A pollen emission and concentration simulation system and method

Abstract

The application discloses a pollen emission and concentration simulation system and method, which aims to solve the problem of low accuracy of pollen emission and concentration simulation. The system receives a pollen emission and concentration simulation request sent by a terminal, predicts the total pollen emission yield of the to-be-observed vegetation at a specified observation station in a pollen emission period according to obtained meteorological observation data of the specified observation station on each day of the pollen emission period and a pollen yield prediction model, determines a pollen emission potential capacity value of the tth day according to a temperature cumulative amount of the tth day of the pollen emission period, a pollen start period accumulated temperature threshold value, a pollen end period accumulated temperature threshold value, a number of days of the pollen emission period and a standardized pollen emission potential model, determines a pollen emission amount of the tth day according to the total pollen emission yield and the pollen emission potential capacity value of the tth day, determines a target pollen emission amount of the tth day according to the pollen emission amount of the tth day and meteorological factors of the tth day, and simulates the pollen emission and concentration of each day of the pollen emission period.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pollen emission concentration analysis, and particularly relates to a pollen emission and concentration simulation system and method. BACKGROUND

[0002] Pollen emission and concentration simulation plays an important role in the fields of environmental science and public health, especially in seasons with high incidence of allergies, and tree pollen is an important source and inducement of spring allergies. Simulation of tree pollen emission and concentration has an important guiding role for personal health management and the formulation of public health policies. Moreover, simulation of pollen emission and concentration has important significance for the study of the characteristics of different species of vegetation in the field of environmental science.

[0003] At present, pollen emission and concentration simulation is mainly based on traditional statistical methods, and uses historical observation data to perform regression analysis by using a simple linear regression model to simulate tree pollen emission and concentration. However, due to the simple structure of the linear regression model, it is difficult to capture the complex nonlinear relationship between pollen emission and concentration and other influencing factors (such as environmental factors), resulting in low accuracy of the simulation results of pollen emission and concentration.

[0004] Therefore, how to improve the accuracy of pollen emission and pollen concentration simulation is one of the technical problems to be solved in the prior art. SUMMARY

[0005] In order to solve the problem of low accuracy of pollen emission and concentration simulation, the embodiments of the present application provide a pollen emission and concentration simulation system and method.

[0006] In a first aspect, the embodiments of the present application provide a pollen emission and concentration simulation system, comprising:

[0007] A communication module, configured to receive a pollen emission and concentration simulation request sent by a terminal, wherein the pollen emission and concentration simulation request carries to-be-observed vegetation information, specified observation site information, and year information of a requested simulation;

[0008] A collection module, configured to obtain meteorological observation data of a specified observation site every day in a pollen emission period of the to-be-observed vegetation according to the year information of the requested simulation;

[0009] a processor configured to predict a total pollen emission amount of the vegetation to be observed at the specified observation site during a pollen emission period according to weather observation data of the specified observation site and a pollen yield prediction model for each day of the pollen emission period of the vegetation to be observed, the pollen yield prediction model being obtained according to historical sample weather observation data of sample observation sites and sample pollen observation data of the vegetation to be observed according to a preset machine learning model; obtain a temperature accumulation amount of a tth day of the pollen emission period, determine a pollen emission potential capacity value of the tth day according to the temperature accumulation amount of the tth day, a pollen start period accumulated temperature threshold value, a pollen end period accumulated temperature threshold value, a number of days of the pollen emission period, and a constructed standardized pollen emission potential model, the standardized pollen emission potential model being used to calculate the pollen emission potential capacity value; determine a pollen emission amount of the tth day according to the total pollen emission amount and the pollen emission potential capacity value of the tth day; obtain a meteorological factor of the tth day, determine a target pollen emission amount of the tth day according to the pollen emission amount of the tth day and the meteorological factor of the tth day, simulate pollen emission and concentration for each day of the pollen emission period, and the target pollen emission amount is a pollen emission amount after adding meteorological disturbance;

[0010] a response module configured to return simulation results of pollen emission and concentration for each day of the pollen emission period to the terminal.

[0011] In a second aspect, an embodiment of the present application provides a pollen emission and concentration simulation method, including:

[0012] receiving a pollen emission and concentration simulation request sent by a terminal, the pollen emission and concentration simulation request carrying vegetation to be observed information, specified observation site information, and year information for which simulation is requested;

[0013] obtaining weather observation data of a specified observation site for each day of a pollen emission period of vegetation to be observed according to the year information for which simulation is requested;

[0014] predicting a total pollen emission amount of the vegetation to be observed at the specified observation site during the pollen emission period according to the weather observation data of the specified observation site and a pollen yield prediction model for each day of the pollen emission period of the vegetation to be observed, the pollen yield prediction model being obtained according to historical sample weather observation data of sample observation sites and sample pollen observation data of the vegetation to be observed according to a preset machine learning model;

[0015] acquire the temperature accumulation of the tth day of the pollen emission period, determine the pollen emission potential value of the tth day according to the temperature accumulation of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, the number of days of the pollen emission period and the constructed standardized pollen emission potential model, the standardized pollen emission potential model being used to calculate the pollen emission potential value;

[0016] determine the pollen emission amount of the tth day according to the total pollen emission yield and the pollen emission potential value of the tth day;

[0017] acquire the meteorological factor of the tth day, determine the target pollen emission amount of the tth day according to the pollen emission amount of the tth day and the meteorological factor of the tth day, simulate the pollen emission and concentration of each day of the pollen emission period, the target pollen emission amount being the pollen emission amount after adding meteorological disturbance;

[0018] return the simulation result of the pollen emission and concentration of each day of the pollen emission period to the terminal.

[0019] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the pollen emission and concentration simulation method when executing the program.

[0020] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the program is executable on a processor to implement the steps of the pollen emission and concentration simulation method.

[0021] The beneficial effects of the present application are as follows:

[0022] The pollen emission and concentration simulation system provided by the embodiments of the present application comprises a communication module, a collection module, a processor and a response module. The communication module is configured to receive a pollen emission and concentration simulation request sent by a terminal, and the pollen emission and concentration simulation request carries to-be-observed vegetation information, specified observation site information and year information for which simulation is requested. The collection module is configured to obtain meteorological observation data of the specified observation site on each day of the pollen emission period of the to-be-observed vegetation according to the year for which simulation is requested. The processor is configured to predict the total pollen emission yield of the to-be-observed vegetation during the pollen emission period according to the meteorological observation data of the specified observation site on each day of the pollen emission period of the to-be-observed vegetation and a pollen yield prediction model. The pollen yield prediction model is obtained according to historical sample meteorological observation data of a sample observation site and sample pollen observation data of the to-be-observed vegetation according to a preset machine learning model. The temperature cumulative amount on the tth day of the pollen emission period is obtained, and the pollen emission potential capacity value on the tth day is determined according to the temperature cumulative amount on the tth day, a pollen start period accumulated temperature threshold value, a pollen end period accumulated temperature threshold value, the number of days of the pollen emission period and a constructed standardized pollen emission potential model. The standardized pollen emission potential model is configured to calculate the pollen emission potential capacity value. The pollen emission amount on the tth day is determined according to the total pollen emission yield and the pollen emission potential capacity value on the tth day. The meteorological factor on the tth day is obtained, and the target pollen emission amount on the tth day is determined according to the pollen emission amount on the tth day and the meteorological factor on the tth day. The pollen emission and concentration on each day of the pollen emission period are simulated, and the target pollen emission amount is the pollen emission amount after adding meteorological disturbance. The response module is configured to return the simulation result of the pollen emission and concentration on each day of the pollen emission period to the terminal.In the embodiments of the present application, when the communication module receives the pollen emission and concentration simulation request sent by the terminal, the vegetation information to be observed, the specified observation site information and the year information for which simulation is requested carried in the pollen emission and concentration simulation request are extracted and sent to the collection module. The collection module obtains the meteorological observation data of each day of the specified observation site in the pollen emission period of the vegetation to be observed corresponding to the year for which simulation is requested. The processor uses the pollen yield prediction model trained in advance based on the machine learning model to predict the total pollen yield of the vegetation to be observed in the pollen emission period. The use of the machine learning model can capture the complex nonlinear relationship (such as the influence of climate, geographical location, year, etc. on pollen yield) in the historical meteorological observation data of the specified observation site, improve the accuracy of the prediction of the total pollen yield, and provide a reliable basis for subsequent determination of the daily pollen emission. After predicting the total pollen yield, the processor combines the set pollen accumulated temperature double threshold (i.e. pollen emission start period accumulated temperature threshold and pollen end period accumulated temperature threshold) and the constructed standardized pollen emission potential model to predict the pollen emission potential value of each day of the vegetation to be observed in its pollen emission period. The pollen accumulated temperature double threshold: start period accumulated temperature threshold and end period accumulated temperature threshold are used as temperature constraints. Compared with a single accumulated temperature threshold, the pollen accumulated temperature double threshold can better adapt to the influence of climate change on the pollen emission potential. The standardized pollen emission potential model constructed based on the pollen accumulated temperature double threshold can accurately simulate the time distribution rule of the pollen emission potential, avoid errors caused by uniform distribution, better match the actual pollen emission curve, and improve the prediction accuracy of the daily pollen emission potential. Furthermore, the processor calculates the daily pollen emission amount according to the total pollen yield of the vegetation to be observed in the pollen emission period and the pollen emission potential value of each day in the pollen emission period. Finally, the target pollen emission amount of each day, i.e. the pollen emission amount after adding meteorological disturbance, is determined by combining the daily pollen emission amount and the corresponding meteorological factors of each day, so as to simulate the pollen emission and concentration of each day in the pollen emission period. By combining the daily pollen emission amount and the meteorological factors to simulate the pollen emission and concentration, the influence of meteorological factors on the pollen emission amount and concentration (such as wind speed which can affect the pollen diffusion speed and diffusion range, precipitation which can inhibit pollen emission and promote settlement, humidity which can affect pollen emission activity and suspension capacity, etc.) is considered. The daily pollen emission amount and environmental diffusion conditions are combined to simulate more accurate daily pollen emission amount and pollen concentration, which provides a more reliable data basis for the analysis and research of spring pollen emission and concentration, and the influence of pollen emission and concentration on health risks (such as pollen allergy).

[0023] Other features and advantages of the present application will be set forth in the following description, and in part will be apparent from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0025] Figure 1 A structure schematic diagram of a pollen emission and concentration simulation system provided by an embodiment of the application;

[0026] Figure 2 A flowchart of a pollen emission and concentration simulation method provided by an embodiment of the application;

[0027] FIG. 3(a) is a scatter plot between predicted and observed pollen emission total production of Cupressaceae and Salicaceae vegetation in the first stage of spring at a certain observation site simulated by a pollen production prediction model corresponding to Cupressaceae and Salicaceae vegetation provided by an embodiment of the application;

[0028] FIG. 3(b) is a scatter plot between predicted and observed pollen emission total production of Pinaceae vegetation in the second stage of spring at a certain observation site simulated by a pollen production prediction model corresponding to Pinaceae vegetation provided by an embodiment of the application;

[0029] Figure 4 A flowchart of determining a pollen emission potential capacity value on the tth day provided by an embodiment of the application;

[0030] Figure 5 A flowchart of determining a pollen cumulative fraction emitted on the tth day from the start time of accumulated temperature to the pollen emission period and a flowering probability on the tth day provided by an embodiment of the application;

[0031] Figure 6 A time series comparison diagram of site average observed and simulated values of pollen emission in spring in a certain city provided by an embodiment of the application;

[0032] FIG. 7(a) is a spatial distribution characteristic diagram of pollen emission in the first stage of spring in a certain city provided by an embodiment of the application;

[0033] FIG. 7(b) is a spatial distribution characteristic diagram of pollen emission in the second stage of spring in a certain city provided by an embodiment of the application;

[0034] Figure 8 A schematic diagram of an architecture of a pollen simulation model provided by an embodiment of the application;

[0035] Figure 9 A potential height distribution diagram of a simulated region provided by an embodiment of the application;

[0036] Figure 10A time series comparison chart of a site average observation value and a simulation value of a pollen concentration in a spring in a certain city based on a WRF-Chem-Pollen model is provided for an embodiment of the present application.

[0037] Figure 11 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to solve the problem of low accuracy of pollen emission and concentration simulation, the present application provides a pollen emission and concentration simulation system and method.

[0039] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings of the specification, it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application, and the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0040] As shown in Figure 1 A structural schematic diagram of a pollen emission and concentration simulation system is provided for an embodiment of the present application, the pollen emission and concentration simulation system 11 comprises:

[0041] The communication module 111 is configured to receive a pollen emission and concentration simulation request sent by the terminal 10, and the pollen emission and concentration simulation request carries to-be-observed vegetation information, specified observation site information and year information requested to be simulated;

[0042] The collection module 112 is configured to obtain meteorological observation data of a specified observation site on each day of a pollen emission period of to-be-observed vegetation according to the year requested to be simulated;

[0043] The processor 113 is configured to predict a total pollen emission yield of to-be-observed vegetation of the specified observation site in the pollen emission period according to the meteorological observation data of the specified observation site on each day of the pollen emission period of the to-be-observed vegetation and a pollen yield prediction model, the pollen yield prediction model is obtained according to historical sample meteorological observation data of a sample observation site and sample pollen observation data of the to-be-observed vegetation according to a preset machine learning model; obtain a temperature cumulative amount of the tth day of the pollen emission period, determine a pollen emission potential capacity value of the tth day according to the temperature cumulative amount of the tth day, a pollen start period accumulated temperature threshold value, a pollen end period accumulated temperature threshold value, a number of days of the pollen emission period and a constructed standardized pollen emission potential model, the standardized pollen emission potential model is used to calculate the pollen emission potential capacity value; determine a pollen emission amount of the tth day according to the total pollen emission yield and the pollen emission potential capacity value of the tth day; obtain a meteorological factor of the tth day, determine a target pollen emission amount of the tth day according to the pollen emission amount of the tth day and the meteorological factor of the tth day, and simulate pollen emission and concentration of each day of the pollen emission period;

[0044] The response module 114 is configured to return simulation results of pollen emission and concentration of each day of the pollen emission period to the terminal.

[0045] In an embodiment, the processor 113 is specifically configured to determine, according to the temperature accumulation amount of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, and the number of days of the pollen emission period, a pollen cumulative score of the observed vegetation emitted from the accumulated temperature start time to the tth day and a flowering probability of the tth day.

[0046] According to the pollen cumulative score emitted from the accumulated temperature start time to the tth day, the flowering probability of the tth day, and the standardized pollen emission potential model, the pollen emission potential value of the tth day is determined.

[0047] In an embodiment, the observed vegetation is divided into at least two categories according to different pollen emission start times, and each category of the observed vegetation corresponds to a different pollen emission period.

[0048] The processor 113 is specifically configured to, for each category of the observed vegetation, determine, according to the temperature accumulation amount of the tth day of the pollen emission period corresponding to the observed vegetation, the pollen start period accumulated temperature threshold, and the pollen end period accumulated temperature threshold, a pollen cumulative score of the observed vegetation emitted from the accumulated temperature start time to the tth day.

[0049] According to the temperature accumulation amount of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, and the number of days of the pollen emission period corresponding to the observed vegetation, the flowering probability of the tth day of the observed vegetation in the corresponding pollen emission period is determined.

[0050] According to the flowering probability of the tth day of the observed vegetation in the corresponding pollen emission period, the flowering probability of the tth day of the observed vegetation in the corresponding pollen emission period is determined.

[0051] In an embodiment, the processor 113 is specifically configured to calculate the pollen cumulative score of the observed vegetation emitted from the accumulated temperature start time to the tth day by the following formula:

[0052]

[0053] wherein, represents the pollen cumulative score of the observed vegetation emitted from the accumulated temperature start time to the tth day of the pollen emission period corresponding to the observed vegetation;

[0054] represents the temperature accumulation amount of the tth day of the pollen emission period corresponding to the observed vegetation, , temperature of the tth day of the corresponding pollen emission period of the vegetation to be observed, preset daily average temperature threshold value;

[0055] pollen start period accumulated temperature threshold value;

[0056] pollen end period accumulated temperature threshold value.

[0057] In an embodiment, the processor 113 is specifically configured to calculate the flowering probability of the vegetation to be observed at the tth day of the corresponding pollen emission period starting from the pollen emission period by the following formula:

[0058]

[0059] wherein, the flowering probability of the vegetation to be observed at the tth day of the corresponding pollen emission period starting from the pollen emission period;

[0060] temperature accumulation of the tth day of the corresponding pollen emission period of the vegetation to be observed, , temperature of the tth day of the corresponding pollen emission period of the vegetation to be observed, preset daily average temperature threshold value, accumulated temperature starting time;

[0061] pollen start period accumulated temperature threshold value;

[0062] relative temperature accumulation tolerance coefficient, used for constructing an over interval of temperature accumulation;

[0063] number of days of the corresponding pollen emission period of the vegetation to be observed, wherein, pollen emission end time of the vegetation to be observed, pollen emission start time of the vegetation to be observed; and

[0064] the flowering probability of the vegetation to be observed at the tth day of the corresponding pollen emission period ending from the pollen emission period is calculated by the following formula:

[0065]

[0066] wherein, the flowering probability of the vegetation to be observed at the tth day of the corresponding pollen emission period ending from the pollen emission period;

[0067] denotes a pollen end period accumulated temperature threshold value; and

[0068] The flowering probability of the to-be-observed vegetation on the t-th day of the corresponding pollen emission period is calculated by the following formula:

[0069]

[0070] wherein, denotes the flowering probability of the to-be-observed vegetation on the t-th day of the corresponding pollen emission period.

[0071] In an embodiment, the processor 113 is specifically configured to calculate the pollen emission potential capability value of the to-be-observed vegetation on the t-th day of the corresponding pollen emission period by the following formula:

[0072]

[0073] wherein, denotes the pollen emission potential capability value of the to-be-observed vegetation on the t-th day of the corresponding pollen emission period;

[0074] denotes the pollen cumulative score of the to-be-observed vegetation emitted from the accumulated temperature starting time to the t-th day of the corresponding pollen emission period of the to-be-observed vegetation;

[0075] denotes the flowering probability of the to-be-observed vegetation on the t-th day of the corresponding pollen emission period;

[0076] denotes the land cover degree of the to-be-observed vegetation;

[0077] denotes a preset scaling factor, the preset scaling factor representing a pollen emission enhancement effect parameter caused by temperature change.

[0078] In an embodiment, the processor 113 is specifically configured to calculate the pollen emission amount of the to-be-observed vegetation on the t-th day of the corresponding pollen emission period by the following formula:

[0079]

[0080] wherein, denotes the pollen emission amount of the to-be-observed vegetation on the t-th day of the corresponding pollen emission period;

[0081] denotes the total yield of pollen emission of the to-be-observed vegetation in the corresponding pollen emission period.

[0082] In an embodiment, the meteorological factor represents the influence degree of meteorology on pollen emission, and the meteorological factor includes a wind factor, a precipitation factor, and a relative humidity factor;

[0083] The processor 113 is specifically configured to input the pollen emission amount of the t-th day into a pollen simulation model, the pollen simulation model is run on the processor 113, the pollen simulation model is obtained by improving a WRF-Chem model, and the pollen simulation model includes a WRF module, a Chem module and a pollen emission adjustment module; the WRF module is used to calculate meteorological factors of the t-th day, and the meteorological factors of the t-th day are sent to the pollen emission adjustment module; the pollen emission adjustment module is used to calculate a target pollen emission amount of the t-th day of the to-be-observed vegetation in a corresponding pollen emission period based on the pollen emission amount of the t-th day and the meteorological factors of the t-th day, and the target pollen emission amount of the t-th day is sent to the Chem module; and the Chem module is used to simulate pollen concentration based on the target pollen emission amount of each day of the to-be-observed vegetation in the corresponding pollen emission period.

[0084] The pollen emission adjustment module calculates the target pollen emission amount of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period according to the following formula:

[0085]

[0086] The target pollen emission amount of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period is represented by Qtarget(t). The target pollen emission amount of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period is represented by Qtarget(t).

[0087] The pollen emission amount of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period is represented by Qt(t).

[0088] The wind factor of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period is represented by W(t).

[0089] The precipitation factor of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period is represented by P(t).

[0090] The relative humidity factor of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period is represented by RH(t).

[0091] In an embodiment, different types of to-be-observed vegetation correspond to different pollen start period accumulated temperature threshold values and pollen end period accumulated temperature threshold values; and

[0092] The processor 113 is further configured to, before the flowering probability of the t-th day and the pollen cumulative score of the t-th day discharged from the accumulated temperature starting time are determined according to the temperature accumulation of the t-th day, the pollen starting period accumulated temperature threshold, the pollen ending period accumulated temperature threshold, and the number of days of the pollen emission period, adopt the simulated annealing algorithm to optimize the pollen starting period accumulated temperature threshold, the pollen ending period accumulated temperature threshold, the accumulated temperature starting time, and the preset daily average temperature threshold of the to-be-observed vegetation, to obtain the optimized pollen starting period accumulated temperature threshold, the pollen ending period accumulated temperature threshold, the accumulated temperature starting time, and the daily average temperature threshold of the to-be-observed vegetation.

[0093] The pollen emission and concentration simulation system in the embodiment of the application can be arranged on a server, and can also be arranged on any electronic device with computing capability, such as a terminal device, and the embodiment of the application does not limit this.

[0094] As shown in FIG. 1, it is an implementation flowchart of a pollen emission and concentration simulation method provided by the embodiment of the application, and the pollen emission and concentration simulation method can be applied to a pollen emission and concentration simulation system as shown in FIG. 2. Figure 2 Figure 1 As shown in FIG. 2, the pollen emission and concentration simulation system can include the following steps:

[0095] S21, receiving a pollen emission and concentration simulation request sent by a terminal, and the pollen emission and concentration simulation request carries to-be-observed vegetation information, specified observation site information, and year information for which simulation is requested.

[0096] In specific implementation, the communication module in the pollen emission and concentration simulation system receives the pollen emission and concentration simulation request sent by the terminal, extracts the to-be-observed vegetation information, the specified observation site information, and the year information for which simulation is requested in the pollen emission and concentration simulation request, and sends the to-be-observed vegetation information, the specified observation site information, and the year information for which simulation is requested to the collection module in the pollen emission and concentration simulation system.

[0097] S22, obtaining meteorological observation data of each day of the pollen emission period of the to-be-observed vegetation at the specified observation site according to the year for which simulation is requested.

[0098] In specific implementation, the specified observation site can be set by itself according to actual needs, and in the application, six specified observation sites (located in six districts of a city: District 1, District 2, District 3, District 4, District 5, and District 6) of a city are taken as an example for illustration. The pollen emission of the city in spring usually starts from March, and the main types of dominant allergenic pollen in spring include Cupressaceae, Salicaceae, and Pinaceae. The pollen emitted by the vegetation of these three families accounts for ​Therefore, this application uses vegetation from these three families as the vegetation to be observed. The vegetation to be observed is divided into at least two categories according to different pollen emission start times (SOS), with each category corresponding to a different pollen emission period. For the pollen emission end time (EOS), when the accumulated pollen concentration reaches a certain percentage of the total pollen emission concentration in spring (i.e., the observation season)... or At that time, pollen emission can be used as the end time ( Based on historical observations (2012-2019) of pollen emission start and end times (EOS) for Cupressaceae, Salicaceae, and Pinaceae at designated observation stations, the pollen emission start times for Cupressaceae and Salicaceae are relatively consistent, and their pollen emission end times also show strong consistency. The pollen emission start and end times for Pinaceae lag significantly behind those of Cupressaceae and Salicaceae. Therefore, to more accurately simulate the temporal variation trend of spring pollen emission concentration in a certain city, this application's embodiments divide the spring pollen emission period into... The pollen release period is divided into two phases: the first phase is the pollen release period for Cupressaceae and Salicaceae, and the second phase is the pollen release period for Pinaceae. That is, Cupressaceae and Salicaceae in the observed vegetation have the same start and end times for pollen release. The start time of pollen release for Pinaceae is later than that for Cupressaceae and Salicaceae, and similarly, the end time of pollen release for Pinaceae is also later than that for Cupressaceae and Salicaceae. The number of days between the end date and the start date of pollen release in the observed vegetation is the pollen release period of the observed vegetation. Although there is some overlap between the two phases, this division method better reflects the temporal characteristics of actual pollen release. According to observations, the peak pollen emission period for Cupressaceae and Salicaceae plants in a certain city is generally from mid-March to early April, while the peak pollen emission period for Pinaceae plants is generally from late April to early May. In practice, the pollen emission start time for Cupressaceae and Salicaceae in a certain city can be set as early March and the pollen emission end time as mid-to-late April, resulting in a pollen emission period for Cupressaceae and Salicaceae from early March to mid-to-late April. Similarly, the pollen emission start time for Pinaceae can be set as late March to early April and the pollen emission end time as mid-to-late May, resulting in a pollen emission period for Pinaceae from late March to early April to mid-to-late May. There is some overlap in the pollen emission periods between the two phases.

[0099] In this step, the collection module in the pollen emission and concentration simulation system receives the to-be-observed vegetation information, the specified observation site information and the request simulation year information sent by the communication module, and can obtain the requested meteorological observation data of each specified observation site for each day of the pollen emission period of each type of to-be-observed vegetation (the vegetation of Cupressaceae and Salicaceae is one type, and the vegetation of Pinaceae is one type) from the ground climate data daily value data set provided by the National Meteorological Science Data Center and sends the obtained meteorological observation data to the processor in the pollen emission and concentration simulation system. The meteorological observation data of one day can include, but is not limited to, at least one or a combination of the following meteorological data: average temperature (TEM_Avg), maximum temperature (TEM_Max), minimum temperature (TEM_Min), sunshine duration (SSH), station height (Alti) (i.e., the altitude of the weather station), average pressure (PRS_Avg), maximum pressure (PRS_Max), minimum pressure (PRS_Min), maximum wind speed (WIN_S_Max), maximum wind speed (WIN_S_Inst_Max), average 2-minute wind speed (WIN_S_2mi_Avg), ground temperature (GST_Avg_Xcm, X=5, 10, 15, 20, 40, 80, 160, 320cm), average ground temperature (GST_Avg), minimum ground temperature (GST_Min), maximum ground temperature (GST_Max), average relative humidity (RHU_Avg), minimum relative humidity (RHU_Min), average water vapor pressure (VAP_Avg), 20-20 hour precipitation (PRE_Time_2020), and 08-08 hour precipitation (PRE_Time_0808), etc., without limitation.

[0100] S23, according to the meteorological observation data of each specified observation site for each day of the pollen emission period of the to-be-observed vegetation and the pollen yield prediction model, the total pollen emission yield of the to-be-observed vegetation at the specified observation site during the pollen emission period is predicted.

[0101] The pollen yield prediction model is obtained by the processor according to the historical sample meteorological observation data of the sample observation site and the sample pollen observation data of the to-be-observed vegetation according to a preset machine learning model, and the preset machine learning model can be, but is not limited to, an XGBoost model, without limitation. Since the pollen emission periods of different types of vegetation are different, when training the pollen yield prediction model, the pollen yield prediction model corresponding to each type of vegetation is trained respectively.

[0102] For each type of vegetation, the historical sample meteorological observation data of all sample observation sites in the pollen emission period of the type of vegetation in the historical years (such as 2006-2020) and the sample pollen emission total yield of the type of vegetation in the respective sample pollen emission period of each sample observation site are collected by the collection module. The sample observation sites can adopt the above six designated observation sites of a city, and the historical sample meteorological observation data of the sample observation sites and the sample pollen emission total yield of each sample observation site in the respective sample pollen emission period are randomly selected as the training set, and the historical sample meteorological observation data of the remaining sample observation sites and the sample pollen emission total yield of each sample observation site in the respective sample pollen emission period are used as the test set to verify the simulation accuracy of the pollen yield prediction model on the total pollen emission yield in the pollen observation period.

[0103] When training the pollen yield prediction model, the processor uses historical meteorological observation data from each sample observation station for each day of the pollen emission period of this type of vegetation as input to the XGBoost model. It performs iterative machine training based on the error between the predicted total pollen emission of this type of vegetation at that sample observation station during the pollen emission period and the sample total pollen emission of this type of vegetation at that sample observation station during the pollen emission period (i.e., the actual total pollen emission). The parameters of the XGBoot model are adjusted until the model converges, resulting in the trained pollen yield prediction model for that vegetation type. In implementation, to improve the prediction performance of the XGBoot model, the GridSearchCV (enumerated grid search) method can be used for hyperparameter optimization during the training phase, combined with five-fold cross-validation to prevent overfitting and enhance the model's robustness and generalization ability. It should be noted that the total pollen emission of the sampled plants during the first spring stage, i.e., the pollen emission period of Cupressaceae and Salicaceae plants, fluctuated significantly around 2013. This change may be related to adjustments in vegetation planting structure or changes in climate conditions. Using all-time data for model training may introduce large errors. Therefore, in this embodiment of the application, for modeling the total pollen emission of Cupressaceae and Salicaceae plants during the first spring stage, the observed data can be divided into two subsets according to time: before 2013 and after 2013. The XGBoost model can be trained independently for each subset to improve simulation accuracy. The total pollen emission of Pinaceae plants during the second spring stage, i.e., the pollen emission period, was relatively stable between 2006 and 2020, with a gentle trend. Therefore, the model training for this stage can use all-time data for unified modeling, thereby improving the model's sensitivity and generalization ability to the spatiotemporal variation characteristics of total pollen emission in different stages, and providing more robust basic data support for subsequent regional-scale total pollen emission estimation and numerical simulation. Figure 3(a) shows the predicted total pollen production of Cupressaceae and Salicaceae plants at a certain observation site during the first stage of spring (i.e., the pollen emission period of Cupressaceae and Salicaceae plants), simulated by the trained pollen production prediction model for Cupressaceae and Salicaceae plants. Simulated values) and observed values ​​(i.e.: The scatter plot between the observed and predicted pollen production values ​​of a certain observation site during the second spring stage (i.e., the pollen emission period of pine and willow trees) is shown in Figure 3(b). This is a scatter plot of the predicted and observed total pollen production values ​​of pine trees at a certain observation site, simulated by a trained pollen production prediction model for pine vegetation. As can be seen from Figures 3(a) and 3(b), the predicted and observed values ​​exhibit a strong linear correlation in both stages, with the correlation coefficient R between the predicted and observed values ​​being greater than or equal to [a certain value]. And all of them passed. The horizontal significance test shows that the simulation method of pollen emission total yield based on the XGBoost algorithm has high accuracy and reliability for different species of vegetation and different time stages, which provides a solid data foundation for subsequent high-resolution pollen spatial simulation.

[0104] In this step, the processor inputs the meteorological observation data of each day of the pollen emission period of the to-be-observed vegetation at the designated observation station into the pollen yield prediction model corresponding to the to-be-observed vegetation, to obtain the predicted pollen emission total yield of the to-be-observed vegetation at the designated observation station in the pollen emission period.

[0105] S24, obtain the temperature cumulative amount of the tth day of the pollen emission period, and determine the pollen emission potential capacity value of the tth day according to the temperature cumulative amount of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, the number of days of the pollen emission period, and the constructed standardized pollen emission potential model.

[0106] In specific implementation, the pollen emission potential capacity value of the tth day can be determined according to the flow as shown in Figure 4 , and includes the following steps:

[0107] S31, determine the pollen cumulative score emitted by the to-be-observed vegetation from the accumulated temperature starting time to the tth day and the flowering probability of the tth day according to the temperature cumulative amount of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, and the number of days of the pollen emission period.

[0108] Since the pollen emission start time and the pollen emission end time of different types of to-be-observed vegetation are different, and the spring climate temperature increases with time, in order to improve the accuracy of the pollen emission potential capacity prediction of different types of to-be-observed vegetation, the present application sets different pollen start period accumulated temperature thresholds SumT s and pollen end period accumulated temperature thresholds SumT e for different types of to-be-observed vegetation. The accumulated temperature starting time corresponding to different types of to-be-observed vegetation is the same as the preset accumulated temperature starting time , which can be set to January 1st, and the preset daily average temperature threshold corresponding to different types of to-be-observed vegetation can be set according to empirical values, which are not limited by the present application.

[0109] Figure 5 In implementation, the pollen cumulative score emitted from the accumulated temperature starting time to the tth day of the pollen emission period and the flowering probability of the tth day can be determined according to the flow as shown in

[0110] S41, for each type of vegetation to be observed, according to the temperature accumulation amount of the tth day of the pollen emission period corresponding to the vegetation to be observed, the pollen start period accumulated temperature threshold and the pollen end period accumulated temperature threshold, determine the pollen cumulative score of the vegetation to be observed from the accumulated temperature start time to the tth day of emission.

[0111] In a specific implementation, the processor can calculate the pollen cumulative score of the vegetation to be observed from the accumulated temperature start time to the tth day of emission by the following formula:

[0112]

[0113] wherein, represents the pollen cumulative score of the vegetation to be observed from the accumulated temperature start time to the tth day of emission of the pollen emission period corresponding to the vegetation to be observed; wherein, the pollen cumulative score represents the cumulative score of the pollen emission capacity, the pollen cumulative score of the vegetation to be observed from the accumulated temperature start time to the tth day of emission of the pollen emission period corresponding to the vegetation to be observed, that is, the cumulative score of the pollen emission capacity of the vegetation to be observed from the accumulated temperature start time to the tth day of the pollen emission period corresponding to the vegetation to be observed, the higher the cumulative score, the stronger the pollen emission capacity;

[0114] represents the temperature accumulation amount of the tth day of the pollen emission period corresponding to the vegetation to be observed, , represents the temperature of the tth day of the pollen emission period corresponding to the vegetation to be observed (that is, the daily average temperature of the tth day), represents the daily average temperature threshold;

[0115] represents the pollen start period accumulated temperature threshold, that is, the cumulative accumulated temperature threshold required when the vegetation to be observed starts to emit pollen;

[0116] represents the pollen end period accumulated temperature threshold, that is, the cumulative accumulated temperature threshold required when the vegetation to be observed ends to emit pollen.

[0117] In this way, the pollen cumulative score of the vegetation to be observed from the accumulated temperature start time to each day of emission of the pollen emission period corresponding to the vegetation to be observed can be calculated.

[0118] Different types of vegetation to be observed correspond to different pollen start period accumulated temperature thresholds and pollen end period accumulated temperature thresholds, and different types of vegetation to be observed correspond to the same accumulated temperature start time and daily average temperature threshold. In an embodiment, the pollen start period accumulated temperature threshold corresponding to the vegetation to be observed, the accumulated temperature starting time and the daily average temperature threshold which can be set according to empirical values in advance.

[0119] In an embodiment, in order to improve the accuracy of evaluating the potential capacity of pollen emission, before determining the accumulated pollen score emitted by the to-be-observed vegetation on the t-th day of the pollen emission period corresponding to the to-be-observed vegetation and the flowering probability on the t-th day from the accumulated temperature starting time of the to-be-observed vegetation, the simulated annealing algorithm can also be used to optimize the pollen starting period accumulated temperature threshold, the pollen ending period accumulated temperature threshold, the accumulated temperature starting time and the preset daily average temperature threshold corresponding to the to-be-observed vegetation, to obtain the optimized pollen starting period accumulated temperature threshold, the pollen ending period accumulated temperature threshold, the accumulated temperature starting time and the daily average temperature threshold corresponding to the to-be-observed vegetation.

[0120] The simulated annealing algorithm is a probability-based heuristic global optimization algorithm, which is derived from the metal annealing process. It can be used for complex nonlinear optimization problems by accepting a certain probability of "inferior solution" to avoid falling into local optimum. The specific process of optimizing the pollen starting period accumulated temperature threshold, the pollen ending period accumulated temperature threshold, the accumulated temperature starting time and the daily average temperature threshold based on the simulated annealing algorithm is as follows:

[0121] First, initialize the parameter space, set the value range of each parameter according to the empirical value, for example, the value range of the accumulated temperature starting time can be set as: 1-90 days (such as starting from January), the value range of the daily average temperature threshold can be set as: 0-15℃, the value range of the pollen starting period accumulated temperature threshold can be set as: 50-300℃, the value range of the pollen ending period accumulated temperature threshold can be set as: 500-1500℃, which is not limited in the embodiments of the present application.

[0122] Further define the objective function, which is used to measure the difference between the simulation value and the observation value, which can be set as:

[0123]

[0124] wherein, is the objective function, represents the simulated phenological day in the i-th year, represents the observed phenological day in the i-th year, wherein the phenological day can be the pollen emission day of the to-be-observed vegetation, and N is the number of years.

[0125] Further, initialize the annealing parameters, as shown in Table 1:

[0126] Table 1

[0127]

[0128] Further, the simulated annealing process is implemented as follows:

[0129] Step one, generate initial solution:

[0130] Randomly generate a set of initial parameters , calculate its objective function value .

[0131] Step two, cycle cooling:

[0132] The current temperature T=T0 (initial temperature), when (minimum temperature), the current solution X is disturbed to generate a new solution X_new, each parameter is randomly disturbed by a set step (such as ), calculate the objective function of the new solution , if , then accept the new solution X_new, otherwise, accept the inferior solution with a probability , update the current optimal solution and cool down to: .

[0133] Step three, output the optimal solution:

[0134] Final output: , is the optimized daily average temperature threshold, is the optimized accumulated temperature start time, is the optimized pollen start period accumulated temperature threshold, is the optimized pollen end period accumulated temperature threshold.

[0135] As shown in Table 2, the optimization parameters corresponding to each of the Cupressaceae and Salicaceae, Pinaceae vegetation are as follows:

[0136] Table 2

[0137]

[0138] Among them, the accumulated temperature start time is in days, which can be an integer, for example, , the accumulated temperature start time can be set to January 23.

[0139] S42, according to the temperature accumulation of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, and the number of days of the pollen emission period corresponding to the observed vegetation, determine the flowering probability of the observed vegetation at the tth day of the corresponding pollen emission period and the flowering probability of the end of the pollen emission period.

[0140] The flowering probability of the start of the pollen emission period and the flowering probability of the end of the pollen emission period is also piecewise linear, affected by the pollen start period accumulated temperature threshold and the pollen end period accumulated temperature threshold and the temperature accumulation. Generally, flowering does not start suddenly, but gradually starts flowering at a time before or after the accumulated temperature reaches the accumulated temperature threshold , and fully flowers when the accumulated temperature threshold is reached. The flowering probability between the start of flowering and the end of flowering increases linearly.

[0141] In the embodiments of the present application, the flowering probability at the start of the pollen emission period and the flowering probability at the end of the pollen emission period are respectively related to the pollen start period accumulated temperature threshold and the pollen end period accumulated temperature threshold , rather than the total pollen emission yield of the observed vegetation in its pollen emission period , indicating that the pollen emission period does not end depending on the termination of pollen emission, but depends on the accumulated temperature threshold, avoiding the abnormal early or delayed end of the pollen emission period due to the simulation error of the total pollen emission yield .

[0142] In specific implementation, the processor can calculate the flowering probability at the start of the pollen emission period of the observed vegetation on the t-th day of the corresponding pollen emission period by the following formula:

[0143]

[0144] wherein, represents the flowering probability at the start of the pollen emission period of the observed vegetation on the t-th day of the corresponding pollen emission period;

[0145] represents the temperature accumulation of the observed vegetation on the t-th day of the corresponding pollen emission period, , represents the temperature of the observed vegetation on the t-th day of the corresponding pollen emission period (i.e. the daily average temperature on the t-th day), represents the preset daily average temperature threshold, represents the accumulated temperature starting time;

[0146] represents the pollen start period accumulated temperature threshold;

[0147] represents the relative temperature accumulation tolerance coefficient, used to construct the excessive interval of temperature accumulation;

[0148] represents the number of days of the corresponding pollen emission period of the observed vegetation, wherein, denotes the end time of pollen emission of the to-be-observed vegetation, denotes the start time of pollen emission of the to-be-observed vegetation.

[0149] In this way, the flowering probability of the to-be-observed vegetation at the start of the pollen emission period on each day of the corresponding pollen emission period can be calculated.

[0150] The processor can calculate the flowering probability of the to-be-observed vegetation at the end of the pollen emission period on the tth day of the corresponding pollen emission period by the following formula:

[0151]

[0152] wherein, denotes the flowering probability of the to-be-observed vegetation at the end of the pollen emission period on the tth day of the corresponding pollen emission period;

[0153] denotes the pollen end period accumulated temperature threshold.

[0154] In this way, the flowering probability of the to-be-observed vegetation at the end of the pollen emission period on the tth day of the corresponding pollen emission period can be calculated.

[0155] In the embodiments of the present application, According to the empirical value, but not limited to, it can be set as , to control the gradual increase and decrease of pollen emission, that is, after the temperature accumulation reaches the pollen start period accumulated temperature threshold , the pollen emission will not end immediately, but gradually decrease until the end.

[0156] S43, according to the flowering probability of the to-be-observed vegetation at the start and end of the pollen emission period on the tth day of the corresponding pollen emission period, determine the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period.

[0157] In specific implementation, the processor can calculate the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period by the following formula:

[0158]

[0159] wherein, denotes the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period;

[0160] denotes the flowering probability of the to-be-observed vegetation at the start of the pollen emission period on the tth day of the corresponding pollen emission period;

[0161] P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period.

[0162] In this way, the flowering probability of the to-be-observed vegetation on each day of the corresponding pollen emission period can be calculated.

[0163] S32, determining, according to the cumulative pollen emission score of the to-be-observed vegetation from the accumulated temperature starting time to the tth day, the flowering probability on the tth day, and the standardized pollen emission potential model, a pollen emission potential value on the tth day.

[0164] The pollen emission potential represents the pollen emission potential of the to-be-observed vegetation, and the standardized pollen emission potential model is used to calculate the pollen emission potential value.

[0165] In a specific implementation, the processor can calculate the pollen emission potential value of the to-be-observed vegetation on the tth day of the corresponding pollen emission period by using the following standardized pollen emission potential model:

[0166]

[0167] wherein, P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period;

[0168] P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period;

[0169] P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period; the derivative of the pollen cumulative score with respect to time t;

[0170] wherein, H (t) is a Heaviside function when t < 0, when t > 0, when t = 0, = 1;

[0171] P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period;

[0172] P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period;

[0173] P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period; P (t) represents the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period;

[0174] ​In this embodiment, the land cover of the vegetation to be observed refers to the proportion of that type of vegetation per unit area. For the land use dataset, this application uses Community Land Model 4 (CLM4). This dataset contains 25 plant functional types, including coniferous forests, broad-leaved forests, shrublands, herbs, and crops, with a spatial resolution of [missing information]. Since this application primarily simulates total pollen concentration in spring (tree pollen), the plant functionality of spring tree pollen shedding is calculated using the sum of land cover of all coniferous and broadleaf forests in the CLM4 data.

[0175] This application takes into account the explosive increase in pollen emission concentration in a certain city during the early spring as temperature rises. To more accurately depict the rapid changes in pollen levels during the early spring, a scaling factor is introduced. This is used to characterize the enhanced pollen emission effect caused by temperature changes. The scaling factor varies with time t, and can be specifically set as follows: after a specified date each year (e.g., March 1st), if the temperature shows the first periodic change process of "rising first and then falling", the pollen emission potential is amplified during this period. times, It can be set to 2; at other times, the default is 2. .

[0176] In this way, the potential pollen emission capacity of the vegetation under observation can be calculated for each day during the corresponding pollen emission period.

[0177] S25. Determine the pollen emission amount on day t based on the total pollen emission production and the pollen emission potential capacity value on day t.

[0178] In practice, the processor can calculate the pollen emission of the observed vegetation on day t of the corresponding pollen emission period using the following formula:

[0179]

[0180] in, This represents the pollen emission of the observed vegetation on day t of the corresponding pollen emission period.

[0181] This represents the total pollen production of the observed vegetation during the corresponding pollen emission period.

[0182] In this way, the pollen emission of the vegetation under observation can be calculated for each day during the corresponding pollen emission period.

[0183] S26, acquire the meteorological factor of the tth day, determine the target pollen emission amount of the tth day according to the pollen emission amount of the tth day and the meteorological factor of the tth day, and simulate the pollen emission and concentration of each day in the pollen emission period.

[0184] The meteorological factor represents the influence degree of the weather on the pollen emission, and at least includes a wind factor, a precipitation factor and a relative humidity factor. The wind factor is a parameter of the influence degree of the wind on the pollen emission, the precipitation factor is a parameter of the influence degree of the precipitation on the pollen emission, and the relative humidity factor is a parameter of the influence degree of the relative humidity on the pollen emission. The target pollen emission amount is the pollen emission amount after adding the meteorological disturbance.

[0185] In specific implementation, the processor can calculate the wind factor of the tth day of the pollen emission period corresponding to the to-be-observed vegetation by the following formula :

[0186]

[0187] wherein, represents the wind factor of the tth day of the pollen emission period corresponding to the to-be-observed vegetation;

[0188] represents the near-surface 10m wind speed of the tth day of the pollen emission period corresponding to the to-be-observed vegetation;

[0189] represents the vertical turbulent wind speed of the tth day of the pollen emission period corresponding to the to-be-observed vegetation.

[0190] The wind factor is exponentially related to the near-surface 10m wind speed and the vertical turbulent wind speed .

[0191] The processor can calculate the precipitation factor of the tth day of the pollen emission period corresponding to the to-be-observed vegetation by the following formula :

[0192]

[0193] wherein, represents the precipitation factor of the tth day of the pollen emission period corresponding to the to-be-observed vegetation;

[0194] represents the precipitation amount of the tth day of the pollen emission period corresponding to the to-be-observed vegetation;

[0195] represents a low precipitation threshold value, represents a high precipitation threshold value.

[0196] When the precipitation amount is lower than the low precipitation threshold value When the precipitation factor is set to 1, and the precipitation amount is higher than the high precipitation threshold, the precipitation factor is set to 1. When the precipitation factor is 0, and the precipitation amount is between the low precipitation threshold, the precipitation factor is set to 0. and high precipitation threshold In the interval, the precipitation factor is the quotient of the difference between the high precipitation threshold and the precipitation amount, and the threshold difference. High precipitation threshold With low precipitation threshold It can be set based on experience values, such as... , However, the embodiments in this application do not limit this.

[0197] The processor can calculate the relative humidity factor on day t of the pollen emission period corresponding to the vegetation under observation using the following formula. :

[0198]

[0199] in, The relative humidity factor represents the day t of the pollen emission period corresponding to the vegetation to be observed.

[0200] The relative humidity represents the day t of the pollen emission period corresponding to the vegetation to be observed.

[0201] This indicates the high relative humidity threshold. This indicates the low relative humidity threshold.

[0202] During implementation, the high relative humidity threshold With low relative humidity threshold It can be set based on experience values, such as... , However, the embodiments in this application do not limit this.

[0203] Furthermore, after determining the values ​​of each meteorological factor, the processor can calculate the target pollen emission of the observed vegetation on day t of the corresponding pollen emission period using the following formula:

[0204]

[0205] in, This represents the target pollen emission of the vegetation to be observed on day t of the corresponding pollen emission period;

[0206] This represents the pollen emission on day t of the pollen emission period corresponding to the vegetation to be observed.

[0207] The wind factor represents the day t of the pollen emission period corresponding to the vegetation to be observed.

[0208] a precipitation factor representing the tth day of the pollen emission period of the vegetation to be observed;

[0209] a relative humidity factor representing the tth day of the pollen emission period of the vegetation to be observed.

[0210] In this way, the target pollen emission amount of the vegetation to be observed at the specified observation site on each day of the pollen emission period thereof can be calculated, thereby simulating the pollen emission amount.

[0211] Suppose the specified observation sites for which the terminal requests simulation include 6 specified observation sites in a city, and the years for which the terminal requests simulation include 2006-2020, the target pollen emission amount of each type of vegetation to be observed at each specified observation site on each day of the corresponding pollen emission period thereof can be calculated through the above process, the pollen emission amount time series of each type of vegetation to be observed at each specified observation site on each day of the corresponding pollen emission period thereof, and further, the average total pollen emission amount of all specified observation sites (e.g., the 6 specified observation sites in the city) on each day of the pollen emission period (including the date of overlap of the two stages) of each type of vegetation to be observed in the two stages can be calculated. The calculation method of the average total pollen emission amount on a day is as follows: first, the sum of the pollen emission amounts of each type of vegetation to be observed at each specified observation site on the day is calculated as the total pollen emission amount of the site on the day, and then the total pollen emission amounts of each specified observation site on the day are averaged to obtain the average total pollen emission amount of each specified observation site on the day. As shown in FIG. 6, it is a time series comparison chart of the site average observation value and the simulation value of the spring pollen emission amount in a city, including data from 2006 to 2020. Figure 6 Figure 6 The blue circles represent the average total pollen emission amount measured daily (the average total pollen emission amount of each specified observation site), and the red solid line represents the average total pollen emission amount simulated daily. To evaluate the consistency between the simulation value and the observation value, we use the correlation coefficient R and the root mean square error (RMSE) as evaluation indexes. As shown in FIG. 6, in most years, the simulation results are highly consistent with the observation values, Figure 6 the correlation coefficient of the two exceeds 0.7, especially in 2008, 2009, 2016, 2017 and 2018, the R value exceeds 0.8, ​​, indicating that the pollen emission potential model has strong pollen emission calculation capability. At the same time, the spring pollen emission usually shows two peaks: the first peak is mainly caused by early spring tree species such as Cupressaceae and Salicaceae, and the second peak corresponds to the late spring stage dominated by Pinaceae. From the simulation results, the emission characteristics of the two stages are well reproduced in most years, especially in 2008, 2013, 2017, 2018 and 2019, and the simulation values are highly consistent with the observation values, showing excellent performance of the model in these years. It is worth noting that the early spring pollen simulation in 2020 is highly consistent with the observation, reflecting the explosive growth of early spring pollen, and the late spring pollen emission also has good simulation effect. It can be seen that the pollen emission potential model constructed in the embodiments of the present application can accurately simulate the starting time, ending time and time sequence change process of the entire pollen season of the spring pollen in a city, and has good simulation capability and application potential.

[0212] As shown in FIG. 7(a) and FIG. 7(b), the spatial distribution characteristics of the spring pollen emission of a city in the first stage (Cupressaceae and Salicaceae) and the second stage (Pinaceae) from 2006 to 2020 are shown. From the overall trend, the emission of cypress and poplar pollen has significant spatial and temporal differences, and the annual fluctuations are obvious, while the overall annual change trend of pine pollen emission is relatively stable. The high-yield area of pollen is mainly concentrated in the northern and western regions of the city, reflecting that the planting density of related tree species in these regions is high or the vegetation growth is good. From the annual change, the spring pollen emission in the first stage is relatively low from 2006 to 2012, and it has increased significantly since 2013, indicating that the vegetation structure may have changed during this period, or human planting activities (such as urban greening) have affected the size of the cypress and poplar population. After 2017, the pollen emission eased, but still maintained at a high level. For pine pollen, the spatial distribution of pollen emission has been relatively stable over the past 15 years. Cypress and poplar pollen accounts for an important position in the total amount of spring pollen in the city, and its emission characteristics are affected by vegetation distribution, meteorological conditions and human intervention. In-depth study of the emission of this type of allergenic pollen is of great significance for accurately identifying high-risk exposure areas, developing individual protection strategies and selecting urban greening plants.

[0213] To further simulate the pollen emission concentration, the pollen simulation model shown in Figure 8 may be used to simulate the pollen emission concentration.

[0214] In specific implementation, the processor can be provided with a pollen simulation model, which is improved from a WRF-Chem (Weather Research and Forecasting model with Chemistry) model, and includes a WRF module 501, a Chem module 502, and a pollen emission adjustment module 503. The processor inputs the pollen emission amount of the t-th day into the pollen emission adjustment module 503 of the pollen simulation model, calculates the meteorological factors of the t-th day based on the acquired global reanalysis data (FNL) through the WRF module 501, and sends the meteorological factors of the t-th day to the pollen emission adjustment module 503. The pollen emission adjustment module calculates the target pollen emission amount of the t-th day of the to-be-observed vegetation in the corresponding pollen emission period based on the pollen emission amount of the t-th day and the meteorological factors of the t-th day, and sends the target pollen emission amount of the t-th day to the Chem module 502. The Chem module 502 simulates the pollen concentration based on the target pollen emission amount of each day of the to-be-observed vegetation in the corresponding pollen emission period. The calculation manner of the WRF module 501 for the meteorological factors and the calculation manner of the pollen emission adjustment module 503 for the target pollen emission amount refer to the calculation manners of the processor for the meteorological factors and the target pollen emission amount, which will not be repeated here.

[0215] As shown in Figure 8 , which is an architecture schematic diagram of a pollen simulation model provided by an embodiment of the present application. The pollen simulation model can be denoted as a WRF-Chem-Pollen model, which is an improvement of a WRF-Chem model (mode). The WRF-Chem mode is a new generation of atmospheric simulation and prediction mode developed by the National Oceanic and Atmospheric Administration (NOAA) of the United States. It realizes the real coupling of spatial and temporal resolution and the online transmission of biochemistry based on the meteorological mode and the chemical transmission mode. The mode not only has good simulation and prediction effect on the emission and chemical transmission of pollution gas and aerosol, but also can be used to analyze the interaction between air quality and chemistry, etc. In addition, due to the comprehensive physical parameterization process, high coupling degree of the chemical mode, convenient operation and high calculation efficiency, the mode is widely used in simulation of meteorological process and atmospheric pollution process ). The present application improves the WRF-Chem ) model, the pollen is considered as a coarse mode particle and is incorporated into the WRF-Chem model to construct a WRF-Chem-Pollen model to simulate the physical processes such as transport, diffusion and deposition of the pollen in the atmosphere. In addition to the WRF module 501 and the Chem module 502, the WRF-Chem-Pollen model introduces a pollen emission adjustment module 503. The WRF module 501 provides meteorological simulation functions for calculating daily meteorological factors based on global reanalysis data. The pollen emission adjustment module 503 is used to determine the target pollen emission amount of each day according to the daily pollen emission amount of the vegetation to be observed during its pollen emission period and the meteorological factors, which can reflect the influence of the meteorological factors on the pollen emission amount. The Chem module 502 is used to simulate the emission process of the pollen in the atmosphere and output the simulated concentration of the pollen. The proposed Secondary Organic Aerosol Model (SORGAM) mechanism is incorporated into the The proposed Modal Aerosol Dynamics Model for Europe (MADE) mechanism constitutes a MADE / SORGAM aerosol mechanism, wherein the MADE / SORGAM aerosol mechanism adopts a modal method to describe three aerosol particle size modes of lognormal distribution, including: Aitken Mode (Aitken mode) ), Accumulation Mode (accumulation mode) ) and Coarse Mode (coarse particle mode) ). On the basis of the above three modes, the pollen (Pollen) is further considered as a separate mode, and the pollen density is about , and the diameter is about , other parameters such as Standard deviation (standard deviation), Hygroscopicity (hygroscopicity) and the like can be set according to the parameters of the Coarse Mode. In the embodiments of the present application, the pollen emission amount of the vegetation to be observed per day during the pollen emission period thereof can be calculated offline, and the pollen emission amount of the vegetation to be observed per day during the pollen emission period thereof and the global reanalysis data as a pollen emission source are respectively input into the pollen emission adjustment module 503 and the WRF module 501 of the WRF-Chem-Pollen model constructed. The WRF module 501 determines the meteorological data of the specified observation site per day according to the global reanalysis data, calculates the meteorological factor per day according to the meteorological data of the specified observation site per day, and transmits the calculated meteorological factor per day to the pollen emission adjustment module 503. The pollen emission adjustment module 503 calculates the target pollen emission amount per day according to the pollen emission amount of the vegetation to be observed per day during the pollen emission period thereof and the meteorological factor per day, and further transmits the target pollen emission amount per day to the Chem module 502 to simulate the transport and evolution process of the pollen in the atmosphere. The pollen emission adjustment module 503 in the WRF-Chem-Pollen model constructed in the present application can also be set as a sub-module of the Chem module 502, and the embodiments of the present application do not limit this.

[0216] In the embodiments of the present application, the WRF-Chem-Pollen model is used to simulate the influence of daily meteorological elements such as temperature, precipitation, humidity, wind speed, etc. on the pollen concentration of 6 observation sites in a city, and to describe the physical processes such as advection diffusion, convective transport, dry and wet deposition, etc. to provide analysis on the propagation and deposition behavior of spring pollen in the atmosphere. As shown in Figure 9 , the potential height distribution map of the simulated area is provided in the embodiments of the present application, and the triangular mark in the figure is the 6 observation sites, and the circular mark is the meteorological monitoring station. In the simulation, the Lambert projection method is used, the horizontal grid is set to , the resolution is 3000m, and the integral time step can be set to 15s. In the calculation of the meteorological factor, the global reanalysis data (FNL) is used as the input initial field and boundary field of the model WRF module, and the spatial accuracy is , the time resolution is 6h (hour), the WRF module calculates the meteorological factors of each observation site in the pollen emission period of the vegetation to be observed every day based on global reanalysis data, wherein each observation site is located in a region composed of grids, for each observation site, the meteorological factors of the observation site can be calculated by using the average of the meteorological data of the grids covered by the observation site, taking the wind factor of the t-th day of the pollen emission period of the vegetation to be observed of a certain observation site as an example, the average of the near-surface 10m wind speed of all grids covered by the observation site on the t-th day is counted, and the average of the vertical turbulent wind speed is counted, the average of the near-surface 10m wind speed is taken as the near-surface 10m wind speed of the observation site on the t-th day, and the average of the vertical turbulent wind speed is taken as the vertical turbulent wind speed of the observation site on the t-th day, the WRF module calculates according to the calculation formula of the aforementioned wind factor , that is, the wind factor of the observation site on the t-th day can be obtained, the calculation methods of the precipitation factor and the relative humidity factor are similar and are not described herein. The East Asian regional land process scheme Noah, the Lin cloud microphysical scheme, the RRTM longwave radiation scheme and the Goddard shortwave radiation scheme are used, the 6h output data of the MOZART (Model for Ozone and Related chemical Tracers) global atmospheric chemical model is used as the chemical field, the MEIC (Multi-resolution Emission Inventory for China) inventory of Tsinghua University is used as the anthropogenic source emission, the RADM2 (Regional Acid Deposition Model Version 2) chemical mechanism is used as the meteorology, the MADE / SORGAM mechanism is used as the aerosol, and the MEGAN (Model of Emissions of Gases and Aerosols from Nature) inventory is used as the biological source emission. The simulation time is from March 1 to June 30 of each year from 2006 to 2020. The specific configuration of the WRF-Chem-Pollen model is shown in Table 3:

[0217] Table 3

[0218]

[0219] In order to prevent data anomalies, the abnormal values of the pollen emission concentration are removed, and the highest pollen concentration is removed according to a preset proportion (such as can be set to ), that is, the pollen concentration data of with the highest pollen emission concentration are removed, and the remaining The pollen concentration data is simulated. At the same time, the pollen concentration data is smoothed by using 5-day moving average, which can not only eliminate the influence of noise on the pollen concentration data, but also weaken the influence of daily meteorological changes and advection diffusion on the daily pollen emission, so that the daily variation trend of pollen emission concentration can be more clearly explored. The improved WRF-Chem-Pollen model is used for simulation, which can deeply analyze the influence of key factors such as meteorological elements and advection diffusion on daily pollen concentration. The model can finely reflect the influence of daily meteorological elements such as temperature, precipitation, humidity and wind speed on pollen emission, that is, concentration, and describe key physical processes such as advection diffusion, convective transport and dry and wet deposition, so as to provide a comprehensive analysis of the transmission and deposition behavior of pollen in the atmosphere.

[0220] As shown in Figure 10 , it is a time series comparison chart of the average observed value and the simulated value of the spring pollen concentration in a certain city based on the WRF-Chem-Pollen model, wherein the red solid line represents the simulated value of the average total pollen concentration of the six observation stations in the city, the blue dot represents the observed value of the average total pollen concentration of the six observation stations in the city, and the red and blue shadows represent the daily average absolute deviation. It can be seen from the figure that the WRF-Chem-Pollen model can better capture the time variation trend of plant pollen concentration in the spring pollen period, which presents a trend of first increasing and then decreasing as a whole, and is affected by meteorological elements such as temperature, precipitation and relative humidity, as well as physical processes such as advection diffusion, convective transport and dry and wet deposition. The daily pollen emission concentration fluctuates obviously, the pollen concentration simulated by the WRF-Chem-Pollen model is consistent with the overall trend of the observed pollen concentration, but there is still some difference.

[0221] Affected by many factors such as meteorological conditions, the start date (SOS) of pollen emission and the total yield of pollen emission in the pollen emission period in a certain city show certain interannual variation characteristics every year. As can be seen from Figure 10 , the peak value of the average total pollen concentration of the gramineous plants (including cypress and willow vegetation, pine vegetation) in the spring from 2006 to 2019 mainly distributes between , while the peak value of the average total pollen concentration in 2020 breaks through , which is significantly higher than that in previous years. At the same time, it can be observed that the peak value of the average total pollen concentration in the region before 2013 (not including 2013) is generally lower than , while that after 2013 (including 2013) basically maintains at , especially in 2018 and 2020, which exceeds 700 and , respectively. This significant upward trend may be related to the change of plant functional type composition before and after 2013, or related to the adjustment of pollen observation method, the specific reason is not clear. FromFigure 10 As can be seen from the shaded areas, there are significant differences in pollen concentration among different designated observation sites, reflecting the significant impact of spatial heterogeneity in meteorological conditions and vegetation distribution on pollen concentration. Overall, the WRF-Chem-Pollen model accurately simulates pollen concentration during the spring pollen season (i.e., the two-stage pollen emission period) and can reproduce the temporal variation characteristics of the observed data well. Regarding the simulation of daily concentration variations, the model successfully captures the "bimodal structure" of pollen concentration commonly found in spring each year. The first peak typically occurs from mid-March to early April, while the second peak is concentrated between late April and early May, corresponding to the main pollen emission periods of Cupressaceae / Saussureaceae and Pinaceae vegetation, respectively. It is worth noting that, due to meteorological conditions, the peak times vary in different years, occurring earlier or later.

[0222] Through comprehensive evaluation, the WRF-Chem-Pollen model showed good consistency between its simulations and observations of spring pollen concentrations in most years, with the correlation coefficient R between predicted and observed values ​​generally higher than that of observed values. The R-values ​​reached [values] in 2009, 2014, 2015, 2017, and 2018. That's all. (Approximately) The year R value exceeds RMSE in The fact that the pollen simulation model constructed in this application has high accuracy and reliability in simulating the spring pollen concentration change trend of grasses in a certain city (excluding 2020) not only verifies the effectiveness of the pollen emission potential model constructed based on machine learning algorithms in the early stage, but also provides strong data support for the analysis and research of pollen-related health risks.

[0223] S27. Return the simulation results of pollen emission and concentration for each day of the pollen emission period to the terminal.

[0224] In practice, the response module in the pollen emission and concentration simulation system returns to the terminal the simulation results of pollen emission and pollen concentration of the vegetation to be observed at the designated observation site for each day of the pollen emission period, so that they can be displayed on the terminal.

[0225] The pollen emission and concentration simulation method provided by the embodiments of the present application can predict the total pollen production of the vegetation to be observed in the pollen emission period by pre-training a pollen production prediction model based on a preset machine learning model according to historical sample meteorological observation data of a sample observation site and sample pollen observation data of the vegetation to be observed. The machine learning model can capture the complex nonlinear relationship (such as the influence of climate, geographical location, year, etc. on pollen production) in the historical meteorological observation data of the specified observation site, improve the accuracy of the prediction of the total pollen production, and provide a reliable basis for subsequent determination of the pollen emission concentration of each day. After the total pollen production is predicted, the pollen emission potential of each day of the vegetation to be observed in its pollen emission period is predicted by combining the set pollen accumulated temperature double threshold (i.e. the pollen emission start period accumulated temperature threshold and the pollen end period accumulated temperature threshold) and the constructed standardized pollen emission potential model. The pollen accumulated temperature double threshold is set as the temperature constraint. Compared with the single accumulated temperature threshold, the pollen accumulated temperature double threshold can better adapt to the influence of climate change on the pollen emission potential. The standardized pollen emission potential model constructed based on the pollen accumulated temperature double threshold can accurately simulate the time distribution rule of the pollen emission potential, avoid the error caused by uniform distribution, better match the actual pollen emission curve, and improve the prediction accuracy of the daily-scale pollen emission potential. Then, the pollen emission amount of each day is calculated according to the total pollen production of the vegetation to be observed in the pollen emission period and the pollen emission potential value of each day in the pollen emission period. Finally, the target pollen emission amount of each day, i.e. the pollen emission amount after adding meteorological disturbance, is determined by combining the pollen emission amount of each day and the corresponding meteorological factor of each day. The pollen emission and concentration of each day in the pollen emission period are simulated. By simulating the pollen emission and concentration by combining the daily pollen emission amount and the meteorological factor, the influence of the meteorological factor on the pollen emission amount and the concentration (such as the wind speed which can affect the pollen diffusion speed and diffusion range, the precipitation which can inhibit the pollen emission and promote the settlement, the humidity which can affect the pollen emission activity and suspension capacity, etc.) is considered. The daily pollen emission amount and the pollen concentration are simulated by combining the daily pollen emission amount and the environmental diffusion condition, so as to provide a more reliable data basis for the analysis and research of the spring pollen emission and concentration, and the influence of the pollen emission and concentration on the health risk (such as pollen allergy).

[0226] Based on the same technical concept, the embodiments of the present application also provide an electronic device 600, which is described with reference to Figure 11As shown, the electronic device 600 is configured to implement the pollen emission and concentration simulation method described in the above method embodiments. The electronic device 600 of the embodiment can include a memory 601, a processor 602, and a computer program stored in the memory and executable on the processor, such as a pollen emission concentration simulation program. The processor implements the steps in each of the above pollen emission and concentration simulation method embodiments when executing the computer program.

[0227] The specific connection medium between the memory 601 and the processor 602 is not limited in the embodiments of the present application. In the embodiments of the present application, the memory 601 and the processor 602 are connected through a bus 603. Figure 11 The connection mode between other components is only schematically illustrated and is not limited. Figure 11 The bus 603 can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, only one thick line is used to represent the bus 603 in some embodiments, but it does not mean that there is only one bus or only one type of bus. Figure 11

[0228] The memory 601 can be a volatile memory such as a random-access memory (RAM), or a non-volatile memory such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), or any other medium capable of carrying or storing desired program codes in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory 601 can be a combination of the above memories.

[0229] The processor 602 is configured to implement the pollen emission and concentration simulation method provided by the embodiments of the present application.

[0230] The embodiments of the present application also provide a computer-readable storage medium storing computer-executable instructions required for the processor to execute, which contains a program for the processor to execute.

[0231] In some possible implementation manners, each aspect of the pollen emission and concentration simulation method provided by the present application can also be implemented in the form of a program product, which includes program codes for causing an electronic device to perform the steps in the pollen emission and concentration simulation method according to the various exemplary embodiments of the present application described in the specification when the program product is running on the electronic device. ​

[0232] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In one

[0233] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0234] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0235] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0236] While preferred embodiments of the application have been described, modifications and alterations thereto will occur to those skilled in the art upon reading the preceding description. In particular, it will be apparent to those skilled in the art that parts can be added to, or substituted for, parts of the described embodiment. It is therefore desired to be secured to the appended claims as they follow.

[0237] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A pollen emission and concentration simulation system, characterized by, The method comprises the following steps: A communication module is configured to receive a pollen emission and concentration simulation request sent by a terminal, wherein the pollen emission and concentration simulation request carries to-be-observed vegetation information, specified observation site information, and a year information for which simulation is requested; An acquisition module is configured to acquire meteorological observation data of a specified observation site on each day of a pollen emission period of the to-be-observed vegetation according to the year information for which simulation is requested; A processor is configured to predict a total pollen emission yield of the to-be-observed vegetation of the specified observation site in the pollen emission period according to the meteorological observation data of the specified observation site on each day of the pollen emission period of the to-be-observed vegetation and a pollen yield prediction model, wherein the pollen yield prediction model is obtained by training historical sample meteorological observation data of a sample observation site and sample pollen observation data of the to-be-observed vegetation according to a preset machine learning model; acquire a temperature cumulative amount of a tth day of the pollen emission period, determine a pollen emission potential capacity value of the tth day according to the temperature cumulative amount of the tth day, a pollen start period accumulated temperature threshold value, a pollen end period accumulated temperature threshold value, a number of days of the pollen emission period, and a constructed standardized pollen emission potential model, wherein the standardized pollen emission potential model is used to calculate the pollen emission potential capacity value; determine a pollen emission amount of the tth day according to the total pollen emission yield and the pollen emission potential capacity value of the tth day; acquire a meteorological factor of the tth day, determine a target pollen emission amount of the tth day according to the pollen emission amount of the tth day and the meteorological factor of the tth day, and simulate pollen emission and concentration of each day of the pollen emission period, wherein the target pollen emission amount is a pollen emission amount after meteorological disturbance is added; The processor is specifically configured to determine a pollen cumulative score of the to-be-observed vegetation from an accumulated temperature starting time to the tth day and a flowering probability of the tth day according to the temperature cumulative amount of the tth day, the pollen start period accumulated temperature threshold value, the pollen end period accumulated temperature threshold value, and the number of days of the pollen emission period of the to-be-observed vegetation; and determine the pollen emission potential capacity value of the tth day according to the pollen cumulative score from the accumulated temperature starting time to the tth day, the flowering probability of the tth day, and the standardized pollen emission potential model; A response module is configured to return simulation results of pollen emission and concentration of each day of the pollen emission period to the terminal.

2. The system of claim 1, wherein, The to-be-observed vegetation is divided into at least two categories according to different pollen emission start times, and each category of to-be-observed vegetation corresponds to a different pollen emission period; The processor is specifically configured to determine, for each category of to-be-observed vegetation, a pollen cumulative score of the to-be-observed vegetation from an accumulated temperature starting time to the tth day according to a temperature cumulative amount of the tth day of the pollen emission period corresponding to the to-be-observed vegetation, the pollen start period accumulated temperature threshold value, and the pollen end period accumulated temperature threshold value; Determine a flowering probability at the start of the pollen emission period and a flowering probability at the end of the pollen emission period of the tth day of the pollen emission period corresponding to the to-be-observed vegetation according to the temperature cumulative amount of the tth day, the pollen start period accumulated temperature threshold value, the pollen end period accumulated temperature threshold value, and the number of days of the pollen emission period corresponding to the to-be-observed vegetation. The processor is specifically configured to determine the flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period according to the flowering probability at the beginning of the pollen emission period and the flowering probability at the end of the pollen emission period of the to-be-observed vegetation on the tth day of the corresponding pollen emission period.

3. The system of claim 2, wherein, The processor is specifically configured to calculate the cumulative pollen emission score of the to-be-observed vegetation from the start time of the accumulated temperature to the tth day by the following formula: wherein, represents the accumulated pollen fraction emitted by the vegetation to be observed on the t-th day of the pollen emission period corresponding to the vegetation to be observed from the accumulated temperature start time represents the accumulated pollen fraction emitted by the vegetation to be observed on the t-th day of the pollen emission period corresponding to the vegetation to be observed from the accumulated temperature start time a temperature cumulative amount of a tth day of a pollen emission period corresponding to the vegetation to be observed, , a temperature of a tth day of a pollen emission period corresponding to the vegetation to be observed, a preset daily average temperature threshold value; denotes the pollen start period accumulated temperature threshold value; represents the pollen endophase accumulated temperature threshold.

4. The system of claim 2, wherein, The processor is specifically configured to calculate the flowering probability at the beginning of the pollen emission period of the to-be-observed vegetation on the tth day of the corresponding pollen emission period by the following formula: wherein, denotes the probability of flowering at the beginning of the pollen emission period on day t of the corresponding pollen emission period for the vegetation to be observed; a temperature cumulative amount of a tth day of a pollen emission period corresponding to the vegetation to be observed, , a temperature of a tth day of a pollen emission period corresponding to the vegetation to be observed, a preset daily average temperature threshold value, a cumulative temperature starting time; denotes the pollen start period accumulated temperature threshold value; a tolerance coefficient representing a relative temperature accumulation for constructing an over interval of temperature accumulation; a number of days representing a pollen emission period of the vegetation to be observed, wherein, a time of end of pollen emission of the vegetation to be observed, a time of start of pollen emission of the vegetation to be observed; and The flowering probability at the end of the pollen emission period of the to-be-observed vegetation on the tth day of the corresponding pollen emission period is calculated by the following formula: wherein, represents the probability of flowering at the end of the pollen emission period on the t-th day of the corresponding pollen emission period for the vegetation to be observed; denotes the pollen endophase accumulated temperature threshold; and The flowering probability of the to-be-observed vegetation on the tth day of the corresponding pollen emission period is calculated by the following formula: wherein, denotes the probability of flowering of the vegetation to be observed on the t-th day of the corresponding pollen emission period.

5. The system of any one of claims 2-4, wherein, The processor is specifically configured to calculate the pollen emission potential value of the to-be-observed vegetation on the tth day of the corresponding pollen emission period by the following formula: wherein, represents the pollen emission potential capacity value of the vegetation to be observed on the tth day of the corresponding pollen emission period; representing the start time of the accumulated temperature for the vegetation to be observed a cumulative pollen score emitted by the vegetation to be observed on the tth day of the pollen emission period corresponding to the vegetation to be observed; represents the probability of flowering of the vegetation to be observed on the t-th day of the corresponding pollen emission period; a land cover degree representing the vegetation to be observed; denotes a preset scaling factor characterizing the pollen emission enhancement effect parameter due to temperature change.

6. The system of claim 5, wherein, The processor is specifically configured to calculate the pollen emission amount of the to-be-observed vegetation on the tth day of the corresponding pollen emission period by the following formula: wherein, represents the pollen emission amount of the vegetation to be observed on the t-th day of the corresponding pollen emission period; represents the total production of pollen emission of the vegetation to be observed in the corresponding pollen emission period.

7. The system of claim 2, wherein, The meteorological factor represents the influence degree of meteorology on pollen emission, and the meteorological factor includes a wind factor, a precipitation factor, and a relative humidity factor; The processor is specifically configured to input the pollen emission amount on the tth day into a pollen simulation model, the pollen simulation model being obtained by improving a WRF-Chem model, and the pollen simulation model including a WRF module, a Chem module, and a pollen emission adjustment module; The WRF module is used to calculate the meteorological factor on the tth day, and the meteorological factor on the tth day is sent to the pollen emission adjustment module; The pollen emission adjustment module is used to calculate the target pollen emission amount of the to-be-observed vegetation on the tth day of the corresponding pollen emission period based on the pollen emission amount on the tth day and the meteorological factor on the tth day, and the target pollen emission amount on the tth day is sent to the Chem module; The Chem module is used to simulate pollen concentration based on the target pollen emission amount of the to-be-observed vegetation on each day of the corresponding pollen emission period; The pollen emission adjustment module calculates the target pollen emission amount of the to-be-observed vegetation on the tth day of the corresponding pollen emission period according to the following formula: wherein, represents the target pollen emission amount of the vegetation to be observed on the t-th day of the corresponding pollen emission period; represents the pollen emission amount of the day t of the pollen emission period corresponding to the vegetation to be observed; wind factor representing the tth day of the pollen emission period corresponding to the vegetation to be observed; a precipitation factor indicative of the t-th day of the pollen emission period corresponding to the vegetation to be observed; represents the relative humidity factor of the day t of the pollen emission period corresponding to the vegetation to be observed.

8. The system of claim 4, wherein, Different types of to-be-observed vegetation correspond to different pollen start period accumulated temperature threshold values and pollen end period accumulated temperature threshold values; and The processor is further configured to, before determining the pollen emission cumulative score from the start time of the accumulated temperature to the tth day and the flowering probability of the tth day according to the accumulated temperature of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, and the number of days of the pollen emission period, optimize the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, the start time of the accumulated temperature, and the preset daily average temperature threshold corresponding to the to-be-observed vegetation by using a simulated annealing algorithm to obtain the optimized pollen start period accumulated temperature threshold, pollen end period accumulated temperature threshold, start time of the accumulated temperature, and daily average temperature threshold of the to-be-observed vegetation.

9. A method of pollen emission and concentration simulation, characterized in that, Comprise: Receiving a pollen emission and concentration simulation request sent by a terminal, the pollen emission and concentration simulation request carrying to-be-observed vegetation information, specified observation site information, and request simulation year information; According to the request simulation year, obtain meteorological observation data of a specified observation site on each day of the pollen emission period of the to-be-observed vegetation; According to the meteorological observation data of the specified observation site on each day of the pollen emission period of the to-be-observed vegetation and a pollen yield prediction model, predict the total pollen emission yield of the to-be-observed vegetation of the specified observation site during the pollen emission period, the pollen yield prediction model being obtained according to historical sample meteorological observation data of a sample observation site and sample pollen observation data of the to-be-observed vegetation according to a preset machine learning model; Obtain the accumulated temperature of the tth day of the pollen emission period, and determine the pollen emission potential value of the tth day according to the accumulated temperature of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, the number of days of the pollen emission period, and a constructed standardized pollen emission potential model, the standardized pollen emission potential model being used to calculate the pollen emission potential value; According to the accumulated temperature of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, the number of days of the pollen emission period, and the constructed standardized pollen emission potential model, determine the pollen emission potential value of the tth day, specifically comprising: determining the pollen emission cumulative score of the to-be-observed vegetation from the start time of the accumulated temperature to the tth day and the flowering probability of the tth day according to the accumulated temperature of the tth day, the pollen start period accumulated temperature threshold, the pollen end period accumulated temperature threshold, and the number of days of the pollen emission period; and determining the pollen emission potential value of the tth day according to the pollen emission cumulative score from the start time of the accumulated temperature to the tth day, the flowering probability of the tth day, and the standardized pollen emission potential model; Determine the pollen emission amount of the tth day according to the total pollen emission yield and the pollen emission potential value of the tth day; Obtain the meteorological factor of the tth day, determine the target pollen emission amount of the tth day according to the pollen emission amount of the tth day and the meteorological factor of the tth day, and simulate the pollen emission and concentration of each day of the pollen emission period, the target pollen emission amount being the pollen emission amount after adding meteorological disturbance; Return the simulation result of the pollen emission and concentration of each day of the pollen emission period to the terminal.

Images