A method, system, and equipment for evaluating the quality of carbon cycle data.

Abstract

This invention relates to a method, system, and equipment for evaluating the quality of carbon cycle data, specifically in the field of carbon cycle quality assessment. The method includes: predicting carbon emissions from coal mining subsidence areas to obtain predicted carbon emissions; predicting the scale changes in soil, vegetation, and water bodies based on subsidence characteristic information; collecting soil physicochemical property parameters, vegetation type parameters, and water composition parameters, and calculating the predicted carbon sequestration amount by combining these parameters with the scale changes in soil, vegetation, and water bodies; and calculating the carbon cycle quality assessment result based on the predicted carbon sequestration amount and predicted carbon emissions. This invention addresses the technical problem that traditional assessment methods fail to fully consider the unique geographical characteristics and changing patterns of coal mining subsidence areas, resulting in inaccurate predictions of carbon emissions and carbon sequestration capacity, and consequently, an inability to effectively quantify and assess carbon cycle quality. It significantly improves the scientific rigor, accuracy, and reliability of carbon emission and carbon sequestration capacity predictions, achieving precise quantitative assessment of carbon cycle quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of carbon cycle quality evaluation, and particularly relates to a cycle quality data evaluation method, system and equipment for carbon cycle. BACKGROUND

[0002] Coal mining subsidence is a special landform formed due to ground subsidence in the process of coal mining, and usually has complex topographic features and environmental conditions. Due to the large amount of damage to the natural ecological system in the process of coal mining, the coal mining subsidence often shows problems such as soil degradation, insufficient vegetation coverage, and water and soil loss, which makes the carbon cycle process in the region very complex and affects the prediction and evaluation of carbon emission and carbon sequestration capacity.

[0003] At present, the traditional carbon cycle evaluation method mainly depends on estimation based on experience or simplified model. These methods usually ignore the specific geographical condition environmental differences and mining subsidence characteristics of these regions, thus resulting in low prediction accuracy of carbon emission and carbon sequestration capacity and failing to comprehensively reflect the actual carbon cycle state. SUMMARY

[0004] The present application aims to solve the technical problem that the traditional carbon cycle evaluation method fails to fully consider the special geographical environmental characteristics of the coal mining subsidence, making it impossible to accurately predict the carbon emission and carbon sequestration capacity, and thus failing to effectively quantify and evaluate the carbon cycle quality, and provides a cycle quality data evaluation method, system and equipment for carbon cycle to solve the problem.

[0005] The technical solution of the present application to solve the above technical problem is as follows:

[0006] In a first aspect, the present application provides a cycle quality data evaluation method for carbon cycle, comprising: collecting carbon emission characteristic information and subsidence characteristic information in a coal mining subsidence, predicting carbon emission of the coal mining subsidence according to the carbon emission characteristic information to obtain a predicted carbon emission amount; collecting soil scale parameters, vegetation scale parameters and water scale parameters in the coal mining subsidence, predicting scale changes of soil, vegetation and water according to the subsidence characteristic information to obtain changed soil scale parameters, changed vegetation scale parameters and changed water scale parameters; collecting soil composition parameters, vegetation type parameters and water composition parameters in the coal mining subsidence, combining the changed soil scale parameters, changed vegetation scale parameters and changed water scale parameters to calculate a predicted carbon sequestration amount; and calculating a carbon cycle quality evaluation result according to the predicted carbon sequestration amount and the predicted carbon emission amount.

[0007] Optionally, the cycle quality data evaluation method for carbon cycle further comprises: collecting scale information of the carbon emission source leaking in the coal mining subsidence area as the carbon emission characteristic information; collecting subsidence area information, subsidence slope information and subsidence depth information in the coal mining subsidence area as the subsidence characteristic information.

[0008] Optionally, the cycle quality data evaluation method for carbon cycle further comprises: collecting a sample carbon emission characteristic information set according to carbon emission monitoring data of a sample coal mining subsidence area, and collecting carbon emission amounts under different sample carbon emission characteristic information to obtain a sample carbon emission amount set; using the sample carbon emission characteristic information set as input features and using the sample carbon emission amount set as output features to train a carbon emission predictor; inputting the carbon emission characteristic information into the carbon emission predictor to output a predicted carbon emission amount.

[0009] Optionally, the cycle quality data evaluation method for carbon cycle further comprises: collecting soil scale parameters, vegetation scale parameters and water scale parameters in the coal mining subsidence area; training a change predictor comprising an integrated change prediction branch; calculating a ratio of the predicted carbon emission amount to a maximum value in the sample carbon emission amount set, multiplying the branch number of the integrated change prediction branch and taking an integer to obtain a configured branch number; randomly selecting change prediction branches of the configured branch number in the change predictor, inputting the soil scale parameters, vegetation scale parameters and water scale parameters, and predicting output to obtain a predicted soil change coefficient set, a predicted vegetation change coefficient set and a predicted water change coefficient set after a preset time length, and calculating the mean values to obtain a soil change coefficient, a vegetation change coefficient and a water change coefficient; using the soil change coefficient, the vegetation change coefficient and the water change coefficient to calculate changes in the soil scale parameters, the vegetation scale parameters and the water scale parameters to obtain changed soil scale parameters, changed vegetation scale parameters and changed water scale parameters.

[0010] Optionally, the cycle quality data evaluation method for carbon cycle further comprises: collecting a sample subsidence characteristic information set according to change monitoring data of soil, vegetation and water in a sample coal mining subsidence area, and collecting scale change coefficients of the soil, the vegetation and the water after a preset time length and labeling as a sample soil change coefficient set, a sample vegetation change coefficient set and a sample water change coefficient set; integrating the sample subsidence characteristic information set, the sample soil change coefficient set, the sample vegetation change coefficient set and the sample water change coefficient set, and dividing to obtain multiple change prediction data; based on ensemble learning, using the multiple change prediction data to train multiple change prediction branches to obtain a change predictor comprising an integrated change prediction branch.

[0011] Optionally, the method further comprises: collecting soil composition parameters, vegetation type parameters and water body composition parameters in the coal mining subsidence area, and testing soil carbon fixation parameters, vegetation carbon fixation parameters and water body carbon fixation parameters of the soil composition parameters, vegetation type parameters and water body composition parameters; calculating predicted soil carbon fixation amount, predicted vegetation carbon fixation amount and predicted water body carbon fixation amount according to the soil carbon fixation parameters, vegetation carbon fixation parameters and water body carbon fixation parameters, and combining the changed soil scale parameters, changed vegetation scale parameters and changed water body scale parameters; and calculating a sum of the predicted soil carbon fixation amount, the predicted vegetation carbon fixation amount and the predicted water body carbon fixation amount to obtain a predicted carbon fixation amount.

[0012] Optionally, the method further comprises: calculating a ratio of the predicted carbon fixation amount and the predicted carbon emission amount; and taking the ratio as a carbon cycle quality evaluation result.

[0013] In a second aspect, the present application provides a carbon cycle quality data evaluation system, comprising: a carbon emission prediction module configured to collect carbon emission characteristic information and subsidence characteristic information in a coal mining subsidence area, and perform carbon emission prediction of the coal mining subsidence area according to the carbon emission characteristic information to obtain a predicted carbon emission amount; a scale change prediction module configured to collect soil scale parameters, vegetation scale parameters and water body scale parameters in the coal mining subsidence area, and perform scale change prediction of soil, vegetation and water body according to the subsidence characteristic information to obtain changed soil scale parameters, changed vegetation scale parameters and changed water body scale parameters; a predicted carbon fixation amount calculation module configured to collect soil composition parameters, vegetation type parameters and water body composition parameters in the coal mining subsidence area, and calculate a predicted carbon fixation amount by combining the changed soil scale parameters, the changed vegetation scale parameters and the changed water body scale parameters; and a carbon cycle quality evaluation result calculation module configured to calculate a carbon cycle quality evaluation result according to the predicted carbon fixation amount and the predicted carbon emission amount.

[0014] In a third aspect, the present application further provides an electronic device, comprising:

[0015] at least one processor; a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method for evaluating carbon cycle quality data according to any one of the first aspect.

[0016] The beneficial effects of the present application are: by collecting carbon emission characteristic information and subsidence characteristic information in the coal mining subsidence area, and according to the carbon emission characteristic information, the carbon emission of the coal mining subsidence area is predicted to obtain the predicted carbon emission; on the other hand, the soil scale parameter, the vegetation scale parameter and the water body scale parameter in the coal mining subsidence area are collected, and according to the subsidence characteristic information, the scale change of the soil, the vegetation and the water body is predicted to obtain the changed soil scale parameter, the changed vegetation scale parameter and the changed water body scale parameter; further, the soil composition parameter, the vegetation type parameter and the water body composition parameter in the coal mining subsidence area are collected, combined with the changed soil scale parameter, the changed vegetation scale parameter and the changed water body scale parameter, and the predicted carbon sequestration amount is calculated; finally, the ratio of the predicted carbon sequestration amount and the predicted carbon emission amount is calculated, and the ratio is taken as the carbon cycle quality evaluation result; that is, by combining the machine learning model, according to the comprehensive analysis of the soil composition, the vegetation type and the water body environment in the coal mining subsidence area, the carbon sequestration amount and the carbon emission amount can be significantly improved, the scientificity, the accuracy and the reliability of the prediction of the carbon emission amount and the carbon sequestration capacity can be improved, and the precise quantitative evaluation of the carbon cycle quality can be realized, so as to provide a scientific basis for carbon emission reduction and ecological restoration. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 A flowchart of a cycle quality data evaluation method for carbon cycle provided by the present application is provided.

[0018] Figure 2 A structure diagram of a cycle quality data evaluation system for carbon cycle provided by the present application is provided.

[0019] Figure 3 A structure diagram of an electronic device provided by the present application is provided.

[0020] In the drawings, the components represented by the numbers are described as follows:

[0021] The carbon emission prediction module 11, the scale change prediction module 12, the predicted carbon sequestration amount calculation module 13, the carbon cycle quality evaluation result calculation module 14, the electronic device 500, the storage 510, the processor 520, the first computer program 511. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] In the description of the present application, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0024] In the description of the present application, the term "for example" is used to indicate "as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given in order to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that those skilled in the art can recognize that the present application can be implemented without using these specific details. In other examples, well-known structures and processes will not be described in detail to avoid unnecessary details making the description of the present application obscure. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope in accordance with the principles and characteristics disclosed.

[0025] Embodiment one, as Figure 1 shown, the present application provides a circulating quality data evaluation method for carbon cycle, comprising:

[0026] S100: collecting carbon emission characteristic information and subsidence characteristic information in the coal mining subsidence area, predicting carbon emission of the coal mining subsidence area according to the carbon emission characteristic information, and obtaining predicted carbon emission.

[0027] Further, the step S100 of the present application further comprises:

[0028] S110: collecting scale information of the carbon emission source in the coal mining subsidence area as the carbon emission characteristic information; S120: collecting subsidence area information, subsidence slope information and subsidence depth information in the coal mining subsidence area as the subsidence characteristic information.

[0029] Specifically, in the process of coal mining, the water-conducting fracture zone caused by the mining and subsidence of underground coal develops to the surface, which will cause a part of coal to be exposed in the air. The exposed coal will undergo oxidation reaction under the action of oxygen and moisture, releasing carbon dioxide and other greenhouse gases; first, the scale information of the carbon emission source in the coal mining subsidence area is collected, including the area of exposed coal, reserves and carbon leakage rate, etc., to obtain the carbon emission characteristic information. Through obtaining the carbon emission characteristic information, the carbon emission source of the coal mining subsidence area can be understood, and data support can be provided for carbon emission prediction.

[0030] On the other hand, the collapse area information, the collapse slope information and the collapse depth information in the coal mining subsidence area are collected as the subsidence feature information. For example, the water conducting fracture zone developed to the surface by a larger subsidence has a larger subsidence area, which means that more coal or other organic matter is exposed, which can lead to a larger range of carbon emissions; the area with a larger slope can accelerate soil erosion, further affecting the loss rate of soil organic carbon, thereby increasing carbon emissions; and the deeper subsidence area can affect the oxidation process of coal. Different exposure time and manner of deep coal can change the carbon emission rate.

[0031] Further, the step S100 further includes:

[0032] S130: According to the carbon emission monitoring data of the sample coal mining subsidence area, a sample carbon emission feature information set is collected, and the carbon emission amount under different sample carbon emission feature information is collected to obtain a sample carbon emission amount set; S140: The sample carbon emission feature information set is used as the input feature, and the sample carbon emission amount set is used as the output feature to train the carbon emission predictor; S150: The carbon emission feature information is input into the carbon emission predictor to output the predicted carbon emission amount.

[0033] Specifically, the monitoring data related to carbon emission of different coal mining subsidence areas is collected to obtain a sample carbon emission feature information set (such as the area of coal exposure, reserves and the rate of carbon leakage, etc.). Then, the carbon emission amount under different sample carbon emission feature information is collected to obtain a sample carbon emission amount set, wherein the sample carbon emission amount and the sample carbon emission feature information correspond one by one.

[0034] Then, a carbon emission predictor is constructed based on the BP neural network, that is, the collected carbon emission characteristic information is processed by a machine learning model to predict future carbon emissions. The BP neural network is a common feedforward neural network that learns through the backpropagation algorithm. Through supervised training, the BP neural network can identify the complex relationship between carbon emissions and various characteristics, and then predict the carbon emissions. The carbon emission predictor includes an input layer, multiple hidden layers, and an output layer. The input data of the input layer is the carbon emission characteristic information, and the output data of the output layer is the carbon emission. Then, the sample carbon emission characteristic information is input, and the sample carbon emission is output. The sample carbon emission characteristic information set and the sample carbon emission set are used as training data to supervise the training of the carbon emission predictor. The training process is as follows. First, the input layer receives the carbon emission characteristic information (such as coal exposure area, soil type, etc.). After processing by multiple hidden layers, the final output layer gives the predicted value of the carbon emission. Then, using the mean square error loss function, the loss (error) is calculated by comparing the network's predicted output with the actual carbon emission. Then, through the backpropagation algorithm, the contribution of each weight and bias to the loss is calculated, that is, the gradient of each weight (the gradient is the partial derivative of the loss function with respect to the weight). Further, according to the calculated gradient, the weights and biases of the network are updated using an optimization algorithm (such as gradient descent) to gradually reduce the loss function. The above process is repeated multiple times on the training data. Each time, the prediction result is calculated by forward propagation, and the weights and biases are adjusted by backpropagation. After each adjustment, the loss of the model becomes smaller, and the prediction result becomes more accurate. The training process is completed through multiple training cycles until the loss function converges to a minimum value, for example, the loss is less than 0.05. The trained carbon emission predictor is obtained. Finally, the carbon emission characteristic information is input into the trained carbon emission predictor, and the predicted carbon emission is output.

[0035] By constructing a carbon emission predictor based on the BP neural network, the intelligence and scientificity of carbon emission prediction can be improved, and the accuracy and efficiency of carbon emission prediction can also be improved, thereby improving the scientificity, accuracy, and efficiency of carbon cycle quality evaluation.

[0036] S200: Collecting soil scale parameters, vegetation scale parameters, and water body scale parameters in the coal mining subsidence area, predicting the scale changes of soil, vegetation, and water body according to the subsidence characteristic information, and obtaining changed soil scale parameters, changed vegetation scale parameters, and changed water body scale parameters.

[0037] Further, the step S200 of the present application further comprises:

[0038] S210: Collecting soil scale parameters, vegetation scale parameters, and water body scale parameters in the coal mining subsidence area.

[0039] Specifically, the soil scale parameters, the vegetation scale parameters and the water body scale parameters in the coal mining subsidence area are collected, wherein the soil scale parameters include soil types, soil volumes, etc., the vegetation scale parameters include vegetation types, vegetation coverage areas, etc., and the water body scale parameters include water body areas, water body depths, etc. By collecting and analyzing the soil, vegetation and water body scale parameters of the coal mining subsidence area, and combining the subsidence characteristic information such as the terrain and the slope, the future ecological changes can be predicted, and these changes have a profound influence on the carbon cycle (especially the carbon fixation and the carbon emission).

[0040] S220: training the change predictor including the integrated change prediction branch.

[0041] Further, the step S220 of the present application further includes:

[0042] S221: according to the change monitoring data of the soil, the vegetation and the water body in the sample coal mining subsidence area, a sample subsidence characteristic information set is collected, and the scale change coefficients of the soil, the vegetation and the water body after a preset time length are collected and labeled as a sample soil change coefficient set, a sample vegetation change coefficient set and a sample water body change coefficient set; S222: the sample subsidence characteristic information set, the sample soil change coefficient set, the sample vegetation change coefficient set and the sample water body change coefficient set are integrated, and multiple change prediction data are obtained by division; S223: based on the ensemble learning, the multiple change prediction data are used to train multiple change prediction branches, and a change predictor including an integrated change prediction branch is obtained.

[0043] Specifically, according to the monitoring data of the changes of soil, vegetation and water body in the sample coal mining subsidence area, sample subsidence characteristic information such as water table, slope, depth, area, subsidence speed, etc. is collected, which will be used as key factors affecting the changes of soil, vegetation and water body, and a sample subsidence characteristic information set is obtained; then the scale change coefficients of soil, vegetation and water body after a preset time length (such as one month) are collected, the preset time length can be set according to the actual scene, and the scale change coefficient is the ratio of the difference between the parameter scale after the preset time length and the initial parameter scale to the initial parameter scale, for example, the soil change coefficient is (soil scale after the preset time-initial soil scale) / initial soil scale, wherein the scale change coefficients of soil, vegetation and water body can be positive or negative, indicating the increase or decrease of these elements within a certain time, for example, the soil scale change coefficient is positive, indicating that the organic carbon content, humidity or other parameters in the soil have increased, indicating that the soil in this area has better carbon sequestration capacity, which may be due to vegetation restoration or increased rainfall and other factors; the soil scale change coefficient is negative, indicating that the soil parameters such as organic carbon content, humidity or pH value have decreased, indicating that the quality of the soil has deteriorated, which may be due to erosion, soil erosion or other degradation processes; a sample soil change coefficient set, a sample vegetation change coefficient set and a sample water change coefficient set are obtained, wherein the sample subsidence characteristic information and the sample soil change coefficient, the sample vegetation change coefficient and the sample water change coefficient have a corresponding relationship.

[0044] Then, the sample subsidence characteristic information set, the sample soil change coefficient set, the sample vegetation change coefficient set and the sample water change coefficient set are integrated to obtain a sample data set, wherein each sample data contains information in the above four sets, and they have a corresponding relationship, and each group of samples includes subsidence characteristic information in the same time period and the change coefficients of soil, vegetation and water body in the time period. Then the sample data set is divided into Q parts, Q is a positive integer greater than 1, the value of Q can be set according to actual needs, for example, Q is set to 30; and a plurality of change prediction data are obtained.

[0045] Further based on the BP neural network, a change prediction branch is constructed, which is used to predict the change trend of soil, vegetation and water at a future time point based on the feature information (such as slope, depth, area, etc.) of the coal mining subsidence; the change prediction branch includes an input layer (the input data is the subsidence feature information), multiple hidden layers and an output layer (the output data is the sample soil change coefficient, the sample vegetation change coefficient and the sample water change coefficient); then the multiple change prediction data are used to supervise the training of the change prediction branch respectively until convergence is obtained, and multiple change prediction branches are obtained; then based on the principle of ensemble learning, the multiple change prediction branches are combined to obtain a change predictor including an ensemble change prediction branch; wherein the training method of a single change prediction branch is as follows: first, the input data is transmitted to the hidden layer through the input layer and is calculated through the weight and bias to obtain the predicted value of the output layer (i.e. the predicted soil, vegetation and water change coefficient); then, in the training process, the difference between the network prediction output and the real label is measured by a loss function (such as mean square error loss function); after the loss function is calculated, the gradient of each layer weight is calculated using the back propagation algorithm, and the weight is updated according to the gradient, the goal is to minimize the loss function, so that the network can more accurately predict the change coefficient of soil, vegetation and water; multiple iterations are repeatedly performed until the loss function converges, for example, the loss is less than 0.05, the prediction ability of the network is stable, and the trained change prediction branch is obtained.

[0046] S230: calculate the ratio of the predicted carbon emission to the maximum value in the sample carbon emission set, multiply the branch number of the ensemble change prediction branch and take the integer to obtain the configuration branch number; S240: randomly select the change prediction branch of the configuration branch number in the change predictor, input the soil scale parameter, vegetation scale parameter and water scale parameter, and predict the output to obtain the predicted soil change coefficient set, predicted vegetation change coefficient set and predicted water change coefficient set after a preset time length, and calculate the mean value to obtain the soil change coefficient, vegetation change coefficient and water change coefficient; S250: use the soil change coefficient, vegetation change coefficient and water change coefficient to calculate the change of the soil scale parameter, vegetation scale parameter and water scale parameter to obtain the changed soil scale parameter, changed vegetation scale parameter and changed water scale parameter.

[0047] Specifically, first, the ratio of the predicted carbon emission to the maximum value in the sample carbon emission set is calculated, and the ratio is multiplied by the branch number of the ensemble change prediction branch and taken as an integer to obtain the configuration branch number, for example, assuming that the predicted carbon emission is 1000 tons of carbon dioxide, the maximum value in the sample carbon emission set is 4000 tons of carbon dioxide, and the branch number of the ensemble change prediction branch is 30, then the configuration branch number is 1000 / 4000 multiplied by 30 and taken as an integer, i.e. the configuration branch number is 8.

[0048] By dynamically adjusting the number of branches according to the current predicted carbon emissions, that is, the greater the carbon emissions, the higher the complexity and uncertainty that the model faces, and therefore using more prediction branches helps to improve the prediction accuracy; the smaller the carbon emissions, the fewer branches are selected, saving computing resources and improving analysis efficiency; thereby being able to flexibly adapt to different scale prediction tasks, ensuring accurate evaluation in complex situations, while reducing resource consumption in the case of smaller carbon emissions.

[0049] Next, a change prediction branch with a variable number of branches is randomly selected in the change predictor, and the soil scale parameter, vegetation scale parameter and water body scale parameter are input, and a predicted soil change coefficient set, a predicted vegetation change coefficient set and a predicted water body change coefficient set after a preset time length (such as one month) are output; then the predicted soil change coefficient set, the predicted vegetation change coefficient set and the predicted water body change coefficient set are respectively subjected to mean value calculation, that is, the prediction results of all prediction branches are averaged to obtain a more stable and reliable result, and by this method, the deviation of individual prediction branches can be reduced, and the overall prediction accuracy can be improved, and the soil change coefficient, the vegetation change coefficient and the water body change coefficient are output.

[0050] Further, the soil change coefficient, the vegetation change coefficient and the water body change coefficient are used to respectively calculate the change of the soil scale parameter, the vegetation scale parameter and the water body scale parameter, that is, the sum of the soil change coefficient and 1 is multiplied by the soil scale parameter, and the product is taken as the change soil scale parameter; the sum of the vegetation change coefficient and 1 is multiplied by the vegetation scale parameter to obtain the change vegetation scale parameter; the sum of the water body change coefficient and 1 is multiplied by the water body scale parameter to obtain the change water body scale parameter.

[0051] S300: Collecting soil composition parameters, vegetation type parameters and water body composition parameters in the coal mining subsidence area, combining the change soil scale parameter, the change vegetation scale parameter and the change water body scale parameter, and calculating to obtain a predicted carbon sequestration amount.

[0052] Further, the step S300 of the present application further comprises:

[0053] S310: Collect soil composition parameters, vegetation type parameters and water body composition parameters in the coal mining subsidence area, and test and obtain soil carbon sequestration parameters, vegetation carbon sequestration parameters and water body carbon sequestration parameters of the soil composition parameters, vegetation type parameters and water body composition parameters; S320: According to the soil carbon sequestration parameters, vegetation carbon sequestration parameters and water body carbon sequestration parameters, combined with the change soil scale parameters, change vegetation scale parameters and change water body scale parameters, the predicted soil carbon sequestration amount, the predicted vegetation carbon sequestration amount and the predicted water body carbon sequestration amount are calculated and obtained; S330: The sum of the predicted soil carbon sequestration amount, the predicted vegetation carbon sequestration amount and the predicted water body carbon sequestration amount is calculated to obtain the predicted carbon sequestration amount.

[0054] Specifically, first, the soil composition parameters (such as the mineral content, pH value, humidity, etc. of the soil) in the coal mining subsidence area, the vegetation type parameters (such as the type, density, coverage, root depth, etc. of the vegetation) and the water body composition parameters (such as the pH value, dissolved oxygen, temperature, dissolved organic matter and inorganic salt contained in the water body, etc.) are collected; then the soil carbon sequestration parameters, vegetation carbon sequestration parameters and water body carbon sequestration parameters of the soil composition parameters, vegetation type parameters and water body composition parameters are tested (obtained by experimental test or existing literature data) and obtained, wherein the soil carbon sequestration parameter refers to the total carbon sequestration amount of the soil under certain conditions, which is calculated by the carbon storage amount per unit mass (for example, the carbon storage amount per unit area); the vegetation carbon sequestration parameter refers to the total carbon sequestration amount of the plant, which is calculated by the carbon sequestration amount per unit biomass; the water body carbon sequestration parameter refers to the total carbon sequestration amount of the water body, which is calculated by the carbon sequestration capacity of algae, microorganisms, etc. in the water body (such as the carbon storage amount per unit water body area).

[0055] Then, the soil carbon sequestration parameter is multiplied by the change soil scale parameter to obtain the predicted soil carbon sequestration amount, the vegetation carbon sequestration parameter is multiplied by the change vegetation scale parameter to obtain the predicted vegetation carbon sequestration amount, and the water body carbon sequestration parameter is multiplied by the change water body scale parameter to obtain the predicted water body carbon sequestration amount. Finally, the predicted soil carbon sequestration amount, the predicted vegetation carbon sequestration amount and the predicted water body carbon sequestration amount are added to obtain the predicted carbon sequestration amount.

[0056] S400: According to the predicted carbon sequestration amount and the predicted carbon emission amount, the carbon cycle quality evaluation result is calculated and obtained.

[0057] Further, the step S400 of the present application further comprises:

[0058] S410: Calculate the ratio of the predicted carbon sequestration amount and the predicted carbon emission amount; S420: Take the ratio as the carbon cycle quality evaluation result.

[0059] Specifically, the ratio of the predicted carbon fixation amount and the predicted carbon emission amount is set as a carbon cycle quality evaluation result, to obtain the carbon cycle quality evaluation result, wherein if the ratio is greater than 1, it indicates that the carbon fixation capacity of the coal mining subsidence land exceeds its carbon emission amount, the carbon cycle quality is better, which shows that the region can realize carbon sink effect and help to reduce the concentration of greenhouse gases in the atmosphere; if the ratio is equal to 1, it indicates that the carbon emission and the carbon fixation amount of the region are roughly balanced, and the carbon cycle quality is in a stable state; if the ratio is less than 1, it indicates that the carbon emission amount is greater than the carbon fixation amount, which shows that the carbon cycle quality of the region is poor, which may lead to excessive carbon emission and affect the ecological balance and climate regulation. By taking the ratio of the predicted carbon fixation amount and the predicted carbon emission amount as the carbon cycle quality evaluation result, the health status of the carbon cycle of the coal mining subsidence land can be effectively quantified and evaluated, and scientific basis can be provided for subsequent carbon emission reduction, ecological restoration and carbon management decision-making.

[0060] The carbon cycle quality data evaluation method for carbon cycle provided by the embodiment has at least the following technical effects:

[0061] By collecting the carbon emission characteristic information and the subsidence characteristic information in the coal mining subsidence land, and predicting the carbon emission of the coal mining subsidence land according to the carbon emission characteristic information, the predicted carbon emission amount is obtained; on the other hand, the soil scale parameter, the vegetation scale parameter and the water body scale parameter in the coal mining subsidence land are collected, and the scale change of the soil, the vegetation and the water body is predicted according to the subsidence characteristic information, to obtain the changed soil scale parameter, the changed vegetation scale parameter and the changed water body scale parameter; further, the soil composition parameter, the vegetation type parameter and the water body composition parameter in the coal mining subsidence land are collected, and the predicted carbon fixation amount is calculated by combining the changed soil scale parameter, the changed vegetation scale parameter and the changed water body scale parameter; finally, the ratio of the predicted carbon fixation amount and the predicted carbon emission amount is calculated, and the ratio is taken as the carbon cycle quality evaluation result; that is, by combining the machine learning model, the carbon fixation amount and the carbon emission amount are comprehensively analyzed according to the soil composition, the vegetation type and the water body environment of the coal mining subsidence land, which can significantly improve the scientificity, accuracy and reliability of the prediction of the carbon emission amount and the carbon fixation capacity, so as to realize the accurate quantitative evaluation of the carbon cycle quality and provide scientific basis for carbon emission reduction and ecological restoration.

[0062] Embodiment two, as Figure 2As shown, based on the same inventive concept of the cycle quality data evaluation method for carbon cycle provided in Embodiment One, the present embodiment also provides a cycle quality data evaluation system for carbon cycle, comprising: a carbon emission prediction module 11, configured to collect carbon emission feature information and subsidence feature information in a coal mining subsidence area, perform carbon emission prediction of the coal mining subsidence area according to the carbon emission feature information, and obtain a predicted carbon emission amount; a scale change prediction module 12, configured to collect soil scale parameters, vegetation scale parameters and water body scale parameters in the coal mining subsidence area, perform scale change prediction of soil, vegetation and water body according to the subsidence feature information, and obtain changed soil scale parameters, changed vegetation scale parameters and changed water body scale parameters; a predicted carbon sequestration amount calculation module 13, configured to collect soil composition parameters, vegetation type parameters and water body composition parameters in the coal mining subsidence area, combine the changed soil scale parameters, the changed vegetation scale parameters and the changed water body scale parameters, and calculate to obtain a predicted carbon sequestration amount; and a carbon cycle quality evaluation result calculation module 14, configured to calculate to obtain a carbon cycle quality evaluation result according to the predicted carbon sequestration amount and the predicted carbon emission amount.

[0063] Further, the cycle quality data evaluation system for carbon cycle is further configured to: collect scale information of a leakage carbon emission source in the coal mining subsidence area as the carbon emission feature information; and collect subsidence area information, subsidence slope information and subsidence depth information in the coal mining subsidence area as the subsidence feature information.

[0064] Further, the cycle quality data evaluation system for carbon cycle is further configured to: collect a sample carbon emission feature information set according to carbon emission monitoring data of a sample coal mining subsidence area, and collect carbon emission amounts under different sample carbon emission feature information to obtain a sample carbon emission amount set; use the sample carbon emission feature information set as input features, use the sample carbon emission amount set as output features, and train a carbon emission predictor; input the carbon emission feature information into the carbon emission predictor to output a predicted carbon emission amount.

[0065] Further, the cycle quality data evaluation system for carbon cycle is further used for: collecting soil scale parameters, vegetation scale parameters and water scale parameters in the coal mining subsidence area; training a change predictor including integrated change prediction branches; calculating a ratio of the predicted carbon emission amount to a maximum value in a sample carbon emission amount set, multiplying a branch number of the integrated change prediction branches and taking an integer to obtain a configuration branch number; randomly selecting change prediction branches of the configuration branch number in the change predictor, inputting the soil scale parameters, vegetation scale parameters and water scale parameters, and predicting output to obtain a predicted soil change coefficient set, a predicted vegetation change coefficient set and a predicted water change coefficient set after a preset time length, and calculating an average to obtain a soil change coefficient, a vegetation change coefficient and a water change coefficient; and using the soil change coefficient, the vegetation change coefficient and the water change coefficient to calculate changes of the soil scale parameters, the vegetation scale parameters and the water scale parameters to obtain changed soil scale parameters, changed vegetation scale parameters and changed water scale parameters.

[0066] Further, the cycle quality data evaluation system for carbon cycle is further used for: collecting sample subsidence feature information sets according to change monitoring data of soil, vegetation and water in a sample coal mining subsidence area, and collecting scale change coefficients of soil, vegetation and water after a preset time length, which are labeled as a sample soil change coefficient set, a sample vegetation change coefficient set and a sample water change coefficient set; integrating the sample subsidence feature information sets, the sample soil change coefficient set, the sample vegetation change coefficient set and the sample water change coefficient set, and dividing to obtain multiple change prediction data; based on integrated learning, using the multiple change prediction data to train multiple change prediction branches to obtain a change predictor including integrated change prediction branches.

[0067] Further, the cycle quality data evaluation system for carbon cycle is further used for: collecting soil composition parameters, vegetation type parameters and water composition parameters in the coal mining subsidence area, and testing and obtaining soil carbon fixation parameters, vegetation carbon fixation parameters and water carbon fixation parameters of the soil composition parameters, the vegetation type parameters and the water composition parameters; according to the soil carbon fixation parameters, the vegetation carbon fixation parameters and the water carbon fixation parameters, combining the changed soil scale parameters, the changed vegetation scale parameters and the changed water scale parameters, and calculating to obtain predicted soil carbon fixation amount, predicted vegetation carbon fixation amount and predicted water carbon fixation amount; and calculating a sum of the predicted soil carbon fixation amount, the predicted vegetation carbon fixation amount and the predicted water carbon fixation amount to obtain a predicted carbon fixation amount.

[0068] Further, the cycle quality data evaluation system for carbon cycle is further used for: calculating a ratio of the predicted carbon fixation amount to the predicted carbon emission amount; and taking the ratio as a carbon cycle quality evaluation result.

[0069] Embodiment three, please refer to Figure 3, Figure 3 An embodiment of an electronic device provided by an embodiment of the present application is shown in the accompanying drawings. As shown in the drawings, Figure 3 The electronic device 500 provided by the embodiment of the present application includes a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: collecting carbon emission feature information and subsidence feature information in a coal mining subsidence area, performing carbon emission prediction of the coal mining subsidence area according to the carbon emission feature information, and obtaining a predicted carbon emission amount; collecting soil scale parameter, vegetation scale parameter, and water body scale parameter in the coal mining subsidence area, performing scale change prediction of soil, vegetation, and water body according to the subsidence feature information, and obtaining changed soil scale parameter, changed vegetation scale parameter, and changed water body scale parameter; collecting soil composition parameter, vegetation type parameter, and water body composition parameter in the coal mining subsidence area, combining the changed soil scale parameter, the changed vegetation scale parameter, and the changed water body scale parameter, and calculating to obtain a predicted carbon fixation amount; and calculating to obtain a carbon cycle quality evaluation result according to the predicted carbon fixation amount and the predicted carbon emission amount.

[0070] It should be noted that in the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0071] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one block or multiple blocks.

[0073] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0075] Although preferred embodiments of the application have been described, those skilled in the art will recognize that additional modifications and variations can be made thereto without departing from the spirit and scope of the application.

[0076] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A method for evaluating circulating mass data for carbon cycle, characterized by, The method comprises: Collecting carbon emission characteristic information and collapse characteristic information in the coal mining subsidence area, performing carbon emission prediction of the coal mining subsidence area according to the carbon emission characteristic information, and obtaining a predicted carbon emission amount; Collecting soil scale parameter, vegetation scale parameter and water body scale parameter in the coal mining subsidence area, performing scale change prediction of soil, vegetation and water body according to the collapse characteristic information, and obtaining changed soil scale parameter, changed vegetation scale parameter and changed water body scale parameter; Collecting soil composition parameter, vegetation type parameter and water body composition parameter in the coal mining subsidence area, combining the changed soil scale parameter, the changed vegetation scale parameter and the changed water body scale parameter, and calculating to obtain a predicted carbon fixation amount, comprising: Collecting soil composition parameter, vegetation type parameter and water body composition parameter in the coal mining subsidence area, and testing to obtain soil carbon fixation parameter, vegetation carbon fixation parameter and water body carbon fixation parameter of the soil composition parameter, the vegetation type parameter and the water body composition parameter; According to the soil carbon fixation parameter, the vegetation carbon fixation parameter and the water body carbon fixation parameter, combining the changed soil scale parameter, the changed vegetation scale parameter and the changed water body scale parameter, calculating to obtain a predicted soil carbon fixation amount, a predicted vegetation carbon fixation amount and a predicted water body carbon fixation amount; Calculating the sum of the predicted soil carbon fixation amount, the predicted vegetation carbon fixation amount and the predicted water body carbon fixation amount, and obtaining a predicted carbon fixation amount; According to the predicted carbon fixation amount and the predicted carbon emission amount, calculating to obtain a carbon cycle quality evaluation result.

2. The circulating mass data evaluation method for carbon cycle according to claim 1, characterized by, Collecting carbon emission characteristic information and collapse characteristic information in the coal mining subsidence area, comprising: Collecting scale information of a leakage carbon emission source in the coal mining subsidence area as the carbon emission characteristic information; Collecting collapse area information, collapse slope information and collapse depth information in the coal mining subsidence area as the collapse characteristic information.

3. The circulating mass data evaluation method for carbon cycle according to claim 1, characterized by, According to the carbon emission characteristic information, performing carbon emission prediction of the coal mining subsidence area to obtain a predicted carbon emission amount, comprising: According to carbon emission monitoring data of a sample coal mining subsidence area, collecting a sample carbon emission characteristic information set, and collecting carbon emission amounts under different sample carbon emission characteristic information to obtain a sample carbon emission amount set; Using the sample carbon emission characteristic information set as input features and using the sample carbon emission amount set as output features, training a carbon emission predictor; Inputting the carbon emission characteristic information into the carbon emission predictor to output a predicted carbon emission amount.

4. The circulating mass data evaluation method for carbon cycle according to claim 3, characterized by, Collecting soil scale parameter, vegetation scale parameter and water body scale parameter in the coal mining subsidence area, performing scale change prediction of soil, vegetation and water body according to the collapse characteristic information, comprising: Collecting soil scale parameter, vegetation scale parameter and water body scale parameter in the coal mining subsidence area; Training a change predictor comprising a plurality of change prediction branches; Calculating the ratio of the predicted carbon emission amount to the maximum value in the sample carbon emission amount set, multiplying the branch number of the plurality of change prediction branches and taking the integer to obtain a configuration branch number; Randomly selecting a change prediction branch with a change branch number in the change predictor, inputting the soil scale parameter, vegetation scale parameter and water body scale parameter, obtaining a predicted soil change coefficient set, a predicted vegetation change coefficient set and a predicted water body change coefficient set after a preset time length, and calculating a mean value to obtain a soil change coefficient, a vegetation change coefficient and a water body change coefficient; Using the soil change coefficient, the vegetation change coefficient and the water body change coefficient, change calculation is performed on the soil scale parameter, the vegetation scale parameter and the water body scale parameter to obtain a changed soil scale parameter, a changed vegetation scale parameter and a changed water body scale parameter.

5. The circulating mass data evaluation method for carbon cycle according to claim 4, characterized by, Training a change predictor including multiple change prediction branches, comprising: According to the change monitoring data of soil, vegetation and water body in the sample coal mining subsidence area, a sample subsidence characteristic information set is collected, and scale change coefficients of soil, vegetation and water body after a preset time length are collected and labeled as a sample soil change coefficient set, a sample vegetation change coefficient set and a sample water body change coefficient set; Integrating the sample subsidence characteristic information set, the sample soil change coefficient set, the sample vegetation change coefficient set and the sample water body change coefficient set, and dividing to obtain multiple change prediction data; Based on ensemble learning, using the multiple change prediction data, training multiple change prediction branches to obtain a change predictor including multiple change prediction branches.

6. The cyclic mass data evaluation method for carbon cycle according to claim 1, characterized by, According to the predicted carbon fixation amount and the predicted carbon emission amount, a carbon cycle quality evaluation result is calculated, comprising: Calculating a ratio of the predicted carbon fixation amount and the predicted carbon emission amount; Taking the ratio as the carbon cycle quality evaluation result.

7. A cycle quality data evaluation system for carbon cycling, characterized by, Steps for implementing the method for evaluating the quality of the carbon cycle according to any one of claims 1 to 6, comprising: A carbon emission prediction module for collecting carbon emission characteristic information and subsidence characteristic information in a coal mining subsidence area, performing carbon emission prediction of the coal mining subsidence area according to the carbon emission characteristic information, and obtaining a predicted carbon emission amount; A scale change prediction module for collecting soil scale parameters, vegetation scale parameters and water body scale parameters in the coal mining subsidence area, performing scale change prediction of soil, vegetation and water body according to the subsidence characteristic information, and obtaining changed soil scale parameters, changed vegetation scale parameters and changed water body scale parameters; A predicted carbon fixation amount calculation module for collecting soil composition parameters, vegetation type parameters and water body composition parameters in the coal mining subsidence area, combining the changed soil scale parameters, the changed vegetation scale parameters and the changed water body scale parameters, and calculating a predicted carbon fixation amount, comprising: Collecting soil composition parameters, vegetation type parameters and water body composition parameters in the coal mining subsidence area, and testing soil carbon fixation parameters, vegetation carbon fixation parameters and water body carbon fixation parameters of the soil composition parameters, the vegetation type parameters and the water body composition parameters; According to the soil carbon fixation parameters, the vegetation carbon fixation parameters and the water body carbon fixation parameters, combining the changed soil scale parameters, the changed vegetation scale parameters and the changed water body scale parameters, and calculating a predicted soil carbon fixation amount, a predicted vegetation carbon fixation amount and a predicted water body carbon fixation amount; calculating a sum of the predicted soil carbon fixation amount, the predicted vegetation carbon fixation amount and the predicted water body carbon fixation amount to obtain a predicted carbon fixation amount; a carbon cycle quality evaluation result calculation module configured to calculate a carbon cycle quality evaluation result according to the predicted carbon fixation amount and the predicted carbon emission amount.

8. An electronic device, comprising: comprising: a memory configured to store a computer software program; a processor configured to read and execute the computer software program, thereby implementing the steps of the method for evaluating the quality of the carbon cycle according to any one of claims 1 to 6.

Images