Air pollutant concentration data prediction method, device, equipment and storage medium

Through the fusion of ground and satellite data and the integrated learning of Bayesian neural networks, an atmospheric pollutant concentration data prediction model is generated, which solves the uncertainty problem of atmospheric pollutant concentration data prediction, improves the prediction accuracy, and is green for the city Development provides reliable data support.

CN118425423BActive Publication Date: 2024-11-19JIANGSU ZHONGKE SANKE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410519674.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-28
Publication Date
2024-11-19
Estimated Expiration
2044-04-28

AI Technical Summary

Technical Problem

There is great uncertainty in the prediction of the current atmospheric pollutant concentration data. Due to factors such as meteorology, terrain and pollutant characteristics, the prediction results are inaccurate.

Method used

By matching ground and satellite monitoring data to the space grid field, logistic regression relationships are constructed, data fusion is carried out, and Bayesian neural networks with different network structures and prior distributions are used for integrated learning to generate atmospheric pollutant concentration data. Prediction model to achieve prediction of short-term future concentration data.

Benefits of technology

It effectively reduces the uncertainty of the prediction of atmospheric pollutant concentration data, improves the prediction accuracy, provides reliable data for route planning and high pollution emission tracking, and has good universality and applicability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118425423B_ABST
    Figure CN118425423B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention provides a method, device, equipment and storage medium for predicting atmospheric pollutant concentration data. The method includes: matching the ground-monitored atmospheric pollutant concentration data and meteorological data of the current time period of the target area to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field and a gridded meteorological field; constructing a gridded satellite concentration field according to the logical regression relationship between the ground-monitored atmospheric pollutant concentration data and the satellite-monitored atmospheric pollutant concentration data and the gridded ground concentration field; fusing the gridded ground concentration field with the gridded satellite concentration field to obtain a gridded fused concentration field, and combining it with the gridded meteorological field to obtain a gridded comprehensive data field; inputting the gridded comprehensive data field into the atmospheric pollutant concentration data prediction model to predict the gridded fused concentration field of the target area in the future time period, thereby effectively reducing the uncertainty of the atmospheric pollutant concentration data prediction in the region in the short term.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring technology, and in particular to an atmospheric pollutant concentration data prediction method, device, equipment and storage medium. Background Art

[0002] In order to improve air quality and reduce emissions of air pollutants, the Chinese government has continuously increased its attention to ecological environmental protection and issued a series of management requirements for air pollutants, aiming to promote urban green development through coordinated control of pollution reduction and carbon reduction. At present, air pollutant monitoring is mainly carried out through fixed-point monitoring, radar scanning, and cruise monitoring. Among them, cruise monitoring mainly focuses on the areas around key emission parks to carry out source tracing cruise work. In addition, cruise monitoring can also monitor weak areas of fixed-point monitoring, thereby improving the assessment accuracy of air pollutants in the overall region.

[0003] However, it should be noted that the current route planning requires the regional short-term atmospheric pollutant concentration data as a basis. However, since the atmospheric diffusion process is affected by factors such as meteorology, topography, and the characteristics of pollutants themselves, its mechanism is relatively complex and has the characteristics of nonlinearity and uncertainty. Therefore, the current forecast of regional short-term atmospheric pollutant concentration data has great uncertainty. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, equipment and storage medium for predicting atmospheric pollutant concentration data.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting atmospheric pollutant concentration data, the method comprising:

[0006] Match the ground-based atmospheric pollutant concentration data and meteorological data of the target area in the current time period to the spatial grid field corresponding to the target area to obtain the gridded ground concentration field and gridded meteorological field;

[0007] Based on the logistic regression relationship between the atmospheric pollutant concentration data monitored on the ground and the atmospheric pollutant concentration data monitored by satellite and the gridded ground concentration field, a gridded satellite concentration field is constructed;

[0008] The gridded ground concentration field is merged with the gridded satellite concentration field to obtain the gridded fused concentration field, and the gridded fused concentration field is combined with the gridded meteorological field to obtain the gridded comprehensive data field;

[0009] The gridded comprehensive data field is input into the atmospheric pollutant concentration data prediction model to predict the gridded fused concentration field of the target area in the future time period.

[0010] In some implementations of the first aspect, the method further includes:

[0011] Match the historical ground-based atmospheric pollutant concentration data, historical satellite-based atmospheric pollutant concentration data, and historical meteorological data of the target area to the spatial grid field corresponding to the target area to obtain the historical gridded ground concentration field, historical gridded satellite concentration field, and historical gridded meteorological field;

[0012] Based on the historical gridded ground concentration field and the historical gridded satellite concentration field, the logistic regression relationship between the ground-based atmospheric pollutant concentration data and the satellite-based atmospheric pollutant concentration data was constructed;

[0013] According to the historical gridded ground concentration field, the historical gridded satellite concentration field and the logistic regression relationship, the missing values ​​of the historical gridded ground concentration field and the historical gridded satellite concentration field are filled;

[0014] The historical gridded ground concentration field and the historical gridded satellite concentration field after missing value filling are fused to obtain the historical gridded fused concentration field, and the historical gridded fused concentration field is combined with the historical gridded meteorological field to obtain the historical gridded comprehensive data field;

[0015] Generate datasets based on historical gridded synthetic data fields;

[0016] The data set is used to train the preset machine learning model to obtain the atmospheric pollutant concentration data prediction model.

[0017] In some implementable embodiments of the first aspect, matching the historical ground-monitored atmospheric pollutant concentration data of the target area to the spatial grid field corresponding to the target area to obtain the historical gridded ground concentration field includes:

[0018] The historical ground-based monitoring atmospheric pollutant concentration data of the target area are normalized and spatially interpolated, and the subsequent historical ground-based monitoring atmospheric pollutant concentration data are matched to the spatial grid field corresponding to the target area to obtain the historical gridded ground concentration field.

[0019] In some implementable embodiments of the first aspect, matching historical satellite-monitored atmospheric pollutant concentration data of a target area to a spatial grid field corresponding to the target area to obtain a historical gridded satellite concentration field includes:

[0020] Kriging interpolation and bias correction are performed on the historical satellite monitoring atmospheric pollutant concentration data of the target area, and the subsequent historical satellite monitoring atmospheric pollutant concentration data are matched to the spatial grid field corresponding to the target area to obtain the historical gridded satellite concentration field.

[0021] In some implementable methods of the first aspect, the historical gridded ground concentration field and the historical gridded satellite concentration field after missing value filling are fused to obtain the historical gridded fused concentration field, including:

[0022] For any grid in the spatial grid field, according to the weight of the ground-based atmospheric pollutant concentration data corresponding to the grid and the weight of the satellite-based atmospheric pollutant concentration data, the atmospheric pollutant concentration data corresponding to the grid in the historical gridded ground concentration field after missing value filling and the atmospheric pollutant concentration data corresponding to the grid in the historical gridded satellite concentration field after missing value filling are weighted averaged, and the weighted average result is used as the pollutant concentration fusion data corresponding to the grid;

[0023] According to the pollutant concentration fusion data corresponding to each grid in the spatial grid field, a historical gridded fusion concentration field is constructed.

[0024] In some implementations of the first aspect, the preset machine learning model is an integrated learning architecture, in which the base learners are Bayesian neural networks with multiple different network structures and different prior distributions;

[0025] The preset machine learning model is trained using the data set to obtain the atmospheric pollutant concentration data prediction model, including:

[0026] Divide the data set into training set and test set;

[0027] Train each Bayesian neural network in the integrated learning model according to the training set, and integrate the trained Bayesian neural networks;

[0028] The test set is used to evaluate the performance of the current integrated learning model. If it passes the performance evaluation, the current integrated learning model is determined to be the atmospheric pollutant concentration data prediction model; otherwise, the prior distribution and network structure of each Bayesian neural network are adjusted, and retrained until it passes the performance evaluation.

[0029] In some implementations of the first aspect, the method further includes:

[0030] According to the gridded fusion concentration field of the target area in the future time period, the navigation route of the target area is planned.

[0031] In a second aspect, an embodiment of the present invention provides an atmospheric pollutant concentration data prediction device, the device comprising:

[0032] A matching module is used to match the ground monitoring atmospheric pollutant concentration data and meteorological data of the target area in the current time period to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field and a gridded meteorological field;

[0033] A construction module is used to construct a gridded satellite concentration field based on the logistic regression relationship between the ground-based atmospheric pollutant concentration data and the satellite-based atmospheric pollutant concentration data and the gridded ground concentration field;

[0034] A fusion module is used to fuse the gridded ground concentration field with the gridded satellite concentration field to obtain a gridded fused concentration field, and to combine the gridded fused concentration field with the gridded meteorological field to obtain a gridded comprehensive data field;

[0035] The prediction module is used to input the gridded comprehensive data field into the atmospheric pollutant concentration data prediction model to predict the gridded fusion concentration field of the target area in the future time period.

[0036] In a third aspect, an embodiment of the present invention provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described above.

[0037] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause a computer to execute the method described above.

[0038] In the embodiments of the present invention, effective prediction of short-term future atmospheric pollutant concentration data can be achieved through joint analysis of satellite and ground data, providing a reliable data analysis basis for route planning; at the same time, it provides a reference basis for follow-up tracking and impact assessment of sudden high-pollution emission processes; in addition, the scheme has good universality and can be used to study and evaluate the short-term change trend characteristics of atmospheric pollutants and greenhouse gases.

[0039] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0041] Figure 1 A flow chart of a method for predicting air pollutant concentration data provided by an embodiment of the present invention is shown;

[0042] Figure 2 A structural diagram of an atmospheric pollutant concentration data prediction device provided by an embodiment of the present invention is shown;

[0043] Figure 3A block diagram of an exemplary electronic device capable of implementing an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0046] In response to the problems arising in the background technology, the embodiments of the present invention provide a method, device, equipment and storage medium for predicting atmospheric pollutant concentration data. Specifically, the ground-monitored atmospheric pollutant concentration data and meteorological data of the current time period of the target area are matched to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field and a gridded meteorological field; a gridded satellite concentration field is constructed based on the logical regression relationship between the ground-monitored atmospheric pollutant concentration data and the satellite-monitored atmospheric pollutant concentration data and the gridded ground concentration field; the gridded ground concentration field is fused with the gridded satellite concentration field to obtain a gridded fused concentration field, and the gridded fused concentration field is combined with the gridded meteorological field to obtain a gridded comprehensive data field; the gridded comprehensive data field is input into the atmospheric pollutant concentration data prediction model to predict the gridded fused concentration field of the target area in the future time period. This can effectively reduce the uncertainty of the prediction of atmospheric pollutant concentration data in the region in the short term, thereby improving the accuracy of the prediction and obtaining more reliable prediction results.

[0047] In conjunction with the accompanying drawings, a method, device, equipment and storage medium for predicting air pollutant concentration data provided by the embodiments of the present invention are described in detail through specific embodiments.

[0048] Figure 1 A flow chart of a method for predicting air pollutant concentration data provided by an embodiment of the present invention is shown. Figure 1 As shown, the atmospheric pollutant concentration data prediction method 100 may include the following steps:

[0049] S110, matching the ground-monitored atmospheric pollutant concentration data and meteorological data of the target area in the current time period to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field and a gridded meteorological field.

[0050] Exemplarily, the ground-monitored atmospheric pollutant concentration data of the target area in the current time period can be preprocessed by normalization, spatial interpolation, etc., and the subsequent ground-monitored atmospheric pollutant concentration data can be matched to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field.

[0051] At the same time, the meteorological data of the current time period in the target area can also be preprocessed by normalization, spatial interpolation, etc., and the subsequent meteorological data can be matched to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field.

[0052] It can be understood that the target area mentioned here is the geographical area where atmospheric pollutant concentration data prediction is required, which may be an urban area, suburbs, townships, etc.; the spatial grid field corresponding to the target area is obtained by dividing the target area into grids of specified size (for example, 3km*3km).

[0053] S120, constructing a gridded satellite concentration field according to the logistic regression relationship between the atmospheric pollutant concentration data monitored on the ground and the atmospheric pollutant concentration data monitored by the satellite and the gridded ground concentration field.

[0054] Among them, the logistic regression relationship between the ground-based monitoring atmospheric pollutant concentration data and the satellite-based monitoring atmospheric pollutant concentration data was obtained through logistic regression analysis based on the historical gridded ground concentration field and the historical gridded satellite concentration field.

[0055] S130, fusing the gridded ground concentration field with the gridded satellite concentration field to obtain a gridded fused concentration field, and combining the gridded fused concentration field with the gridded meteorological field to obtain a gridded comprehensive data field.

[0056] Exemplarily, for any grid in the spatial grid field, the atmospheric pollutant concentration data corresponding to the grid in the gridded ground concentration field and the atmospheric pollutant concentration data corresponding to the grid in the gridded satellite concentration field can be weighted averaged according to the weight of the atmospheric pollutant concentration data corresponding to the grid and the weight of the atmospheric pollutant concentration data corresponding to the grid, and the weighted average result is used as the pollutant concentration fusion data corresponding to the grid. Thus, a gridded fusion concentration field is constructed according to the pollutant concentration fusion data corresponding to each grid in the spatial grid field. Then, based on each grid in the spatial grid field, the gridded fusion concentration field is correspondingly combined with the gridded meteorological field to obtain a gridded comprehensive data field.

[0057] S140, inputting the gridded comprehensive data field into the atmospheric pollutant concentration data prediction model to predict the gridded fused concentration field of the target area in the future time period.

[0058] It is worth noting that the atmospheric pollutant concentration data prediction model used here can be pre-trained in the following way:

[0059] (a) The historical ground-based atmospheric pollutant concentration data, historical satellite-based atmospheric pollutant concentration data, and historical meteorological data of the target area are matched to the spatial grid field corresponding to the target area to obtain the historical gridded ground concentration field, historical gridded satellite concentration field, and historical gridded meteorological field.

[0060] In some embodiments, historical ground-monitored atmospheric pollutant concentration data of the target area are normalized and spatially interpolated, and subsequent historical ground-monitored atmospheric pollutant concentration data are matched to the spatial grid field corresponding to the target area to obtain a historical gridded ground concentration field.

[0061] Specifically, the historical ground monitoring atmospheric pollutant concentration data of the target area are normalized so that the original data are converted into a unified scale or range, thereby eliminating the influence of different dimensions and units on data analysis, and further converting the original data into an input format that meets the model requirements. In addition, since ground monitoring sites are usually unevenly distributed and there are missing data, it is necessary to estimate the data values ​​of the missing points through spatial interpolation to construct a complete historical gridded ground concentration field.

[0062] Kriging interpolation and bias correction are performed on the historical satellite monitoring atmospheric pollutant concentration data of the target area, and the subsequent historical satellite monitoring atmospheric pollutant concentration data are matched to the spatial grid field corresponding to the target area to obtain the historical gridded satellite concentration field.

[0063] Specifically, Kriging interpolation is used to fill in missing values ​​or smooth out noise in historical satellite monitoring of atmospheric pollutant concentration data, thereby obtaining a more complete and continuous data set. The satellite data is preliminarily processed through bias correction to make the processed data closer to the true value. Finally, it is matched to the corresponding spatial grid field to obtain the historical gridded satellite concentration field to ensure its continuity and consistency in space.

[0064] The historical meteorological data of the target area are normalized and spatially interpolated, and the subsequent historical meteorological data are matched to the spatial grid field corresponding to the target area to obtain the historical gridded meteorological field.

[0065] For details, please refer to the construction of the historical gridded ground concentration field above, which will not be elaborated here.

[0066] (b) Logistic regression analysis was performed based on the historical gridded ground concentration field and the historical gridded satellite concentration field to construct the logistic regression relationship between the ground-based monitoring atmospheric pollutant concentration data and the satellite-based monitoring atmospheric pollutant concentration data.

[0067] (c) Based on the historical gridded ground concentration field, the historical gridded satellite concentration field and the logistic regression relationship, the missing values ​​of the historical gridded ground concentration field and the historical gridded satellite concentration field are filled.

[0068] That is to say, the concentration fields in areas with sparse ground monitoring stations and satellite monitoring are corrected.

[0069] (d) The historical gridded ground concentration field and the historical gridded satellite concentration field after missing value filling are fused to obtain the historical gridded fused concentration field, and the historical gridded fused concentration field is combined with the historical gridded meteorological field to obtain the historical gridded comprehensive data field.

[0070] In some embodiments, for any grid in the spatial grid field, according to the weight of the atmospheric pollutant concentration data of ground monitoring corresponding to the grid and the weight of the atmospheric pollutant concentration data of satellite monitoring, the atmospheric pollutant concentration data corresponding to the grid in the historical gridded ground concentration field after missing value filling and the atmospheric pollutant concentration data corresponding to the grid in the historical gridded satellite concentration field after missing value filling are weighted averaged, and the weighted average result is used as the pollutant concentration fusion data corresponding to the grid. Thus, according to the pollutant concentration fusion data corresponding to each grid in the spatial grid field, a historical gridded fusion concentration field is constructed. Then, based on each grid in the spatial grid field, the historical gridded fusion concentration field is correspondingly combined with the historical gridded meteorological field to obtain a historical gridded comprehensive data field.

[0071] It is worth noting that the weights of the ground-based monitoring atmospheric pollutant concentration data and the satellite-based monitoring atmospheric pollutant concentration data corresponding to each grid in the spatial grid field are determined based on the characteristics of the data, spatial distribution, and analysis objectives, and are allocated by constructing a weight matrix.

[0072] (e) Generate datasets based on historical gridded comprehensive data fields.

[0073] (f) The preset machine learning model is trained using the data set to obtain an atmospheric pollutant concentration data prediction model.

[0074] In some embodiments, the preset machine learning model is an integrated learning architecture, in which the base learners are Bayesian neural networks with multiple different network structures and different prior distributions.

[0075] The data set can be divided into a training set and a test set. The Bayesian neural networks in the integrated learning model are trained according to the training set, and the trained Bayesian neural networks are integrated. The performance of the current integrated learning model is evaluated using the test set. If the performance evaluation is passed, the current integrated learning model is determined to be the atmospheric pollutant concentration data prediction model; otherwise, the prior distribution and network structure of each Bayesian neural network are adjusted, and retrained until the performance evaluation is passed. Specifically, the above process can be as follows:

[0076] (1) Define the network structure and parameter initialization: Define the number of layers of the Bayesian neural network, the number of neurons in each layer, and the activation function. Assign initial weights and biases to each neuron in the network. These parameters will be continuously updated during the training process.

[0077] (2) Introducing prior distribution: In order to improve the generalization ability and stability of the model, Gaussian distribution is introduced as the prior distribution of network parameters (weights and biases), and the corresponding parameters are adjusted according to the data quality.

[0078] (3) Introducing multi-fidelity: By introducing multiple independent Bayesian neural networks, each with a different structure or parameter setting, these networks can be trained on the same dataset to obtain different prediction results.

[0079] (4) Training the network: Input the training set and use the Bayesian inference method to train each network. During the training process, adjust the network parameters according to the actual situation so that the model can better fit the training data.

[0080] (5) Ensemble network: Multiple trained Bayesian neural networks can obtain different prediction results. Ensemble learning methods are used to integrate the prediction results, that is, to integrate the Bayesian neural networks.

[0081] (6) Evaluate the model: Use a validation set or a test set to evaluate the performance of the ensemble model and assess the accuracy of the calculated predictions as well as the model prediction uncertainty.

[0082] (7) Adjusting the prior distribution and network structure: According to the performance of the model on the test set, adjust the parameters of the prior distribution and the network structure. Through repeated training and adjustment of the prior distribution and network structure, until the performance of the model on the test set reaches a satisfactory level, the model is used as the prediction model for atmospheric pollutant concentration data.

[0083] According to the embodiments of the present invention, at least the following technical effects are achieved:

[0084] Through the joint analysis of satellite and ground data combined with a multi-fidelity trained Bayesian neural network, effective prediction of short-term future atmospheric pollutant concentration data can be achieved, providing a reliable data basis for route planning; at the same time, it provides a reference for follow-up tracking and impact assessment of sudden high-pollution emission processes; in addition, this scheme has good universality and can be used to study and evaluate the short-term trend characteristics of atmospheric pollutants and greenhouse gases.

[0085] It is worth noting that the atmospheric pollutant concentration data prediction model can be deployed on the cruising platform, and the cruising platform predicts the atmospheric pollutant concentration data based on the prediction model.

[0086] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0087] The above is an introduction to a method embodiment. The following is a further explanation of the solution of the present invention through an apparatus embodiment.

[0088] Figure 2 FIG. 4 shows a structural diagram of an atmospheric pollutant concentration data prediction device provided by an embodiment of the present invention. Figure 2 As shown, the atmospheric pollutant concentration data prediction device 200 may include:

[0089] A matching module 210 is used to match the ground monitoring atmospheric pollutant concentration data and meteorological data of the target area in the current time period to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field and a gridded meteorological field;

[0090] A construction module 220 is used to construct a gridded satellite concentration field according to the logistic regression relationship between the ground-monitored atmospheric pollutant concentration data and the satellite-monitored atmospheric pollutant concentration data and the gridded ground concentration field;

[0091] A fusion module 230 is used to fuse the gridded ground concentration field with the gridded satellite concentration field to obtain a gridded fused concentration field, and to combine the gridded fused concentration field with the gridded meteorological field to obtain a gridded comprehensive data field;

[0092] The prediction module 240 is used to input the gridded comprehensive data field into the atmospheric pollutant concentration data prediction model to predict the gridded fusion concentration field of the target area in the future time period.

[0093] Understandably, Figure 2 Each module / unit in the atmospheric pollutant concentration data prediction device 200 has the following functions: Figure 1 The functions of the various steps in the atmospheric pollutant concentration data prediction method 100 shown in the figure can achieve their corresponding technical effects, and for the sake of brevity, they will not be repeated here.

[0094] Figure 3 A block diagram of an exemplary electronic device capable of implementing an embodiment of the present invention is shown. Electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0095] like Figure 3 As shown, the electronic device 300 may include a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 may also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0096] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0097] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer program product, including a computer program, which is tangibly contained in a computer-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0098] The various embodiments described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs, which may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general programmable processor, which may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of the present invention, a computer-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a computer-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] It should be noted that the present invention also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by the embodiments of the present invention executing the method. For the sake of concise description, they are not repeated here.

[0102] In addition, the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method 100 is implemented.

[0103] To provide interaction with a user, the above-described embodiments may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0104] The embodiments described above can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0105] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0106] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0107] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting atmospheric pollutant concentration data, characterized in that: The method comprises: Matching the ground-based atmospheric pollutant concentration data and meteorological data of the target area in the current time period to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field and a gridded meteorological field; Constructing a gridded satellite concentration field based on the logistic regression relationship between the ground-based atmospheric pollutant concentration data and the satellite-based atmospheric pollutant concentration data and the gridded ground concentration field; The gridded ground concentration field is merged with the gridded satellite concentration field to obtain a gridded fused concentration field, and the gridded fused concentration field is combined with the gridded meteorological field to obtain a gridded comprehensive data field; Inputting the gridded comprehensive data field into the atmospheric pollutant concentration data prediction model to predict the gridded fusion concentration field of the target area in the future time period; The method further comprises: Matching the historical ground-based atmospheric pollutant concentration data, historical satellite-based atmospheric pollutant concentration data, and historical meteorological data of the target area to the spatial grid field corresponding to the target area to obtain the historical gridded ground concentration field, the historical gridded satellite concentration field, and the historical gridded meteorological field; Constructing a logistic regression relationship between ground-based atmospheric pollutant concentration data and satellite-based atmospheric pollutant concentration data based on the historical gridded ground concentration field and the historical gridded satellite concentration field; Filling missing values ​​of the historical gridded ground concentration field and the historical gridded satellite concentration field according to the historical gridded ground concentration field, the historical gridded satellite concentration field and the logistic regression relationship; The historical gridded ground concentration field and the historical gridded satellite concentration field after missing value filling are fused to obtain a historical gridded fused concentration field, and the historical gridded fused concentration field is combined with the historical gridded meteorological field to obtain a historical gridded comprehensive data field; generating a data set based on the historical gridded synthetic data field; The data set is used to train a preset machine learning model to obtain an atmospheric pollutant concentration data prediction model; The step of matching the historical ground-based monitoring atmospheric pollutant concentration data of the target area to the spatial grid field corresponding to the target area to obtain the historical gridded ground concentration field includes: Normalizing and spatially interpolating the historical ground-monitored atmospheric pollutant concentration data of the target area, and matching the subsequent historical ground-monitored atmospheric pollutant concentration data to the spatial grid field corresponding to the target area to obtain a historical gridded ground concentration field; The step of matching the historical satellite-monitored atmospheric pollutant concentration data of the target area to the spatial grid field corresponding to the target area to obtain the historical gridded satellite concentration field includes: Performing Kriging interpolation and deviation correction on the historical satellite monitoring atmospheric pollutant concentration data of the target area, and matching the subsequent historical satellite monitoring atmospheric pollutant concentration data to the spatial grid field corresponding to the target area, to obtain a historical gridded satellite concentration field; The preset machine learning model is an integrated learning architecture, in which the base learners are Bayesian neural networks with multiple different network structures and different prior distributions; The method of using the data set to train the preset machine learning model to obtain the atmospheric pollutant concentration data prediction model includes: Dividing the data set into a training set and a test set; Training each Bayesian neural network in the integrated learning model according to the training set, and integrating the trained Bayesian neural networks; The test set is used to perform performance evaluation on the current integrated learning model. If the performance evaluation is passed, the current integrated learning model is determined to be an atmospheric pollutant concentration data prediction model; otherwise, the prior distribution and network structure of each Bayesian neural network are adjusted, and retrained until the performance evaluation is passed.

2. The method according to claim 1, characterized in that The historical gridded ground concentration field and the historical gridded satellite concentration field after missing value filling are fused to obtain the historical gridded fused concentration field, including: For any grid in the spatial grid field, according to the weight of the ground-based atmospheric pollutant concentration data corresponding to the grid and the weight of the satellite-based atmospheric pollutant concentration data, weighted average is performed on the atmospheric pollutant concentration data corresponding to the grid in the historical gridded ground concentration field after missing value filling and the atmospheric pollutant concentration data corresponding to the grid in the historical gridded satellite concentration field after missing value filling, and the weighted average result is used as the pollutant concentration fusion data corresponding to the grid; According to the pollutant concentration fusion data corresponding to each grid in the spatial grid field, a historical gridded fusion concentration field is constructed.

3. The method according to claim 1, characterized in that The method further comprises: A navigation route is planned for the target area according to the gridded fused concentration field of the target area in the future time period.

4. An atmospheric pollutant concentration data prediction device, characterized in that: The device is used to perform the method according to any one of claims 1 to 3, comprising: A matching module is used to match the ground monitoring atmospheric pollutant concentration data and meteorological data of the target area in the current time period to the spatial grid field corresponding to the target area to obtain a gridded ground concentration field and a gridded meteorological field; A construction module, for constructing a gridded satellite concentration field according to the logistic regression relationship between the ground-monitored atmospheric pollutant concentration data and the satellite-monitored atmospheric pollutant concentration data and the gridded ground concentration field; A fusion module, used for fusing the gridded ground concentration field with the gridded satellite concentration field to obtain a gridded fused concentration field, and combining the gridded fused concentration field with the gridded meteorological field to obtain a gridded comprehensive data field; The prediction module is used to input the gridded comprehensive data field into the atmospheric pollutant concentration data prediction model to predict the gridded fusion concentration field of the target area in the future time period.

5. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 3.