Carbon emission determination method and device and storage medium

Abstract

The invention discloses a carbon emission determination method and device and a storage medium. The method comprises the following steps: acquiring energy consumption data of each industry on the same industry chain; inputting the energy consumption data into a pre-trained neural network to obtain predicted carbon emission of each industry; determining a first type of industry and a second type of industry according to the predicted carbon emission and the corresponding actual carbon emission of each industry; and constructing a random forest model, and inputting the industrial energy consumption data and the carbon emission into the random forest model to obtain the Nth year predicted carbon emission of the second type of industry. According to the method, the carbon emission of the low-accuracy industry is predicted according to the carbon emission parameters, including the energy consumption data and the carbon emission, of the high-accuracy industry on the same industry chain, and the influence of different application effects of different industries on the same industry chain on the carbon emission is considered, so that the accuracy and the reliability of determining the carbon emission can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission technology, and in particular to a method, device and storage medium for determining carbon emission. Background Art

[0002] As global actions to combat climate change intensify, accurate monitoring and management of carbon emissions have become key to achieving national and international carbon reduction targets. At present, traditional methods for determining carbon emissions mainly include fuel emission factor method, material balance method and actual measurement method. Although these methods can provide accurate data in specific application scenarios, they often find it difficult to strike a balance between real-time, simplicity, accuracy and low cost. In particular, the limitations of these methods are particularly evident in non-power-intensive industries.

[0003] In recent years, the existing methods for determining carbon emissions usually estimate carbon emissions by analyzing the relationship between electricity consumption and carbon emissions, without considering the different application effects of different industries in the same industrial chain, making it difficult to accurately determine carbon emissions. Summary of the invention

[0004] The present invention provides a carbon emissions determination method, device and storage medium to solve the technical problem that the existing carbon emissions determination method estimates carbon emissions by analyzing the relationship between electricity consumption and carbon emissions, but does not consider the different application effects of different industries in the same industrial chain, resulting in difficulty in accurately determining carbon emissions.

[0005] The present invention provides a method for determining carbon emissions, comprising:

[0006] Obtain energy consumption data of various industries in the same industrial chain;

[0007] Inputting the energy consumption data into a pre-trained neural network to obtain the predicted carbon emissions of each industry;

[0008] Determine the first category of industry and the second category of industry according to the predicted carbon emissions of each of the industries and the corresponding actual carbon emissions;

[0009] A random forest model is constructed, and the energy consumption data and carbon emissions of the industry are input into the random forest model to obtain the predicted carbon emissions of the second category of industry in the Nth year, wherein the energy consumption data and carbon emissions of the industry include the energy consumption data of the first category of industry from the 1st year to the Nth year, the actual carbon emissions of the first category of industry from the 1st year to the N-1th year, the predicted carbon emissions of the first category of industry from the 1st year to the Nth year, the energy consumption data of the second category of industry from the 1st year to the Nth year, and the actual carbon emissions of the second category of industry from the 1st year to the N-1th year.

[0010] Furthermore, before inputting the energy consumption data into the pre-trained neural network, the method further includes:

[0011] The energy consumption data is preprocessed, and the preprocessing includes data cleaning and missing value filling.

[0012] Furthermore, the missing value filling includes:

[0013] Use the following formula to determine the data to be filled:

[0014]

[0015] Among them, X N,filled is the data to be filled in the Nth year, X N-1,available Energy consumption data for year N-1 and X N+1,available Energy consumption data for year N+1.

[0016] Furthermore, the calculation formula for the actual carbon emissions is:

[0017]

[0018] Among them, Y N,m represents the actual carbon emissions of industry m in year N, EF i represents the carbon emission factor of the i-th energy source, C N,m,i Represents the consumption data of the i-th energy in industry m in the Nth year.

[0019] Furthermore, after obtaining the predicted carbon emissions of the second type of industry in the Nth year, the method further includes:

[0020] Calculate the mean square error of the predicted carbon emissions of the second category of industries in year N;

[0021] When the mean square error is less than a preset threshold, it is determined that the predicted carbon emissions of the second category of industry in the Nth year are valid.

[0022] Furthermore, the calculation formula of the mean square error is:

[0023]

[0024] in, The model predicts carbon emissions for the second industry in year i, y k,i represents the corresponding actual carbon emissions, and N is the year.

[0025] The present invention also provides a device for determining carbon emissions, comprising:

[0026] Energy consumption data acquisition module, used to obtain energy consumption data of various industries in the same industrial chain;

[0027] A carbon emission prediction module is used to input the energy consumption data into a pre-trained neural network to obtain the predicted carbon emissions of various industries;

[0028] An industrial classification module, used for determining a first category of industry and a second category of industry according to the predicted carbon emissions and the corresponding actual carbon emissions of each of the industries;

[0029] A carbon emissions determination module is used to construct a random forest model, input the energy consumption data and carbon emissions of the industry into the random forest model, and obtain the predicted carbon emissions of the second category of industry in the Nth year, wherein the energy consumption data and carbon emissions of the industry include the energy consumption data of the first category of industry from the 1st year to the Nth year, the actual carbon emissions of the first category of industry from the 1st year to the N-1st year, the predicted carbon emissions of the first category of industry from the 1st year to the Nth year, the energy consumption data of the second category of industry from the 1st year to the Nth year, and the actual carbon emissions of the second category of industry from the 1st year to the N-1st year.

[0030] Furthermore, the carbon emission determination device further includes a carbon emission verification module, which is used to:

[0031] Calculate the mean square error of the predicted carbon emissions of the second category of industries in year N;

[0032] When the mean square error is less than a preset threshold, it is determined that the predicted carbon emissions of the second category of industry in the Nth year are valid.

[0033] The present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the carbon emission determination method as described above when executing the computer program.

[0034] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the carbon emission determination method as described above.

[0035] The present invention determines the first category of industries and the second category of industries based on the predicted carbon emissions and the corresponding actual carbon emissions of each industry, inputs the energy consumption data and carbon emissions of different industries in the same industrial chain into the random forest model, and uses the carbon emission parameters of industries with higher accuracy in the same industrial chain, including energy consumption data and carbon emissions, to predict the carbon emissions of industries with lower accuracy. The impact of different application effects on carbon emissions in different industries in the same industrial chain is taken into account, thereby effectively improving the accuracy and reliability of carbon emissions determination, thereby helping related industries to more effectively formulate and implement carbon reduction strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of a method for determining carbon emissions provided by an embodiment of the present invention;

[0037] Figure 2 It is a structural schematic diagram of a device for determining carbon emissions provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0040] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" 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 it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0041] See also Figure 1 The present invention provides a method for determining carbon emissions, comprising:

[0042] S1. Obtain energy consumption data of each industry in the same industrial chain;

[0043] The embodiment of the present invention can obtain energy consumption data of various industries according to regional statistical yearbooks, industry statistical yearbooks, etc. Among them, energy consumption data may include power consumption data and other energy consumption data, such as energy consumption data of liquefied natural gas, crude oil, gasoline, kerosene, diesel, fuel oil, liquefied petroleum gas, etc. The same industrial chain means that in the production and supply chain, enterprises or organizations at various links are interconnected and jointly complete the entire production and distribution process of products from raw materials to final consumers. For example, the ferrous metal mining and smelting industry and the ferrous metal smelting and rolling processing industry are industries in the same industrial chain.

[0044] S2, input the energy consumption data into the pre-trained neural network to obtain the predicted carbon emissions of each industry;

[0045] In the embodiment of the present invention, carbon emissions of various industries can be predicted based on pre-trained neural networks and energy consumption data, thereby obtaining predicted carbon emissions of various industries.

[0046] S3. Determine the first category of industries and the second category of industries based on the predicted carbon emissions of each industry and the corresponding actual carbon emissions; wherein the deviation between the predicted carbon emissions of the first category of industries and the actual carbon emissions is less than a preset deviation threshold;

[0047] In an embodiment of the present invention, the first category of industry and the second category of industry can be determined by comparing the deviation value between the predicted carbon emissions and the corresponding actual carbon emissions. The first category of industry is the industry with a higher accuracy of the preliminary predicted value, and the second category of industry is the industry with a lower accuracy of the preliminary predicted value. The first category of industry and the second category of industry can be determined as follows: if the deviation value between the preliminary predicted carbon emissions and the corresponding actual carbon emissions is less than the preset deviation value, the industry corresponding to the predicted carbon emissions is considered to be the first category of industry, otherwise it is the second category of industry; the deviation value can also be calculated, the deviation value = |predicted carbon emissions-actual value| / actual value, when the deviation value is less than the preset deviation value, the industry corresponding to the predicted carbon emissions is considered to be the first category of industry, otherwise it is the second category of industry. Among them, the preset deviation value can be set according to actual needs, for example, it can be set to 8%, 10%, etc.

[0048] In the embodiment of the present invention, the first and second industries in each industry of different industrial chains are also determined first, and then the industrial chains of these industries are classified according to the industrial chains with reference to the "National Economic Industry Classification" standard to obtain industries in the same industrial chain.

[0049] S4. Construct a random forest model, input the energy consumption data and carbon emissions of the industry into the random forest model, and obtain the predicted carbon emissions of the second category of industry in the Nth year, where the energy consumption data and carbon emissions of the industry include the energy consumption data of the first category of industry from the 1st year to the Nth year. Actual carbon emissions of the first category of industry from year 1 to year N-1 Forecasted carbon emissions of the first category of industry from year 1 to year N Energy consumption data of the second industry from the 1st to the Nth year Actual carbon emissions of the second category of industries from year 1 to year N-1

[0050] In the embodiment of the present invention, the industrial energy consumption data and carbon emissions are used as the data set D to train the model, where the expression of D can be:

[0051]

[0052] The predicted carbon emissions of the second type of industry in the Nth year output by the model can be:

[0053]

[0054] in, It represents the predicted carbon emissions of the second industry in year N.

[0055] In an embodiment of the present invention, after constructing the random forest model, the parameters may be set as the number of decision trees n, the maximum depth d, and the minimum number of leaf node samples s, and then model training and data prediction may be performed based on these parameters. In an embodiment of the present invention, after the model training is completed, the energy consumption data to be analyzed and the corresponding carbon emission data, such as the relevant predicted carbon emissions and the actual carbon emissions, may be input into the model, and the predicted carbon emissions of the second category industry in the required predicted year may be output.

[0056] When training the model, all pre-processed actual energy consumption data and actual carbon emissions in the current industrial chain can be divided into training sets and test sets, of which 80% of the data is used as the training set for model training; 20% of the data is used as the test set for model verification. Time series data is divided in chronological order to avoid future data leakage into the training set.

[0057] The embodiment of the present invention determines the first category of industries and the second category of industries based on the predicted carbon emissions of each industry and the corresponding actual carbon emissions, and inputs the energy consumption data and carbon emissions of different industries in the same industrial chain into the random forest model. The carbon emission parameters of industries with higher accuracy in the same industrial chain, including energy consumption data and carbon emissions, are used to predict the carbon emissions of industries with lower accuracy. The impact of different application effects on carbon emissions in different industries in the same industrial chain is taken into account, thereby effectively improving the accuracy and reliability of carbon emissions determination, thereby helping related industries to more effectively formulate and implement carbon reduction strategies.

[0058] In one embodiment, before inputting the energy consumption data into the pre-trained neural network, the method further includes:

[0059] The energy consumption data is preprocessed, including data cleaning and missing value filling.

[0060] In an embodiment of the present invention, by performing data cleaning processing on energy consumption data, including removing outliers and excluding data beyond the normal operating range, the impact of outliers and data beyond the normal operating range on the determination of carbon emissions is effectively reduced, thereby effectively improving the reliability of the determination of carbon emissions.

[0061] In one embodiment, missing value filling includes:

[0062] Use the following formula to determine the data to be filled:

[0063]

[0064] Among them, X N,filled is the data to be filled in the Nth year, X N-1,available Energy consumption data for year N-1 and X N+1,available Energy consumption data for year N+1.

[0065] In the embodiment of the present invention, by performing missing value filling processing on energy consumption data, the comprehensiveness of the data can be effectively improved, thereby effectively improving the accuracy of carbon emission determination.

[0066] In one embodiment, the actual carbon emissions are calculated as follows:

[0067]

[0068] Among them, Y N,m represents the actual carbon emissions of industry m in year N, EF i represents the carbon emission factor of the i-th energy source, C N,m,i Represents the consumption data of the i-th energy in industry m in the Nth year.

[0069] In one embodiment, the Z-score can also be used to perform data standardization on the preprocessed energy consumption data to ensure that data of different dimensions are comparable in the model, reduce the dimension effect, and improve the accuracy of subsequent models. The data standardization process can be expressed as:

[0070]

[0071] Among them, X represents the original data, μ represents the mean, and σ represents the standard deviation.

[0072] In one embodiment, after obtaining the predicted carbon emissions of the second industry in the Nth year, the method further includes:

[0073] Calculate the mean square error of the predicted carbon emissions of the second category of industries in year N;

[0074] When the mean square error is less than a preset threshold, it is determined that the predicted carbon emissions of the second category of industries in the Nth year are valid.

[0075] In the embodiment of the present invention, when the mean square error is less than the preset threshold, it means that the deviation between the current prediction value and the actual prediction value is within an acceptable range, and the current prediction value is a valid prediction value. On this basis, carbon emissions in other time periods can also be further predicted.

[0076] In one embodiment, the calculation formula of the mean square error is:

[0077]

[0078] in, The model predicts carbon emissions for the second industry in year i, y k,i represents the corresponding actual carbon emissions, and N is the year.

[0079] The implementation of the embodiments of the present invention has the following beneficial effects:

[0080] The embodiment of the present invention determines the first category of industries and the second category of industries based on the predicted carbon emissions of each industry and the corresponding actual carbon emissions, and inputs the energy consumption data and carbon emissions of different industries in the same industrial chain into the random forest model. The carbon emission parameters of industries with higher accuracy in the same industrial chain, including energy consumption data and carbon emissions, are used to predict the carbon emissions of industries with lower accuracy. The impact of different application effects on carbon emissions in different industries in the same industrial chain is taken into account, thereby effectively improving the accuracy and reliability of carbon emissions determination, thereby helping related industries to more effectively formulate and implement carbon reduction strategies.

[0081] See also Figure 2 Based on the same inventive concept as the above embodiment, the present invention also provides a carbon emission determination device, comprising:

[0082] The energy consumption data acquisition module 10 is used to acquire the energy consumption data of each industry in the same industrial chain;

[0083] The carbon emission prediction module 20 is used to input the energy consumption data into the pre-trained neural network to obtain the predicted carbon emission of each industry;

[0084] An industrial classification module 30, for determining a first category of industry and a second category of industry according to the predicted carbon emissions of each industry and the corresponding actual carbon emissions;

[0085] The carbon emissions determination module 40 is used to construct a random forest model, input the energy consumption data and carbon emissions of the industry into the random forest model, and obtain the predicted carbon emissions of the second category of industry in the Nth year, wherein the energy consumption data and carbon emissions of the industry include the energy consumption data of the first category of industry from the 1st year to the Nth year, the actual carbon emissions of the first category of industry from the 1st year to the N-1st year, the predicted carbon emissions of the first category of industry from the 1st year to the Nth year, the energy consumption data of the second category of industry from the 1st year to the N-1st year, and the actual carbon emissions of the second category of industry from the 1st year to the N-1st year.

[0086] In one embodiment, before inputting the energy consumption data into the pre-trained neural network, the method further includes:

[0087] The energy consumption data is preprocessed, including data cleaning and missing value filling.

[0088] In one embodiment, missing value filling includes:

[0089] Use the following formula to determine the data to be filled:

[0090]

[0091] Among them, X N,filled is the data to be filled in the Nth year, X N-1,available Energy consumption data for year N-1 and X N+1,available Energy consumption data for year N+1.

[0092] In one embodiment, the actual carbon emissions are calculated as follows:

[0093]

[0094] Among them, Y N,m represents the actual carbon emissions of industry m in year N, EF i represents the carbon emission factor of the i-th energy source, C N,m,i Represents the consumption data of the i-th energy in industry m in the Nth year.

[0095] In one embodiment, the carbon emission determination device further comprises a carbon emission verification module, which is used to:

[0096] Calculate the mean square error of the predicted carbon emissions of the second category of industries in year N;

[0097] When the mean square error is less than a preset threshold, it is determined that the predicted carbon emissions of the second category of industries in the Nth year are valid.

[0098] In one embodiment, the calculation formula of the mean square error is:

[0099]

[0100] in, The model predicts carbon emissions for the second industry in year i, y k,i represents the corresponding actual carbon emissions, and N is the year.

[0101] Correspondingly, an embodiment of the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the carbon emission determination method of any one of the above embodiments is implemented.

[0102] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment, such as the carbon emission determination module 40, are implemented.

[0103] Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device. For example, the carbon emission determination module 40 is used to build a random forest model, input the energy consumption data and carbon emissions of the industry into the random forest model, and obtain the predicted carbon emissions of the second category of industry in the Nth year, wherein the energy consumption data and carbon emissions of the industry include the energy consumption data of the first category of industry from the 1st year to the Nth year, the actual carbon emissions of the first category of industry from the 1st year to the N-1st year, the predicted carbon emissions of the first category of industry from the 1st year to the Nth year, the energy consumption data of the second category of industry from the 1st year to the Nth year, and the actual carbon emissions of the second category of industry from the 1st year to the N-1st year.

[0104] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0105] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0106] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0107] Among them, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0108] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the carbon emission determination method of any one of the above embodiments.

[0109] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for determining carbon emissions, characterized in that: include: Obtain energy consumption data of various industries in the same industrial chain; Inputting the energy consumption data into a pre-trained neural network to obtain the predicted carbon emissions of each industry; Determine a first category of industry and a second category of industry according to the predicted carbon emissions and the corresponding actual carbon emissions of each of the industries; wherein a deviation between the predicted carbon emissions and the actual carbon emissions of the first category of industry is less than a preset deviation threshold; A random forest model is constructed, and the energy consumption data and carbon emissions of the industry are input into the random forest model to obtain the predicted carbon emissions of the second category of industry in the Nth year, wherein the energy consumption data and carbon emissions of the industry include the energy consumption data of the first category of industry from the 1st year to the Nth year, the actual carbon emissions of the first category of industry from the 1st year to the N-1th year, the predicted carbon emissions of the first category of industry from the 1st year to the Nth year, the energy consumption data of the second category of industry from the 1st year to the Nth year, and the actual carbon emissions of the second category of industry from the 1st year to the N-1th year.

2. The method for determining carbon emissions according to claim 1, characterized in that: Before inputting the energy consumption data into the pre-trained neural network, the method further includes: The energy consumption data is preprocessed, and the preprocessing includes data cleaning and missing value filling.

3. The method for determining carbon emissions according to claim 2, wherein: The missing value filling includes: Use the following formula to determine the data to be filled: Among them, X N,filled is the data to be filled in the Nth year, X N-1,available Energy consumption data for year N-1 and X N+1,available Energy consumption data for year N+1.

4. The method for determining carbon emissions according to claim 1, wherein: The actual carbon emissions calculation formula is: Among them, Y N,m represents the actual carbon emissions of industry m in year N, EF i represents the carbon emission factor of the i-th energy source, C N,m,i Represents the consumption data of the i-th energy in industry m in the Nth year.

5. The method for determining carbon emissions according to claim 1, wherein: After obtaining the predicted carbon emissions of the second category of industries in the Nth year, it also includes: Calculate the mean square error of the predicted carbon emissions of the second category of industries in year N; When the mean square error is less than a preset threshold, it is determined that the predicted carbon emissions of the second category of industry in the Nth year are valid.

6. The method for determining carbon emissions according to claim 5, characterized in that: The calculation formula of the mean square error is: in, The model predicts carbon emissions for the second industry in year i, y k,i represents the corresponding actual carbon emissions, and N is the year.

7. A device for determining carbon emissions, characterized in that: include: Energy consumption data acquisition module, used to obtain energy consumption data of various industries in the same industrial chain; A carbon emission prediction module is used to input the energy consumption data into a pre-trained neural network to obtain the predicted carbon emissions of various industries; An industrial classification module, used for determining a first category of industry and a second category of industry according to the predicted carbon emissions and the corresponding actual carbon emissions of each of the industries; wherein a deviation value between the predicted carbon emissions and the actual carbon emissions of the first category of industry is less than a preset deviation threshold; A carbon emissions determination module is used to construct a random forest model, input the energy consumption data and carbon emissions of the industry into the random forest model, and obtain the predicted carbon emissions of the second category of industry in the Nth year, wherein the energy consumption data and carbon emissions of the industry include the energy consumption data of the first category of industry from the 1st year to the Nth year, the actual carbon emissions of the first category of industry from the 1st year to the N-1st year, the predicted carbon emissions of the first category of industry from the 1st year to the Nth year, the energy consumption data of the second category of industry from the 1st year to the Nth year, and the actual carbon emissions of the second category of industry from the 1st year to the N-1st year.

8. The carbon emission determination device according to claim 7, characterized in that: Also includes Carbon Emissions Verification Module for: Calculate the mean square error of the predicted carbon emissions of the second category of industries in year N; When the mean square error is less than a preset threshold, it is determined that the predicted carbon emissions of the second category of industry in the Nth year are valid.

9. A terminal device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the carbon emission determination method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the carbon emission determination method according to any one of claims 1 to 6.

Images