, in scenarios where transportation route feasibility is analyzed based on Geographic Information Systems (GIS), when acquiring terrain relief data from high-resolution digital elevation models (DEMs), SRTM data sources with a resolution of up to 30 meters can be used to extract slope information. Assuming a region has a slope range of 0 to 15 degrees, combined with road network data, such as road types provided by OpenStreetMap, a terrain constraint dataset containing slope and road type can be generated. The dataset might show that primary roads have slopes of 2 to 5 degrees, while secondary roads have slopes of 8 to 12 degrees, clearly distinguishing the ease or difficulty of transportation.

[0111] In this embodiment, if the slope value exceeds a preset threshold such as 10 degrees, the path weight is adjusted using the least squares method.

[0112] For example, a route has a gradient of 12 degrees, exceeding a threshold. The initial weight is 0.8. After fitting historical travel data using the least squares method, the weight is adjusted to 0.6 to reflect the impact of higher gradients on transportation costs. The adjusted weight set can be used for subsequent route planning to reduce the probability of selecting high-gradient routes.

[0113] Specifically, the shortest path is calculated using the Dijkstra algorithm based on the optimized set of path weights.

[0114] For example, in an agricultural area, the starting point is warehouse A, and the ending point is waste treatment center B. The road network contains three paths with weights of 0.6, 0.7, and 0.9, respectively. The algorithm prioritizes the path with weight 0.9 to ensure transportation efficiency. The generated initial set of transportation paths includes three feasible paths from A to B, with lengths of 5 km, 6 km, and 7 km, respectively.

[0115] In this embodiment, a preliminary path set is overlaid with agricultural waste distribution data using spatial analysis methods. Assuming the waste distribution data shows a waste density of 10 tons / km² in a certain area, the path set and density map are overlaid to identify path nodes with higher densities. The spatial matching dataset may show that a certain path covers 80% of the high-density area, indicating high transportation efficiency.

[0116] For example, if the matching degree of the spatial matching dataset is lower than a preset threshold such as 70%, the kernel density estimation method is used to smooth the path distribution. Assuming that the matching degree of a certain path is 60%, kernel density estimation generates a continuous density distribution map, and after smoothing, the matching degree of the path coverage area is improved to 75%, which is more in line with actual transportation needs.

[0117] Specifically, by combining road network capacity data, such as main roads supporting 10-ton trucks and secondary roads supporting 5-ton trucks, the final set of transportation route costs is generated.

[0118] For example, one route is 5 kilometers long with a capacity of 10 tons and a cost weight of 0.9; another route is 7 kilometers long with a capacity of 5 tons and a cost weight of 0.7. The final set prioritizes routes with high capacity and low cost to ensure transportation efficiency and economy.

[0119] In this embodiment, the path cost set can be further optimized by combining real-time traffic data.

[0120] For example, a route may have high capacity under normal circumstances, but its capacity may decrease by 30% during a specific time period due to congestion. In this case, the cost weight is dynamically adjusted to 0.6. This dynamic adjustment can better adapt to actual transportation scenarios and improve the flexibility of route planning.

[0121] Step S104: Based on the optimized path cost set and combined with the distribution data of environmentally sensitive areas, spatial overlay analysis is used to screen out a set of candidate facility site selection points that meet environmental constraints.

[0122] Specifically, spatial constraint features are extracted from the distribution data of environmentally sensitive areas. A rasterization method is used to divide these areas into discrete spatial units, resulting in an environmental constraint raster dataset. Based on this dataset and the path cost set, spatial overlay analysis is employed to calculate the spatial correlation between each spatial unit and the path cost, yielding a spatial correlation distribution. If any areas in the spatial correlation distribution are below a preset threshold, a weighted distance algorithm is used to initially screen candidate facility site selection points, resulting in a preliminary site selection point set. Based on this preliminary set, and considering topographic constraints in the geospatial data, the least squares method is used to optimize the location weights of the site selection points, resulting in an optimized set of site selection point weights. Based on this optimized set, spatial clustering analysis is used to determine the spatial distribution characteristics of the site selection point set, resulting in a clustered candidate site selection point set. Finally, based on this clustered candidate site selection point set and path accessibility data, spatial network analysis is used to calculate the connectivity between the site selection points and the path network, yielding a connectivity distribution for facility site selection. Based on the connectivity distribution of facility sites and combined with environmental impact factors, a weighted overlay analysis is used to select the final set of facility sites that meet environmental constraints and accessibility requirements.

[0123] In this embodiment, the extraction of environmentally sensitive area distribution data can be based on a geographic information system (GIS) platform, using remote sensing images and land use data to identify sensitive areas such as wetlands, protected forests, or water source protection areas.

[0124] For example, wetland distribution data for a certain area can be interpreted using satellite imagery to generate a spatial map, from which spatial constraint features such as slope and vegetation cover can be extracted. These features reflect the environmental sensitivity of the area and provide constraints for subsequent site selection.

[0125] For example, rasterization can divide environmentally sensitive areas into discrete spatial units of 10 meters × 10 meters. Each unit is labeled with a sensitivity level, such as high-sensitivity areas (wetlands), medium-sensitivity areas (buffer forests), and low-sensitivity areas (ordinary farmland). Through rasterization, the generated environmental constraint raster dataset is easy to spatially overlay with path cost sets for analysis.

[0126] For example, in a scenario involving the transportation of agricultural waste, the path cost set includes information such as road length, slope, and traffic capacity. Overlay analysis calculates the correlation between each grid cell and the path. Areas with low correlation may be unsuitable for site selection due to complex terrain or distance from main roads.

[0127] Specifically, if some areas in the spatial correlation distribution are found to have a correlation degree lower than the threshold (e.g., 0.6), a weighted distance algorithm is used to screen candidate facility site selection points.

[0128] For example, the algorithm comprehensively considers factors such as distance from sensitive areas, road accessibility, and terrain limitations, and initially selects 20 candidate points. These points are spatially evenly distributed, avoiding sensitive areas, and are close to major transportation routes.

[0129] In this embodiment, the least squares method is used to optimize the location weights of the site selection points.

[0130] For example, for the initial set of site selections, combined with terrain constraints (such as a slope of less than 15 degrees), the weights of each site selection are adjusted (e.g., 40% for accessibility and 60% for environmental impact) to generate an optimized set of site selection weights. This method ensures that site selections achieve a balance between environmental protection and transportation efficiency.

[0131] For example, spatial clustering analysis can employ the K-means algorithm to cluster the optimized site selection points according to their geographical location, generating three candidate site selection point sets located in the north, center, and south of the region, respectively. These point sets reflect spatial distribution characteristics, facilitating further analysis of their connectivity with the path network.

[0132] Specifically, spatial network analysis methods assess the accessibility of each site by calculating the connectivity between the site and the road network.

[0133] For example, the northern site selection point is only 2 kilometers from the main road, with a connectivity score of 0.9, while the southern site selection point, due to its complex terrain, only scored 0.7. The connectivity distribution provided a basis for subsequent selection.

[0134] In this embodiment, a weighted overlay analysis is used to integrate environmental impact factors (such as noise and emissions) and connectivity distribution to select the final facility site selection point set.

[0135] For example, sites in the north are preferred due to their high connectivity and low environmental impact. This approach ensures that site selection meets transportation efficiency requirements while minimizing disruption to environmentally sensitive areas.

[0136] Step S105: Using the candidate facility site selection point set, the K-means clustering algorithm is used to divide the service radius range and determine the service coverage area of ​​each facility.

[0137] Specifically, based on the candidate facility site selection point set, the K-means clustering algorithm is used to cluster and group the facility site selection point set. According to a preset service radius threshold, the service coverage area of ​​each facility site selection point is divided, resulting in a preliminary service coverage area set. Traffic capacity data is obtained from the path network data. For the preliminary service coverage area set, spatial network analysis is used to calculate the connectivity between each service coverage area and the path network. If the connectivity is lower than a preset threshold, the service radius is adjusted to obtain an optimized service coverage area set. Based on the optimized service coverage area set, combined with terrain factors and environmental impact data, a weighted overlay analysis is used to calculate the comprehensive weight of terrain factors and environmental impact within each service coverage area. If the comprehensive weight is lower than a preset threshold, the service coverage area is removed, resulting in the final service coverage area set.

[0138] For example, when performing K-means clustering on a set of candidate facility sites, the sites can be grouped based on spatial coordinates and environmental constraints. Suppose a city is planning a waste treatment facility, and the set of candidate sites contains 100 points, each with latitude, longitude, and environmental sensitivity data. K-means clustering can be set to 5 groups, generating 5 clusters based on spatial distance and environmental sensitivity weighting. Each group represents different regional characteristics, such as points near rivers or points far from residential areas. After grouping, the center point of each group can serve as the core of the service area, facilitating subsequent analysis.

[0139] In this embodiment, when dividing the service coverage area, the service range of each cluster center can be determined based on a preset service radius threshold, such as 3 kilometers. Assuming a cluster center is located on the edge of a city with complex terrain, the service radius can be used to generate a coverage area map using GIS tools, and the coverage area includes residential and industrial areas.

[0140] It should be noted that the choice of service radius needs to take into account the type of facility. For example, a waste treatment plant needs to cover more residential areas, but an excessively large radius may increase transportation costs. Spatial analysis should be used to ensure that the population density and facility needs within the coverage area are matched.

[0141] Specifically, connectivity analysis of the path network can extract road capacity, such as hourly traffic flow or road width, from the path network data. Suppose a service coverage area has a main road with a traffic flow of 2000 vehicles per hour, but a secondary road with only 500 vehicles per hour. Through spatial network analysis, the connectivity score between roads and selected points within the coverage area is calculated. If the score is below a threshold, such as 0.6, it indicates that road bottlenecks restrict facility accessibility. In this case, the service radius can be reduced to 2 kilometers, and connectivity can be recalculated until the requirements are met. The adjusted service coverage area better reflects actual traffic demand.

[0142] For example, when performing weighted overlay analysis combining topographic factors and environmental impact data, topographic slope and vegetation cover can be selected as key factors. Assuming a region has a slope greater than 15 degrees and a vegetation cover of 60%, the environmental impact factor has a high weight. Using GIS tools, the topographic and environmental data are rasterized, and each cell is assigned a weight, such as a slope weight of 0.4 and a vegetation weight of 0.6, to calculate the overall weight. If the overall weight of a region is lower than 0.5, that region is excluded to avoid site selection in ecologically sensitive areas. This method ensures that site selection balances environmental considerations and practicality.

[0143] In this embodiment, the final selection of the service coverage area set can be validated using multi-dimensional data. Assume a city ultimately selects three service coverage areas, located in the city center, suburbs, and industrial zones. Through comparative analysis, the city center area is retained due to its high connectivity but low environmental weight, the suburban area is prioritized due to its flat terrain and moderate connectivity, and the industrial zone is eliminated due to its high environmental sensitivity. This selection process ensures the rationality and feasibility of facility site selection, while balancing environmental and service efficiency.

[0144] Step S106: Calculate the waste treatment capacity requirements of each region based on the service coverage area and dynamic distribution characteristics to obtain a facility scale configuration plan.

[0145] Specifically, by using service coverage area and waste distribution data, a weighted analysis method is employed to predict the waste generation volume in each region, thus obtaining the regional waste distribution characteristics. Based on these regional waste distribution characteristics and waste type data, a classification algorithm is used to determine the processing capacity requirements for each region. If the processing capacity requirements exceed a preset threshold, a spatial analysis method is used, combined with facility location distribution data, to adjust the facility scale configuration and obtain a preliminary facility scale plan. Based on the preliminary facility scale plan and transportation route planning data, a network analysis method is used to calculate the transportation efficiency of each facility, resulting in an optimized facility scale plan. Using the optimized facility scale plan and environmental carrying capacity data, a weighted overlay analysis is employed to calculate the environmental impact weight of each region and determine whether the environmental carrying capacity meets the requirements. If the environmental carrying capacity is lower than a preset threshold, the transportation route planning is adjusted, and the facility scale configuration is recalculated to obtain the final facility scale configuration plan.

[0146] In this embodiment, a weighted analysis method is used to predict the amount of waste generated in each region based on service coverage area and waste distribution data.

[0147] For example, a city is divided into 10 service coverage areas. Waste distribution data for each area includes population density, industrial activity intensity, and commercial activity frequency. A weighted analysis method can calculate the waste generation of each area by assigning weights to these factors, such as 40% for population density and 60% for agricultural activity. Assuming area A has a population density of 5000 people / km² and a high agricultural activity frequency, the predicted daily waste generation is 20 tons. This method, through multi-dimensional data fusion, ensures that the prediction results reflect the regional characteristics.

[0148] For example, based on data on waste distribution characteristics and waste types, classification algorithms can be used to determine the processing capacity requirements of each region. Classification algorithms, such as decision trees, can categorize regions into high, medium, and low processing capacity requirements according to waste type (e.g., organic waste, plastics, metals) and its generation volume.

[0149] For example, Region B, which primarily generates organic waste, produces 15 tons daily. The classification algorithm identifies it as a high-demand region requiring large-scale processing facilities. This method ensures that processing capacity matches actual needs by refining the types of waste generated.

[0150] In this embodiment, if the processing capacity requirement exceeds a preset threshold, the facility scale configuration is adjusted using spatial analysis methods based on facility location distribution data.

[0151] For example, Region C's processing demand is 25 tons per day, exceeding the threshold of 20 tons. Spatial analysis revealed that the existing facilities are located in a remote area, necessitating the addition of a medium-sized facility in the regional center, adjusting the coverage radius to 5 kilometers. This adjustment, through spatial optimization, ensures a rational facility layout.

[0152] Specifically, based on preliminary facility scale plans and transportation route planning data, network analysis methods are used to calculate transportation efficiency.

[0153] For example, the average transportation distance from the facility to the waste collection point in region D is 10 kilometers. Network analysis, through route optimization, shortens this distance to 7 kilometers, improving transportation efficiency by 30%. This method reduces transportation costs through route optimization.

[0154] For example, by combining the optimized facility scale plan with environmental carrying capacity data, a weighted overlay analysis is used to calculate the environmental impact weight. Assume that the environmental carrying capacity data for region E includes soil pollution index, water pollution index, and air quality, with weights of 40%, 30%, and 30%, respectively. If the overall weight for region E is 0.6, which is lower than the threshold of 0.8, it indicates insufficient environmental carrying capacity, necessitating adjustments to transportation routes, reduction of heavy vehicle use, and a replanning of facility scale. This analysis, by comprehensively considering environmental factors, ensures that facility configuration meets environmental requirements.

[0155] In this embodiment, if the environmental carrying capacity does not meet the requirements, the transportation route is adjusted and the facility size is recalculated.

[0156] For example, due to high water pollution levels in region F, the transportation route needs to be adjusted to a route farther from the water source, and the scale of the facilities needs to be reduced from large to medium-sized, with the daily processing capacity reduced to 15 tons. This adjustment ensures environmental sustainability through the synergistic optimization of route and scale.

[0157] Step S107: If the processing capacity requirement exceeds the preset threshold, the site selection point set and coverage area are adjusted through an iterative optimization algorithm to obtain the final resource-based facility layout scheme.

[0158] Specifically, by using regional waste generation data and employing cluster analysis, the waste distribution density of each region is determined, yielding regional waste distribution characteristics. If the density exceeds a preset threshold, a genetic algorithm is used to adjust the site selection set and coverage area, resulting in a preliminary resource recovery facility layout plan. Based on this plan, network analysis is used to calculate the transportation path efficiency between facilities, leading to an optimized transportation path plan. This optimized plan, combined with environmental carrying capacity data, is used with weighted overlay analysis to calculate the environmental impact weight of each region, determining if the environmental carrying capacity meets requirements. If the environmental carrying capacity falls below a preset threshold, simulated annealing is used to readjust the site selection set and coverage area, resulting in an updated resource recovery facility layout plan. Based on this updated plan, spatial analysis is used to verify the matching degree between facility distribution and regional waste distribution characteristics, resulting in a final resource recovery facility layout plan. Finally, this final plan, combined with regional waste treatment needs, is used with weighted analysis to calculate the allocation ratio of treatment capacity for each facility, determining the scale and configuration of the resource recovery facilities.

[0159] For example, by using regional waste generation data and cluster analysis to determine distribution density, regions can be classified according to the amount of waste generated.

[0160] In this embodiment, a city is divided into 10 areas, with daily waste generation ranging from 50 tons to 200 tons. Using the K-means clustering algorithm, the areas are divided into three categories—high density, medium density, and low density—based on the amount of waste generated and their geographical location.

[0161] For example, high-density areas generate more than 150 tons of waste per day, and their distribution characteristics indicate that large-scale treatment facilities should be prioritized.

[0162] Specifically, if the distribution density is higher than a preset threshold, such as 100 tons per square kilometer per day, a genetic algorithm is used to adjust the site selection set and coverage area.

[0163] In this embodiment, for high-density areas, the algorithm aims to minimize transportation distance, with an initial set of 5 site selection points and a coverage radius of 5 kilometers. Through iterative optimization, 3 site selection points are retained, and the coverage radius is adjusted to 4 kilometers, forming a preliminary resource recovery facility layout scheme. This scheme ensures that waste collection points cover more than 80% of high-density areas.

[0164] For example, based on the initial layout plan, network analysis methods can be used to optimize transportation route efficiency.

[0165] In this embodiment, the road network is analyzed using three site selection points as centers to calculate the shortest path from the waste generation point to the facility. Assuming there are 10 collection points in a certain area, the average transportation time is reduced from 40 minutes to 30 minutes after optimization, improving path efficiency by 25%.

[0166] Optionally, route planning can take into account traffic conditions during peak hours to ensure smooth transportation.

[0167] In this embodiment, environmental impact weights are calculated by combining environmental carrying capacity data and using weighted overlay analysis.

[0168] For example, a region might have a soil pollution sensitivity of 0.8, a water resource protection weight of 0.6, and an air quality weight of 0.4. If the overall weight is below 0.5, it indicates insufficient environmental carrying capacity, necessitating adjustments to the environmental layout.

[0169] It should be noted that if the load-bearing capacity does not meet the requirements, the simulated annealing algorithm can readjust the site selection.

[0170] For example, moving a facility from a water source protection area to a secondary sensitive area can reduce environmental impact by 10%.

[0171] Specifically, spatial analysis methods are used to verify the matching degree between facility distribution and waste distribution characteristics.

[0172] For example, the target is to cover over 90% of the waste generated within the facility's coverage area. Assuming a layout scheme covers 85%, by fine-tuning the facility's location, it can ultimately reach 92%, ensuring efficient matching.

[0173] In this embodiment, processing capacity is allocated using a weighted analysis method based on the final layout scheme.

[0174] For example, the three facilities handle 40%, 35%, and 25% of the processing volume respectively, ensuring that the scale of the resource recovery facilities is precisely matched with the regional demand.

[0175] like Figure 2 As shown, this embodiment also provides a simulation system for the layout of agricultural waste resource utilization based on big data analysis, including:

[0176] The data acquisition module is used to acquire remote sensing images of agricultural waste and agricultural production records through a multi-source data acquisition system, determine the types, quantities, and seasonal variation patterns of waste, and obtain dynamic distribution characteristics;

[0177] The spatial constraint modeling module is used to construct a spatial constraint model based on dynamic distribution characteristics, using a geographic information system to analyze terrain undulations and road conditions, and to determine the feasibility range of transportation routes.

[0178] The route optimization module is used to adjust the transportation route using a weighted distance algorithm if the terrain undulation exceeds a preset threshold, thereby obtaining an optimized set of route costs.

[0179] The environmental constraint screening module is used to screen out a set of candidate facility site selection points that meet environmental constraints based on the optimized path cost set and the distribution data of environmentally sensitive areas, using spatial overlay analysis.

[0180] The service area division module is used to divide the service radius range and determine the service coverage area of ​​each facility by using the K-means clustering algorithm based on the candidate facility site selection point set.

[0181] The demand calculation module is used to calculate the waste treatment capacity requirements of each region based on the service coverage area and dynamic distribution characteristics, and to obtain a facility scale configuration plan.

[0182] The layout optimization module is used to adjust the set of site selection points and coverage area through iterative optimization algorithms if the processing capacity demand exceeds a preset threshold, so as to obtain the final resource-based facility layout scheme.

[0183] This embodiment also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0184] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for simulating the layout of agricultural waste resource utilization based on big data analysis, characterized in that, Includes the following steps: Acquire spatiotemporal distribution data of agricultural waste, determine the types, quantities, and seasonal variation patterns of waste based on the spatiotemporal distribution data, and obtain dynamic distribution characteristics; The obtained dynamic distribution characteristics include: Remote sensing image data and agricultural production records related to agricultural waste were acquired through a multi-source data acquisition system, and a spatiotemporal distribution dataset containing timestamps and geographic coordinates was constructed. By employing a data fusion analysis method, remote sensing image data is matched with agricultural production records to generate preliminary classification results of the types and quantities of agricultural waste; If the confidence level of the classification result is lower than the preset threshold, the remote sensing image data is used to extract features through the support vector machine algorithm to obtain the distribution characteristics of agricultural waste types. Based on the distribution characteristics of different types and combined with time series data in agricultural production records, analyze the seasonal variation patterns of agricultural waste and determine the seasonal variation trend. By modeling seasonal variation trends using the random forest algorithm, the dynamic distribution characteristics of agricultural waste are predicted, generating spatiotemporal distribution prediction results. Based on the spatiotemporal distribution prediction results, the spatiotemporal distribution pattern of generated agricultural waste is obtained, and a distribution characteristic description is derived. Based on the dynamic distribution characteristics, a geographic information system is used to analyze the terrain undulations and road conditions, construct a spatial constraint model, and obtain the feasibility range of transportation routes. When the terrain undulations exceed a preset threshold, the transportation route is adjusted using a weighted distance algorithm to obtain an optimized set of route costs. Based on the optimized path cost set and combined with the distribution data of environmentally sensitive areas, spatial overlay analysis is used to screen out a set of candidate facility site selection points that meet environmental constraints. Based on the set of candidate facility sites, the service radius range is divided using the K-means clustering algorithm to determine the service coverage area of ​​each facility; Based on the service coverage area and dynamic distribution characteristics, the waste treatment capacity requirements of each region are calculated to obtain a facility scale configuration plan. When the processing capacity demand exceeds the preset threshold, the site selection point set and coverage area are adjusted through iterative optimization algorithms to obtain the final resource-based facility layout scheme.

2. The method according to claim 1, characterized in that, The feasibility range of obtaining the transportation route includes: Topographic relief data is obtained from a high-resolution digital elevation model using a geographic information system, and combined with road network data to generate a topographic constraint dataset that includes slope and road type. By using a weighted overlay analysis method, combining terrain relief data and road condition data, the spatial constraint weights of transportation routes are calculated to obtain the route feasibility distribution. Based on the distribution of path feasibility and combined with the distribution characteristics of agricultural waste, a spatial matching relationship between the path and the waste distribution is generated to obtain the matched path distribution data. The matched path distribution data is smoothed using spatial interpolation to generate a continuous transportation path feasibility distribution.

3. The method according to claim 1, characterized in that, The optimized path cost set includes: When the slope value of the terrain constraint dataset exceeds the preset threshold, the transport path weights are adjusted by the least squares method to obtain the optimized path weight set. Based on the optimized set of path weights, the Dijkstra algorithm is used to calculate the shortest path in the road network, generating a preliminary set of transportation paths. By using spatial analysis methods, the preliminary set of transportation routes is spatially overlaid with agricultural waste distribution data to obtain a spatially matched dataset of routes and waste distribution. If the matching degree of the spatial matching dataset is lower than the preset threshold, the kernel density estimation method is used to smooth the path distribution and generate continuous path distribution features. Based on the continuous path distribution characteristics and combined with the road network capacity data, a set of transportation path costs is generated.

4. The method according to claim 1, characterized in that, The set of candidate facility sites that meet environmental constraints includes: Spatial constraint features are extracted from the distribution data of environmentally sensitive areas. The environmentally sensitive areas are divided into discrete spatial units using a rasterization method to obtain an environmental constraint raster dataset. Based on the environmental constraint raster dataset and the path cost set, spatial overlay analysis is used to calculate the spatial correlation degree between each spatial unit and the path cost, and the spatial correlation degree distribution is obtained. If there are areas in the spatial correlation distribution that are below the preset threshold, a weighted distance algorithm is used to preliminarily screen the candidate facility site selection point set to obtain a preliminary site selection point set. Based on the preliminary set of site selection points and combined with the terrain constraint factors in the geospatial data, the least squares method is used to optimize the location weights of the site selection points, resulting in the optimized set of site selection point weights. Based on the optimized set of site selection point weights, spatial clustering analysis is used to determine the spatial distribution characteristics of the site selection point set, and the clustered candidate site selection point set is obtained. Based on the clustered candidate site selection point set and combined with the path capacity data, the spatial network analysis method is used to calculate the connectivity between the site selection points and the path network, and obtain the connectivity distribution of facility site selection. Based on the connectivity distribution of facility sites and combined with environmental impact factors, a weighted overlay analysis is used to select the final set of facility sites that meet environmental constraints and accessibility requirements.

5. The method according to claim 1, characterized in that, The determination of the service coverage area of ​​each facility includes: Based on the candidate facility site selection point set, the K-means clustering algorithm is used to cluster and group the facility site selection point set. According to the preset service radius threshold, the service coverage area of ​​each facility site selection point is divided to obtain a preliminary service coverage area set. Traffic capacity data is obtained from the path network data. Based on the preliminary service coverage area set, spatial network analysis method is used to calculate the connectivity between each service coverage area and the path network. If the connectivity is lower than a preset threshold, the service radius range is adjusted to obtain an optimized service coverage area set. Based on the optimized service coverage area set, combined with terrain factors and environmental impact data, a weighted overlay analysis is used to calculate the comprehensive weight of terrain factors and environmental impact in each service coverage area. If the comprehensive weight is lower than a preset threshold, the service coverage area is removed to obtain the final service coverage area set.

6. The method according to claim 1, characterized in that, The obtained facility scale configuration scheme includes: By using service coverage area and waste distribution data, a weighted analysis method is employed to predict the amount of waste generated in each region, thereby obtaining the regional waste distribution characteristics. Based on the regional waste distribution characteristics and combined with waste type data, a classification algorithm is used to determine the processing capacity requirements of each region. If the processing capacity requirement exceeds the preset threshold, then by combining the facility location distribution data and using spatial analysis methods, the facility scale configuration is adjusted to obtain a preliminary facility scale plan. Based on the preliminary facility scale plan and combined with transportation route planning data, network analysis methods are used to calculate the transportation efficiency of each facility, resulting in an optimized facility scale plan. By using the optimized facility scale plan and combining environmental carrying capacity data, a weighted overlay analysis is adopted to calculate the environmental impact weight of each region and determine whether the environmental carrying capacity meets the requirements. If the environmental carrying capacity is lower than the preset threshold, the transportation route planning will be adjusted, the facility scale configuration will be recalculated, and the final facility scale configuration scheme will be obtained.

7. The method according to claim 1, characterized in that, The final resource utilization facility layout scheme includes: By using regional waste generation data and cluster analysis, the waste distribution density of each region is determined, and the regional waste distribution characteristics are obtained. If the distribution characteristics of waste in the region show that the density is higher than the preset threshold, the genetic algorithm is used to adjust the site selection point set and coverage area to obtain a preliminary resource recovery facility layout plan. Based on the preliminary resource utilization facility layout plan, network analysis method is used to calculate the transportation path efficiency between facilities and obtain the optimized transportation path plan. By optimizing the transportation route planning and combining it with environmental carrying capacity data, a weighted overlay analysis is used to calculate the environmental impact weight of each region and determine whether the environmental carrying capacity meets the requirements. If the environmental carrying capacity is lower than the preset threshold, the site selection point set and coverage area are readjusted through the simulated annealing algorithm to obtain an updated resource recovery facility layout scheme. Based on the updated resource recovery facility layout plan, spatial analysis methods are used to verify the matching degree between the facility distribution and the regional waste distribution characteristics, and the final resource recovery facility layout plan is obtained.

8. A simulation system for the layout of agricultural waste resource utilization based on big data analysis, characterized in that, include: The data acquisition module is used to acquire remote sensing images of agricultural waste and agricultural production records through a multi-source data acquisition system, determine the types, quantities, and seasonal variation patterns of waste, and obtain dynamic distribution characteristics. The spatial constraint modeling module is used to construct a spatial constraint model based on dynamic distribution characteristics, using geographic information systems to analyze terrain undulations and road conditions, and to determine the feasibility range of transportation routes. The route optimization module is used to adjust the transportation route using a weighted distance algorithm if the terrain undulation exceeds a preset threshold, thereby obtaining an optimized set of route costs. The environmental constraint screening module is used to screen out a set of candidate facility site selection points that meet environmental constraints based on the optimized path cost set and the distribution data of environmentally sensitive areas, using spatial overlay analysis. The service area division module is used to divide the service radius range and determine the service coverage area of ​​each facility by using the K-means clustering algorithm based on the candidate facility site selection point set. The demand calculation module is used to calculate the waste treatment capacity requirements of each region based on the service coverage area and dynamic distribution characteristics, and to obtain a facility scale configuration plan. The layout optimization module is used to adjust the set of site selection points and coverage area through iterative optimization algorithms if the processing capacity demand exceeds a preset threshold, so as to obtain the final resource-based facility layout scheme.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

Images