Greenhouse gas emission amount accounting method and device and electronic equipment

Abstract

The embodiment of the invention provides a greenhouse gas emission amount accounting method and device and electronic equipment, and relates to the technical field of greenhouse gas emission accounting. The accounting method for the greenhouse gas emission comprises the following steps: determining an accounting data set according to a greenhouse gas database, a plurality of gas concentration in-situ observation data and a plurality of gas flux in-situ observation data; establishing a random forest model of predictive factors and greenhouse gas concentration; predicting greenhouse gas concentrations of the plurality of reservoirs according to the random forest model; calculating a gas exchange coefficient; determining a predicted gas exchange coefficient through a random forest model; determining the greenhouse gas diffusion flux and the total discharge amount of the reservoir according to the greenhouse gas concentration and the predicted gas exchange coefficient; determining a greenhouse gas footprint before water storage according to the accounting data set; and determining the net discharge amount of the greenhouse gas of each reservoir according to the total discharge amount after water storage and the greenhouse gas footprint before water storage. According to the scheme of the invention, the accuracy of calculating the net discharge amount of the greenhouse gas in the reservoir is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of greenhouse gas emission accounting, and in particular, to a method, device, and electronic device for accounting greenhouse gas emissions. Background Art

[0002] Carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O) are three important greenhouse gases, and the increase in their atmospheric concentrations is one of the important factors leading to global warming. Dam construction and water storage inevitably cause a certain degree of land inundation, and the retention of soil and vegetation organic matter makes reservoirs important sites for carbon burial and transformation.

[0003] Currently, the existing methods for accounting greenhouse gas emissions have the following key defects in application: Most studies focus on the greenhouse gas emissions of a single reservoir, or simply extrapolate based on the average value of the three greenhouse gases. This method highly depends on the balance of the original data. However, the collected literature data is not evenly distributed, and most studies may be concentrated in certain regions. The emissions of reservoirs calculated by the method of average value extrapolation may have large deviations. Moreover, most of the studies on reservoir greenhouse gases focus on large reservoirs, but the proportion of small reservoirs is much larger than that of large reservoirs. Only conducting a linear regression analysis of a single environmental factor for large reservoirs cannot reasonably explain the main influencing factors and differences in the process of reservoir greenhouse gas emissions.

[0004] Therefore, in order to improve the accuracy of accounting for reservoir greenhouse gas emissions, how to propose a method for accounting greenhouse gas emissions for reservoirs has become an urgent problem to be solved currently. Summary of the Invention

[0005] The objective of the technical solution of the present invention is to provide a method, device, and electronic device for accounting greenhouse gas emissions, which can solve the technical problem that in the existing technology, when accounting for reservoir greenhouse gas emissions, only a linear regression analysis of a single environmental factor is conducted for large reservoirs, affecting the accuracy of accounting for reservoir greenhouse gas emissions.

[0006] In view of this, the first aspect of the technical solution of the present invention provides a method for accounting greenhouse gas emissions.

[0007] The second aspect of the technical solution of the present invention provides a device for accounting greenhouse gas emissions.

[0008] The third aspect of the technical solution of the present invention provides an electronic device.

[0009] To achieve the above object, a technical solution of the first aspect of the present invention provides a method for accounting greenhouse gas emissions. The method for accounting greenhouse gas emissions includes: obtaining a greenhouse gas database, in-situ observation data of gas concentrations corresponding to greenhouse gas concentrations of multiple reservoirs, and in-situ observation data of gas fluxes corresponding to greenhouse gas fluxes of multiple reservoirs; determining an accounting data set according to the greenhouse gas database, multiple in-situ observation data of gas concentrations, and multiple in-situ observation data of gas fluxes; establishing a random forest model of prediction factors and greenhouse gas concentrations according to the accounting data set in combination with the random forest algorithm; predicting the greenhouse gas concentrations of multiple reservoirs according to the random forest model; calculating a gas exchange coefficient when the Schmidt constant is equal to 600 under standard conditions according to the thin film boundary layer theory; predicting the gas exchange coefficient through the random forest model to determine a predicted gas exchange coefficient; determining the greenhouse gas diffusion flux of the reservoir according to the greenhouse gas concentration and the predicted gas exchange coefficient; determining the greenhouse gas emissions of the reservoir according to the greenhouse gas diffusion flux of the reservoir and the area of the reservoir, and determining the total emissions corresponding to multiple reservoirs according to the greenhouse gas emissions of the reservoir; determining the greenhouse gas footprint before water storage for each reservoir according to the accounting data set; and determining the net greenhouse gas emissions of each reservoir according to the total emissions after water storage and the greenhouse gas footprint before water storage.

[0010] According to the greenhouse gas emissions accounting method provided by the present invention, the net greenhouse gas emissions corresponding to multiple reservoirs are determined by accounting for the greenhouse gas concentration and greenhouse gas flux in the reservoirs. The greenhouse gases include carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O). Specifically, a multi-dimensional database is constructed through the in-situ observation data of the greenhouse gas concentration and flux in the reservoirs in relevant literature. Among them, the greenhouse gas database includes GRanD and HydroLAKES. After determining the multi-dimensional database, prediction factors are determined based on the publicly available reservoir dam information dataset. The prediction factors include reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors. The accounting dataset is determined according to the prediction factors and the multi-dimensional database. A random forest model is constructed for the gas concentrations of CO2, CH4, and N2O based on the data in the accounting dataset, and the parameters of the random forest model are optimized and trained. The gas exchange coefficient under standard conditions when the Schmidt constant is equal to 600 is calculated according to the thin film boundary layer theory, and the gas exchange coefficient under standard conditions when the Schmidt constant is equal to 600 is predicted by the random forest model to determine the predicted gas exchange coefficient. Finally, the greenhouse gas diffusion flux corresponding to each reservoir is determined according to the predicted gas exchange coefficient and the reservoir greenhouse gas concentration predicted by the random forest model. The greenhouse gas emissions determined according to the predicted gas exchange coefficient and the reservoir greenhouse gas concentration predicted by the random forest model are the total greenhouse gas emissions after the reservoir is impounded. The greenhouse gas footprint before the reservoirs are impounded is determined according to the surface area of the land cover sub-units corresponding to each reservoir and the greenhouse gas emission coefficient. The net greenhouse gas emissions of each reservoir, that is, the net flux, are determined according to the total emissions after the reservoir is impounded and the greenhouse gas footprint before the reservoir is impounded. Among them, the net emission flux before and after the reservoir construction is defined as the average value of the total emissions after removing the greenhouse gas footprint before impoundment per unit area of each reservoir.

[0011] In some technical solutions, optionally, the accounting dataset includes a multi-dimensional feature matrix. The multi-dimensional feature matrix includes reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors. The reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors are prediction factors.

[0012] In this solution, by integrating multi-dimensional data, a prediction factor system affecting reservoir greenhouse gas emissions is constructed to determine a multi-dimensional feature matrix. Specifically, based on the publicly available reservoir dam information dataset, characteristic parameters corresponding to multiple reservoirs are determined. An open-source Geographic Information System (GIS) is obtained, and a basin environmental element assimilation platform is constructed according to the open-source GIS technology to obtain environmental characteristic information of multiple different basins from it. According to the environmental characteristic information of multiple different basins and the characteristic parameters corresponding to multiple reservoirs, reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors are determined. The reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors are prediction factors, and the prediction factors are stored structurally to form a multi-dimensional feature matrix input into the machine learning model. Each row in the multi-dimensional feature matrix represents a reservoir sample, and each column represents a characteristic factor.

[0013] In some technical solutions, optionally, a random forest model of prediction factors and greenhouse gas concentration is established according to the accounting dataset combined with the random forest algorithm, including: constructing an initial model for greenhouse gas concentration according to the accounting dataset; dividing multiple data in the accounting dataset into intervals to determine a first interval and a second interval, where the first interval is greater than the second interval; determining the data in the first interval in the accounting dataset as valid data; dividing the valid data into a training set and a test set, where the number of data in the training set is greater than the number of data in the test set; training the initial model according to the training set and the prediction factors to determine the random forest model; among them, the first model result of the random forest model is determined by constructing a parameter network and combining cross-validation; the test set is characterized by the coefficient of determination and the root mean square error, and the characterized result is used to determine the prediction performance of the random forest model.

[0014] In this solution, a random forest model is constructed for the gas concentrations of CO2, CH4, and N2O based on R language, and model training, hyperparameter tuning, and performance evaluation are carried out. Specifically, during the model establishment process, to avoid the influence of extreme values, data outside the first interval is excluded. Multiple groups of data within the first interval are used as valid data, and the valid data is randomly divided. The valid data is randomly assigned according to 75% training set and 25% test set to ensure that the number of data in the training set is significantly larger than that in the test set to meet the requirements of machine learning for the sample size. All predictors are composed into a multi-dimensional feature matrix and input into the initial model for training to determine the random forest model. The optimal parameters in the random forest model, that is, the selection of the first model result, are achieved by constructing a parameter grid and combining cross-validation. Constructing the parameter grid includes setting the number of decision trees, tree depth, and the number of samples in the minimum leaf node. Through cross-validation, the performance of different parameter combinations is evaluated on the training set, and the optimal parameters are selected as the output result of the random forest model.

[0015] In some technical solutions, optionally, determining the greenhouse gas footprint before impoundment for each reservoir according to the accounting dataset includes: determining the land cover sub-units of each reservoir; determining the surface area of the land cover sub-units; determining the greenhouse gas emission coefficient of each reservoir before impoundment according to the accounting dataset; and determining the greenhouse gas footprint before impoundment of the reservoir according to the greenhouse gas emission coefficient and the surface area.

[0016] In this solution, the greenhouse gas footprint before impoundment is evaluated by multiplying the surface area of each land cover sub-unit by the greenhouse gas emission coefficient. For river-type reservoirs, the geomorphic features before impoundment consist of flooded land and the original river channel; for non-river-type reservoirs, the geomorphic features before impoundment are considered to consist entirely of flooded land. The area before reservoir inundation is divided into multiple land cover sub-units according to land cover types, such as forests, farmlands, wetlands, grasslands, and natural river channels, etc. The length of the river channel inundated by the reservoir is estimated from the overlapping part of the reservoir polygon in the refined reservoir spatial data (China Reservoir Dataset, CRD) and the river network in the natural runoff simulation data (GRADES). The width of the river channel inundated by the reservoir is estimated from the hydraulic geometry structure of the downstream site and the river reach flow in GRADES. The surface area of the inundated river channel is determined by the length and width of the river channel inundated by the reservoir.

[0017] In some technical solutions, optionally, after determining the net greenhouse gas emissions of each reservoir based on the total emissions after water storage and the greenhouse gas footprint before water storage, it further includes: determining the reservoir area and soil climate type of each reservoir; determining the area of each soil climate type based on the soil climate type and the reservoir area; determining the greenhouse gas emission factor corresponding to the soil climate type; and determining the greenhouse gas balance based on the reservoir area, the area of the soil climate type, and the greenhouse gas emission factor corresponding to the soil climate type.

[0018] In this solution, the total area of the actual water surface and the surrounding affected area after the completion of reservoir construction is obtained. The reservoir area of each reservoir is determined through GIS data, and the reservoir area is divided into multiple sub-units according to the soil climate type and climate zone. The greenhouse gas balance is determined based on the reservoir area, the area of the soil climate type, and the greenhouse gas emission factor corresponding to the soil climate type.

[0019] In some technical solutions, optionally, the accounting dataset further includes: the geospatial coordinates, time metadata, and time resolution of the sampling points corresponding to each reservoir.

[0020] In this solution, the data in the accounting dataset further includes time dimension information, that is, it includes the geospatial coordinates, time metadata, and time resolution of the sampling points of each reservoir. Among them, the geospatial coordinates are the longitude and latitude coordinates of the sampling points of each reservoir, which are used to map the reservoir sampling points to the geospatial and support the overlay analysis with raster data such as climate, soil, and land use rate; the time metadata includes the monitoring date and duration corresponding to the sampling, which are used to track the seasonal changes of greenhouse gas concentration or the dynamic response after water level regulation; the time resolution includes the time interval of data sampling, for example, per hour, per day, per month, per quarter, or per year, which is used to match the time scales of different source data.

[0021] The technical solution of the second aspect of the present invention provides a device for calculating greenhouse gas emissions. The device for calculating greenhouse gas emissions includes: a data unit, configured to obtain a greenhouse gas database, in-situ observation data of gas concentrations corresponding to a plurality of reservoirs, and in-situ observation data of gas fluxes corresponding to a plurality of reservoirs; determine an accounting data set according to the greenhouse gas database, a plurality of in-situ observation data of gas concentrations, and a plurality of in-situ observation data of gas fluxes; a model unit, configured to establish a random forest model of a predictor and a greenhouse gas concentration according to the accounting data set in combination with a random forest algorithm; a prediction unit, configured to predict the greenhouse gas concentrations of a plurality of reservoirs according to the random forest model; calculate a gas exchange coefficient when the Schmidt constant is equal to 600 under standard conditions according to the thin film boundary layer theory; predict the gas exchange coefficient through the random forest model to determine a predicted gas exchange coefficient; a determination unit, configured to determine a reservoir greenhouse gas diffusion flux according to the greenhouse gas concentration and the predicted gas exchange coefficient; determine the greenhouse gas emissions of the reservoir according to the reservoir greenhouse gas diffusion flux and the area of the reservoir, and determine the total emissions corresponding to a plurality of reservoirs according to the reservoir greenhouse gas emissions; determine the greenhouse gas footprint before water storage for each reservoir according to the accounting data set; an accounting unit, configured to determine the net greenhouse gas emissions of each reservoir according to the total emissions after water storage and the greenhouse gas footprint before water storage.

[0022] In some technical solutions, optionally, the model unit is further configured to: construct an initial model for the greenhouse gas concentration according to the accounting data set; divide a plurality of data in the accounting data set into intervals to determine a first interval and a second interval, where the first interval is greater than the second interval; determine the data in the first interval in the accounting data set as valid data; divide the valid data into a training set and a test set, where the number of data in the training set is greater than the number of data in the test set; train the initial model according to the training set and the predictor to determine the random forest model; wherein, determine a first model result of the random forest model by constructing a parameter network and combining cross-validation; the test set is characterized by a coefficient of determination and a root mean square error, and the characterized result is used to determine the prediction performance of the random forest model.

[0023] In some technical solutions, optionally, the accounting unit is further configured to: determine the reservoir area and soil climate type of each reservoir; determine the area of each soil climate type according to the soil climate type and the reservoir area; determine the greenhouse gas emission coefficient corresponding to the soil climate type; determine the greenhouse gas balance according to the reservoir area, the area of each soil climate type, and the greenhouse gas emission coefficient corresponding to the soil climate type.

[0024] The technical solution of the third aspect of the present application provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the accounting method for greenhouse gas emissions in the first aspect are implemented.

[0025] The additional aspects and advantages of the technical solution of the present invention will become apparent in the following description section or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 The flowchart showing the accounting method for greenhouse gas emissions according to an embodiment of the present application; Figure 2 The partial flowchart showing the accounting method for greenhouse gas emissions according to an embodiment of the present application; Figure 3 The partial flowchart showing the accounting method for greenhouse gas emissions according to an embodiment of the present application; Figure 4 The partial flowchart showing the accounting method for greenhouse gas emissions according to an embodiment of the present application; Figure 5 The structural schematic block diagram showing the accounting device for greenhouse gas emissions according to an embodiment of the present application; Figure 6 The structural schematic block diagram showing the electronic device according to an embodiment of the present application; Figure 7 The sampling point location map showing the greenhouse gas concentration of the collection reservoir according to an embodiment of the present application; Figure 8 The sampling point location map showing the greenhouse gas diffusion flux of the collection reservoir according to an embodiment of the present application; Figure 9 The spatial distribution map showing the gas concentration of carbon dioxide according to an embodiment of the present application; Figure 10 The spatial distribution map showing the diffusion flux of carbon dioxide according to an embodiment of the present application; Figure 11 The spatial distribution map showing the gas concentration of methane according to an embodiment of the present application; Figure 12 The spatial distribution map showing the diffusion flux of methane according to an embodiment of the present application; Figure 13 The spatial distribution map showing the gas concentration of nitrous oxide according to an embodiment of the present application; Figure 14Shows the spatial distribution map of the diffusion flux of nitrous oxide according to an embodiment of the present application.

[0027] Wherein, Figure 5 and Figure 6 The corresponding relationship between the reference numerals and the component names in the figure is as follows: 900: Accounting device for greenhouse gas emissions; 902: Data unit; 904: Model unit; 906: Prediction unit; 908: Determination unit; 910: Accounting unit; 1000: Electronic device; 1109: Memory; 1110: Processor. Detailed implementation manners

[0028] In order to more clearly understand the above objects, features and advantages of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below with reference to the drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0029] In the following description, many specific details are set forth in order to fully understand the present application. However, the embodiments of the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present application is not limited to the limitations of the specific embodiments disclosed below.

[0030] The following combines the attached Figures 1 to 14 , and through specific embodiments and their application scenarios, the accounting method, device and electronic device for greenhouse gas emissions provided by the embodiments of the present application are described in detail.

[0031] This embodiment provides an accounting method for greenhouse gas emissions, as Figure 1 shown, including: Step S100: Obtain a greenhouse gas database, in-situ gas concentration observation data of greenhouse gas concentrations corresponding to multiple reservoirs, and in-situ gas flux observation data of greenhouse gas fluxes corresponding to multiple reservoirs; Step S102: Determine an accounting data set according to the greenhouse gas database, multiple in-situ gas concentration observation data, and multiple in-situ gas flux observation data; Step S104: Establish a random forest model of prediction factors and greenhouse gas concentrations according to the accounting data set in combination with the random forest algorithm; Step S106: Predict the greenhouse gas concentrations of multiple reservoirs according to the random forest model; Step S108: Calculate the gas exchange coefficient when the Schmidt constant is equal to 600 under standard conditions according to the thin-film boundary layer theory; Step S110: Predict the gas exchange coefficient through the random forest model to determine the predicted gas exchange coefficient; Step S112: Determine the reservoir greenhouse gas diffusion flux according to the greenhouse gas concentration and the predicted gas exchange coefficient; Step S114: Determine the reservoir greenhouse gas emissions according to the reservoir greenhouse gas diffusion flux and the area of the reservoir, and determine the total emissions corresponding to multiple reservoirs according to the reservoir greenhouse gas emissions; Step S116: Determine the greenhouse gas footprint before impoundment of each reservoir according to the accounting data set; Step S118: Determine the greenhouse gas net emissions of each reservoir according to the total emissions after impoundment and the greenhouse gas footprint before impoundment.

[0032] According to the accounting method for greenhouse gas emissions provided by the present invention, by accounting for the greenhouse gas concentration and greenhouse gas flux of the reservoir, the greenhouse gas net emissions corresponding to multiple reservoirs are determined. The greenhouse gases include carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O). Specifically, a multi-dimensional database is constructed through the in-situ observation data of reservoir greenhouse gas concentration and flux in the CO2 Measurements Database, the Global River Methane Database, and relevant literature. Among them, the greenhouse gas database includes GRanD and HydroLAKES. After determining the multi-dimensional database, prediction factors are determined based on the publicly available reservoir dam information data set. The prediction factors include reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors. The accounting data set is determined according to the prediction factors and the multi-dimensional database. A random forest model is constructed for the gas concentrations of CO2, CH4, and N2O based on the data in the accounting data set, and the parameters of the random forest model are optimized and trained. The gas exchange coefficient under the standard condition when the Schmidt constant is equal to 600 is calculated according to the thin film boundary layer theory, and the gas exchange coefficient under the standard condition when the Schmidt constant is equal to 600 is predicted by the random forest model to determine the predicted gas exchange coefficient. Finally, the greenhouse gas diffusion flux corresponding to each reservoir is determined according to the predicted gas exchange coefficient and the reservoir greenhouse gas concentration predicted by the random forest model. The greenhouse gas emissions determined according to the predicted gas exchange coefficient and the reservoir greenhouse gas concentration predicted by the random forest model are the total greenhouse gas emissions after reservoir impoundment. The greenhouse gas footprint before impoundment of multiple reservoirs is determined according to the surface area of the land cover sub-unit corresponding to each reservoir and the greenhouse gas emission coefficient. The greenhouse gas net emissions of each reservoir are determined according to the total emissions after reservoir impoundment and the greenhouse gas footprint before reservoir impoundment, that is, the net flux. Among them, the net emission flux before and after reservoir construction is defined as the average value of the total emissions after removing the greenhouse gas footprint before impoundment per unit area of each reservoir.

[0033] Understandably, by integrating multi-source data, machine learning modeling, and double accounting benchmarks, the net greenhouse gas emissions before and after reservoir construction within a precise quantification range are achieved. The data sources cover the global scope, compensating for the problems existing in existing international models, such as the sample bias in the application of the reservoir greenhouse gas net flux assessment model (G-res Tool) for specific regions and the too low monitoring coverage frequency of small reservoirs. Through the random forest model combined with multi-dimensional predictors, the non-linear mechanism of greenhouse gas generation is captured, and the greenhouse gas emissions are predicted from multiple aspects, avoiding the uncertainty of greenhouse gas accounting caused by extrapolation based on the average value and improving the robustness of reservoir greenhouse gas emissions accounting.

[0034] Optionally, the multi-dimensional database also includes the Global Reservoir and Dam Database (GRanD) and the Global Lakes Database (HydroLAKES).

[0035] Furthermore, through the double accounting benchmark method, separated according to the greenhouse gas emission sources, the system automatically separates the pre-impoundment greenhouse gas footprint of natural river channels and land emissions and the post-impoundment greenhouse gas emissions caused by human engineering, revealing the net climate benefit of hydropower and laying a scientific premise for evaluating the cleanliness of hydropower.

[0036] Exemplarily, the greenhouse gas footprint is used to measure the net greenhouse gas emissions generated by the reservoir system over a period of time. For example, the pre-impoundment greenhouse gas footprint is the total amount of greenhouse gases naturally released or absorbed by the original inundated area (land or river channel) before the reservoir was built; the post-impoundment greenhouse gas footprint is the total amount of greenhouse gas emissions in the water body and sediment caused by water impoundment after the reservoir is completed.

[0037] Optionally, during the process of obtaining in-situ observation data of reservoir greenhouse gas concentration and flux, the geospatial coordinates, time metadata, and time resolution of the sampling points are determined simultaneously. For example, the geospatial coordinates include the longitude and latitude of the sampling points, the time metadata includes the monitoring date and duration of the sampling, and the time resolution includes the time interval corresponding to the sampling, such as quarterly or annually.

[0038] Furthermore, the greenhouse gas emissions accounting method is used to determine the net greenhouse gas flux of reservoirs within a specific regional scope, that is, the net greenhouse gas emissions of each reservoir within a specific regional scope.

[0039] Optionally, the greenhouse gas emissions accounting method is applied to the accounting of inland water body greenhouse gas emissions, such as lakes and rivers, etc.

[0040] Exemplarily, the thin-film boundary layer theory is used to describe the gas transfer rate at the water-air interface. To eliminate the influence of temperature, the gas exchange coefficient is standardized to the condition where the Schmidt number is equal to 600, corresponding to the standard water temperature at 20°C. Based on the in-situ observation data of greenhouse gas fluxes and greenhouse gas concentrations, the gas exchange coefficient under the condition where the Schmidt number is equal to 600 can be determined. Based on the random forest model, the relationship between the gas exchange coefficient and multiple predictors such as wind speed, reservoir area, and water temperature is established to determine the predicted gas exchange coefficient. The thin-film boundary layer theory provides a physical basis for the calculation and prediction of the predicted gas exchange coefficient, ensuring the reliability and accuracy of the flux calculation.

[0041] In some embodiments, optionally, the accounting dataset includes a multi-dimensional feature matrix, which includes reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors. The reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors are predictors.

[0042] In this embodiment, by integrating multi-dimensional data, a prediction factor system affecting reservoir greenhouse gas emissions is constructed to determine the multi-dimensional feature matrix. Specifically, based on the publicly available reservoir dam information dataset, the characteristic parameters corresponding to multiple reservoirs are determined. And an open-source Geographic Information System (GIS) is obtained, and a basin environmental element assimilation platform is constructed according to the open-source GIS technology to obtain the environmental characteristic information of multiple different basins from it. According to the environmental characteristic information of multiple different basins and the characteristic parameters corresponding to multiple reservoirs, the reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors are determined. The reservoir characteristic factors, climate characteristic factors, basin environmental factors, and socio-economic factors are predictors, and the predictors are stored in a structured manner to form a multi-dimensional feature matrix input into the machine learning model. Each row in the multi-dimensional feature matrix represents a reservoir sample, and each column represents a characteristic factor.

[0043] It can be understood that by constructing a "machine learning - environmental factor" model framework through the multi-dimensional feature matrix, the random forest model is used to capture the non-linear mechanism of greenhouse gas generation, making up for the limitation of extrapolation based on the average value in traditional methods. The multi-dimensional feature matrix captures the non-linear relationship through the random forest algorithm, improving the scientific nature of the model, thereby improving the accuracy of the accounting of reservoir greenhouse gas emissions and reducing the accounting deviation.

[0044] Optionally, before determining the multi-dimensional feature matrix, it further includes: performing spatial alignment, unit unification, and missing value imputation on data from different sources (literature, database, or GIS).

[0045] Exemplarily, the reservoir characteristic factors include basic reservoir characteristics such as the reservoir age, water depth of the reservoir, and hydraulic residence time.

[0046] Exemplarily, the climate characteristic factors include weather characteristics such as air temperature, rainfall, and wind speed.

[0047] Exemplarily, the basin environmental factors include basin environmental characteristics such as total primary productivity, soil organic carbon, and proportion of landscape types.

[0048] Exemplarily, the socio-economic factors include human activity characteristics such as population density and Gross Domestic Product (GDP).

[0049] In some embodiments, optionally, as Figure 2 shown, step S104: Establish a random forest model of the prediction factors and greenhouse gas concentration according to the accounting dataset in combination with the random forest algorithm, including: Step S1040: Construct an initial model for the greenhouse gas concentration according to the accounting dataset; Step S1042: Divide multiple data in the accounting dataset into intervals, and determine the first interval and the second interval; Step S1044: Determine the data within the first interval in the accounting dataset as valid data; Step S1046: Divide the valid data into a training set and a test set; Step S1048: Train the initial model according to the training set and the prediction factors to determine the random forest model; Among them, the first model result of the random forest model is determined by constructing a parameter network and combining cross-validation; the test set is characterized by the coefficient of determination and the root mean square error, and the characterized result is used to determine the prediction performance of the random forest model.

[0050] In this embodiment, a random forest model is constructed for the gas concentrations of CO2, CH4, and N2O based on R language, and model training, hyperparameter tuning, and performance evaluation are carried out. Specifically, during the model establishment process, to avoid the influence of extreme values, the data outside the first interval is removed. Multiple groups of data within the first interval are used as valid data, and the valid data is randomly divided. The valid data is randomly assigned according to 75% training set and 25% test set to ensure that the number of data in the training set is significantly larger than that in the test set to meet the sample size requirements of machine learning. All prediction factors are formed into a multi-dimensional feature matrix and input into the initial model for training to determine the random forest model. The optimal parameters in the random forest model, that is, the selection of the first model result, are achieved by constructing a parameter grid and combining cross-validation. The construction of the parameter grid includes setting the number of decision trees, tree depth, and the number of samples in the minimum leaf node. Through cross-validation, the performance of different parameter combinations is evaluated on the training set, and the optimal parameters are selected as the output result of the random forest model.

[0051] Furthermore, the coefficient of determination and the root mean square error (RMSE) are calculated using the test set. Among them, the coefficient of determination is used to measure the fitting degree between the predicted value and the true value of the model. The closer the coefficient of determination is to 1, the stronger the explanatory ability of the model. The root mean square error is used to quantify the average deviation between the predicted value and the true value. The smaller the RMSE, the higher the prediction accuracy of the model. Calculating the coefficient of determination and the root mean square error using the test set independently verifies the generalization ability of the model and avoids overfitting.

[0052] It can be understood that by removing outliers and optimizing hyperparameters, the interference of extreme values in the data is excluded, enabling the model to focus on the variation law of greenhouse gas concentration under normal working conditions and reducing the prediction error of greenhouse gas concentration. By means of grid search and cross-validation, the deviation of artificially set parameters is avoided, ensuring the generalization of the model.

[0053] Exemplarily, the greenhouse gas concentration data is screened according to a 95% confidence interval (the first interval), the extreme maximum or minimum values in the first 5% are removed, 95% of the valid data is retained, and the outliers caused by instrument errors or extreme environmental events are deleted to avoid the interference of abnormal data in model training and improve the robustness of the model.

[0054] Optionally, the random forest model includes a multi-dimensional feature matrix and a target variable, and the optimal combination is determined by means of grid search and cross-validation selection. The random forest model captures the non-linear interaction between multiple predictors, improving the accuracy of gas exchange coefficient and greenhouse gas concentration prediction and the reliability of data.

[0055] Optionally, by selecting multiple pairs of data that simultaneously report greenhouse gas concentration and greenhouse gas flux in the accounting dataset, a random forest model is constructed in combination with the reservoir characteristic factors and watershed environmental factors in the predictors.

[0056] Furthermore, during the screening of multiple data in the accounting dataset, the data that simultaneously reports greenhouse gas concentration and greenhouse gas flux is used as valid data.

[0057] In some embodiments, optionally, as Figure 3 shown, step S116: Determine the greenhouse gas footprint before impoundment for each reservoir according to the accounting dataset, including: Step S1160: Determine the land cover sub-units for each reservoir; Step S1162: Determine the surface area of the land cover sub-units; Step S1164: Determine the greenhouse gas emission coefficient for each reservoir before impoundment according to the accounting dataset; Step S1166: Determine the greenhouse gas footprint of the reservoir before impoundment based on the greenhouse gas emission factor and the surface area.

[0058] In this embodiment, the greenhouse gas footprint before impoundment is evaluated by multiplying the surface area of each land cover sub-unit by the greenhouse gas emission factor. For riverine reservoirs, the pre-impoundment geomorphic features consist of flooded land and the original river channel; for non-riverine reservoirs, the pre-impoundment geomorphic features are considered to consist entirely of flooded land. The area before reservoir impoundment is divided into multiple land cover sub-units according to land cover types, such as forests, farmland, wetlands, grasslands, and natural river channels, etc. The length of the river channel flooded by the reservoir is estimated from the overlapping part of the reservoir polygon in the refined reservoir spatial data (China Reservoir Dataset, CRD) and the river network in the natural runoff simulation data (GRADES). The width of the river channel flooded by the reservoir is estimated from the hydraulic geometry structure at the downstream site and the river reach flow in GRADES. The surface area of the flooded river channel is determined by the length and width of the river channel flooded by the reservoir.

[0059] It can be understood that by calculating the greenhouse gas before impoundment, the natural emission baseline before reservoir construction is clarified, the carbon emissions of the original ecosystem and the greenhouse gases artificially generated by reservoir construction are separated, and the error generated by unified accounting is reduced.

[0060] Exemplarily, assuming that the pre-impoundment landform of the reservoir is the same as the land cover of the reservoir basin, the emissions or absorptions of each land cover sub-unit before reservoir impoundment are calculated according to the spatial distribution characteristics of the greenhouse gas emission intensity of the terrestrial ecosystem recorded in the literature or dataset or the published greenhouse gas emission factors for each land use type.

[0061] In some embodiments, optionally, as Figure 4 shown, after step S118: Determine the net greenhouse gas emissions of each reservoir based on the total emissions after impoundment and the greenhouse gas footprint before impoundment, further including: Step S1200: Determine the reservoir area and soil climate type of each reservoir; Step S1202: Determine the area of each soil climate type according to the soil climate type and the reservoir area; Step S1204: Determine the greenhouse gas emission factor corresponding to the soil climate type; Step S1206: Determine the greenhouse gas balance according to the reservoir area, the area of the soil climate type, and the greenhouse gas emission factor corresponding to the soil climate type.

[0062] In this embodiment, the total area of the actual water surface and the surrounding affected area after the completion of reservoir construction is obtained. The reservoir area of each reservoir is determined through GIS data, and the reservoir area is divided into multiple sub-units according to soil climate types and climate zones. The greenhouse gas balance is determined based on the reservoir area, the area of the soil climate type, and the greenhouse gas emission factor corresponding to the soil climate type. The calculation formula for the greenhouse gas balance is as follows: ; where, is the greenhouse gas balance, i is the soil climate type, j is the greenhouse gas type, is the emission factor of the j-th greenhouse gas of the i-th soil climate type, is the area of the i-th soil climate type, is the reservoir area.

[0063] Understandably, by differentiating different soil climate types, combining the areas of different soil climate types and the reservoir area to determine the greenhouse gas balance, and using the greenhouse gas balance as an evaluation index for the greenhouse gas emissions of the reservoir, it is used to determine the carbon offset benefit of the hydropower project, laying a foundation for evaluating the hydropower cleanliness of the reservoir.

[0064] Exemplarily, by calculating the greenhouse gas balance, the net impact of reservoir construction on greenhouse gas emissions is determined. For example, when the value of the greenhouse gas balance is positive, it indicates that the greenhouse gas emissions after impoundment are greater than the baseline before impoundment, and the reservoir is a net emission source, and optimization management of greenhouse gas emissions is required; when the value of the greenhouse gas balance is negative, it indicates that the greenhouse gas emissions after impoundment are less than the baseline before impoundment, and the reservoir has carbon sink potential, which can strengthen the clean energy status of the hydropower in the reservoir.

[0065] In some embodiments, optionally, the accounting dataset further includes: the geospatial coordinates, time metadata, and time resolution of the sampling points corresponding to each reservoir.

[0066] In this embodiment, the data in the accounting dataset also includes time dimension information, that is, it includes the geospatial coordinates, time metadata, and time resolution of the sampling points of each reservoir. Among them, the geospatial coordinates are the longitude and latitude coordinates of the sampling points of each reservoir, which are used to map the reservoir sampling points to the geospatial and support the overlay analysis with raster data such as climate, soil, and land use rate; the time metadata includes the monitoring date and duration corresponding to the sampling, which are used to track the seasonal changes of greenhouse gas concentrations or the dynamic response after water level regulation; the time resolution includes the time interval of data sampling, for example, per hour, per day, per month, per quarter, or per year, which is used to match the time scales of different source data.

[0067] Understandably, by determining the geospatial coordinates, time metadata, and time resolution of the sampling points for each reservoir, it facilitates the visualization of the accounting data. Combining with the time metadata reveals the seasonal patterns of greenhouse gas emissions and improves the traceability of the data.

[0068] In a specific embodiment, optionally, the method for accounting greenhouse gas emissions is a method for estimating the net emissions of multiple reservoirs within a specific area by establishing an accounting model for greenhouse gas emissions from reservoirs within the area, including the following steps: Step 1: Establish a database. Through the in-situ observation data of greenhouse gas concentrations and fluxes in mainstream domestic and foreign databases and 169 relevant literature, a total of 3,984 independent spatio-temporal data items are obtained, including 7,342 individual greenhouse gas concentration and flux measurement values. At the same time, the geospatial coordinates (latitude / longitude) of the sampling points, time metadata (monitoring date and duration), and time resolution (such as quarterly and annual) are collected.

[0069] The sampling point locations of the greenhouse gas concentration in the reservoir are as Figure 7 shown. In the figure, the abscissa represents longitude and the ordinate represents latitude. The yellow circles represent the sampling point locations of the gas concentration corresponding to carbon dioxide (CO2), with a total of 1,070 points; the red circles represent the sampling point locations of the gas concentration corresponding to methane (CH4), with a total of 1,167 points; the blue circles represent the sampling point locations of the gas concentration corresponding to nitrous oxide (N2O), with a total of 437 points.

[0070] The sampling point locations of the greenhouse gas diffusion flux in the reservoir are as Figure 8 shown. In the figure, the abscissa represents longitude and the ordinate represents latitude. The yellow circles represent the sampling point locations of the gas diffusion flux corresponding to carbon dioxide (CO2), with a total of 2,364 points; the red circles represent the sampling point locations of the gas diffusion flux corresponding to methane (CH4), with a total of 508 points; the blue circles represent the sampling point locations of the gas diffusion flux corresponding to nitrous oxide (N2O), with a total of 727 points.

[0071] Furthermore, the sampling point location map is divided according to the climatic zone. The divided areas include plateau and mountain, subtropical, temperate, and tropical.

[0072] Step 2: Collect characteristic factors. Seven reservoir characteristic parameters were compiled based on the publicly available reservoir dam information dataset. To determine the environmental and socioeconomic predictors for the catchment area corresponding to the reservoir, relying on the basin environmental element assimilation platform constructed based on open-source GIS technology, 45 pieces of multivariate environmental characteristic information of the basin were obtained. By integrating all the above data, a database of reservoir greenhouse gas concentrations and emissions including three greenhouse gases was constructed.

[0073] Step 3: Establish a model for the concentrations of three greenhouse gases in the reservoir. Use the RStudio-2024.12.0-467 program to construct a random forest model for the concentrations of CO2, CH4, and N2O, and conduct model training, hyperparameter tuning, and performance evaluation. During the modeling process, to avoid the influence of extreme values, data outside the 95% interval were excluded, and the remaining data were randomly divided into a training set (75%) and a test set (25%). All the aforementioned predictors were input into the model for training, and the selection of the optimal model parameters was achieved by constructing a parameter grid and combining the method of cross-validation. To measure the model prediction performance, it was characterized by using the coefficient of determination (R2) and the root mean square error (RMSE) on the test set.

[0074] Step 4: Select 1197 pairs of data that report both concentrations and fluxes in the reservoir greenhouse gas dataset, and establish a gas exchange coefficient by combining the reservoir characteristic parameters and the basin environmental characteristics. Random forest model; according to the model prediction results, and based on the reservoir greenhouse gas concentrations predicted by the concentration model and the thin film boundary layer theory, calculate the diffusion fluxes of the three greenhouse gases in the reservoir to obtain the greenhouse gas emissions after impoundment.

[0075] Step 5: Calculate the net greenhouse gas emissions of the reservoir. The net emission flux before and after reservoir construction is defined as the average value of the total emissions per unit area of each reservoir after removing the greenhouse gas footprint before water storage, that is: Net flux = (Cumulative flux after water storage - Greenhouse gas footprint before water storage) / Reservoir area. The greenhouse gas footprint before water storage is evaluated by multiplying the surface area of each land cover sub-unit by the greenhouse gas emission coefficient. For river-type reservoirs, the geomorphic features before water storage consist of flooded land and the original river channel; for non-river-type reservoirs, the geomorphic features before water storage are considered to consist entirely of flooded land. Assuming that the land geomorphology before reservoir water storage is the same as the land cover of the reservoir's watershed, calculate the emissions or absorptions of each land cover sub-unit before reservoir water storage according to the spatial distribution characteristics of greenhouse gas emission intensities in terrestrial ecosystems reported in the literature or the published greenhouse gas emission coefficients for each land use type. The length of the river channel flooded by the reservoir is estimated from the overlapping part of the CRD reservoir polygon and the GRADES river network, and the river width is estimated by combining the hydraulic geometry of the downstream site with the river segment flow of GRADES.

[0076] Finally, calculate the cumulative greenhouse gas balance, and the formula is as follows: ; where, is the greenhouse gas balance, i is the soil climate type, j is the greenhouse gas type, is the emission coefficient of the j-th greenhouse gas of the i-th soil climate type, is the area of the i-th soil climate type, is the reservoir area.

[0077] Exemplarily, the spatial distribution maps of the greenhouse gas concentration and diffusion flux of the reservoirs in the specific area accounted for by the present invention are as shown in Figures 9 to 14 . In the figure, the abscissa represents longitude and the ordinate represents latitude. Among them, Figure 9 is the spatial distribution map of carbon dioxide gas concentration (CO2 concentration). The numerical size of the carbon dioxide gas concentration (unit: ) is positively correlated with the color distribution of the spatial distribution map. The larger the value, the darker the corresponding color. For example, the color concentration of the carbon dioxide gas concentration value in the range of 28.80 - 34.94 is greater than the color concentration of the carbon dioxide gas concentration value in the range of 18.78 - 28.79; Figure 10 is the spatial distribution map of carbon dioxide diffusion flux (CO2 flux). The carbon dioxide diffusion flux (unit: The numerical magnitude and the color distribution of the spatial distribution map are positively correlated. The larger the value, the darker the corresponding color. For example, the color concentration of the carbon dioxide diffusion flux value in the range of 7.24 - 10.97 is greater than the color concentration of the carbon dioxide diffusion flux value in the range of 0.73 - 7.23; Figure 11 is the spatial distribution map of methane gas concentration (CH4 concentration). The methane gas concentration (unit: The numerical magnitude and the color distribution of the spatial distribution map are positively correlated. The larger the value, the darker the corresponding color. For example, the color concentration of the methane gas concentration value in the range of 0.14 - 0.15 is greater than the color concentration of the methane gas concentration value in the range of 0.13 - 0.14; Figure 12 is the spatial distribution map of methane diffusion flux (CH4 flux). The methane diffusion flux (unit: The numerical magnitude and the color distribution of the spatial distribution map are positively correlated. The larger the value, the darker the corresponding color. For example, the color concentration of the methane diffusion flux value in the range of 0.08 - 0.09 is greater than the color concentration of the methane diffusion flux value in the range of 0.06 - 0.07; Figure 13 is the spatial distribution map of nitrous oxide gas concentration (N2O concentration). The nitrous oxide gas concentration (unit: The numerical magnitude and the color distribution of the spatial distribution map are positively correlated. The larger the value, the darker the corresponding color. For example, the color concentration of the nitrous oxide gas concentration value in the range of 27.41 - 33.16 is greater than the color concentration of the nitrous oxide gas concentration value in the range of 12.51 - 27.40; Figure 14 is the spatial distribution map of nitrous oxide diffusion flux (N2O flux). The nitrous oxide diffusion flux (unit: The numerical magnitude and the color distribution of the spatial distribution map are positively correlated. The larger the value, the darker the corresponding color. For example, the color concentration of the nitrous oxide diffusion flux value in the range of 10.71 - 12.16 is greater than the color concentration of the nitrous oxide diffusion flux value in the range of 7.14 - 10.70.

[0078] The accounting method for greenhouse gas emissions provided by the present invention can achieve the following beneficial effects: Through systematic data collection and the random forest method, the greenhouse gas concentrations and fluxes of 974,35 reservoirs are estimated, and the net greenhouse gas emissions of reservoirs in the region are obtained by estimating the greenhouse gas footprint before inundation. Compared with the traditional method of estimating the emissions of multiple reservoirs based on collected data and average extrapolation, the present invention can effectively reduce the uncertainty of accounting; using the method proposed by the present invention, the specific emissions of each reservoir can be accounted, and the contributions of various types of reservoirs and each greenhouse gas can be obtained, while the traditional method can only account for the total greenhouse gas emissions; adopting the accounting method for greenhouse gas emissions of the present invention, the greenhouse gas concentration and diffusion flux in a specific region can be visualized, the greenhouse gas emissions of local and overall regional reservoirs can be intuitively understood, and the emission hotspots and net emission hotspots of reservoir greenhouse gases can be statistically identified, which has important value for greenhouse gas emission reduction work.

[0079] In addition, the method and model proposed by the present invention are for the accounting of greenhouse gas emissions from reservoirs, but are not limited to reservoirs only. The idea of the present invention can also be applied to the accounting of greenhouse gas emissions from other inland water bodies, such as lakes and rivers.

[0080] As Figure 5 shown, the embodiment of the present application also provides an accounting device 900 for greenhouse gas emissions. The accounting device 900 for greenhouse gas emissions includes: a data unit 902, configured to obtain a greenhouse gas database, in-situ gas concentration observation data corresponding to the greenhouse gas concentrations of multiple reservoirs, and in-situ gas flux observation data corresponding to the greenhouse gas fluxes of multiple reservoirs; determine an accounting data set according to the greenhouse gas database, multiple in-situ gas concentration observation data, and multiple in-situ gas flux observation data; a model unit 904, configured to establish a random forest model of predictors and greenhouse gas concentrations according to the accounting data set in combination with the random forest algorithm; a prediction unit 906, configured to predict the greenhouse gas concentrations of multiple reservoirs according to the random forest model; calculate the gas exchange coefficient when the Schmidt constant is equal to 600 under standard conditions according to the thin film boundary layer theory; predict the gas exchange coefficient through the random forest model to determine the predicted gas exchange coefficient; a determination unit 908, configured to determine the reservoir greenhouse gas diffusion flux according to the greenhouse gas concentration and the predicted gas exchange coefficient; determine the reservoir greenhouse gas emissions according to the reservoir greenhouse gas diffusion flux and the area of the reservoir, and determine the total emissions corresponding to multiple reservoirs according to the reservoir greenhouse gas emissions; determine the greenhouse gas footprint before impoundment of each reservoir according to the accounting data set; an accounting unit 910, configured to determine the greenhouse gas net emissions of each reservoir according to the total emissions after impoundment and the greenhouse gas footprint before impoundment.

[0081] In some embodiments, optionally, the model unit 904 is further configured to: construct an initial model for the greenhouse gas concentration based on the accounting data set; divide the multiple data in the accounting data set into intervals to determine a first interval and a second interval, where the first interval is greater than the second interval; determine the data within the first interval in the accounting data set as valid data; divide the valid data into a training set and a test set, where the number of data in the training set is greater than the number of data in the test set; train the initial model based on the training set and the predictors to determine a random forest model; wherein, the first model result of the random forest model is determined by constructing a parameter network and combining cross-validation; the test set is characterized by the coefficient of determination and the root mean square error, and the characterized result is used to determine the prediction performance of the random forest model.

[0082] In some embodiments, optionally, the accounting unit 910 is further configured to: determine the reservoir area and soil climate type of each reservoir; determine the area of each soil climate type according to the soil climate type and the reservoir area; determine the greenhouse gas emission factor corresponding to the soil climate type; determine the greenhouse gas balance according to the reservoir area, the area of the soil climate type, and the greenhouse gas emission factor corresponding to the soil climate type.

[0083] By using the greenhouse gas emission accounting device 900 provided by the present invention to implement the greenhouse gas emission accounting method, through the methods of integrating multi-source data, machine learning modeling, and dual accounting benchmarks, the net greenhouse gas emissions before and after reservoir construction within a regional scope are accurately quantified. The data sources are covered globally. Through the random forest model combined with multi-dimensional predictors, the non-linear mechanism of greenhouse gas generation is captured, and the greenhouse gas emissions are predicted from multiple aspects, avoiding the uncertainty of greenhouse gas accounting caused by extrapolation based on the average value, and improving the robustness of reservoir greenhouse gas emission accounting.

[0084] As Figure 6 shown, the embodiment of the present application further provides an electronic device 1000, including a processor 1110, a memory 1109, a program or instruction stored on the memory 1109 and executable on the processor 1110. When the program or instruction is executed by the processor 1110, it implements each process of the embodiment of the above greenhouse gas emission accounting method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0085] Optionally, the processor 1110 is configured to obtain a greenhouse gas database, in-situ gas concentration observation data of greenhouse gas concentrations corresponding to multiple reservoirs, and in-situ gas flux observation data of greenhouse gas fluxes corresponding to multiple reservoirs. Optionally, the processor 1110 is further configured to determine an accounting data set according to the greenhouse gas database, multiple in-situ gas concentration observation data, and multiple in-situ gas flux observation data. Optionally, the processor 1110 is further configured to establish a random forest model of the predictor and the greenhouse gas concentration according to the accounting data set in combination with the random forest algorithm; Optionally, the processor 1110 is further configured to predict the greenhouse gas concentrations of multiple reservoirs according to the random forest model; Optionally, the processor 1110 is further configured to calculate the gas exchange coefficient when the Schmidt constant is equal to 600 under standard conditions according to the thin film boundary layer theory; predict the gas exchange coefficient through the random forest model to determine the predicted gas exchange coefficient; Optionally, the processor 1110 is further configured to determine the greenhouse gas diffusion flux of the reservoir according to the greenhouse gas concentration and the predicted gas exchange coefficient; determine the greenhouse gas emissions of the reservoir according to the greenhouse gas diffusion flux of the reservoir and the area of the reservoir, and determine the total emissions corresponding to multiple reservoirs according to the greenhouse gas emissions of the reservoir; determine the greenhouse gas footprint before impoundment of each reservoir according to the accounting data set; Optionally, the processor 1110 is further configured to determine the net greenhouse gas emissions of each reservoir according to the total emissions after impoundment and the greenhouse gas footprint before impoundment.

[0086] The memory 1109 can be used to store software programs and various data. The memory 1109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1109 may include a volatile memory or a non-volatile memory, or the memory 1109 may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synch link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory 1109 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memories.

[0087] In the present invention, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance; the term "plural" means two or more, unless otherwise clearly defined. Terms such as "installed", "connected", "connected to", and "fixed" should all be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0088] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "front", "rear", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or unit referred to must have a specific direction, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0089] In the description of this specification, the description of terms such as "one embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or instance. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0090] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for accounting greenhouse gas emissions, characterized in that, Including: Obtaining a greenhouse gas database, in-situ gas concentration observation data corresponding to the greenhouse gas concentrations of multiple reservoirs, and in-situ gas flux observation data corresponding to the greenhouse gas fluxes of multiple said reservoirs; Determining an accounting data set based on the greenhouse gas database, multiple said in-situ gas concentration observation data, and multiple said in-situ gas flux observation data; Establishing a random forest model of prediction factors and greenhouse gas concentration based on the accounting data set in combination with the random forest algorithm; Predicting the greenhouse gas concentrations of multiple said reservoirs according to the random forest model; Calculating the gas exchange coefficient when the Schmidt constant is equal to 600 under standard conditions according to the thin film boundary layer theory; Predicting the gas exchange coefficient through the random forest model to determine the predicted gas exchange coefficient; Determining the reservoir greenhouse gas diffusion flux based on the greenhouse gas concentration and the predicted gas exchange coefficient; Determining the reservoir greenhouse gas emissions based on the reservoir greenhouse gas diffusion flux and the area of the reservoir, and determining the total emissions corresponding to multiple said reservoirs according to the reservoir greenhouse gas emissions; Determining the pre-impoundment greenhouse gas footprint of each said reservoir according to the accounting data set; Determining the greenhouse gas net emissions of each said reservoir according to the total emissions after impoundment and the pre-impoundment greenhouse gas footprint.

2. The accounting method for greenhouse gas emissions according to claim 1, wherein The accounting data set includes a multi-dimensional feature matrix, the multi-dimensional feature matrix includes reservoir characteristic factors, climate characteristic factors, basin environment factors, and socio-economic factors, and the reservoir characteristic factors, the climate characteristic factors, the basin environment factors, and the socio-economic factors are prediction factors.

3. The accounting method for greenhouse gas emissions according to claim 2, characterized in that, The establishing a random forest model of prediction factors and greenhouse gas concentration based on the accounting data set in combination with the random forest algorithm includes: Constructing an initial model for the greenhouse gas concentration based on the accounting data set; Dividing multiple data in the accounting data set into intervals to determine a first interval and a second interval, the first interval being larger than the second interval; Determining the data within the first interval in the accounting data set as valid data; Dividing the valid data into a training set and a test set, the number of data in the training set being larger than the number of data in the test set; Training the initial model according to the training set and the prediction factors to determine the random forest model; Wherein, a first model result of the random forest model is determined by constructing a parameter network and combining cross-validation; The test set is characterized by the coefficient of determination and the root mean square error, and the characterized result is used to determine the prediction performance of the random forest model.

4. The accounting method for greenhouse gas emissions according to claim 1, wherein The determining the pre-impoundment greenhouse gas footprint of each said reservoir according to the accounting data set includes: Determining the land cover sub-units of each said reservoir; Determining the surface area of the land cover sub-units; Determining the greenhouse gas emission coefficient of each said reservoir before impoundment according to the accounting data set; Determining the pre-impoundment greenhouse gas footprint of the reservoir according to the greenhouse gas emission coefficient and the surface area.

5. The accounting method for greenhouse gas emissions according to claim 4, wherein After the determining the greenhouse gas net emissions of each said reservoir according to the total emissions after impoundment and the pre-impoundment greenhouse gas footprint, it further includes: Determine the reservoir area and soil climate type of each of the said reservoirs; Determine the area of each soil climate type based on the said soil climate type and the reservoir area; Determine the greenhouse gas emission factor corresponding to the said soil climate type; Determine the greenhouse gas balance amount based on the reservoir area, the area of each soil climate type, and the greenhouse gas emission factor corresponding to the said soil climate type.

6. The accounting method for greenhouse gas emissions according to any one of claims 1 to 5, characterized in that The said accounting data set further includes: The geospatial coordinates, time metadata, and time resolution of the sampling points corresponding to each of the said reservoirs.

7. An accounting device for greenhouse gas emissions, characterized in that, It includes: A data unit for obtaining a greenhouse gas database, in-situ gas concentration observation data of greenhouse gas concentrations corresponding to multiple reservoirs, and in-situ gas flux observation data of greenhouse gas fluxes corresponding to multiple of the said reservoirs; determining an accounting data set based on the greenhouse gas database, multiple of the said in-situ gas concentration observation data, and multiple of the said in-situ gas flux observation data; A model unit for establishing a random forest model of a predictor and a greenhouse gas concentration based on the said accounting data set in combination with a random forest algorithm; A prediction unit for predicting the greenhouse gas concentrations of multiple of the said reservoirs according to the said random forest model; calculating a gas exchange coefficient when the Schmidt constant is equal to 600 under standard conditions according to the thin film boundary layer theory; predicting the gas exchange coefficient through the said random forest model to determine a predicted gas exchange coefficient; A determination unit for determining the reservoir greenhouse gas diffusion flux based on the said greenhouse gas concentration and the predicted gas exchange coefficient; determining the reservoir greenhouse gas emissions based on the reservoir greenhouse gas diffusion flux and the area of the reservoir, and determining the total emissions corresponding to multiple of the said reservoirs based on the reservoir greenhouse gas emissions; determining the greenhouse gas footprint before water storage of each of the said reservoirs according to the said accounting data set; An accounting unit for determining the net greenhouse gas emissions of each of the said reservoirs based on the total emissions after water storage and the greenhouse gas footprint before water storage.

8. The accounting device for greenhouse gas emissions according to claim 7, wherein The said model unit is further used for: Constructing an initial model for the greenhouse gas concentration based on the said accounting data set; Dividing multiple data in the said accounting data set into intervals to determine a first interval and a second interval, where the first interval is greater than the second interval; Determining the data within the first interval in the said accounting data set as valid data; Dividing the said valid data into a training set and a test set, where the number of data in the training set is greater than the number of data in the test set; Training the said initial model according to the training set and the predictor to determine a random forest model; Among them, a first model result of the said random forest model is determined by constructing a parameter network and combining cross-validation; The said test set is characterized by a coefficient of determination and a root mean square error, and the characterized result is used to determine the prediction performance of the said random forest model.

9. The accounting device for greenhouse gas emissions according to claim 7, characterized in that, The said accounting unit is further used for: Determine the reservoir area and soil climate type of each of the said reservoirs; Determine the area of each soil climate type based on the said soil climate type and the reservoir area; Determine the greenhouse gas emission factor corresponding to the said soil climate type; Determine the greenhouse gas balance according to the reservoir area, the area of the soil climate type, and the greenhouse gas emission coefficient corresponding to the soil climate type.

10. An electronic device, characterized in that, It includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it realizes the steps of the greenhouse gas emission accounting method according to any one of claims 1 to 6.

Images