An online intelligent early warning system for solid fuel environmental protection projects based on big data

Abstract

The application discloses an online intelligent early warning system for solid fuel environmental protection projects based on big data, relates to the technical field of data processing, and solves the technical problems that it is difficult to establish a solid fuel environmental protection project database to store monitoring data, it is difficult to establish a temperature pollutant diffusion correlation model to analyze pollutant emission rate and pollutant diffusion influence range, it is difficult to evaluate the influence degree of solid fuel on environmental sensitive areas, soil and underground water, and it is difficult to comprehensively evaluate an environmental protection risk evaluation index and establish a three-level early warning system accordingly. The application realizes monitoring and early warning of the solid fuel environmental protection projects by comprehensively evaluating environmental protection risk evaluation indexes of the solid fuel on the atmosphere, soil, underground water and environmental sensitive areas in various links.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, specifically an online intelligent early warning system for solid fuel environmental protection projects based on big data. Background Technology

[0002] With the development of big data technology, the environmental impacts of solid fuel production, storage, transportation, and use are becoming increasingly complex, along with increasingly stringent environmental protection requirements. This necessitates real-time monitoring and data collection at each stage of solid fuel production, including environmental monitoring data for the atmosphere, soil, and groundwater, as well as relevant parameters from production, storage, and transportation processes. By combining multi-source data such as remote sensing and infrared data, and employing technologies like Geographic Information Systems (GIS) and Computational Fluid Dynamics (CFD), data analysis and evaluation can be conducted to achieve a comprehensive assessment and intelligent early warning of the environmental impact of solid fuels at each stage.

[0003] The existing online intelligent early warning system for solid fuel environmental protection projects has the following problems: it is difficult to establish a database of solid fuel environmental protection projects to store monitoring data; it is difficult to establish a temperature-pollutant diffusion correlation model to analyze pollutant emission rates and the scope of pollutant diffusion impact; it is difficult to assess the impact of solid fuels on environmentally sensitive areas, soil, and groundwater; and it is difficult to comprehensively assess the environmental risk assessment index and establish a three-level early warning system based on it. Summary of the Invention

[0004] This invention aims to at least solve one of the technical problems existing in the prior art; to this end, the first aspect of this invention provides an online intelligent early warning system for solid fuel environmental protection projects based on big data, comprising the following modules:

[0005] Data acquisition module: Collects monitoring data on solid fuel at each stage;

[0006] Data processing module: Establishes a database for solid fuel environmental protection projects and stores pre-processed monitoring data;

[0007] Data Analysis Module: By fusing infrared and remote sensing data, a temperature-pollutant diffusion correlation model is established to analyze pollutant emission rates; by combining real-time meteorological data and emission source locations, the impact range of pollutant diffusion is calculated; by overlaying map layers of solid fuel at each stage, the impact of solid fuel on environmentally sensitive areas is assessed; and the impact index of solid fuel on soil and groundwater is analyzed and evaluated.

[0008] Risk assessment module: comprehensively assesses the environmental risk assessment index of the atmosphere, soil, groundwater and environmentally sensitive areas in each stage;

[0009] Early warning module: Utilizes environmental risk assessment indices to establish a three-level early warning system.

[0010] A further embodiment of the proposed data acquisition module includes the following steps: real-time monitoring and acquisition of remote sensing data, infrared data, and environmental monitoring data of solid fuels in four stages of production, storage, transportation, and use; the environmental monitoring data includes: atmospheric monitoring data, soil monitoring data, groundwater monitoring data, and environmentally sensitive area monitoring data.

[0011] A further solution, the data processing module includes the following steps: establishing a solid fuel environmental protection project database, classifying the pre-processed real-time monitoring data according to four stages: production, storage, transportation, and use, establishing a multi-dimensional database index, and integrating and storing it with historical monitoring data.

[0012] A further approach involves fusing infrared and remote sensing data to establish a temperature-based pollutant diffusion correlation model and analyze pollutant emission rates, including the following steps:

[0013] The preprocessed infrared data and remote sensing data are overlaid and fused, and geographic registration is performed based on the geographic information system platform. Each infrared pixel is matched with the corresponding pixel-level location in the remote sensing image to obtain a fused dataset that simultaneously contains temperature information and spatial distribution information.

[0014] Computational fluid dynamics was used to simulate the pollutant diffusion path, and a temperature-pollutant diffusion correlation model was established; the model diffusion parameters were dynamically adjusted based on the calorific value of solid fuel.

[0015] Based on the usage and monitoring data of solid fuels, the specific location and type of pollutant emission sources are determined using a geographic information system platform; real-time meteorological data of the emission source area is collected and preprocessed.

[0016] Based on the diffusion equation in the temperature-pollutant diffusion correlation model, combined with meteorological data, the specific location of pollutant emission sources, and diffusion parameters, the source strength information of pollutants is calculated in reverse. According to the principle of mass conservation, the emission rate of pollutants is equal to the mass of pollutants emitted per unit time, and dynamic corrections are made in combination with meteorological data.

[0017] A further approach, combining real-time meteorological data and emission source locations, calculates the extent of pollutant diffusion impact, including the following steps:

[0018] Temperature data and pollutant concentration data are converted into raster format. Using the raster calculator of the geographic information system platform, the magnitude and direction of the temperature gradient or concentration gradient are obtained by calculating the temperature or concentration difference between each raster cell and its neighboring raster cells, and the temperature gradient field and pollutant concentration gradient field are generated respectively.

[0019] The gradient vector of each grid cell is extracted from the temperature gradient field and pollutant concentration gradient field raster data. The vector dot product formula in the raster calculator is used to calculate the angle between the temperature gradient vector and the pollutant concentration gradient vector, and an angle distribution map is generated.

[0020] Centered on a high-temperature solid fuel source, a multi-level buffer zone of 500m, 1km, and 2km was established on a geographic information system platform, and the average pollutant concentration within each buffer zone was statistically analyzed. Combined with wind direction data, a cost-distance weighted function was used to simulate the diffusion path of pollutants from the high-temperature source to the low-temperature zone.

[0021] Real-time meteorological data, emission source location information, pollutant emission rates, and the generated temperature gradient field, concentration gradient field, angle distribution map, and diffusion path are used as input parameters and substituted into the temperature-pollutant diffusion correlation model; the diffusion process of pollutants in the atmosphere is simulated, the concentration distribution of pollutants in time and space is calculated, and the influence range of pollutant diffusion is obtained.

[0022] A further approach involves overlaying map layers of solid fuels at each stage to assess the impact of solid fuels on environmentally sensitive areas, including the following steps:

[0023] The collected map layer data includes: map layers of solid fuel in the four stages and distribution maps of environmentally sensitive areas, and is preprocessed;

[0024] The processed map layer data is imported into the geographic information system platform, and the overlay analysis tool is used to overlay all the map layer data to generate the first new layer.

[0025] By combining the 500m, 1km, and 2km multi-level buffer zones established on the geographic information system platform, the buffer zone layer is overlaid with the environmentally sensitive area layer to identify the overlapping areas between the buffer zone and the environmentally sensitive area, and a second new layer is generated.

[0026] Statistical analysis is performed on the first new layer to calculate the area and number of environmentally sensitive areas within or near the solid fuel activity area; statistical analysis is performed on the second new layer to calculate the area of ​​environmentally sensitive areas within each buffer zone and the proportion of environmentally sensitive areas within the buffer zone.

[0027] The comprehensive assessment of the impact of solid fuels on environmentally sensitive areas is calculated using the following formula:

[0028]

[0029] Wherein, H represents the comprehensive impact index of solid fuels on environmentally sensitive areas. The extent of the impact of pollutant diffusion, It is the average range of influence of pollutant diffusion. For pollutant emission rate, For pollutant emission rate limits, It is the area of ​​the environmentally sensitive region within the i-th buffer. The total area of ​​environmentally sensitive areas It is the radius of the i-th buffer; Let i be the weight coefficient of the i-th buffer. , , These are the correction factors.

[0030] Further plans include analyzing and assessing the impact of solid fuels on soil and groundwater, including the following steps:

[0031] Real-time monitoring and collection of soil microbial respiration rate, soil enzyme activity, and microbial biomass; weighted summation to assess soil microbial community activity index.

[0032] Real-time monitoring and collection of microbial metabolic activity and microbial community abundance in groundwater, and assessment of the microbial community activity index in groundwater by weighted summation;

[0033] By real-time monitoring of pollutant concentrations related to solid fuel residues in soil and groundwater, Pearson correlation coefficients between microbial activity indices and pollutant concentrations in soil and groundwater were calculated.

[0034] The soil impact index is calculated by multiplying the soil microbial activity index by the absolute value of pollutant concentration and the Pearson correlation coefficient; similarly, the groundwater impact index is obtained.

[0035] A further proposed solution, the risk assessment module, includes the following steps:

[0036] The formula for calculating the environmental risk assessment index is as follows:

[0037]

[0038] in, This is an environmental risk assessment index. Let k be the extent of the pollutant diffusion in the k-th stage. Let be the pollutant emission rate at the k-th stage, and t be the pollutant exposure time. Let be the comprehensive impact index of solid fuel in the k-th stage on environmentally sensitive areas. Let be the soil impact index for the k-th stage. Let be the groundwater impact index for the k-th stage; denoted as the distance from the pollution emission source at the k-th stage to the environmentally sensitive area; k = 1, 2, 3, 4 respectively represent the four stages of solid fuel production, storage, transportation, and use.

[0039] A further proposed solution is that the early warning module includes the following steps:

[0040] Based on the calculation results of the environmental risk assessment index, the historical average of the environmental risk assessment index was statistically analyzed. and standard deviation ;

[0041] when When the risk level is low, a Level 1 warning is triggered. When the risk level is medium, a level 2 warning is triggered. When the risk level is high, a Level 3 warning will be triggered.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] This invention integrates infrared and remote sensing data, utilizes a geographic information system platform for data processing and the establishment of a temperature-based pollutant diffusion correlation model, thereby enabling the analysis and simulation of solid fuel pollutant diffusion.

[0044] This invention comprehensively assesses the impact of solid fuels on environmentally sensitive areas by overlaying map layers of each stage of solid fuel production with a distribution map of environmentally sensitive areas and combining buffer zone analysis; it also assesses the impact of solid fuels on soil and groundwater by introducing a microbial community activity index, real-time monitoring, and correlation analysis.

[0045] This invention establishes an environmental risk assessment index formula by comprehensively considering multiple factors and formulates a three-level early warning mechanism by combining historical data. Compared with traditional single-risk factor early warning, it can more accurately reflect the overall risk situation, issue early warning signals in a timely manner, and provide strong support for environmental management and decision-making. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a system module diagram of the present invention;

[0048] Figure 2 This is a flowchart of the temperature-based pollutant diffusion correlation model analysis method in this invention. Detailed Implementation

[0049] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Please see Figure 1-2 The first aspect of this invention provides an online intelligent early warning system for solid fuel environmental protection projects based on big data, comprising the following modules:

[0051] Data acquisition module: Collects monitoring data on solid fuel at each stage;

[0052] Data processing module: Establishes a database for solid fuel environmental protection projects and stores pre-processed monitoring data;

[0053] Data Analysis Module: By fusing infrared and remote sensing data, a temperature-pollutant diffusion correlation model is established to analyze pollutant emission rates; by combining real-time meteorological data and emission source locations, the impact range of pollutant diffusion is calculated; by overlaying map layers of solid fuel at each stage, the impact of solid fuel on environmentally sensitive areas is assessed; and the impact index of solid fuel on soil and groundwater is analyzed and evaluated.

[0054] Risk assessment module: comprehensively assesses the environmental risk assessment index of the atmosphere, soil, groundwater and environmentally sensitive areas in each stage;

[0055] Early warning module: Utilizes environmental risk assessment indices to establish a three-level early warning system.

[0056] Specifically, the data acquisition module is used to monitor and collect remote sensing data, infrared data, and environmental monitoring data of the atmosphere, soil, groundwater, and environmentally sensitive areas in real time during the four stages of solid fuel production, storage, transportation, and use. The data processing module is used to establish a solid fuel environmental protection project database, classifying pre-processed real-time monitoring data by stage, establishing a multi-dimensional database index, and integrating and storing it with historical monitoring data. The data analysis module first overlays and fuses the pre-processed infrared data with remote sensing data, performing geographic registration using a geographic information system platform to obtain a fused dataset containing temperature and spatial distribution information. Then, computational fluid dynamics is used to simulate pollutant diffusion paths, establishing a temperature-pollutant diffusion correlation model, and dynamically adjusting the model diffusion parameters based on the calorific value of solid fuel. Simultaneously, real-time meteorological data of the emission source area is collected to determine the specific location and type of pollutant emission sources, and the source strength information, i.e., the emission rate, is calculated in reverse. Finally, combining real-time meteorological data and emission source locations, the impact range of pollutant diffusion is calculated through spatial distribution analysis and raster calculation steps using the geographic information system platform. Then, by overlaying map layers of solid fuel at each stage with distribution maps of environmentally sensitive areas, and combining buffer zone analysis, the impact of solid fuel on environmentally sensitive areas is assessed. Finally, real-time monitoring and collection of microbial respiration rates, soil enzyme activity, and microbial biomass in the soil, as well as microbial metabolic activity and microbial community abundance in groundwater, are used to assess the microbial community activity index in soil and groundwater through weighted summation. The Pearson correlation coefficient between the microbial community activity index in soil and groundwater and pollutant concentration is calculated to obtain the soil and groundwater impact index. The risk assessment module is used to comprehensively assess the environmental risk assessment index of the atmosphere, soil, groundwater, and environmentally sensitive areas at each stage by calculating the environmental risk assessment index formula. The early warning module is used to statistically analyze the historical mean and standard deviation of the environmental risk assessment index based on the calculation results, and establish a three-level early warning mechanism. When the risk level is low, medium, or high, a level one, level two, or level three early warning is triggered, respectively. This invention, through the collaborative work of each module, achieves online intelligent early warning for solid fuel environmental protection projects, which helps to promptly detect and respond to environmental risks.

[0057] In this embodiment, the data acquisition module includes the following steps: real-time monitoring and acquisition of remote sensing data, infrared data, and environmental monitoring data of solid fuel in four stages of production, storage, transportation, and use; the environmental monitoring data includes: atmospheric monitoring data, soil monitoring data, groundwater monitoring data, and environmentally sensitive area monitoring data.

[0058] Specifically, real-time monitoring and collection of various data points related to solid fuels at four stages—production, storage, transportation, and use—are employed. Remote sensing data, acquired via satellite or drones equipped with remote sensing devices, is used to understand the macroscopic distribution and environmental conditions of solid fuels at each stage. Infrared data, collected using infrared thermal imagers, monitors temperature changes in solid fuels at each stage, helping to identify abnormal heat generation areas, such as incomplete combustion during production or potential spontaneous combustion during storage. Environmental monitoring data covers atmospheric, soil, groundwater, and environmentally sensitive areas. Atmospheric monitoring data includes the concentrations of pollutants such as sulfur dioxide, nitrogen oxides, and particulate matter, which are monitored in real time by deploying automatic atmospheric monitoring stations and mobile monitoring equipment around each stage of solid fuel production. Soil monitoring data involves the content of pollutants such as heavy metals and organic matter in the soil, and is collected regularly by setting up soil sampling points in areas such as solid fuel storage sites, transportation routes, and land after use. Groundwater monitoring data focuses on indicators such as total coliforms, ammonia nitrogen, and volatile organic compounds in groundwater, which are obtained by regularly sampling and testing groundwater wells or monitoring boreholes in the area surrounding solid fuel production. Environmentally sensitive area monitoring data focuses on the ecological environment quality of environmentally sensitive areas such as nature reserves, residential areas, and water sources around each stage of solid fuel production, and data is collected using appropriate ecological monitoring methods.

[0059] In this embodiment, the data processing module includes the following steps: establishing a solid fuel environmental protection project database, classifying the pre-processed real-time monitoring data according to the four stages of production, storage, transportation, and use, establishing a multi-dimensional database index, and integrating and storing it with historical monitoring data.

[0060] Specifically, firstly, a solid fuel environmental protection project database is established. Next, the collected real-time monitoring data is preprocessed, including noise removal, data cleaning, and normalization, to ensure data accuracy. Then, the preprocessed real-time monitoring data is categorized according to four stages: solid fuel production, storage, transportation, and use. Monitoring data from the production stage can be stored in a production data table, storage data in a storage data table, transportation data in a transportation data table, and use data in a use data table. Simultaneously, multi-dimensional database indexes are created for each data table. Indexes can be created based on time (facilitating queries of monitoring data within a specific time period), space (facilitating the location of monitoring data in specific areas), and data type (e.g., air monitoring data, soil monitoring data) to improve data query and retrieval efficiency. Finally, the preprocessed real-time monitoring data is integrated and stored with historical monitoring data. For example, new real-time monitoring data is appended to the corresponding historical data table, ensuring the database's data is complete and continuous.

[0061] In this embodiment, a temperature-based pollutant diffusion correlation model is established by fusing infrared data and remote sensing data to analyze pollutant emission rates, including the following steps:

[0062] The preprocessed infrared data and remote sensing data are overlaid and fused, and geographic registration is performed based on the geographic information system platform. Each infrared pixel is matched with the corresponding pixel-level location in the remote sensing image to obtain a fused dataset that simultaneously contains temperature information and spatial distribution information.

[0063] Computational fluid dynamics was used to simulate the pollutant diffusion path, and a temperature-pollutant diffusion correlation model was established; the model diffusion parameters were dynamically adjusted based on the calorific value of solid fuel.

[0064] Based on the usage and monitoring data of solid fuels, the specific location and type of pollutant emission sources are determined using a geographic information system platform; real-time meteorological data of the emission source area is collected and preprocessed.

[0065] Based on the diffusion equation in the temperature-pollutant diffusion correlation model, combined with meteorological data, the specific location of pollutant emission sources, and diffusion parameters, the source strength information of pollutants is calculated in reverse. According to the principle of mass conservation, the emission rate of pollutants is equal to the mass of pollutants emitted per unit time, and dynamic corrections are made in combination with meteorological data.

[0066] Specifically, the acquired infrared data undergoes preprocessing, including noise and outlier removal, filtering, and smoothing. Radiometric and geometric corrections are performed on the remote sensing data. Using a Geographic Information System (GIS) platform, the preprocessed infrared thermal images are georeferenced with satellite remote sensing imagery. This ensures that each infrared pixel matches its corresponding pixel location in the remote sensing image. Through georeferenced mapping, a fused dataset containing both temperature and spatial distribution information is generated. Fusion methods can employ pixel-level fusion, feature-level fusion, and other techniques. Based on the fused dataset, Computational Fluid Dynamics (CFD) is used to simulate the pollutant diffusion path. CFD simulations can consider physical processes such as fluid flow, heat transfer, and mass transfer. The specific mathematical expression for the diffusion equation is: Where C is the pollutant concentration, t is time, and u is the fluid velocity vector, expressed as: ,in , , These are the velocity components of the fluid in the x, y, and z directions, respectively, and D is the diffusion coefficient; It is a gradient of pollutant concentrations. , pointing in the direction of the fastest increase in concentration, and its magnitude is the maximum rate of concentration change; Represents the dot product of two vectors; This describes the diffusion process of pollutants in a static fluid, i.e., molecular diffusion or turbulent diffusion caused by concentration differences; D is the diffusion coefficient, and S represents the source-sink intensity, indicating the change in pollutant concentration per unit volume per unit time due to source emission or sink absorption. Based on the calorific value of solid fuels, the diffusion parameters of the model are dynamically adjusted, including the diffusion coefficient and boundary conditions. The specific mathematical expression is as follows: Where D is the adjusted diffusion coefficient. Let Q be the initial diffusion coefficient and Q be the calorific value of the solid fuel. The baseline calorific value is used. Specifically, calorific value data of solid fuels is collected and preprocessed in real time. Through controlled variable experiments, the functional relationship between calorific value and diffusion coefficient is fitted. The corrected diffusion coefficient is then input into the computational fluid dynamics model in real time to update the coefficient terms in the diffusion equation. Based on the usage and monitoring data of solid fuels, the specific location and type of pollutant emission sources are determined using a GIS platform. Emission sources can include chimneys, storage tanks, and transport vehicles. Real-time meteorological data of the emission source area, including wind speed, wind direction, temperature, and humidity, is collected. The meteorological data undergoes data cleaning and standardization preprocessing; meteorological data can be obtained from weather stations or numerical weather prediction models. Based on the diffusion equation in the temperature-pollutant diffusion correlation model, combined with meteorological data, the specific location of pollutant emission sources, and diffusion parameters, the source strength information of the pollutants is calculated inversely, i.e., the mass of pollutants emitted per unit time. The source strength formula is: ,in, It is Yuanqiang, It is the initial source strength. It is the actual pollutant concentration at the i-th monitoring point. The pollutant concentration calculated by the model for the i-th monitoring point is... This is the total number of monitoring points; The initial source strength can be set based on historical emission data or expert experience; This is the fitting coefficient. The initial fitting coefficient is set to 0.05, and adjusted through cross-validation, the L-curve method, or empirical selection. Based on the principle of mass conservation, the emission rate of pollutants equals the mass of pollutants emitted per unit time, and is dynamically corrected using meteorological data. The formula is: ,in, It is Yuanqiang, It is the dynamically corrected pollutant emission rate. It is the real-time temperature. It is the reference temperature; It is real-time humidity. This is the baseline humidity; F is the real-time wind speed. That is the base wind speed. , and These are correction coefficients, 0.5, 0.3, and 0.2 respectively. These coefficients can be adjusted based on historical data or actual conditions. The dynamic correction method can consider the impact of meteorological factors such as temperature, wind speed, and wind direction on pollutant dispersion. Infrared and remote sensing data are continuously collected, and the fused dataset and model parameters are updated in real time to reflect the latest situation of pollutant emissions and dispersion. Based on real-time monitoring data, the temperature-pollutant dispersion correlation model is dynamically updated to ensure the accuracy and timeliness of the model.

[0067] This process includes: constructing a temperature-pollutant diffusion correlation model using a neural network model derived from machine learning. The input layer receives fused infrared and remote sensing data, including temperature, pollutant concentration, and meteorological parameters. The output layer outputs predicted pollutant diffusion results. A large amount of fused data is used as input samples, and the corresponding actual pollutant diffusion conditions are used as output samples to train the model. By adjusting parameters such as the neural network weights, the error between the model output and the actual results is minimized, thereby learning a linear mapping relationship between temperature and pollutant diffusion. A subset of data is used as a validation set to validate the trained model and evaluate its accuracy and generalization ability. Based on the validation results, the model is optimized and adjusted, such as by adjusting the network structure and optimizing algorithm parameters, to improve model performance.

[0068] In this embodiment, the range of pollutant diffusion impact is calculated by combining real-time meteorological data and the location of emission sources, including the following steps:

[0069] Temperature data and pollutant concentration data are converted into raster format. Using the raster calculator of the geographic information system platform, the magnitude and direction of the temperature gradient or concentration gradient are obtained by calculating the temperature or concentration difference between each raster cell and its neighboring raster cells, and the temperature gradient field and pollutant concentration gradient field are generated respectively.

[0070] The gradient vector of each grid cell is extracted from the temperature gradient field and pollutant concentration gradient field raster data. The vector dot product formula in the raster calculator is used to calculate the angle between the temperature gradient vector and the pollutant concentration gradient vector, and an angle distribution map is generated.

[0071] Centered on a high-temperature solid fuel source, a multi-level buffer zone of 500m, 1km, and 2km was established on a geographic information system platform, and the average pollutant concentration within each buffer zone was statistically analyzed. Combined with wind direction data, a cost-distance weighted function was used to simulate the diffusion path of pollutants from the high-temperature source to the low-temperature zone.

[0072] Real-time meteorological data, emission source location information, pollutant emission rates, and the generated temperature gradient field, concentration gradient field, angle distribution map, and diffusion path are used as input parameters and substituted into the temperature-pollutant diffusion correlation model; the diffusion process of pollutants in the atmosphere is simulated, the concentration distribution of pollutants in time and space is calculated, and the influence range of pollutant diffusion is obtained.

[0073] Specifically, a geographic information system (GIS) platform is used to perform spatial distribution analysis on monitoring data, creating spatial distribution maps of the atmosphere, soil, groundwater, and environmentally sensitive areas. Temperature and pollutant concentration data are converted into raster format, with each raster cell representing a temperature or pollutant concentration value. Using the platform's raster calculator, the temperature or concentration difference between each raster cell and its neighboring cells is calculated, yielding temperature and pollutant concentration gradient fields that reflect the spatial rate and direction of temperature and pollutant concentration variation. The gradient vector of each raster cell, containing the magnitude and direction of the gradient, is extracted from these fields. The angle between the temperature gradient vector and the pollutant concentration gradient vector is calculated using the vector dot product formula, generating an angle distribution map to aid in understanding the relationship between the temperature and pollutant concentration fields. A multi-level buffer zone of 500m, 1km, and 2km is established on the GIS platform, centered on a high-temperature solid fuel source. The average pollutant concentration within each buffer zone is statistically analyzed to assess the degree of pollutant diffusion at different distances. Combined with wind direction data, a cost-distance weighted function is used to simulate the diffusion path of pollutants from the high-temperature source to the low-temperature zone, considering the influence of wind speed and direction on pollutant diffusion. Real-time meteorological data, including wind speed, wind direction, temperature, humidity, emission source location information, pollutant emission rates, and the generated temperature gradient field, concentration gradient field, angle distribution map, and diffusion path, are used as input parameters and fed into the temperature-pollutant diffusion correlation model. The model is run to simulate the diffusion process of pollutants in the atmosphere, calculating the concentration distribution of pollutants in different times and spaces. By simulating the diffusion process of pollutants in the atmosphere and calculating their concentration distribution in time and space, the model can determine the scope of influence of pollutant diffusion and identify the affected areas and their extent.

[0074] In this embodiment, the impact of solid fuels on environmentally sensitive areas is assessed by overlaying map layers of solid fuels at each stage, including the following steps:

[0075] The collected map layer data includes: map layers of solid fuel in the four stages and distribution maps of environmentally sensitive areas, and is preprocessed;

[0076] The processed map layer data is imported into the geographic information system platform, and the overlay analysis tool is used to overlay all the map layer data to generate the first new layer.

[0077] By combining the 500m, 1km, and 2km multi-level buffer zones established on the geographic information system platform, the buffer zone layer is overlaid with the environmentally sensitive area layer to identify the overlapping areas between the buffer zone and the environmentally sensitive area, and a second new layer is generated.

[0078] Statistical analysis is performed on the first new layer to calculate the area and number of environmentally sensitive areas within or near the solid fuel activity area; statistical analysis is performed on the second new layer to calculate the area of ​​environmentally sensitive areas within each buffer zone and the proportion of environmentally sensitive areas within the buffer zone.

[0079] The comprehensive assessment of the impact of solid fuels on environmentally sensitive areas is calculated using the following formula:

[0080]

[0081] Wherein, H represents the comprehensive impact index of solid fuels on environmentally sensitive areas. The extent of the impact of pollutant diffusion, It is the average range of influence of pollutant diffusion. For pollutant emission rate, For pollutant emission rate limits, It is the area of ​​the environmentally sensitive region within the i-th buffer. The total area of ​​environmentally sensitive areas It is the radius of the i-th buffer; Let i be the weight coefficient of the i-th buffer. , , These are the correction factors.

[0082] Specifically, map layer data, including solid fuel production distribution maps, storage maps, transportation route maps, usage maps, and environmentally sensitive area distribution maps, are collected. The collected map layer data is converted to a format recognizable by the GIS platform, such as Shapefile or GeoJSON. The coordinate systems of all layers are ensured to be consistent, typically using WGS-84 or projected coordinate systems such as UTM. The processed map layer data is then imported into the GIS platform. Using an overlay analysis tool, the solid fuel production, storage, transportation, and usage layers are overlaid with the environmentally sensitive area layer to generate a first new layer. This layer displays the overlapping areas between solid fuel activity areas and environmentally sensitive areas. Multi-level buffer zones of 500m, 1km, and 2km are established on the GIS platform, centered on the high-temperature source of solid fuel. The buffer zone layer is overlaid with the environmentally sensitive area layer to identify overlapping areas within the buffer zones, generating a second new layer. Statistical analysis is performed on the first new layer to calculate the area and number of environmentally sensitive areas within or near the solid fuel activity areas. Statistical analysis is also performed on the second new layer to calculate the area of ​​environmentally sensitive areas within each buffer zone and the proportion of environmentally sensitive areas within the buffer zone. Using a formula to assess the impact of solid fuels on environmentally sensitive areas, where, The weighting factor for the first 500m buffer is 0.5. The weighting factor for the second 1km buffer zone is 0.3. The weighting factor for the third 2km buffer zone is 0.2. , , The correction coefficients are 0.4, 0.3, and 0.3, respectively; the values ​​of the buffer weight coefficient and the correction coefficient are dynamically adjusted based on historical data or experimental results. The impact of solid fuels on environmentally sensitive areas is assessed based on the calculated comprehensive impact index. Generally, a larger H value indicates a higher degree of impact.

[0083] In this embodiment, the impact index of solid fuels on soil and groundwater is analyzed and evaluated, including the following steps:

[0084] Real-time monitoring and collection of soil microbial respiration rate, soil enzyme activity, and microbial biomass; weighted summation to assess soil microbial community activity index.

[0085] Real-time monitoring and collection of microbial metabolic activity and microbial community abundance in groundwater, and assessment of the microbial community activity index in groundwater by weighted summation;

[0086] By real-time monitoring of pollutant concentrations related to solid fuel residues in soil and groundwater, Pearson correlation coefficients between microbial activity indices and pollutant concentrations in soil and groundwater were calculated.

[0087] The soil impact index is calculated by multiplying the soil microbial activity index by the absolute value of pollutant concentration and the Pearson correlation coefficient; similarly, the groundwater impact index is obtained.

[0088] Specifically, through sensor networks and laboratory analysis, real-time monitoring and collection of data are conducted on soil microbial respiration rate, soil enzyme activity, and microbial biomass, as well as groundwater microbial metabolic activity and microbial community abundance. Based on relevant research and practical experience, the weights for microbial respiration rate, soil enzyme activity, and microbial biomass can be set to 0.3, 0.4, and 0.3, respectively. For example, if the microbial respiration rate is R, soil enzyme activity is E, and microbial biomass is B, then the soil microbial community activity index is 0.3R + 0.4E + 0.3B. Based on research and actual conditions, the weights for microbial metabolic activity and microbial community abundance can be set to 0.6 and 0.4, respectively. Assuming microbial metabolic activity is M and microbial community abundance is A, then the groundwater microbial community activity index is 0.6M + 0.4A. The various weighting coefficients are dynamically adjusted based on historical data or experimental results. Real-time monitoring of pollutant concentrations related to solid fuel residues in soil and groundwater is also conducted, and the Pearson correlation coefficient between the microbial community activity index and pollutant concentrations in soil and groundwater is calculated using statistical software. The soil microbial community activity index is multiplied by the absolute value of the pollutant concentration and the Pearson correlation coefficient. Similarly, the groundwater microbial community activity index is multiplied by the absolute value of the pollutant concentration and the Pearson correlation coefficient to obtain the corresponding soil impact index and groundwater impact index, respectively.

[0089] In this embodiment, the risk assessment module includes the following steps:

[0090] The formula for calculating the environmental risk assessment index is as follows:

[0091]

[0092] in, This is an environmental risk assessment index. Let k be the extent of the pollutant diffusion in the k-th stage. Let be the pollutant emission rate at the k-th stage, and t be the pollutant exposure time. Let be the comprehensive impact index of solid fuel in the k-th stage on environmentally sensitive areas. Let be the soil impact index for the k-th stage. Let be the groundwater impact index for the k-th stage; denoted as the distance from the pollution emission source at the k-th stage to the environmentally sensitive area; k = 1, 2, 3, 4 respectively represent the four stages of solid fuel production, storage, transportation, and use.

[0093] Specifically, based on the fused infrared and remote sensing data, a temperature-based pollutant diffusion correlation model is used to simulate the atmospheric diffusion process of pollutants, calculate the temporal and spatial concentration distribution of pollutants, and obtain the impact range of pollutant diffusion. By inversely calculating the source strength information of pollutants, i.e., the mass of pollutants emitted per unit time, and combining it with meteorological data for dynamic correction, the pollutant emission rate at each stage is obtained. By overlaying map layers of solid fuel at each stage with the distribution map of environmentally sensitive areas, and combining buffer zone analysis, the area and number of environmentally sensitive areas within or near the solid fuel activity area, as well as the area and proportion of environmentally sensitive areas within each buffer zone, are calculated. A comprehensive assessment is then performed using a formula for the degree of impact of solid fuel on environmentally sensitive areas, determining the comprehensive impact index of solid fuel on environmentally sensitive areas at each stage. Real-time monitoring and collection of relevant data from soil and groundwater are conducted. The microbial community activity index in soil and groundwater is assessed through weighted summation, and the Pearson correlation coefficient between the microbial community activity index and pollutant concentration is calculated, finally obtaining the soil impact index and groundwater impact index. Using a geographic information system platform, the specific locations of pollution emission sources and the distribution of environmentally sensitive areas are determined, and the distance between them is calculated to determine the distance from pollution emission sources to environmentally sensitive areas at each stage. By substituting the various parameters determined above into the environmental risk assessment index formula, the environmental risk assessment index is calculated. This achieves a comprehensive assessment of various parameters in the four stages of solid fuel production, storage, transportation, and use, and then calculates the environmental risk assessment index to provide a basis for risk early warning.

[0094] In this embodiment, the early warning module includes the following steps:

[0095] Based on the calculation results of the environmental risk assessment index, the historical average of the environmental risk assessment index was statistically analyzed. and standard deviation ;

[0096] when When the risk level is low, a Level 1 warning is triggered. When the risk level is medium, a level 2 warning is triggered. When the risk level is high, a Level 3 warning will be triggered.

[0097] Specifically, historical environmental risk assessment index data is collected to ensure data completeness and accuracy. The mean and standard deviation of historical data are statistically calculated. The mean represents the average level of risk, while the standard deviation measures the degree of risk fluctuation. When the environmental risk assessment index is lower than the historical mean and lower than the mean minus one standard deviation, a Level 1 warning is triggered, indicating that the current risk is low, but potential changes still require monitoring. When the index is between the mean minus one standard deviation and the mean plus one standard deviation, a Level 2 warning is triggered, indicating a moderate level of risk, requiring increased vigilance and preventative measures. When the index is higher than the mean plus one standard deviation, a Level 3 warning is triggered, indicating a high current risk that may have a significant impact on the environment, requiring immediate countermeasures. During real-time monitoring, the calculated environmental risk assessment index is compared with the set warning thresholds to trigger the corresponding level of warning, thus implementing a multi-level warning mechanism.

[0098] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An online intelligent early warning system for solid fuel environmental protection projects based on big data, characterized in that, Includes the following modules: Data acquisition module: Collects monitoring data on solid fuel at each stage; Data processing module: Establishes a database for solid fuel environmental protection projects and stores pre-processed monitoring data; Data Analysis Module: By fusing infrared and remote sensing data, a temperature-pollutant diffusion correlation model is established to analyze pollutant emission rates; by combining real-time meteorological data and emission source locations, the impact range of pollutant diffusion is calculated; by overlaying map layers of solid fuel at each stage, the impact of solid fuel on environmentally sensitive areas is assessed; and the impact index of solid fuel on soil and groundwater is analyzed and evaluated. Risk assessment module: comprehensively assesses the environmental risk assessment index of the atmosphere, soil, groundwater and environmentally sensitive areas in each stage; Early warning module: Establish a three-level early warning system using environmental risk assessment indices; By fusing infrared and remote sensing data, a temperature-based pollutant diffusion correlation model was established to analyze pollutant emission rates, including: The preprocessed infrared data and remote sensing data are overlaid and fused, and geographic registration is performed based on the geographic information system platform. Each infrared pixel is matched with the corresponding pixel-level location in the remote sensing image to obtain a fused dataset that simultaneously contains temperature information and spatial distribution information. Computational fluid dynamics was used to simulate the pollutant diffusion path, and a temperature-pollutant diffusion correlation model was established; the model diffusion parameters were dynamically adjusted based on the calorific value of solid fuel. Based on the usage and monitoring data of solid fuels, the specific location and type of pollutant emission sources are determined using a geographic information system platform; real-time meteorological data of the emission source area is collected and preprocessed. Based on the diffusion equation in the temperature-pollutant diffusion correlation model, combined with meteorological data, the specific location of pollutant emission sources, and diffusion parameters, the source strength information of pollutants is calculated in reverse. According to the principle of mass conservation, the emission rate of pollutants is equal to the mass of pollutants emitted per unit time, and dynamic correction is made in combination with meteorological data. By combining real-time meteorological data and the location of emission sources, the extent of pollutant diffusion impact is calculated, including: Temperature data and pollutant concentration data are converted into raster format. Using the raster calculator of the geographic information system platform, the magnitude and direction of the temperature gradient or concentration gradient are obtained by calculating the temperature or concentration difference between each raster cell and its neighboring raster cells, and the temperature gradient field and pollutant concentration gradient field are generated respectively. The gradient vector of each grid cell is extracted from the temperature gradient field and pollutant concentration gradient field raster data. The vector dot product formula in the raster calculator is used to calculate the angle between the temperature gradient vector and the pollutant concentration gradient vector, and an angle distribution map is generated. Centered on a high-temperature solid fuel source, a multi-level buffer zone of 500m, 1km, and 2km was established on a geographic information system platform, and the average pollutant concentration within each buffer zone was statistically analyzed. Combined with wind direction data, a cost-distance weighted function was used to simulate the diffusion path of pollutants from the high-temperature source to the low-temperature zone. Real-time meteorological data, emission source location information, pollutant emission rates, and the generated temperature gradient field, concentration gradient field, angle distribution map, and diffusion path are used as input parameters and substituted into the temperature-pollutant diffusion correlation model; the diffusion process of pollutants in the atmosphere is simulated, the concentration distribution of pollutants in time and space is calculated, and the influence range of pollutant diffusion is obtained.

2. The online intelligent early warning system for solid fuel environmental protection projects based on big data as described in claim 1, characterized in that, The data acquisition module includes: real-time monitoring and acquisition of remote sensing data, infrared data, and environmental monitoring data of solid fuels in four stages: production, storage, transportation, and use; the environmental monitoring data includes: atmospheric monitoring data, soil monitoring data, groundwater monitoring data, and environmentally sensitive area monitoring data.

3. The online intelligent early warning system for solid fuel environmental protection projects based on big data as described in claim 1, characterized in that, The data processing module includes: establishing a solid fuel environmental protection project database, classifying pre-processed real-time monitoring data according to four stages: production, storage, transportation, and use, establishing a multi-dimensional database index, and integrating and storing it with historical monitoring data.

4. The online intelligent early warning system for solid fuel environmental protection projects based on big data as described in claim 1, characterized in that, By overlaying map layers of solid fuels at various stages, the impact of solid fuels on environmentally sensitive areas is assessed, including: The collected map layer data includes: map layers of solid fuel in the four stages and distribution maps of environmentally sensitive areas, and is preprocessed; The processed map layer data is imported into the geographic information system platform, and the overlay analysis tool is used to overlay all the map layer data to generate the first new layer. By combining the 500m, 1km, and 2km multi-level buffer zones established on the geographic information system platform, the buffer zone layer is overlaid with the environmentally sensitive area layer to identify the overlapping areas between the buffer zone and the environmentally sensitive area, and a second new layer is generated. Statistical analysis is performed on the first new layer to calculate the area and number of environmentally sensitive areas within or near the solid fuel activity area; statistical analysis is performed on the second new layer to calculate the area of ​​environmentally sensitive areas within each buffer zone and the proportion of environmentally sensitive areas within the buffer zone. The comprehensive assessment of the impact of solid fuels on environmentally sensitive areas is calculated using the following formula: Wherein, H represents the comprehensive impact index of solid fuels on environmentally sensitive areas. The extent of the impact of pollutant diffusion, It is the average range of influence of pollutant diffusion. For pollutant emission rate, For pollutant emission rate limits, It is the area of ​​the environmentally sensitive region within the i-th buffer. The total area of ​​environmentally sensitive areas It is the radius of the i-th buffer; Let i be the weight coefficient of the i-th buffer. , , These are the correction factors.

5. The online intelligent early warning system for solid fuel environmental protection projects based on big data as described in claim 1, characterized in that, The analysis and assessment of the impact indices of solid fuels on soil and groundwater includes: Real-time monitoring and collection of soil microbial respiration rate, soil enzyme activity, and microbial biomass; weighted summation to assess soil microbial community activity index. Real-time monitoring and collection of microbial metabolic activity and microbial community abundance in groundwater, and assessment of the microbial community activity index in groundwater by weighted summation; By real-time monitoring of pollutant concentrations related to solid fuel residues in soil and groundwater, Pearson correlation coefficients between microbial activity indices and pollutant concentrations in soil and groundwater were calculated. The soil impact index is calculated by multiplying the soil microbial activity index by the absolute value of pollutant concentration and the Pearson correlation coefficient; similarly, the groundwater impact index is obtained.

6. The online intelligent early warning system for solid fuel environmental protection projects based on big data as described in claim 1, characterized in that, The risk assessment module includes: The formula for calculating the environmental risk assessment index is as follows: in, This is an environmental risk assessment index. Let k be the extent of the pollutant diffusion in the k-th stage. Let be the pollutant emission rate at the k-th stage, and t be the pollutant exposure time. Let be the comprehensive impact index of solid fuel in the k-th stage on environmentally sensitive areas. Let be the soil impact index for the k-th stage. Let be the groundwater impact index for the k-th stage; denoted as the distance from the pollution emission source at the k-th stage to the environmentally sensitive area; k = 1, 2, 3, 4 respectively represent the four stages of solid fuel production, storage, transportation, and use.

7. The online intelligent early warning system for solid fuel environmental protection projects based on big data as described in claim 6, characterized in that, The early warning module includes: Based on the calculation results of the environmental risk assessment index, the historical average of the environmental risk assessment index was statistically analyzed. and standard deviation ; when When the risk level is low, a Level 1 warning is triggered. When the risk level is medium, a level 2 warning is triggered. When the risk level is high, a Level 3 warning will be triggered.

Images