Urban and rural greenhouse gas emission simulation method based on space-air-ground integration, simulator, terminal and readable storage medium

Abstract

The invention discloses an urban and rural greenhouse gas emission simulation method based on space-air-ground integration, a simulator, a terminal and a readable storage medium, and the method comprises the steps: obtaining a historical emission list, landform information and a meteorological mode, and obtaining a simulation three-dimensional concentration field based on an atmospheric diffusion model according to the emission list, the landform information and the meteorological mode; constructing a data inversion model according to the historical emission list, the landform information, the meteorological mode and the simulated three-dimensional concentration field; and a simulator is constructed and used for obtaining a current emission list according to the current three-dimensional concentration field of the target area, forming an initial emission reduction strategy according to the current emission list, generating emission lists and concentration fields of different initial emission reduction strategies, and selecting the emission list of the optimal emission reduction strategy according to the emission reduction requirement of the future scene target. By constructing the data inversion model and the simulator, efficient monitoring of the urban and rural greenhouse gas emission situation and reliable evaluation of the emission reduction strategy effect are achieved.

Description

Technical Field

[0001] The present invention relates to the field of environmental science and engineering technology, and in particular to a method, simulator, terminal and readable storage medium for simulating urban and rural greenhouse gas emissions based on air-ground integration. Background Art

[0002] Nowadays, urban and rural areas have become hotspots for greenhouse gas emissions. How to reduce greenhouse gas emissions while maintaining high-quality development has become an important issue facing sustainable urban and rural development. In order to formulate accurate, reasonable and targeted greenhouse gas emission reduction strategies, it is necessary to monitor the status of greenhouse gas emissions in different urban and rural sectors in real time and accurately, and then identify hotspots for production, emission and sink.

[0003] At present, the relevant technologies for greenhouse gas emission assessment mainly include ground measurement methods, satellite remote sensing and other methods. Among them, the ground measurement method can go deep into different urban and rural areas, near the emission source, through field sampling combined with offline analysis or online analysis and other technical means to achieve accurate accounting of greenhouse gases. However, the ground measurement method has high labor costs and limited coverage, and is mostly used for timed monitoring of discrete points. For this reason, with the rapid development of satellite remote sensing technology, based on satellite-borne sensors, existing technologies have realized convenient space-based monitoring of greenhouse gases. However, the existing satellite remote sensing products have limited temporal and spatial resolution, and it is difficult to meet the needs of high-precision assessment of urban and rural greenhouse gases.

[0004] In summary, existing technologies lack an integrated air-ground-urban greenhouse gas emissions monitoring method. In addition, existing applications mostly focus on emission monitoring and evaluation, lacking a comprehensive evaluation and selection of potential emission reduction strategies from a future perspective. Summary of the invention

[0005] The purpose of the present invention is to provide a method, system, terminal and readable storage medium for simulating urban and rural greenhouse gas emissions based on the integration of air, space and land, so as to realize efficient monitoring of the current status of urban and rural greenhouse gas emissions and reliable evaluation and selection of the effects of emission reduction strategies.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows: The present invention provides a method for simulating urban and rural greenhouse gas emissions based on air-ground-land integration, and the method for simulating urban and rural greenhouse gas emissions based on air-ground-land integration includes: Obtaining historical emission inventories, geomorphic information, and meteorological models, and obtaining a simulated three-dimensional concentration field based on the emission inventories, geomorphic information, and meteorological models based on an atmospheric diffusion model; constructing a data inversion model according to the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field; The data inversion model, the future scenario module and the emission reduction strategy module are coupled to construct a simulator, wherein the future scenario module is used to form future scenario targets, and the emission reduction strategy module is used to form an initial emission reduction strategy based on the current emission inventory. The simulator is used to obtain the current emission inventory based on the current three-dimensional concentration field of the target area, form an initial emission reduction strategy based on the current emission inventory, generate emission inventories and concentration fields for different initial emission reduction strategies, and select the best emission reduction strategy based on the emission reduction requirements of the future scenario targets.

[0007] Furthermore, the constructing of a data inversion model according to the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field specifically includes: Using the historical emission inventory, geomorphic information, meteorological model and the simulated three-dimensional concentration field as training data, a forward diffusion module is constructed through deep learning training, which takes the emission inventory, the geomorphic information and the meteorological model as input and the three-dimensional concentration field as output; According to the forward diffusion module, a reverse emission inventory reasoning module is constructed, which takes the target three-dimensional concentration field, the landform information and the meteorological model as inputs and takes the emission inventory corresponding to the target three-dimensional concentration field as output; The reverse emission inventory inference module generates a priori emission inventory, and adopts the forward diffusion module to iteratively correct the priori emission inventory according to the target three-dimensional concentration field, the landform information and the meteorological model, until an emission inventory that meets the conditions is generated and output; Among them, the prior emission inventory is iteratively corrected. In each iteration, the prior emission inventory, geomorphic information and meteorological model are input into the forward diffusion module. According to the concentration difference between the intermediate concentration field output by the forward diffusion module and the target three-dimensional concentration field, the prior emission inventory is iteratively corrected based on the gradient descent algorithm.

[0008] Furthermore, the forward diffusion module includes a first convolutional neural network, a second convolutional neural network and a long short-term memory neural network; The forward diffusion module is constructed by deep learning training using the historical emission inventory, the landform information, the meteorological model and the simulated three-dimensional concentration field as training data, and using the emission inventory, the landform information and the meteorological model as input and the three-dimensional concentration field as output, specifically including: constructing the first convolutional neural network that extracts the spatial patterns of the emission inventory, the geomorphic information, and the meteorological pattern; constructing the LSTM neural network that extracts the temporal patterns of the emission inventory and the meteorological pattern; Constructing the second convolutional neural network for forward mapping from the spatial pattern and the temporal pattern to a three-dimensional concentration field; The forward diffusion module is trained using the historical emission inventory, geomorphic information, meteorological model and the simulated three-dimensional concentration field as training data.

[0009] Furthermore, the current emission inventory is obtained according to the current three-dimensional concentration field of the target area, an initial emission reduction strategy is formed according to the current emission inventory, emission inventories and concentration fields of different initial emission reduction strategies are generated, and the best emission reduction strategy is selected according to the emission reduction requirements of future scenario targets, specifically including: The simulator obtains the current three-dimensional concentration field of the target area, calls the data inversion model, inputs the current three-dimensional concentration field into the reverse emission inventory reasoning module, obtains the current emission inventory, and visualizes the current emission inventory; The simulator obtains user input and sets different future scenario targets and initial emission reduction strategies according to the input; The simulator calls the future scenario module and the emission reduction strategy module to form future scenario targets and initial emission reduction strategies, and calculates the initial emission inventory of the initial emission reduction strategy based on the emission factor method; The simulator calls the forward diffusion module in the data inversion model, generates initial concentration fields corresponding to different initial emission reduction strategies based on the initial emission inventory, and visualizes the results; The simulator selects the best emission reduction strategy based on the future scenario target by comparing the initial emission inventory and the initial concentration field of different initial emission reduction strategies.

[0010] Furthermore, the obtaining of the current three-dimensional concentration field of the target area specifically includes: Obtain near-source greenhouse gas concentration data, as well as near-ground concentration monitoring data based on drones and regional concentration monitoring data based on satellite remote sensing; The near-source greenhouse gas concentration data, the UAV-based near-ground concentration monitoring data, and the satellite remote sensing-based regional concentration monitoring data are fused to obtain the current three-dimensional concentration field.

[0011] Furthermore, the obtaining of near-source greenhouse gas concentration data specifically includes: Obtain measured data of near-source emission flux; Based on the mechanism model, the near-source greenhouse gas concentration data is obtained according to the near-source emission flux measured data.

[0012] In addition, to achieve the above object, the present invention further provides a simulator, the simulator comprising: An atmospheric diffusion module, for obtaining a historical emission inventory, geomorphic information and meteorological patterns, and obtaining a simulated three-dimensional concentration field based on the emission inventory, geomorphic information and meteorological patterns based on an atmospheric diffusion model; A data inversion module, used to construct a data inversion model based on the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field; Future scenario module, used to form future scenario goals; The emission reduction strategy module is used to form an initial emission reduction strategy based on the current emission inventory; The simulator is coupled with the data inversion model, the future scenario module and the emission reduction strategy module to obtain the current three-dimensional concentration field, and obtain the current emission inventory according to the current three-dimensional concentration field of the target area, form an initial emission reduction strategy according to the current emission inventory, generate emission inventories and concentration fields for different initial emission reduction strategies, and select the best emission reduction strategy according to the emission reduction requirements of the future scenario targets.

[0013] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, which includes: a memory, a processor, and an urban and rural greenhouse gas emission simulation program based on the integration of air, land and sky stored in the memory and run on the processor. When the urban and rural greenhouse gas emission simulation program based on the integration of air, land and sky is executed by the processor, the terminal is controlled to implement the steps of the urban and rural greenhouse gas emission simulation method based on the integration of air, land and sky as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present invention also provides a readable storage medium, which stores an urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land. When the urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land is executed by a processor, the steps of the urban and rural greenhouse gas emission simulation method based on the integration of air, space, and land as described above are implemented.

[0015] The present invention adopts the above technical solution to achieve the following effects: The present invention obtains multi-source monitoring data from the air, space, and ground, and performs data fusion on the multi-source monitoring data to obtain a three-dimensional concentration field, laying a foundation for subsequent utilization. Then, by learning the emission inventory, geomorphic information, meteorological patterns, and the relationship between the three-dimensional concentration field, a mapping relationship between the emission inventory, geomorphic information, meteorological pattern information and the three-dimensional concentration field is established, a data inversion model is constructed, and on this basis, a simulator is constructed for obtaining an emission inventory based on the existing three-dimensional concentration field, formulating an emission reduction strategy based on the emission inventory, and simulating future emission reduction situations, thereby achieving efficient monitoring of the current status of urban and rural greenhouse gas emissions and reliable evaluation of the effectiveness of emission reduction strategies, thereby selecting the best emission reduction strategy and generating an emission inventory. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the steps of a method for simulating urban and rural greenhouse gas emissions based on air-ground integration in a preferred embodiment of the present invention; Figure 2It is a structural schematic diagram of a simulator in a preferred embodiment of the present invention; Figure 3 It is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] Embodiment 1 See also Figure 1 Embodiment 1 of the present application is a method for simulating urban and rural greenhouse gas emissions based on air-ground integration, which specifically includes the following steps: S1. Obtain historical emission inventories, geomorphic information and meteorological models, and obtain a simulated three-dimensional concentration field based on the emission inventories, geomorphic information and meteorological models based on an atmospheric diffusion model.

[0019] This step is to obtain data for subsequent data inversion model training. The data inversion model includes a forward diffusion module, which is a proxy model of the atmospheric diffusion model. Therefore, the training data of the forward diffusion module can come from the simulated data of the atmospheric diffusion model. Using the historical emission inventory or simulated inventory, the landform information and the meteorological model, the atmospheric diffusion model is used to calculate the corresponding simulated three-dimensional concentration field and obtain a large amount of simulated data.

[0020] Step S2: constructing a data inversion model based on the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field.

[0021] Specifically, in this embodiment, the data inversion model is a data inversion model based on deep learning, and the data inversion model includes a forward diffusion module and a reverse emission inventory reasoning module.

[0022] Among them, the forward diffusion module is used to learn the complex relationship between greenhouse gas emission inventory, meteorological model, topographic information and three-dimensional concentration field to establish a forward mapping from emission inventory to three-dimensional concentration field, and the reverse emission inventory reasoning module is used to establish a reverse mapping from three-dimensional concentration field to emission inventory based on the forward mapping established by the forward diffusion module. Specifically, in this implementation, the forward diffusion module is implemented in the form of a deep learning proxy model for building an atmospheric diffusion model (such as CMAQ, WRF-Chem, CALPUFF).

[0023] Specifically, in this embodiment, the forward diffusion module proxy model can be constructed based on the first convolutional neural network, the second convolutional neural network and the long short-term memory neural network, wherein the first convolutional neural network is used for spatial information extraction, specifically for mining the spatial distribution laws of greenhouse gas emission patterns, meteorological patterns, and topographic information; the long short-term memory neural network is used for temporal information extraction, specifically for mining the temporal variation laws of greenhouse gas emission patterns and meteorological patterns; finally, the second convolutional neural network is used to integrate the above information to realize the construction of a three-dimensional concentration field.

[0024] After the structures of the first convolutional neural network, the second convolutional neural network and the long short-term memory neural network are established, the forward diffusion module can be trained using the historical emission inventory, geomorphic information, meteorological model and the training three-dimensional concentration field as training data to adjust the parameters of each network of the forward diffusion module.

[0025] After constructing the forward diffusion module, the reverse emission inventory reasoning module can use the gradient descent algorithm based on the forward diffusion module to realize the reverse mapping from the three-dimensional concentration field to the emission inventory.

[0026] Specifically, a reverse emission inventory reasoning module is constructed based on the forward diffusion module, which takes the target three-dimensional concentration field, the landform information and the meteorological model as input and takes the emission inventory corresponding to the target three-dimensional concentration field as output; The reverse emission inventory inference module generates a priori emission inventory, and adopts the forward diffusion module to iteratively correct the priori emission inventory according to the target three-dimensional concentration field, the landform information and the meteorological model, until an emission inventory that meets the conditions is generated and output; Among them, the prior emission inventory is iteratively corrected. In each iteration, the prior emission inventory, geomorphic information and meteorological model are input into the forward diffusion module. According to the concentration difference between the intermediate concentration field output by the forward diffusion module and the target three-dimensional concentration field, the prior emission inventory is iteratively corrected based on the gradient descent algorithm.

[0027] It is worth noting that in the traditional atmospheric diffusion model, since it is not differentiable, if the traditional atmospheric diffusion model is used as the forward reasoning module, the emission inventory cannot be obtained in reverse through the gradient descent algorithm. To this end, the present invention adopts a forward diffusion module based on deep learning. Since deep learning is differentiable, the emission inventory can be obtained in reverse based on the gradient descent method.

[0028] S3. Couple the data inversion model, future scenario module and emission reduction strategy module to construct a simulator, wherein the future scenario module is used to form future scenario targets, and the emission reduction strategy module is used to form an initial emission reduction strategy based on the current emission inventory. The simulator is used to obtain the current emission inventory based on the current three-dimensional concentration field of the target area, form an initial emission reduction strategy based on the current emission inventory, generate emission inventories and concentration fields for different initial emission reduction strategies, and select the best emission reduction strategy based on the emission reduction requirements of future scenario targets.

[0029] Specifically, the simulator first obtains the current three-dimensional concentration field of the target area. In this embodiment, obtaining the current three-dimensional concentration field refers to obtaining three-dimensional, multi-source monitoring data of the air, space, and land, which includes near-source emission flux measured data, near-ground concentration monitoring data based on drones, and regional concentration monitoring data based on satellite remote sensing.

[0030] Among them, the measured data of near-source emission flux and the near-ground concentration monitoring data based on drones can be obtained based on real-time monitoring or by calling historical monitoring results stored in storage devices. The regional concentration monitoring data based on satellite remote sensing can be downloaded through the Internet public data platform or by calling the satellite remote sensing data acquisition API.

[0031] After acquiring the monitoring data, it is necessary to preprocess the data and then call the data fusion module of the coupling mechanism model and the deep learning model to obtain the current three-dimensional concentration field of the target area. The main purpose of preprocessing the data is to achieve the unification of the storage format of three-dimensional and multi-source monitoring data. Generally speaking, the original near-source emission flux measured data and the near-ground concentration monitoring data based on drones are mostly stored in tabular form, and the regional concentration monitoring data based on satellite remote sensing are mostly stored in the form of geographic information data. To this end, the multi-source data needs to be formatted in a unified manner.

[0032] Specifically, data preprocessing can be performed using geographic information processing software such as ArcGIS or a geographic information processing library based on the Python programming language. Ultimately, all data is converted into NetCDF or GeoTIFF format and stored in a storage device.

[0033] After completing the preprocessing of the data, the data fusion module of the coupling mechanism model and the deep learning model is called to obtain the current three-dimensional concentration field of the target area. Among them, the data fusion module of the coupling mechanism model and the deep learning model mainly includes two processing steps.

[0034] First, the measured data of the near-source emission flux is input into a mechanism model (such as CALPUFF, etc.), and the near-source greenhouse gas concentration data is output.

[0035] Afterwards, the near-source greenhouse gas concentration data, the near-ground concentration monitoring data based on drones, and the regional concentration monitoring data based on satellite remote sensing are input into a fusion model based on deep learning, and the fusion model based on deep learning outputs a three-dimensional concentration field of the area to be analyzed.

[0036] In this embodiment, the deep learning-based fusion model is specifically a convolutional neural network-based fusion model, which is used to output a three-dimensional concentration field with a spatial resolution and height profile set by the user based on the near-source greenhouse gas concentration data of the area to be analyzed, the near-ground concentration monitoring data based on drones, and the regional concentration monitoring data based on satellite remote sensing.

[0037] In this embodiment, the current emission inventory is obtained according to the current three-dimensional concentration field of the target area, an initial emission reduction strategy is formed according to the current emission inventory, emission inventories and concentration fields of different initial emission reduction strategies are generated, and the best emission reduction strategy is selected according to the emission reduction requirements of future scenario targets, specifically including: The simulator calls the data inversion model, inputs the current three-dimensional concentration field into the reverse emission inventory reasoning module, obtains the current emission inventory, and visualizes the current emission inventory; The simulator obtains input settings from the user, and sets different future scenario targets and initial emission reduction strategies according to the input; The simulator calls the future scenario module and the emission reduction strategy module to form future scenario targets and initial emission reduction strategies, and calculates the initial emission inventory of the initial emission reduction strategy based on the emission factor method; The simulator calls the forward diffusion module in the data inversion model, generates initial concentration fields corresponding to different initial emission reduction strategies based on the initial emission inventory, and visualizes the results; The simulator selects the best emission reduction strategy based on the future scenario target by comparing the initial emission inventory and the initial concentration field of different initial emission reduction strategies.

[0038] Embodiment 2 See also Figure 2 Based on the above method, the present invention further provides a simulator 50, the simulator 50 comprising: The atmospheric diffusion module 51 is used to obtain the historical emission inventory, geomorphic information and meteorological model, and obtain the simulated three-dimensional concentration field according to the emission inventory, geomorphic information and meteorological model based on the atmospheric diffusion model; Data inversion 52, for constructing a data inversion model based on the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field; A future scenario module 53, for forming future scenario goals; an emission reduction strategy module 54, for forming an initial emission reduction strategy based on the current emission inventory; The simulator 50 is coupled with the data inversion model, the future scenario module and the emission reduction strategy module to obtain the current three-dimensional concentration field, and obtain the current emission inventory according to the current three-dimensional concentration field of the target area, form an initial emission reduction strategy according to the current emission inventory, generate emission inventories and concentration fields for different initial emission reduction strategies, and select the best emission reduction strategy according to the emission reduction requirements of the future scenario targets.

[0039] Embodiment 3 See also Figure 3 Based on the above method, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 3 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0040] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 20 stores an urban and rural greenhouse gas emission simulation program 40 based on the integration of air, space, and land, which can be executed by the processor 10, thereby realizing the urban and rural greenhouse gas emission simulation program platform based on the integration of air, space, and land in this application.

[0041] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing related programs of the urban and rural greenhouse gas emission simulation program method based on the integration of air, space and land.

[0042] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0043] Embodiment 4 This embodiment provides a storage medium, which stores a readable storage medium that stores an urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land. When the urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land is executed by a processor, the steps of the urban and rural greenhouse gas emission simulation method based on the integration of air, space, and land as described above are implemented.

[0044] To summarize, the present invention obtains multi-source monitoring data from the air, space, and ground, and performs data fusion on the multi-source monitoring data to obtain a three-dimensional concentration field, laying a foundation for subsequent utilization, and then studies the emission inventory, geomorphic information, meteorological patterns, and the relationship between the three-dimensional concentration field, thereby establishing a mapping relationship between the emission inventory, geomorphic information, meteorological pattern information and the three-dimensional concentration field, constructing a data inversion model, and on this basis constructing a simulator that obtains emission inventories based on existing three-dimensional concentration fields, formulates emission reduction strategies based on the emission inventories, and simulates future emission reduction situations, thereby achieving efficient monitoring of the current status of urban and rural greenhouse gas emissions and reliable evaluation of the effectiveness of emission reduction strategies, and then selecting the best emission reduction measurements and generating an emission inventory.

[0045] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0046] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The storage medium can be a memory, a disk, an optical disk, etc.

[0047] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for simulating urban and rural greenhouse gas emissions based on air-ground integration, characterized in that: The urban and rural greenhouse gas emission simulation method based on air-ground integration includes: Obtaining historical emission inventories, geomorphic information, and meteorological models, and obtaining a simulated three-dimensional concentration field based on the emission inventories, geomorphic information, and meteorological models based on an atmospheric diffusion model; constructing a data inversion model according to the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field; The data inversion model, the future scenario module and the emission reduction strategy module are coupled to construct a simulator, wherein the future scenario module is used to form future scenario targets, and the emission reduction strategy module is used to form an initial emission reduction strategy based on the current emission inventory. The simulator is used to obtain the current emission inventory based on the current three-dimensional concentration field of the target area, form an initial emission reduction strategy based on the current emission inventory, generate emission inventories and concentration fields for different initial emission reduction strategies, and select the best emission reduction strategy based on the emission reduction requirements of the future scenario targets.

2. The method for simulating urban and rural greenhouse gas emissions based on air-ground integration according to claim 1 is characterized in that: The constructing of a data inversion model according to the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field specifically includes: Using the historical emission inventory, geomorphic information, meteorological model and the simulated three-dimensional concentration field as training data, a forward diffusion module is constructed through deep learning training, which takes the emission inventory, the geomorphic information and the meteorological model as input and the three-dimensional concentration field as output; According to the forward diffusion module, a reverse emission inventory reasoning module is constructed, which takes the target three-dimensional concentration field, the landform information and the meteorological model as inputs and takes the emission inventory corresponding to the target three-dimensional concentration field as output; The reverse emission inventory inference module generates a priori emission inventory, and adopts the forward diffusion module to iteratively correct the priori emission inventory according to the target three-dimensional concentration field, the landform information and the meteorological model, until an emission inventory that meets the conditions is generated and output; Among them, the prior emission inventory is iteratively corrected. In each iteration, the prior emission inventory, geomorphic information and meteorological model are input into the forward diffusion module. According to the concentration difference between the intermediate concentration field output by the forward diffusion module and the target three-dimensional concentration field, the prior emission inventory is iteratively corrected based on the gradient descent algorithm.

3. The method for simulating urban and rural greenhouse gas emissions based on air-ground integration according to claim 2 is characterized in that: The forward diffusion module includes a first convolutional neural network, a second convolutional neural network and a long short-term memory neural network; The forward diffusion module is constructed by deep learning training using the historical emission inventory, the landform information, the meteorological model and the simulated three-dimensional concentration field as training data, and using the emission inventory, the landform information and the meteorological model as input and the three-dimensional concentration field as output, specifically including: constructing the first convolutional neural network that extracts the spatial patterns of the emission inventory, the geomorphic information, and the meteorological pattern; constructing the LSTM neural network that extracts the temporal patterns of the emission inventory and the meteorological pattern; Constructing the second convolutional neural network for forward mapping from the spatial pattern and the temporal pattern to a three-dimensional concentration field; The forward diffusion module is trained using the historical emission inventory, geomorphic information, meteorological model and the simulated three-dimensional concentration field as training data.

4. The method for simulating urban and rural greenhouse gas emissions based on air-ground integration according to claim 2 is characterized in that: The method of obtaining a current emission inventory according to the current three-dimensional concentration field of the target area, forming an initial emission reduction strategy according to the current emission inventory, generating emission inventories and concentration fields of different initial emission reduction strategies, and selecting the best emission reduction strategy according to the emission reduction requirements of future scenario targets, specifically includes: The simulator obtains the current three-dimensional concentration field of the target area, calls the data inversion model, inputs the current three-dimensional concentration field into the reverse emission inventory reasoning module, obtains the current emission inventory, and visualizes the current emission inventory; The simulator obtains user input and sets different future scenario targets and initial emission reduction strategies according to the input; The simulator calls the future scenario module and the emission reduction strategy module to form future scenario targets and initial emission reduction strategies, and calculates the initial emission inventory of the initial emission reduction strategy based on the emission factor method; The simulator calls the forward diffusion module in the data inversion model, generates initial concentration fields corresponding to different initial emission reduction strategies based on the initial emission inventory, and visualizes the results; The simulator selects the best emission reduction strategy based on the future scenario target by comparing the initial emission inventory and the initial concentration field of different initial emission reduction strategies.

5. The method for simulating urban and rural greenhouse gas emissions based on air-ground integration according to claim 4 is characterized in that: The step of obtaining the current three-dimensional concentration field of the target area specifically includes: Obtain near-source greenhouse gas concentration data, as well as near-ground concentration monitoring data based on drones and regional concentration monitoring data based on satellite remote sensing; The near-source greenhouse gas concentration data, the UAV-based near-ground concentration monitoring data, and the satellite remote sensing-based regional concentration monitoring data are fused to obtain the current three-dimensional concentration field.

6. The method for simulating urban and rural greenhouse gas emissions based on air-ground integration according to claim 5 is characterized in that: The obtaining of near-source greenhouse gas concentration data specifically includes: Obtain measured data of near-source emission flux; Based on the mechanism model, the near-source greenhouse gas concentration data is obtained according to the near-source emission flux measured data.

7. A simulator, characterized in that: The simulator comprises: An atmospheric diffusion module, for obtaining a historical emission inventory, geomorphic information and meteorological patterns, and obtaining a simulated three-dimensional concentration field based on the emission inventory, geomorphic information and meteorological patterns based on an atmospheric diffusion model; A data inversion module, used to construct a data inversion model based on the historical emission inventory, the geomorphic information, the meteorological model and the simulated three-dimensional concentration field; Future scenario module, used to form future scenario goals; The emission reduction strategy module is used to form an initial emission reduction strategy based on the current emission inventory; The simulator is coupled with the data inversion model, the future scenario module and the emission reduction strategy module to obtain the current three-dimensional concentration field, and obtain the current emission inventory according to the current three-dimensional concentration field of the target area, form an initial emission reduction strategy according to the current emission inventory, generate emission inventories and concentration fields for different initial emission reduction strategies, and select the best emission reduction strategy according to the emission reduction requirements of the future scenario targets.

8. A terminal, characterized in that: The terminal includes: a memory, a processor, and an urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land stored in the memory and executable on the processor. When the urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land is executed by the processor, the terminal is controlled to implement the steps of the urban and rural greenhouse gas emission simulation method based on the integration of air, space, and land as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores an urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land. When the urban and rural greenhouse gas emission simulation program based on the integration of air, space, and land is executed by the processor, the steps of the urban and rural greenhouse gas emission simulation method based on the integration of air, space, and land as described in any one of claims 1 to 6 are implemented.

Images