Process carbon emission source tracing method based on spatiotemporal big data

Abstract

The present invention provides a process carbon emission source tracing method based on spatiotemporal big data, including: determining the target carbon emission source of process carbon and the emission factors of each target carbon emission source, determining the emission distribution type of process carbon according to the spatiotemporal data of the emission factors; establishing a carbon emission diffusion model based on the emission distribution type of process carbon; sampling from the spatiotemporal data of the emission distribution type to obtain a target sampling sample, and inputting the target sampling sample into the carbon emission diffusion model for spatiotemporal evolution simulation, thereby obtaining the carbon concentration change data of the process carbon changing with time and space; performing Bayesian network analysis on the carbon concentration change data through a preset Bayesian network model, thereby determining the diffusion path of the process carbon. It can effectively simulate high-dimensional environments with large uncertainty and randomness in natural evolution or complex ecosystems, and improve the accuracy of tracing the diffusion path.

Description

Technical Field

[0001] The present invention relates to the field of environmental data management, and in particular to a process carbon emission source tracing method based on spatiotemporal big data. Background Art

[0002] Process carbon refers to carbon emissions generated by specific production processes during industrial production. It is the amount of greenhouse gases such as carbon dioxide released due to physical and chemical changes in each link of the product from raw material processing to finished product. For example, in the steel production process, carbon emissions are generated in a series of links from iron ore sintering, ironmaking, steelmaking to steel rolling. In the process of iron ore smelting in a blast furnace, coke, as a reducing agent, reacts with iron ore to produce a large amount of carbon dioxide. This part of carbon emissions belongs to process carbon.

[0003] Related technologies use isotope labeling for traceability analysis, but since isotope labeling requires high-precision isotope analysis instruments and sampling is more difficult, its analysis cost is high. In addition, since the spread of some process carbon is greatly affected by factors such as temperature, geographical location and time, isotope labeling is difficult to accurately determine the diffusion path of the emission source. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a process carbon emission source tracing method based on spatiotemporal big data, which solves the problem in the prior art that it is difficult to accurately determine the diffusion path of the emission source.

[0005] In the first aspect, the present application provides a process carbon emission source tracing method based on spatiotemporal big data, including:

[0006] Determine the target carbon emission sources of process carbon and the emission factors of each target carbon emission source, and determine the emission distribution type of process carbon based on the spatiotemporal data of the emission factors;

[0007] Establishing a carbon emission diffusion model based on the emission distribution type of the process carbon;

[0008] Sampling target sampling samples from the spatiotemporal data of the emission distribution type, and inputting the target sampling samples into the carbon emission diffusion model for spatiotemporal evolution simulation, thereby obtaining carbon concentration change data of the process carbon changing with time and space;

[0009] The carbon concentration change data is subjected to Bayesian network analysis using a preset Bayesian network model, thereby determining the diffusion path of the process carbon.

[0010] In one embodiment, determining the emission distribution type of process carbon according to the spatiotemporal data of the emission factors specifically includes:

[0011] Draw a distribution probability graph according to the spatiotemporal data, compare the distribution probability graph with a preset probability distribution model and obtain corresponding similarity;

[0012] The probability distribution model with the highest similarity among the preset probability distribution models is used as the target probability distribution model, and the emission distribution type of the target probability distribution model is used as the emission distribution type of the distribution probability graph.

[0013] In one embodiment, after taking the emission distribution type of the target probability distribution model as the emission distribution type of the distribution probability graph, the method further includes:

[0014] Determine the corresponding empirical cumulative distribution function according to the arrangement order of the sample points of the spatiotemporal data;

[0015] Determining characteristic parameters of the target probability distribution model, and determining a theoretical cumulative distribution function of each sample point based on the characteristic parameters of the target probability distribution model;

[0016] According to the comparison result of the empirical cumulative distribution function and the theoretical cumulative distribution function, it is determined whether the spatiotemporal data obeys the target probability distribution model.

[0017] In one embodiment, the emission factor further includes wind speed data; and establishing a carbon emission diffusion model based on the emission distribution type of the process carbon specifically includes:

[0018] Establishing a virtual emission box model at the target carbon emission source;

[0019] Based on the virtual emission box model, the carbon emission diffusion model is established according to the mass balance equation.

[0020] In one embodiment, the expression according to the mass balance equation is: Among them, C is the concentration of process carbon in the virtual emission box model, Q is the intensity of the target carbon emission source, V is the volume of the virtual emission box model, u is the wind speed data, and L is the length of the emission box model along the wind speed direction.

[0021] In one embodiment, sampling from the spatiotemporal data of the emission distribution type to obtain a target sampling sample specifically includes:

[0022] Determine a probability density function corresponding to the emission distribution type, and determine an enclosing function that meets a preset condition based on the probability density function;

[0023] Randomly select a sampling sample from the spatiotemporal data, and calculate the acceptance probability of the sampling sample under the enclosing function;

[0024] When the acceptance probability is greater than or equal to a preset random number, the sampling sample is recorded as a target sampling sample.

[0025] In one embodiment, before performing Bayesian network analysis on the carbon concentration change data through a preset Bayesian network model to determine the diffusion path of process carbon, the method further includes:

[0026] A Bayesian network structure is constructed according to the correlation between the types of factors in the emission factors; the Bayesian network structure includes a plurality of nodes; the types of factors of the emission factors include carbon emission sources, meteorological factors, geographical factors and carbon concentration monitoring data;

[0027] The conditional probability distribution of each node in the Bayesian network structure is estimated according to historical data, and the Bayesian network model is obtained according to the conditional probability distribution.

[0028] In the second aspect, the present application provides a process carbon emission source tracing device based on spatiotemporal big data, comprising:

[0029] A distribution type determination module is used to determine the target carbon emission source of process carbon and the emission factors of each target carbon emission source, and determine the emission distribution type of process carbon according to the spatiotemporal data of the emission factors;

[0030] A diffusion model building module, used to build a carbon emission diffusion model based on the emission distribution type of the process carbon;

[0031] A spatiotemporal evolution simulation module, for sampling from the spatiotemporal data of the emission distribution type to obtain a target sampling sample, and inputting the target sampling sample into the carbon emission diffusion model for spatiotemporal evolution simulation, thereby obtaining the carbon concentration change data of the process carbon changing with time and space;

[0032] The analysis module is used to perform Bayesian network analysis on the carbon concentration change data through a preset Bayesian network model, so as to determine the diffusion path of the process carbon.

[0033] In a third aspect, the present application provides a process carbon emission source tracing system based on spatiotemporal big data, comprising a processor and a memory; wherein the memory stores a computer program, and the computer program is used to be loaded by the processor and execute the process carbon emission source tracing method based on spatiotemporal big data as described in any one of the first aspects.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, wherein the instructions are used by a processor to load and execute a process carbon emission source tracing method based on spatiotemporal big data as described in any one of the first aspects.

[0035] In the process carbon emission source tracing method based on spatiotemporal big data in the embodiment of the present application, by sampling the spatiotemporal data of a determined emission distribution type and performing spatiotemporal evolution simulation based on the sampled spatiotemporal data, the problem that the propagation of process carbon is greatly affected by factors such as temperature, geographical location and time, resulting in poor traceability of the propagation path, is effectively solved. It can effectively simulate high-dimensional environments with greater uncertainty and randomness in natural evolution or complex ecosystems, and improve the accuracy of diffusion path tracing. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 It is a flow chart of the process carbon emission source tracing method based on spatiotemporal big data in an embodiment of the present application.

[0038] Figure 2 It is a schematic diagram of the structure of a process carbon emission source tracing device based on spatiotemporal big data in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the description of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In the description of the present invention, unless otherwise clearly specified and limited, the terms "set", "install", "connection" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0041] The directions or positional relationships indicated by terms such as “upper”, “lower”, “left”, “right”, “front”, “back”, “top”, “bottom”, “inside” and “outside” are based on the directions or positional relationships shown in the accompanying drawings, or are the directions or positional relationships in which the inventive product is usually placed when used. They are only for the convenience of description and simplified description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present invention.

[0042] The terms "first", "second", "third", etc. are merely used to distinguish elements of similar nature, and do not indicate or imply relative importance or a particular order.

[0043] The terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of the elements listed and may also include additional elements not expressly listed.

[0044] like Figure 1 As shown, this embodiment provides a process carbon emission source tracing method based on spatiotemporal big data, including:

[0045] Step S100: determining the target carbon emission source of process carbon and the emission factor of each target carbon emission source, and determining the emission distribution type of process carbon according to the spatiotemporal data of the emission factor;

[0046] Step S200: establishing a carbon emission diffusion model based on the emission distribution type of the process carbon;

[0047] Step S300: sampling from the spatiotemporal data of the emission distribution type to obtain target sampling samples, and inputting the target sampling samples into the carbon emission diffusion model for spatiotemporal evolution simulation, thereby obtaining carbon concentration change data of the process carbon changing with time and space;

[0048] Step S400: performing Bayesian network analysis on the carbon concentration change data using a preset Bayesian network model to determine the diffusion path of process carbon.

[0049] In the process carbon emission source tracing method based on spatiotemporal big data of the present embodiment, by sampling the spatiotemporal data of the determined emission distribution type and performing spatiotemporal evolution simulation based on the sampled spatiotemporal data, the problem that the propagation of process carbon is greatly affected by factors such as temperature, geographical location and time, resulting in poor traceability accuracy of the propagation path is effectively solved. It can effectively simulate high-dimensional environments with greater uncertainty and randomness in natural evolution or complex ecosystems, and improve the accuracy of diffusion path tracing.

[0050] This embodiment takes the process carbon in the processing and production of bamboo and wood handicrafts as an example. Bamboo and wood products usually include the steps of material selection, cutting, drying, carving and shaping, grinding and polishing, assembly and splicing, and painting. In the process of processing and production, the sources of process carbon mainly involve three aspects. The first is the carbon emissions from energy consumption. For example, in the process of bamboo and wood handicraft processing, cutting, drying and other links require energy consumption, as well as carbon emissions in the transportation of raw materials. Bamboo and wood raw materials usually need to be transported from the place of origin to the processing plant. Whether by road, rail or water, fuel will be consumed and carbon emissions will be generated. The second is the carbon emissions generated during the processing. Some bamboo and wood products need to be shaped or removed from the water vapor in the bamboo and wood products through processes such as baking green or baking black. Bamboo and wood products will produce carbon dioxide, methane and other gases during the heating process, thereby generating carbon emissions. The third is the carbon emissions generated by the treatment of processing waste. A large amount of waste, such as sawdust, bamboo chips, etc., will be generated during the bamboo and wood processing process. If these wastes are treated by incineration, greenhouse gases such as carbon dioxide will be directly generated.

[0051] Since the carbon emission sources of electricity are usually power plants and the transportation process involves a large space, the carbon emission sources of energy consumption in this embodiment only involve the carbon emissions involved in the processing of relevant processing equipment in the production plant.

[0052] Step S100: Determine the target carbon emission source of process carbon and the emission factors of each target carbon emission source, and determine the emission distribution type of process carbon according to the spatiotemporal data of the emission factors.

[0053] In the process of bamboo and wood products processing, it is usually necessary to bake the bamboo and wood products in an oven to bake them green or black. During the baking process, the bamboo and wood products will produce carbon dioxide, methane and other gases during the heating process, thus generating carbon emissions. Therefore, the oven and the exhaust port are selected as the target emission sources. In addition, wood chips, bamboo chips and unusable waste are burned in an incinerator to produce charcoal and ash. At this time, the incinerator and the exhaust port of the incinerator are also used as target emission sources.

[0054] Emission factors include carbon emission source data, spatiotemporal data, and other influencing factor data. Carbon emission source data include energy consumption data (such as fuel usage and electricity consumption of factories; fuel consumption and electricity consumption of vehicles), production process data (such as carbon emissions generated by chemical reactions, waste emissions during processing), etc. Spatiotemporal data include time data and space data. Time data includes equipment operating time, production shifts, etc.; spatial data includes the geographical location (coordinates) and geographical environment (topography, vegetation coverage) of carbon emission sources. Other influencing factor data are other factors that may affect carbon emissions and carbon transmission, such as meteorological data (wind speed, wind direction, atmospheric stability), because they affect the diffusion of carbon in the atmosphere.

[0055] Determining the emission distribution type of process carbon according to the spatiotemporal data of the emission factors specifically includes:

[0056] Draw a distribution probability graph according to the spatiotemporal data, compare the distribution probability graph with a preset probability distribution model and obtain corresponding similarity;

[0057] The probability distribution model with the highest similarity among the preset probability distribution models is used as the target probability distribution model, and the emission distribution type of the target probability distribution model is used as the emission distribution type of the distribution probability graph.

[0058] In this embodiment, the collected data is made into a distribution probability map with carbon emissions as the ordinate and time and geographic coordinates as the abscissa. By comparing the similarity between the distribution probability map and the profile and change trend of the preset probability distribution model, the emission distribution type corresponding to the spatiotemporal data can be determined. For example, if the distribution probability map presents a shape that is high in the middle, low on both sides, and approximately symmetrical, then the data may obey a normal distribution; if the distribution probability map is right-skewed (with a long tail on the right), it may obey a lognormal distribution or a gamma distribution; if it is left-skewed (with a long tail on the left), it may be another asymmetric distribution. For other distributions, such as Weibull distribution, exponential distribution and other probability distribution models, there are also corresponding probability maps that can be used for comparison.

[0059] After determining the target probability distribution model, the KS test method is used to further determine whether the spatiotemporal data obeys the target probability distribution model. If not, it means that the probability distribution model with the highest similarity does not match, and the probability distribution models with lower similarity are selected for testing.

[0060] After taking the emission distribution type of the target probability distribution model as the emission distribution type of the distribution probability graph, the method further includes:

[0061] Determine the corresponding empirical cumulative distribution function according to the arrangement order of the sample points of the spatiotemporal data;

[0062] Determining characteristic parameters of the target probability distribution model, and determining a theoretical cumulative distribution function of each sample point based on the characteristic parameters of the target probability distribution model;

[0063] According to the comparison result of the empirical cumulative distribution function and the theoretical cumulative distribution function, it is determined whether the spatiotemporal data obeys the target probability distribution model.

[0064] In this embodiment, when performing the KS test, the null hypothesis is "the spatiotemporal data obeys the target probability distribution model", and the alternative hypothesis is "the spatiotemporal data does not come from the target probability distribution model". Taking the target probability distribution model as a normal distribution as an example, for the sample data x1, x2, ..., xn Sort from small to large and get x （1） ≤x （2） ≤......≤x （n） Then the empirical cumulative distribution function F n The formula for (x) is:

[0065] When x < x （1） When F n (x)=0;

[0066] When x （i） ≤x< x （i+1） When F n (x)=i / n, where i=1, 2..., n-1;

[0067] When x ≥ x （1） When F n (x)=1

[0068] For the normal distribution N(μ,σ 2 ), by calculating the sample mean To estimate the normal distribution μ, and calculate the sample standard deviation s to estimate the normal distribution σ. At this time, the formula of the theoretical cumulative distribution function is: For each sample point x （i） , calculate the maximum value of the empirical cumulative distribution function value and the theoretical cumulative distribution function value . And obtain the critical value D of the standard normal distribution by looking up the KS test critical value table n0 .

[0069] If D n ≤D n0 , then accept the null hypothesis, believe that the sample data comes from the assumed probability distribution, and determine that the spatiotemporal data obeys the target probability distribution model;

[0070] If D n >D n0 , then reject the null hypothesis and believe that the sample data does not come from the assumed probability distribution. Then reselect the new probability distribution model as the target probability distribution model.

[0071] Step S200: establishing a carbon emission diffusion model based on the emission distribution type of the process carbon.

[0072] In one embodiment, the emission factor further includes wind speed data; and establishing a carbon emission diffusion model based on the emission distribution type of the process carbon specifically includes:

[0073] Establishing a virtual emission box model at the target carbon emission source;

[0074] Based on the virtual emission box model, the carbon emission diffusion model is established according to the mass balance equation.

[0075] In this embodiment, the study area is regarded as a box and a virtual emission box model is established. It is assumed that the pollutants are evenly mixed in the box, and the box has input (emission source) and output (diffusion and sedimentation of process carbon). Since the emission sources of this embodiment are mainly concentrated in the factory that makes bamboo and wood products, all emission sources in the factory are regarded as a whole for research, which can effectively provide the accumulation and diffusion trend of process carbon under temporal and spatial changes.

[0076] It is understandable that in order to further improve the accuracy of the carbon emission diffusion model, the entire factory can be divided into multiple small boxes (for example, each workshop is a box), and then the operating results of each box are summarized.

[0077] In one embodiment, the expression according to the mass balance equation is: Among them, C is the concentration of process carbon in the virtual emission box model, Q is the intensity of the target carbon emission source, V is the volume of the virtual emission box model, u is the wind speed data, and L is the length of the emission box model along the wind speed direction.

[0078] In the mass balance equation, Expresses the input rate of process carbon per unit volume, Expresses the output rate of process carbon per unit volume, It expresses the rate of change of the concentration of process carbon in the box over time. The virtual emission box model can easily divide time into discrete time periods for research. In each time period, the change of pollutant concentration can be recalculated according to factors such as the intensity of emission sources and meteorological conditions at that time. Through this simulation of dynamic changes in time, the virtual emission box model can well describe the accumulation and dissipation process of process carbon in a region.

[0079] Step S300: sampling from the spatiotemporal data of the emission distribution type to obtain target sampling samples, and inputting the target sampling samples into the carbon emission diffusion model for spatiotemporal evolution simulation, thereby obtaining the carbon concentration change data of the process carbon changing with time and space.

[0080] In this embodiment, since the relationship between carbon emission sources and spatiotemporal data is complex and diverse, and may involve the interaction of multiple factors, the Monte Carlo method is used to sample from the spatiotemporal data to more accurately simulate the carbon emission and propagation process. As the number of spatiotemporal evolution simulations increases, the results of the Monte Carlo method will gradually converge to the true solution. In the process of carbon tracing, through a large number of random sampling and simulations, the tracing results can be made closer and closer to the real carbon emission sources and emission paths.

[0081] In one embodiment, sampling from the spatiotemporal data of the emission distribution type to obtain a target sampling sample specifically includes:

[0082] Determine a probability density function corresponding to the emission distribution type, and determine an enclosing function that meets a preset condition based on the probability density function;

[0083] Randomly select a sampling sample from the spatiotemporal data, and calculate the acceptance probability of the sampling sample under the enclosing function;

[0084] When the acceptance probability is greater than or equal to a preset random number, the sampling sample is recorded as a target sampling sample.

[0085] After determining the emission distribution type, the theoretical cumulative distribution function of the target probability distribution model corresponding to the emission distribution type can be used to derive the time, space, wind speed and other variable factors to obtain the corresponding probability density function f(t, x), where t is the time variable and x is the spatial position variable.

[0086] When the probability density function satisfies When For example, when the emission distribution type is two-dimensional uniform distribution, if the value range of the carbon emission time variable t is [a, b], and the value range of the spatial variable x is [c, d], then within the value range, the enclosing function is , when it exceeds the value range, Where M is a constant, which can be obtained by comparing and The maximum value within its area is determined.

[0087] For the extracted spatiotemporal data sample points , calculate its acceptance probability , then generate a random number u uniformly distributed in the interval [0, 1], and compare u with p. If , then accept the sample As target sampling sample; if , then reject the sample and return to the enveloping function The step of extracting samples from the sample is repeated until the required number of samples is obtained.

[0088] This embodiment selects sampling samples from the spatiotemporal data by rejection sampling, and focuses on sampling in areas with these emission distribution types, thereby improving sampling efficiency and finding the location and intensity of carbon emission sources that match the actual spatiotemporal distribution of carbon concentration more quickly. In addition, in carbon traceability, the relationship between carbon emission sources and the spatiotemporal distribution of carbon concentration may be very complex, resulting in irregular posterior distributions (i.e., the probability distribution of carbon emission sources under given spatiotemporal data), and rejection sampling can adapt to such complex posterior distributions. For example, when carbon emissions are affected by wind direction, terrain, and the interaction of different types of emission sources, the spatiotemporal distribution of carbon concentration will present a complex shape. Rejection sampling can sample throughout the entire possible parameter space without being restricted by the shape of the posterior distribution, effectively exploring those high-probability carbon emission source areas.

[0089] Step S400: performing Bayesian network analysis on the carbon concentration change data using a preset Bayesian network model to determine the diffusion path of process carbon.

[0090] The Bayesian network model is built based on a directed acyclic graph, and the connections between its nodes represent the causal relationship between variables. The Bayesian network model can integrate various information such as the characteristics of carbon emission sources in the process (such as emission intensity, emission time, etc.), meteorological conditions (wind speed, wind direction, atmospheric stability), geographical environment (topography, building distribution) and carbon concentration monitoring data into a unified framework. These factors interact with each other in the process of carbon diffusion, and the Bayesian network can well describe this complex relationship. The Bayesian network can process time series data and can analyze the dynamic process of carbon concentration changes well. Over time, the activity intensity of emission sources, meteorological conditions and other factors will change. The Bayesian network can update the inference of the carbon diffusion path based on these dynamically changing data, which improves the accuracy and predictability of the diffusion path traceability.

[0091] In one embodiment, before performing Bayesian network analysis on the carbon concentration change data through a preset Bayesian network model to determine the diffusion path of process carbon, the method further includes:

[0092] A Bayesian network structure is constructed according to the correlation between the types of factors in the emission factors; the Bayesian network structure includes a plurality of nodes; the types of factors of the emission factors include carbon emission sources, meteorological factors, geographical factors and carbon concentration monitoring data;

[0093] The conditional probability distribution of each node in the Bayesian network structure is estimated according to historical data, and the Bayesian network model is obtained according to the conditional probability distribution.

[0094] In this embodiment, when constructing the Bayesian network structure, the carbon emission source is the starting point of carbon diffusion, so it is the "root node", which points to the meteorological and geographical nodes related to carbon diffusion. The meteorological and geographical nodes jointly affect the carbon concentration monitoring point node, and the wind direction node and the emission source node both point to the carbon concentration monitoring point node, because the value of carbon concentration at a certain monitoring point depends on the intensity of the emission source and whether the wind direction brings carbon to the monitoring point.

[0095] Frequency statistics can be used to estimate conditional probabilities; for example, for wind direction nodes, the frequency of each wind direction under different emission source intensities and geographical environments is counted, and this is used as the conditional probability. The conditional probability can also be estimated by fitting a probability density function; such as emission intensity or carbon concentration. For example, assuming that emission intensity follows a normal distribution, the mean and standard deviation of the normal distribution are estimated through the collected historical emission intensity data, thereby determining its probability density function and using it as the conditional probability.

[0096] When the Bayesian network model is running, it uses Bayesian network inference algorithms (such as variable elimination, belief propagation algorithm, Gibbs sampling, etc.) to determine the most likely carbon diffusion path. Taking variable elimination as an example, by gradually eliminating variables that are not related to the carbon diffusion path estimation, the probability of different carbon diffusion path hypotheses under given carbon concentration change data is calculated.

[0097] To summarize, in the process carbon emission source tracing method based on spatiotemporal big data of the present embodiment, on the one hand, by sampling the spatiotemporal data of a determined emission distribution type and performing spatiotemporal evolution simulation based on the sampled spatiotemporal data, the problem that the propagation of process carbon is greatly affected by factors such as temperature, geographical location and time, resulting in poor traceability of the propagation path, is effectively solved. It can effectively simulate high-dimensional environments with large uncertainty and randomness in natural evolution or complex ecosystems, and improve the accuracy of diffusion path tracing; on the other hand, sampling is performed from spatiotemporal data through the Monte Carlo method, so as to more accurately simulate the carbon emission and propagation process; as the number of spatiotemporal evolution simulations increases, the results of the Monte Carlo method will gradually converge to the true solution. In carbon traceability, through a large number of random sampling and simulations, the traceability results can be made closer and closer to the real carbon emission sources and emission paths.

[0098] like Figure 2 As shown, based on the same inventive concept as the above-mentioned embodiment, the present application also provides a process carbon emission source tracing device based on spatiotemporal big data, including:

[0099] The distribution type determination module M10 is used to determine the target carbon emission source of the process carbon and the emission factors of each target carbon emission source, and determine the emission distribution type of the process carbon according to the spatiotemporal data of the emission factors;

[0100] A diffusion model building module M20 is used to build a carbon emission diffusion model based on the emission distribution type of the process carbon;

[0101] The spatiotemporal evolution simulation module M30 is used to sample target sampling samples from the spatiotemporal data of the emission distribution type, and input the target sampling samples into the carbon emission diffusion model for spatiotemporal evolution simulation, so as to obtain the carbon concentration change data of the process carbon changing with time and space;

[0102] The analysis module M40 is used to perform Bayesian network analysis on the carbon concentration change data through a preset Bayesian network model, so as to determine the diffusion path of the process carbon.

[0103] Based on the same inventive concept as the above embodiments, this embodiment also provides a process carbon emission source tracing system based on spatiotemporal big data, including: a processor and a memory; wherein the memory stores a computer program, and the computer program is used to be loaded by the processor and execute the process carbon emission source tracing method based on spatiotemporal big data as described above.

[0104] Based on the same inventive concept as the above embodiments, this embodiment also provides a computer-readable storage medium, which stores instructions, and the instructions are used by a processor to load and execute the process carbon emission source tracing method based on spatiotemporal big data as mentioned above.

[0105] In the embodiments of the mobile terminal and computer-readable storage medium provided in the present application, all technical features of the above-mentioned control method embodiments are included, and the expansion and explanation content of the specification are basically the same as those of the above-mentioned method embodiments, which will not be repeated here.

[0106] The embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer executes the methods in the above various possible implementation modes.

[0107] An embodiment of the present application also provides a chip, including a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.

[0108] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0109] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.

[0110] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium as above, including a number of instructions for a terminal device to execute the method of each embodiment of the present application. The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is similarly included in the patent protection scope of the present application.

[0113] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0114] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A process carbon emission source tracing method based on spatiotemporal big data, characterized in that: include: Determine the target carbon emission sources of process carbon and the emission factors of each target carbon emission source, and determine the emission distribution type of process carbon based on the spatiotemporal data of the emission factors; Establishing a carbon emission diffusion model based on the emission distribution type of the process carbon; Sampling target sampling samples from the spatiotemporal data of the emission distribution type, and inputting the target sampling samples into the carbon emission diffusion model for spatiotemporal evolution simulation, thereby obtaining carbon concentration change data of the process carbon changing with time and space; Performing Bayesian network analysis on the carbon concentration change data using a preset Bayesian network model to determine the diffusion path of process carbon; Determining the emission distribution type of process carbon according to the spatiotemporal data of the emission factors specifically includes: Draw a distribution probability graph according to the spatiotemporal data, compare the distribution probability graph with a preset probability distribution model and obtain corresponding similarity; Taking the probability distribution model with the highest similarity among the preset probability distribution models as the target probability distribution model, and taking the emission distribution type of the target probability distribution model as the emission distribution type of the distribution probability graph; The emission factors also include wind speed data; the carbon emission diffusion model is established based on the emission distribution type of the process carbon, specifically including: Establishing a virtual emission box model at the target carbon emission source; Based on the virtual emission box model, establishing the carbon emission diffusion model according to the mass balance equation; The expression according to the mass balance equation is: Among them, C is the concentration of process carbon in the virtual emission box model, Q is the intensity of the target carbon emission source, V is the volume of the virtual emission box model, u is the wind speed data, and L is the length of the emission box model along the wind speed direction.

2. The process carbon emission source tracing method based on spatiotemporal big data according to claim 1 is characterized in that: After taking the emission distribution type of the target probability distribution model as the emission distribution type of the distribution probability graph, the method further includes: Determine the corresponding empirical cumulative distribution function according to the arrangement order of the sample points of the spatiotemporal data; Determining characteristic parameters of the target probability distribution model, and determining a theoretical cumulative distribution function of each sample point based on the characteristic parameters of the target probability distribution model; According to the comparison result of the empirical cumulative distribution function and the theoretical cumulative distribution function, it is determined whether the spatiotemporal data obeys the target probability distribution model.

3. The process carbon emission source tracing method based on spatiotemporal big data according to claim 1 is characterized in that: The step of sampling from the spatiotemporal data of the emission distribution type to obtain a target sampling sample specifically includes: Determine a probability density function corresponding to the emission distribution type, and determine an enclosing function that meets a preset condition based on the probability density function; Randomly select a sampling sample from the spatiotemporal data, and calculate the acceptance probability of the sampling sample under the enclosing function; When the acceptance probability is greater than or equal to a preset random number, the sampling sample is recorded as a target sampling sample.

4. The process carbon emission source tracing method based on spatiotemporal big data according to claim 1 is characterized in that: Before performing Bayesian network analysis on the carbon concentration change data through a preset Bayesian network model to determine the diffusion path of process carbon, the method further includes: A Bayesian network structure is constructed according to the correlation between the types of factors in the emission factors; the Bayesian network structure includes a plurality of nodes; the types of factors of the emission factors include carbon emission sources, meteorological factors, geographical factors and carbon concentration monitoring data; The conditional probability distribution of each node in the Bayesian network structure is estimated according to historical data, and the Bayesian network model is obtained according to the conditional probability distribution.

5. A process carbon emission source tracing device based on spatiotemporal big data, characterized in that: include: A distribution type determination module is used to determine the target carbon emission source of process carbon and the emission factors of each target carbon emission source, and determine the emission distribution type of process carbon according to the spatiotemporal data of the emission factors; A diffusion model building module, used to build a carbon emission diffusion model based on the emission distribution type of the process carbon; A spatiotemporal evolution simulation module, for sampling from the spatiotemporal data of the emission distribution type to obtain a target sampling sample, and inputting the target sampling sample into the carbon emission diffusion model for spatiotemporal evolution simulation, thereby obtaining the carbon concentration change data of the process carbon changing with time and space; An analysis module, used to perform Bayesian network analysis on the carbon concentration change data through a preset Bayesian network model, so as to determine the diffusion path of process carbon; Determining the emission distribution type of process carbon according to the spatiotemporal data of the emission factors specifically includes: Draw a distribution probability graph according to the spatiotemporal data, compare the distribution probability graph with a preset probability distribution model and obtain corresponding similarity; Taking the probability distribution model with the highest similarity among the preset probability distribution models as the target probability distribution model, and taking the emission distribution type of the target probability distribution model as the emission distribution type of the distribution probability graph; The emission factors also include wind speed data; the carbon emission diffusion model is established based on the emission distribution type of the process carbon, specifically including: Establishing a virtual emission box model at the target carbon emission source; Based on the virtual emission box model, establishing the carbon emission diffusion model according to the mass balance equation; The expression according to the mass balance equation is: Among them, C is the concentration of process carbon in the virtual emission box model, Q is the intensity of the target carbon emission source, V is the volume of the virtual emission box model, u is the wind speed data, and L is the length of the emission box model along the wind speed direction.

6. A process carbon emission source tracing system based on spatiotemporal big data, characterized in that: It comprises a processor and a memory; wherein the memory stores a computer program, and the computer program is used for the processor to load and execute the process carbon emission source tracing method based on spatiotemporal big data as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which are used by a processor to load and execute the process carbon emission source tracing method based on spatiotemporal big data as described in any one of claims 1 to 4.

Images