A method, device and equipment for selecting a waste dump site

Abstract

The present invention relates to the technical field of engineering waste treatment, and specifically discloses a method, device and equipment for selecting a waste dump site. The present invention uses GIS technology to identify low-lying areas and stable slopes suitable for waste dumps, and provides basic data for preliminary site selection; the present invention can maximize the correlation between various risk factors through weighted analysis of multi-dimensional risk factors, and reflect the overall risk level through comprehensive scoring, and can comprehensively consider all factors to provide a more comprehensive and accurate basis for site selection, ensure the scientificity and accuracy of the site selection process, and improve the efficiency and accuracy of decision-making; at the same time, the present invention evaluates and predicts each risk factor based on time series, and can dynamically perform environmental predictions and long-term risk assessments on the site to be selected for the waste dump. The present invention can effectively predict the impacts that the waste dump may face in the future, and ensure its long-term safety and sustainability.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering waste treatment, and in particular to a method, device and equipment for selecting a waste dump site. Background Art

[0002] At present, the site selection and quantity calculation process of waste dumps in large-scale infrastructure projects mainly rely on experience and judgment, lacking scientific data support. Existing methods are difficult to systematically integrate multiple data such as topography, meteorology, and hydrology, and cannot accurately assess long-term environmental changes and potential ecological risks. Existing static assessment methods cannot effectively predict the impact of future extreme climate and hydrological changes, which is particularly important when extreme climate change becomes more frequent.

[0003] CN113807724A discloses a method for selecting a waste dump site based on comprehensive risk assessment. This method only identifies and evaluates the risk factors in the waste dump site selection process, but does not comprehensively consider the changes in risk factors in the future at the site selection location. Summary of the invention

[0004] In order to overcome the problems existing in the existing waste dump site selection, such as the inability to accurately assess long-term environmental changes and potential ecological risks, the present invention provides a waste dump site selection method, device and equipment.

[0005] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for selecting a waste dump site, the method comprising:

[0007] Acquire three-dimensional terrain data of the first site selection location, identify the three-dimensional terrain data using GIS technology, and select a second site selection location that includes a low-lying area and a stable slope;

[0008] Acquire a variety of environmental data of the second site selection location, extract characteristic data affecting the site selection of the waste dump from the various environmental data, and set them as risk factors; the risk factors include terrain risk factors, meteorological risk factors, hydrological risk factors, social risk factors, and ecological risk factors;

[0009] Evaluate and predict the risk factors based on the time series to obtain the evaluation value and prediction value of each risk factor of each second site selection location in the continuous time;

[0010] Performing a comprehensive risk assessment on the assessed values ​​and predicted values ​​of all risk factors of each second site selection location according to the time series to obtain a plurality of comprehensive scores for each second site selection location in a continuous time;

[0011] Performing a site selection evaluation on the second site selection location based on the multiple comprehensive scores within the continuous time to determine the most preferred site selection location;

[0012] The risk factors are evaluated and predicted based on the time series, specifically including:

[0013] The data of each risk factor collected at the current time point is used as input, and the assessment value of each risk factor in the continuous time is output through the risk assessment model, and the predicted value of each risk factor in the continuous time is output through the risk prediction model;

[0014] The comprehensive risk assessment specifically includes:

[0015] According to the time series, the predicted value of the risk factor at each time point is standardized, and the formula is:

[0016] ,

[0017] in, r ij is the standardized value of risk factor i at the jth time point, x ij is the predicted value of risk factor i at the jth time point, and n is the total number of risk factors i;

[0018] The predicted value of the processed risk factor is calculated by the entropy weight method to obtain the weight of each risk factor in the time series. The formula is:

[0019] , ,

[0020] in, E i is the entropy value of risk factor i, m is the number of time points in the time series, W i ( j ) is the weight of risk factor i at the jth time point;

[0021] Based on the evaluation value of the risk factor at each time point and the corresponding weight, a weighted calculation is performed to obtain the comprehensive score of all risk factors at each time point. The formula is:

[0022] ,

[0023] in, S ( j ) is the comprehensive score at the jth time point, F i ( j ) is the estimated value of risk factor i at the jth time point;

[0024] Output the comprehensive score according to the time series to generate multiple comprehensive scores within a continuous time;

[0025] The site selection assessment includes:

[0026] Calculate the average of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the average comprehensive score of each second site selection location;

[0027] Calculate the range of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the range of the comprehensive score of each second site selection location;

[0028] Select at least three second site selection locations with the lowest average comprehensive score, and then select the second site selection location with the lowest range of comprehensive scores from the at least three second site selection locations as the optimal site selection location.

[0029] According to a specific implementation, in the above-mentioned site selection method, the risk assessment model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location and the corresponding degree of risk, outputs an assessment value between 0 and 1 for different risk factors; the risk prediction model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location, outputs a prediction value for different risk factors.

[0030] According to a specific implementation, in the above-mentioned site selection method, the characteristic data include elevation difference, slope, rainfall, water level, distance to the nearest road, distance to the nearest protected area, distance to wildlife habitat, environmental sensitivity and distance to the nearest ecological farmland.

[0031] In a second aspect, the present invention provides a device for selecting a waste dump site, the device comprising:

[0032] A terrain acquisition module, used to obtain three-dimensional terrain data of the first site selection location;

[0033] A GIS identification module, used to identify the three-dimensional terrain data using GIS technology, and screen out a second site selection location including a low-lying area and a stable slope;

[0034] A data acquisition module, used to obtain various environmental data of the second selected site;

[0035] A risk factor setting module is used to extract characteristic data that affect the site selection of the waste dump from the multiple environmental data and set them as risk factors; the risk factors include terrain risk factors, meteorological risk factors, hydrological risk factors, social risk factors and ecological risk factors;

[0036] An evaluation and prediction module, used to evaluate and predict the risk factors based on a time series, and obtain an evaluation value and a prediction value of each risk factor of each second site selection location in a continuous time;

[0037] A comprehensive assessment module, used to perform a comprehensive risk assessment on the assessment values ​​and predicted values ​​of all risk factors of each second site selection location according to the time series, obtain a plurality of comprehensive scores of each second site selection location in a continuous time, and perform a site selection assessment on the second site selection location based on the plurality of comprehensive scores in the continuous time to determine the most preferred site selection location;

[0038] Wherein, the evaluation prediction module is specifically used for:

[0039] The data of each risk factor collected at the current time point is used as input, and the assessment value of each risk factor in the continuous time is output through the risk assessment model, and the predicted value of each risk factor in the continuous time is output through the risk prediction model;

[0040] The comprehensive evaluation module is specifically used for:

[0041] According to the time series, the predicted value of the risk factor at each time point is standardized, and the formula is:

[0042] ,

[0043] in, r ij is the standardized value of risk factor i at the jth time point, x ij is the predicted value of risk factor i at the jth time point, and n is the total number of risk factors i;

[0044] The predicted value of the processed risk factor is calculated by the entropy weight method to obtain the weight of each risk factor in the time series. The formula is:

[0045] , ,

[0046] in, E i is the entropy value of risk factor i, m is the number of time points in the time series, W i ( j ) is the weight of risk factor i at the jth time point;

[0047] Based on the evaluation value of the risk factor at each time point and the corresponding weight, a weighted calculation is performed to obtain the comprehensive score of all risk factors at each time point. The formula is:

[0048] ,

[0049] in, S ( j ) is the comprehensive score at the jth time point, F i ( j ) is the estimated value of risk factor i at the jth time point;

[0050] Output the comprehensive score according to the time series to generate multiple comprehensive scores within a continuous time;

[0051] The comprehensive assessment module is also used to:

[0052] Calculate the average of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the average comprehensive score of each second site selection location;

[0053] Calculate the range of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the range of the comprehensive score of each second site selection location;

[0054] Select at least three second site selection locations with the lowest average comprehensive score, and then select the second site selection location with the lowest range of comprehensive scores from the at least three second site selection locations as the optimal site selection location.

[0055] According to a specific implementation, in the above-mentioned site selection device, the risk assessment model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location and the corresponding degree of risk, outputs an assessment value between 0 and 1 for different risk factors; the risk prediction model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location, outputs a prediction value for different risk factors.

[0056] According to a specific implementation, in the above-mentioned site selection device, the characteristic data include elevation difference, slope, rainfall, water level, distance to the nearest road, distance to the nearest protected area, distance to wildlife habitat, environmental sensitivity and distance to the nearest ecological farmland.

[0057] In a third aspect, the present invention provides an electronic device, the device comprising a memory and a processor; wherein:

[0058] The memory is used to store computer programs;

[0059] The processor is used to call and execute the computer program so that the device executes any one of the above-mentioned methods for selecting a waste dump site.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The present invention uses GIS technology to identify low-lying areas and stable slopes suitable for waste dumps, and provides basic data for preliminary site selection. On the basis of site selection based on basic terrain data, the weighted analysis of multi-dimensional risk factors can be further used to integrate the correlation of various risk factors to the greatest extent, and then the overall risk level can be reflected through comprehensive scoring. By comprehensively considering multi-dimensional factors, a more comprehensive and accurate site selection basis is provided to ensure the scientificity and accuracy of the site selection process and improve the efficiency and accuracy of decision-making. At the same time, the present invention evaluates and predicts each risk factor based on time series, and can dynamically predict the environment and conduct long-term risk assessment of the site to be selected for the waste dump. Especially in the face of sustainable development of the ecological, social and environmental environment, the present invention can effectively identify the social and ecological impacts that the waste dump may cause in the future, and ensure its long-term safety and sustainability. In addition, the present invention integrates multi-dimensional data sources, including terrain, meteorology, hydrology, ecology and social environment data, to achieve a comprehensive analysis of the site selection of the waste dump and conduct a comprehensive risk assessment. Compared with the limitations of traditional methods that rely on empirical judgment or a single data source, the present invention can not only improve the comprehensiveness and effectiveness of site selection, but also provide continuous risk management and decision support throughout the life cycle of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A schematic diagram of a process flow of a method for selecting a waste dump site provided by an embodiment of the present invention;

[0063] Figure 2 A schematic diagram of the comprehensive scoring of the second site selection location provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The present invention is further described in detail below in conjunction with test examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0065] The terms "first", "second", etc. in the embodiments of the specification, claims, and drawings of the present invention are used only for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying an order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, including a series of steps or units. The method, system, product, or device is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0066] In order to solve the problems that traditional waste dump site selection methods cannot effectively integrate multiple environmental data and are difficult to accurately predict and dynamically evaluate future environmental changes, the present invention provides a method for comprehensive evaluation of GIS technology, deep learning and multi-dimensional risk factors to solve these problems, thereby achieving multi-source data integration, long-term dynamic analysis and comprehensive risk assessment.

[0067] Please refer to Figure 1 , which shows a schematic flow chart of a method for selecting a waste dump site provided by an embodiment of the present invention, the method comprising:

[0068] S1. Obtain three-dimensional terrain data of a first site selection location, use GIS technology to identify the three-dimensional terrain data, and screen out a second site selection location that includes a low-lying area and a stable slope.

[0069] Specifically, in the early stage of the site selection of the waste dump, there are multiple site selection locations after preliminary investigation, namely the first site selection location. These site selection locations are locations that meet certain conditions in the waste dump setting conditions, such as relatively flat terrain, and the elevation difference in the terrain does not change much. The embodiment of the present invention first performs basic screening after obtaining the three-dimensional terrain data of the first site selection location. In a possible implementation, the above-mentioned three-dimensional terrain data can be obtained in a variety of ways, including remote sensing images, topographic maps, GPS measurement technology, photogrammetry technology, laser scanning measurement technology (LIDAR) and SAR and InSAR technology, and the use of a laser radar system (LIDAR) can obtain high-density and high-precision laser point cloud data, which can directly reflect the three-dimensional coordinates of the terrain and provide important geographic information such as elevation, slope, soil type, and water distribution. After obtaining these three-dimensional terrain data, the three-dimensional terrain data in different formats (such as vectors and rasters) are unified into a standard format that can be used for three-dimensional analysis (such as GeoTIFF, DEM) to facilitate processing in a GIS system. The embodiment of the present invention uses GIS technology for identification. Furthermore, GIS software, such as ArcGIS, is used to convert the above three-dimensional terrain data into DEM, which reflects the height changes of the terrain surface and provides a basis for identifying slopes and low-lying areas. By analyzing the data of different elevation bands in DEM, necessary clipping and smoothing are performed to reduce noise and highlight the main terrain features.

[0070] Furthermore, the slope and aspect information are extracted from the DEM through the "slope" and "aspect" tools in the GIS software. Specifically, slope calculation: The slope map is generated using the DEM, and the slope map shows the slope size of each grid cell. By setting the slope threshold (such as areas below 15°), relatively gentle areas suitable for waste dumping can be identified. The slope classification can be carried out according to certain critical values, for example: <5° is a slight slope, 5°~8° is a gentle slope, 8°~15° is a gentle slope, 15°~25° is a steep slope, 25°~35° is a steep slope, and >35° is a steep slope; Slope aspect analysis: Slope aspect (i.e., slope direction) analysis can help identify which slopes are more stable. GIS software can be used to screen areas with specific slope aspects to avoid soil erosion and landslide risks that may be caused by waste dumping areas.

[0071] Furthermore, the hydrological analysis module in the GIS software was used to simulate the water flow path and the catchment area through the elevation data. Low-lying areas are usually the end points of the catchment path, and these areas are suitable as waste dumps. Subsequently, in the three-dimensional terrain model, by analyzing the terrain depressions and water distribution data, potential waterlogging areas were identified to prevent the waste dump from being flooded.

[0072] Combined with the analysis results of slope, aspect and low-lying area, a site suitable for a waste dump with a low-lying area and a stable slope was selected from the first site selection and set as the second site selection.

[0073] In addition, in a possible implementation, GIS can also be used for stability analysis, including geological condition query: by superimposing geological layer data on GIS, the geological stability of the site selection area (such as soil type, fault line distribution) is analyzed to ensure that the waste dump will not cause landslides due to unstable geological conditions; slope classification and stability assessment: combining slope data and geological information, the slope surface is classified for stability through GIS. Generally speaking, the steeper the slope, the worse the stability. Areas suitable for waste dumping should be selected from areas with smaller slopes and higher stability. Furthermore, through the three-dimensional modeling function in GIS software, elevation and slope data can be generated into a three-dimensional visualization model for designers to intuitively view the terrain characteristics of the site selection area. In addition, the expansion of the waste dump can be simulated in the three-dimensional model to evaluate the space occupancy and impact on the surrounding terrain under different waste volumes. Furthermore, GIS can also be used for buffer zone analysis, including buffer zone analysis of sensitive areas: using the buffer zone function of GIS, sensitive areas around the site selection area (such as water bodies, farmland, roads, etc.) are identified, and buffer zones are created to ensure that the waste dump will not have a negative impact on these areas. Optimize the site selection scope: select a suitable waste dump location outside the buffer zone, and adjust the buffer zone scope according to project requirements to further optimize the site selection plan. In addition, GIS software can also integrate the three-dimensional data of the site selection and risk assessment data, and output them in the form of reports or maps to provide engineers with an operational waste dump planning plan; as well as integrate historical data and real-time data (such as meteorological data, geological change data, etc.) to dynamically update the site selection evaluation and feasibility analysis of the waste dump.

[0074] At present, in the preliminary screening process of the site selection of the waste dump, most of the methods such as field survey, drone oblique photography and engineering tests are used to draw basic conclusions and make judgments. Although these methods are technically feasible, it is usually difficult to accurately obtain the rock and soil parameters obtained through engineering tests, and field surveys and drone oblique photography rely on static soil data. The embodiment of the present invention can dynamically generate soil change information through GIS technology, avoiding the above method from affecting the subsequent comprehensive evaluation in the process of providing basic screening, and providing technical support for the site selection of the waste dump.

[0075] S2. Obtain a variety of environmental data of the second site selection location, extract characteristic data that affect the site selection of the waste dump from the various environmental data, and set them as risk factors; the risk factors include terrain risk factors, meteorological risk factors, hydrological risk factors, social risk factors and ecological risk factors.

[0076] The various environmental data include information such as elevation and slope based on three-dimensional terrain data; extreme weather data such as rainfall and rainstorms obtained through meteorological data; the relative position of the waste dump and the water area, as well as the water level and water velocity changes in the water area obtained through hydrological data; and data obtained through the ecological environment distance, residential area distance, road network, etc. around the second site selection location. Specifically, the risk factors that may be involved in the embodiments of the present invention are further explained.

[0077] For terrain risk factors, they include:

[0078] Elevation: Elevation determines the height of the waste dump. Low-elevation areas are usually relatively flat and easy to accumulate. Too high an elevation may cause the waste dump to be overly exposed on the surface, which not only affects the landscape, but may also form a large amount of runoff during rainfall, increasing the risk of soil erosion.

[0079] Slope: Slope is an important indicator for determining the stability of the waste dump. A steeper slope increases the risk of landslide and collapse, while a gentler slope helps to keep the waste dump stable. Generally, it is safer to choose an area with a slope of less than 15°.

[0080] Slope aspect data: Slope aspect affects the exposure of the slope to sunlight and wind erosion; for example, sunny slopes are more likely to dry out, reducing soil moisture and reducing landslide risk; while shady slopes may accumulate water and increase humidity, which is not conducive to long-term accumulation;

[0081] Geological data: The location of the waste dump also needs to consider the stability of the soil and rock formations; sandy or loose soils are less stable and may cause landslides or ground subsidence, while hard rock formations help to enhance the support of the waste dump.

[0082] For hydrological risk factors, they include:

[0083] Water level: Changes in the water level of nearby water bodies will directly affect the safety of the waste dump. A waste dump that is too low may be submerged when the water level rises, causing the risk of waste scouring and spreading. A relatively high waste dump can avoid erosion caused by water level fluctuations.

[0084] Water flow speed: For waste dumps near rivers or streams, water flow speed must be considered. The faster the water flow speed, the greater the impact on the waste dump, which may cause soil loss or the spread of waste. A lower water flow speed reduces the risk of erosion.

[0085] Flood frequency: Hydrologically sensitive areas, such as areas prone to flooding, are not suitable for waste dumping sites; the higher the flood frequency, the greater the possibility that the waste will be washed away and spread;

[0086] Groundwater level: A high groundwater level will increase the moisture content of the soil under the waste dump, thereby reducing soil friction and increasing the risk of landslides. Areas with high groundwater levels are more suitable for waste dump site selection.

[0087] For meteorological risk factors, they include:

[0088] Precipitation: Precipitation affects soil moisture and the stability of the waste. The soil in high precipitation areas is more slippery, and the waste is prone to settlement or landslides, while low precipitation areas are more suitable for long-term accumulation. In the embodiment of the present invention, it is necessary to predict future precipitation changes based on historical precipitation data to evaluate the long-term stability of the waste site.

[0089] Temperature: Temperature affects the freezing and thawing conditions of the soil. In areas with cold winters and warm summers, the soil may experience repeated freeze-thaw cycles, which reduces soil stability and increases the risk of spoil landslides. Areas with relatively stable temperatures are more suitable for spoil site selection.

[0090] Wind speed: Wind speed has a direct impact on the spread of waste slag. High wind speed may cause the waste slag to be blown away, affecting the surrounding environment, especially for light dusty waste slag. Low wind speed areas help control the spread of waste slag.

[0091] Air pressure and humidity: Air pressure and humidity affect the formation and distribution of precipitation; in areas of high humidity and low air pressure, precipitation may be more frequent and more concentrated, increasing the risk of landslides and soil saturation in waste dumps.

[0092] Social risk factors include:

[0093] Distance to the nearest road: Areas closer to roads have lower transportation costs, but may also interfere with traffic; too close a distance may cause problems such as dust, noise and traffic jams, while too far a distance will increase transportation costs; the best site selection should strike a balance between transportation costs and social impacts;

[0094] Distance from the nearest residents and communities: The waste dump should be kept at an appropriate distance from residential areas to reduce dust pollution, noise and other problems caused by the waste dump; being too close to residents may cause complaints and legal issues, so a reasonable buffer zone should be set up when selecting the site;

[0095] Distance to the nearest protected area: The site selection of the waste dump must take into account the distance from nature reserves, wetlands and other ecologically sensitive areas. A waste dump that is too close to a protected area may affect the habitats of rare animals and plants and may be subject to supervision and restrictions by environmental protection departments.

[0096] Ecological risk factors include:

[0097] Vegetation coverage: The site selection of waste dumps should avoid areas with high vegetation coverage. Areas with high vegetation coverage have greater protection value for the ecological environment and are not suitable for waste dumps; while areas with low vegetation coverage have less ecological impact on waste and are more suitable for accumulation;

[0098] Distance from the nearest ecological farmland: The waste dump should be kept at an appropriate distance from the ecological farmland to prevent waste pollution or harmful substances such as heavy metals from penetrating into the farmland and affecting crop growth;

[0099] Distance from wildlife habitats: The site selection of the waste dump needs to avoid wildlife habitats to prevent the construction of the waste dump from having a negative impact on biodiversity. Reasonable site selection can reduce interference with the local ecosystem;

[0100] Environmental sensitivity: Some areas may be particularly ecologically sensitive, and the construction of waste dumps may cause environmental damage. This can be done based on GIS data analysis to identify and avoid these environmentally sensitive areas to minimize the impact of waste dumping activities on the environment.

[0101] Based on the above risk factors, the present invention studies the linkage, complexity and dynamics of service functions and ecological risks in ecosystems. The present invention not only considers the topography, hydrology and meteorology that may affect the site selection of traditional waste dumps, but also includes the environmental and ecological impacts that may be caused by waste dumps into the assessment scope, and further constructs a more complete comprehensive risk assessment system. While avoiding the impact of the environment on the waste dump, it can also identify and avoid potential social ecological risks and ensure the sustainability of site selection. The present invention can reflect the different risk levels in site selection by considering multi-dimensional risk factors, providing designers with a scientific reference basis to help them quickly select the best waste dump location.

[0102] S3. Evaluate and predict the risk factors based on the time series to obtain the evaluation value and prediction value of each risk factor of each second site selection location in a continuous time.

[0103] Among them, the embodiment of the present invention uses the data of each risk factor collected at the current time point as input, outputs the evaluation value of each risk factor in the continuous time through the risk assessment model, and outputs the predicted value of each risk factor in the continuous time through the risk prediction model. Specifically, the risk assessment model uses any one of logistic regression, random forest, support vector machine or neural network, and after training with the historical environmental data of the second site selection location and the corresponding degree of risk, outputs an evaluation value between 0 and 1 for different risk factors (the larger the value, the higher the assessed risk); the risk prediction model uses any one of logistic regression, random forest, support vector machine or neural network, and after training with the historical environmental data of the second site selection location, outputs predicted values ​​for different risk factors.

[0104] S4. Perform a comprehensive risk assessment on the evaluation values ​​and predicted values ​​of all risk factors of each second site selection location according to the time series to obtain multiple comprehensive scores for each second site selection location in a continuous time.

[0105] The comprehensive risk assessment specifically includes:

[0106] According to the time series, the predicted value of the risk factor at each time point is standardized, and the formula is:

[0107] ,

[0108] in, r ij is the standardized value of risk factor i at the jth time point, x ij is the predicted value of risk factor i at the jth time point, and n is the total number of risk factors i;

[0109] The predicted value of the processed risk factor is calculated by the entropy weight method to obtain the weight of each risk factor in the time series. The formula is:

[0110] , ,

[0111] in, E i is the entropy value of risk factor i, m is the number of time points in the time series, W i ( j ) is the weight of risk factor i at the jth time point;

[0112] Based on the evaluation value of the risk factor at each time point and the corresponding weight, a weighted calculation is performed to obtain the comprehensive score of all risk factors at each time point. The formula is:

[0113] ,

[0114] in, S ( j ) is the comprehensive score at the jth time point, F i ( j ) is the estimated value of risk factor i at the jth time point;

[0115] The comprehensive scores are output according to the time series, and a plurality of comprehensive scores within a continuous time are generated.

[0116] In a possible implementation, an embodiment of the present invention provides an example.

[0117] At a certain location with an elevation of 0m, a 100m high waste dump is placed. Please refer to Table 1 for the evaluation and prediction values ​​of each risk factor at the site in continuous time.

[0118] In this example, the elevation difference in the terrain data is selected as the terrain risk factor, which can assess the safety under extreme climate and geological changes; the rainfall in the meteorological data is selected as the meteorological risk factor, which can assess the possible risks of soil erosion and collapse; the water level in the hydrological data is selected as the hydrological risk factor, which can assess the impact of the water level in the water area and predict the possible impact of floods; the nearest road distance in the ecological environment is selected as the social risk factor, and the nearest ecological farmland is selected as the ecological risk factor, which can assess the impact of the waste dump on the surrounding ecological environment, especially the long-term impact on fragile ecosystems.

[0119] Table 1 is an example table of the evaluation and prediction values ​​of each risk factor in continuous time

[0120]

[0121] According to Table 1, the entropy value of each risk factor E i The calculation process is:

[0122] Step 1: Normalize the calculated values r i,j (Refer to the previous standardization step).

[0123] Standardized data (at each time point):

[0124] Time point 1:

[0125] Terrain risk factors: r terrain,1 =0.00492;

[0126] Meteorological risk factors: rWeather,1 =0.000492;

[0127] Hydrological risk factors: r Hydrological,1 =0.0059;

[0128] Social risk factors: r Society,1 =0.00516;

[0129] Ecological risk factors: r Ecological,1 =0.9836;

[0130] Time point 2:

[0131] Terrain risk factors: r terrain,2 =0.00492;

[0132] Meteorological risk factors: r Weather,2 =0.00059;

[0133] Hydrological risk factors: r Hydrological,2 =0.00614;

[0134] Social risk factors: r Society,2 =0.00516;

[0135] Ecological risk factors: r Ecological,2 =0.9832;

[0136] Time point 3:

[0137] Terrain risk factors: r terrain,3 =0.09354;

[0138] Meteorological risk factors: r Weather,3 =0.00935;

[0139] Hydrological risk factors: r Hydrological,3 =0.12755;

[0140] Social risk factors: r Society,3 =0.08928;

[0141] Ecological risk factors: r Ecological,3 =0.6802;

[0142] Time point 4:

[0143] Terrain risk factors: r terrain,4 =0.09244;

[0144] Meteorological risk factors: r Weather,4 =0.01261;

[0145] Hydrological risk factors: r Hydrological,4 =0.13445;

[0146] Social risk factors: r Society,4 =0.08824;

[0147] Ecological risk factors: r Ecological,4 =0.67227.

[0148] Step 2: Calculate the entropy value of each risk factor E i .

[0149] Entropy value of terrain risk factor:

[0150] E terrain =0.00492ln(0.00492)+0.00492ln(0.00492)+0.09354ln(0.09354)+0.09244ln(0.09244);

[0151] E terrain =-0.034+(-0.034)+(-0.221)+(-0.222)=-0.511;

[0152] Entropy value of meteorological risk factors:

[0153] E Weather =0.000492ln(0.00492)+0.00059ln(0.00059)+0.00935ln(0.00935)+0.01261ln(0.01261);

[0154] E Weather =-0.003+(-0.003)+(-0.046)+(-0.051)=-0.103;

[0155] Entropy value of hydrological risk factor:

[0156] EHydrological =0.0059ln(0.0059)+0.00614ln(0.00614)+0.12755ln(0.12755)+0.13445ln(0.13445);

[0157] E Hydrological =-0.031+(-0.032)+(-0.238)+(-0.248)=-0.549;

[0158] Social risk factor entropy value:

[0159] E Society =0.00516ln(0.00516)+0.00516ln(0.00516)+0.08928ln(0.08928)+0.08824ln(0.08824);

[0160] E Society =-0.032+(-0.032)+(-0.216)+(-0.215)=-0.495;

[0161] Ecological risk factor entropy value:

[0162] E Ecological =0.9836ln(0.9836)+0.9832ln(0.9832)+0.6802ln(0.6802)+0.67227ln(0.67227);

[0163] E Ecological =-0.016+(-0.016)+(-0.196)+(-0.199)=-0.427.

[0164] Final entropy summary:

[0165] Entropy value of terrain risk factor E terrain =-0.511;

[0166] Entropy value of meteorological risk factors E Weather =-0.103;

[0167] Entropy value of hydrological risk factor E Hydrological =-0.549;

[0168] Social risk factor entropy E Society =-0.495;

[0169] Ecological risk factor entropy E Ecological =-0.427.

[0170] Calculating weights W i :

[0171] Total entropy calculation:

[0172] .

[0173] The weight calculation for each risk factor is:

[0174] Topographic risk factor weights:

[0175] ;

[0176] Meteorological risk factor weights:

[0177] ;

[0178] Hydrological risk factor weights:

[0179] ;

[0180] Social risk factor weights:

[0181] ;

[0182] Ecological risk factor weights:

[0183] .

[0184] Step 3: Final comprehensive score:

[0185] The predicted value of each risk factor was substituted into the formula, and the data at each time point were used to calculate the final score.

[0186] Specifically, the comprehensive score calculation at time point 1 is:

[0187] S 1=0.2132*0.75+0.1557*0.6+0.2186*0.85+0.2109*0.4+0.2016*0.6;

[0188] S 1=0.1599+0.0934+0.1858+0.0844+0.12096=0.64446;

[0189] Calculation of comprehensive score at time point 2:

[0190] S 2=0.2132*0.7+0.1557*0.65+0.2186*0.7+0.2109*0.4+0.2016*0.62;

[0191] S 2=0.14924+0.1012+0.15302+0.0844+0.12499=0.61285;

[0192] Calculation of comprehensive score at time point 3:

[0193] S 3=0.2132*0.72+0.1557*0.58+0.2186*0.72+0.2109*0.42+0.2016*0.78;

[0194] S 3=0.1535+0.0903+0.1574+0.0886+0.15725=0.64705;

[0195] Calculation of comprehensive score at time point 4:

[0196] S 4=0.2132*0.8+0.1557*0.54+0.2186*0.68+0.2109*0.4+0.2016*0.8;

[0197] S 4=0.1706+0.0841+0.1486+0.0844+0.16128=0.64898.

[0198] Final result:

[0199] The comprehensive risk score for placing a waste dump at this location is calculated as follows:

[0200] Rating at time point 1: 0.64446;

[0201] Rating at time point 2: 0.61285;

[0202] Rating at time point 3: 0.64705;

[0203] Rating at time point 4: 0.64898.

[0204] It is understandable that the above is only a process of comprehensive risk assessment of one of the second site selection locations. In the embodiment of the present invention, the optimal site selection is performed after comprehensive risk assessment is performed on all the second site selection locations.

[0205] S5. Performing a site selection evaluation on the second site selection location based on the multiple comprehensive scores within the continuous time to determine the most optimal site selection location.

[0206] Specifically, the site selection assessment includes:

[0207] Calculate the average of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the average comprehensive score of each second site selection location;

[0208] Calculate the range of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the range of the comprehensive score of each second site selection location;

[0209] Select at least three second site selection locations with the lowest average comprehensive score, and then select the second site selection location with the lowest range of comprehensive scores from the at least three second site selection locations as the optimal site selection location.

[0210] It should be noted that the comprehensive score reflects the overall risk level of the site selection scheme. The higher the score, the greater the overall risk of the site selection scheme, so the location is not suitable for being selected as a waste dump. The plan with a lower score indicates a lower risk, which means that the site selection of the waste dump is relatively safe at this location. On this basis, when the mean value of the comprehensive score is high, it means that the location has a greater risk in certain risk factors. For example, areas with high slopes, high rainfall, or close to water may cause landslides, erosion, etc., so high-mean locations should be avoided as waste dump sites as much as possible. When the mean value of the comprehensive score is low, it means that considering all factors, the risk of the location is low and it is suitable for being a waste dump. Such areas usually have stable terrain, are far away from water, and have little ecological impact. In addition, based on the range of the comprehensive score in continuous time, the larger the range, the more likely the site selection location is to have high-risk impacts in a short period of time, such as increased precipitation or large changes in terrain elevation differences, which are not suitable for consideration as a waste dump site. The smaller the range, the more stable the site selection location is in a short period of time, and no high-risk situations are found.

[0211] In practical applications, for multiple comprehensive scores calculated for multiple second site selection locations within a continuous time, the mean and range of the comprehensive scores need to be considered comprehensively. The embodiment of the present invention provides a scientific reference for designers to help them quickly select the optimal waste dump location.

[0212] Based on the above technical solution, the present invention uses GIS technology to identify low-lying areas and stable slopes suitable for waste dumps, and provides basic data for preliminary site selection; on the basis of site selection based on basic terrain data, further weighted analysis of multi-dimensional risk factors can be used to maximize the integration of the correlation of various risk factors, and then the overall risk level can be reflected through comprehensive scoring. By comprehensively considering multi-dimensional factors, a more comprehensive and accurate site selection basis is provided to ensure the scientificity and accuracy of the site selection process and improve the efficiency and accuracy of decision-making; at the same time, the present invention evaluates and predicts each risk factor based on time series, and can dynamically select the site for the waste dump. The present invention can effectively identify the social and ecological impacts that the waste dump may cause in the future, and ensure its long-term safety and sustainability, especially in the face of sustainable development of the ecological, social and environmental environment. In addition, the present invention integrates multi-dimensional data sources, including topographic, meteorological, hydrological, ecological and social environmental data, to achieve a comprehensive analysis of the site selection of the waste dump and conduct a comprehensive risk assessment. Compared with traditional methods that rely on empirical judgment or the limitations of a single data source, the present invention can not only improve the comprehensiveness and effectiveness of site selection, but also provide continuous risk management and decision-making support throughout the life cycle of the project.

[0213] Furthermore, the embodiment of the present invention provides an example of selecting a second site through site selection evaluation in the actual implementation process. After evaluating and predicting the risk factors of each second site, multiple comprehensive scores of each second site in a continuous time are obtained through comprehensive risk evaluation. Please refer to Figure 2 , which shows a schematic diagram of the comprehensive scoring of the second site selection location provided by an embodiment of the present invention.

[0214] like Figure 2As shown in the figure, the average comprehensive score of site A is 0.640925, the range is 0.004875, the risk is medium, the future risk is relatively controllable, and it is suitable for the site selection of the waste dump; the average comprehensive score of site B is 0.66717, the range is 0.013405, the risk is high, the risk change is small, and it is suitable for short-term, small or secondary site selection; the average comprehensive score of site C is 0.63737, the range is 0.015255, the risk is low, but the risk gradually increases in the later period, and it is suitable for short-term, small or secondary site selection; The average comprehensive score is: 0.64883, the range is 0.012835, the risk is medium, slightly increased, the risk change is small, suitable as an alternative, and the risk is within a controllable range; the average comprehensive score of site E is: 0.67429, the range is 0.01590, the risk is high, and the risk is gradually increasing. It is recommended to avoid long-term use; the average comprehensive score of site F is: 0.6433, the range is 0.007135, the risk is medium, slightly increased, but the risk in the future is controllable, and it can still be used as an alternative for the waste dump.

[0215] Based on the above calculation results, it can be seen that the three second site selection locations with the lowest average comprehensive scores are Site A, Site C and Site F. Among them, Site A has the smallest range among these three second site selection locations, so Site A is finally selected as the optimal site selection location.

[0216] In summary, the present invention has greatly improved the intelligence and scientific nature of waste dump site selection through innovative functions such as data integration, dynamic analysis and risk assessment, and can effectively reduce environmental and social risks. It has broad application prospects and practical value.

[0217] On the other hand, an embodiment of the present invention further provides a device for selecting a site for a waste dump, the device comprising:

[0218] A terrain acquisition module, used to obtain three-dimensional terrain data of the first site selection location;

[0219] A GIS identification module, used to identify the three-dimensional terrain data using GIS technology, and screen out a second site selection location including a low-lying area and a stable slope;

[0220] A data acquisition module, used to obtain various environmental data of the second selected site;

[0221] A risk factor setting module is used to extract characteristic data that affect the site selection of the waste dump from the multiple environmental data and set them as risk factors; the risk factors include terrain risk factors, meteorological risk factors, hydrological risk factors, social risk factors and ecological risk factors;

[0222] An evaluation and prediction module, used to evaluate and predict the risk factors based on a time series, and obtain an evaluation value and a prediction value of each risk factor of each second site selection location in a continuous time;

[0223] A comprehensive assessment module, used to perform a comprehensive risk assessment on the assessment values ​​and predicted values ​​of all risk factors of each second site selection location according to the time series, obtain a plurality of comprehensive scores of each second site selection location in a continuous time, and perform a site selection assessment on the second site selection location based on the plurality of comprehensive scores in the continuous time to determine the most preferred site selection location;

[0224] Wherein, the evaluation prediction module is specifically used for:

[0225] The data of each risk factor collected at the current time point is used as input, and the assessment value of each risk factor in the continuous time is output through the risk assessment model, and the predicted value of each risk factor in the continuous time is output through the risk prediction model;

[0226] The comprehensive evaluation module is specifically used for:

[0227] According to the time series, the predicted value of the risk factor at each time point is standardized, and the formula is:

[0228] ,

[0229] in, r ij is the standardized value of risk factor i at the jth time point, x ij is the predicted value of risk factor i at the jth time point, and n is the total number of risk factors i;

[0230] The predicted value of the processed risk factor is calculated by the entropy weight method to obtain the weight of each risk factor in the time series. The formula is:

[0231] , ,

[0232] in, E i for W i ( j ) is the entropy value of risk factor i, m is the number of time points in the time series, W i ( j ) is the weight of risk factor i at the jth time point;

[0233] Based on the evaluation value of the risk factor at each time point and the corresponding weight, a weighted calculation is performed to obtain the comprehensive score of all risk factors at each time point. The formula is:

[0234] ,

[0235] in, S ( j ) is the comprehensive score at the jth time point, F i ( j ) is the estimated value of risk factor i at the jth time point;

[0236] Output the comprehensive score according to the time series to generate multiple comprehensive scores within a continuous time;

[0237] The comprehensive assessment module is also used to:

[0238] Calculate the average of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the average comprehensive score of each second site selection location;

[0239] Calculate the range of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the range of the comprehensive score of each second site selection location;

[0240] Select at least three second site selection locations with the lowest average comprehensive score, and then select the second site selection location with the lowest range of comprehensive scores from the at least three second site selection locations as the optimal site selection location.

[0241] According to a specific implementation, in the above-mentioned site selection device, the risk assessment model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location and the corresponding degree of risk, outputs an assessment value between 0 and 1 for different risk factors; the risk prediction model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location, outputs a prediction value for different risk factors.

[0242] According to a specific implementation, in the above-mentioned site selection device, the characteristic data include elevation difference, slope, rainfall, water level, distance to the nearest road, distance to the nearest protected area, distance to wildlife habitat, environmental sensitivity and distance to the nearest ecological farmland.

[0243] It should be understood that the above technical solution provided in the embodiment of the present invention corresponds to the technical solution of the method for selecting a slag dump site provided in the embodiment of the present invention, and the beneficial effects achieved in various aspects and corresponding feasible implementation methods are similar, which will not be repeated here.

[0244] On the other hand, an embodiment of the present invention further provides an electronic device, the device comprising a memory and a processor; wherein:

[0245] The memory is used to store computer programs;

[0246] The processor is used to call and execute the computer program so that the device executes any one of the above-mentioned methods for selecting a waste dump site.

[0247] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0248] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0249] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0250] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0251] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link DRAM (SLDRAM), and direct rambus RAM (DRRAM).

[0252] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0253] It should be understood that the device disclosed in the embodiment of the present invention can be implemented in other ways. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the communication connection between modules can be through some interfaces, servers or indirect coupling or communication connection, which can be electrical or other forms.

[0254] In addition, each module unit in each embodiment of the present invention may be integrated into one processing unit, or each module may exist physically separately, or two or more modules may be integrated into one processing unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0255] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0256] Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way for easy understanding.

[0257] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for selecting a waste dump site, characterized in that: The method comprises: Acquire three-dimensional terrain data of the first site selection location, identify the three-dimensional terrain data using GIS technology, and select a second site selection location that includes a low-lying area and a stable slope; Acquire a variety of environmental data of the second site selection location, extract characteristic data affecting the site selection of the waste dump from the various environmental data, and set them as risk factors; the risk factors include terrain risk factors, meteorological risk factors, hydrological risk factors, social risk factors, and ecological risk factors; Evaluate and predict the risk factors based on the time series to obtain the evaluation value and prediction value of each risk factor of each second site selection location in the continuous time; Performing a comprehensive risk assessment on the assessed values ​​and predicted values ​​of all risk factors of each second site selection location according to the time series to obtain a plurality of comprehensive scores for each second site selection location in a continuous time; Performing a site selection evaluation on the second site selection location based on the multiple comprehensive scores within the continuous time to determine the most preferred site selection location; The risk factors are evaluated and predicted based on the time series, specifically including: The data of each risk factor collected at the current time point is used as input, and the assessment value of each risk factor in the continuous time is output through the risk assessment model, and the predicted value of each risk factor in the continuous time is output through the risk prediction model; The comprehensive risk assessment specifically includes: According to the time series, the predicted value of the risk factor at each time point is standardized, and the formula is: ， in, r ij is the standardized value of risk factor i at the jth time point, x ij is the predicted value of risk factor i at the jth time point, and n is the total number of risk factors i; The predicted value of the processed risk factor is calculated by the entropy weight method to obtain the weight of each risk factor in the time series. The formula is: ， ， in, E i is the entropy value of risk factor i, m is the number of time points in the time series, is the weight of risk factor i at the jth time point; Based on the evaluation value of the risk factor at each time point and the corresponding weight, a weighted calculation is performed to obtain the comprehensive score of all risk factors at each time point. The formula is: ， in, S ( j ) is the comprehensive score at the jth time point, is the estimated value of risk factor i at the jth time point; Output the comprehensive score according to the time series to generate multiple comprehensive scores within a continuous time; The site selection assessment includes: Calculate the average of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the average comprehensive score of each second site selection location; Calculate the range of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the range of the comprehensive score of each second site selection location; Select at least three second site selection locations with the lowest average comprehensive score, and then select the second site selection location with the lowest comprehensive score range from the at least three second site selection locations as the optimal site selection location; The risk assessment model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location and the corresponding degree of risk, outputs an assessment value between 0 and 1 for different risk factors; the risk prediction model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location, outputs a prediction value for different risk factors.

2. A method for selecting a waste dump site according to claim 1, characterized in that: The characteristic data include elevation difference, slope, rainfall, water level, distance to the nearest road, distance to the nearest protected area, distance to wildlife habitat, environmental sensitivity and distance to the nearest ecological farmland.

3. A device for selecting a waste dump site, characterized in that: The device comprises: A terrain acquisition module, used to obtain three-dimensional terrain data of the first site selection location; A GIS identification module, used to identify the three-dimensional terrain data using GIS technology, and screen out a second site selection location including a low-lying area and a stable slope; A data acquisition module, used to obtain various environmental data of the second selected site; A risk factor setting module is used to extract characteristic data that affect the site selection of the waste dump from the multiple environmental data and set them as risk factors; the risk factors include terrain risk factors, meteorological risk factors, hydrological risk factors, social risk factors and ecological risk factors; An evaluation and prediction module, used to evaluate and predict the risk factors based on a time series, and obtain an evaluation value and a prediction value of each risk factor of each second site selection location in a continuous time; A comprehensive assessment module, used to perform a comprehensive risk assessment on the assessment values ​​and predicted values ​​of all risk factors of each second site selection location according to the time series, obtain a plurality of comprehensive scores of each second site selection location in a continuous time, and perform a site selection assessment on the second site selection location based on the plurality of comprehensive scores in the continuous time to determine the most preferred site selection location; Wherein, the evaluation prediction module is specifically used for: The data of each risk factor collected at the current time point is used as input, and the assessment value of each risk factor in the continuous time is output through the risk assessment model, and the predicted value of each risk factor in the continuous time is output through the risk prediction model; The comprehensive evaluation module is specifically used for: According to the time series, the predicted value of the risk factor at each time point is standardized, and the formula is: ， in, r ij is the standardized value of risk factor i at the jth time point, x ij is the predicted value of risk factor i at the jth time point, and n is the total number of risk factors i; The predicted value of the processed risk factor is calculated by the entropy weight method to obtain the weight of each risk factor in the time series. The formula is: ， ， in, E i is the entropy value of risk factor i, m is the number of time points in the time series, is the weight of risk factor i at the jth time point; Based on the evaluation value of the risk factor at each time point and the corresponding weight, a weighted calculation is performed to obtain the comprehensive score of all risk factors at each time point. The formula is: ， in, S ( j ) is the comprehensive score at the jth time point, is the estimated value of risk factor i at the jth time point; Output the comprehensive score according to the time series to generate multiple comprehensive scores within a continuous time; The comprehensive evaluation module is specifically used for: Calculate the average of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the average comprehensive score of each second site selection location; Calculate the range of multiple comprehensive scores of each second site selection location within a continuous period of time to obtain the range of the comprehensive score of each second site selection location; Select at least three second site selection locations with the lowest average comprehensive score, and then select the second site selection location with the lowest comprehensive score range from the at least three second site selection locations as the optimal site selection location; The risk assessment model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location and the corresponding degree of risk, outputs an assessment value between 0 and 1 for different risk factors; the risk prediction model adopts any one of logistic regression, random forest, support vector machine or neural network, and after being trained with the historical environmental data of the second site selection location, outputs a prediction value for different risk factors.

4. A waste dump site selection device according to claim 3, characterized in that: The characteristic data include elevation difference, slope, rainfall, water level, distance to the nearest road, distance to the nearest protected area, distance to wildlife habitat, environmental sensitivity and distance to the nearest ecological farmland.

5. An electronic device, characterized in that: The device comprises a memory and a processor; wherein, The memory is used to store computer programs; The processor is used to call and execute the computer program so that the device executes a method for selecting a waste dump site as described in any one of claims 1 to 2.

Images