CN114580178B - Mosquito distribution prediction method, device, equipment and storage medium - Google Patents

Mosquito distribution prediction method, device, equipment and storage medium Download PDF

Info

Publication number
CN114580178B
CN114580178B CN202210223156.0A CN202210223156A CN114580178B CN 114580178 B CN114580178 B CN 114580178B CN 202210223156 A CN202210223156 A CN 202210223156A CN 114580178 B CN114580178 B CN 114580178B
Authority
CN
China
Prior art keywords
current
target
variable
information
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210223156.0A
Other languages
Chinese (zh)
Other versions
CN114580178A (en
Inventor
任周鹏
刘新
刘祥龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Geographic Sciences and Natural Resources of CAS
Original Assignee
Institute of Geographic Sciences and Natural Resources of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Institute of Geographic Sciences and Natural Resources of CAS filed Critical Institute of Geographic Sciences and Natural Resources of CAS
Priority to CN202210223156.0A priority Critical patent/CN114580178B/en
Publication of CN114580178A publication Critical patent/CN114580178A/en
Application granted granted Critical
Publication of CN114580178B publication Critical patent/CN114580178B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9537Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention discloses a method, a device, equipment and a storage medium for predicting mosquito distribution. The method comprises the following steps: acquiring current appearance position points and current missing position points of target mosquitoes in a preset area, and current and future climate and land utilization information of each position point; performing univariate modeling based on climate and land utilization information at the current appearance position and the current missing position to determine a target prediction variable; modeling based on variable information of a current occurrence point and variable information of a current missing point with different distances, determining the relationship between the distance and a model of each model, and determining a target distance and a target model; modeling is carried out based on the current variable information and the target missing point variable information, and a target prediction model is obtained; and inputting each future variable information into a target prediction model to predict whether target mosquitoes appear in the future or not, and obtaining a distribution prediction result, so that the accuracy of mosquito distribution prediction can be improved.

Description

Mosquito distribution prediction method, device, equipment and storage medium
Technical Field
The embodiment of the invention relates to computer technology, in particular to a method, a device, equipment and a storage medium for predicting mosquito distribution.
Background
Mosquito-borne infectious diseases refer to vector infectious diseases transmitted by mosquitoes, such as malaria and the like. The geographical distribution of mosquitoes is highly correlated with the occurrence place of the sensing diseases, so that the prediction of the geographical distribution of mosquitoes can provide key information for understanding the potential distribution pattern of the diseases. Climate change can affect the geographical distribution of mosquitoes. For example, temperature and precipitation are the two most important influencing factors. Future changes in temperature rise and precipitation patterns may affect the entire life process of mosquitoes, including the eggs, larvae, pupae, and adults.
At present, target missing position points required for modeling are usually artificially selected or randomly generated from all missing position points where mosquitoes do not appear at present, modeling is performed based on climate information at the target missing position points and the climate information at the mosquito appearing position points, and mosquito distribution prediction is performed based on a modeled model so as to analyze the influence of climate change on mosquito distribution.
However, in the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
the target missing position points which are artificially selected or randomly generated may not be the situation that mosquitoes do not appear due to climate reasons, so that an error prediction result is caused when the target missing position points are used for modeling, the prediction precision of the model is reduced, and the mosquito distribution prediction accuracy is further reduced.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for predicting mosquito distribution, which are used for improving the accuracy of mosquito distribution prediction.
In a first aspect, an embodiment of the present invention provides a method for predicting mosquito distribution, including:
acquiring a current appearance position point of a current target mosquito in a preset geographic area, a current missing position point of a current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographic area;
performing univariate modeling based on the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to target mosquitoes from all climate variables and all land utilization variables;
performing modeling operation of at least one prediction model based on variable information of a current occurrence point and variable information of a current missing point generated by different distances from a current occurrence position point, determining a variation relation between the distance and the model performance of each model, and determining a target distance and a target model based on the variation relation, wherein the variable information of the current occurrence point comprises: current variable information of the target predictive variable at the current appearance position point, the current missing point variable information including: current variable information of the target predictor variable at the current missing position point outside each distance from the current occurrence position point;
performing modeling operation on a target model based on current variable information of a target prediction variable at a current position and target missing point variable information corresponding to a target distance to obtain a modeled target prediction model;
and inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into a target prediction model to predict whether target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
In a second aspect, an embodiment of the present invention further provides a mosquito distribution prediction apparatus, where the apparatus includes:
the information acquisition module is used for acquiring a current appearance position point of a current target mosquito in a preset geographic area, a current missing position point of a current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographic area;
the target prediction variable determination module is used for carrying out univariate modeling on the basis of the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to target mosquitoes from all climate variables and all land utilization variables;
the target distance determining module is used for carrying out modeling operation on at least one prediction model based on variable information of a current occurrence point and variable information of a current missing point generated by different distances from a current occurrence position point, determining a variation relation between the distance and the model performance of each model, and determining a target distance and a target model based on the variation relation, wherein the variable information of the current occurrence point comprises: current variable information of the target predictive variable at the current appearance position point, the current missing point variable information including: current variable information of the target predictor variable at the current missing position point outside each distance from the current occurrence position point;
the target prediction model determining module is used for carrying out modeling operation on a target model based on the current variable information of a target prediction variable at a current position and the target missing point variable information corresponding to the target distance to obtain a modeled target prediction model;
and the prediction result determining module is used for inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into the target prediction model to predict whether target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the mosquito distribution prediction method according to any embodiment of the present invention.
In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a mosquito distribution prediction method according to any embodiment of the present invention.
The embodiment of the invention has the following advantages or beneficial effects:
the method comprises the steps of carrying out univariate modeling based on current climate information and current land utilization information at a current occurrence position point of a current occurrence target mosquito in a preset geographic area and current climate information and current land utilization information at a current deletion position point of a current absence target mosquito, and determining target prediction variables related to target mosquito distribution from all climate variables and all land utilization variables so as to further improve the accuracy of mosquito distribution prediction. The modeling operation of at least one prediction model is carried out on the basis of the variable information of the current occurrence point and the variable information of the current missing point generated at different distances from the current occurrence position point, the change relation between the distance and the model performance of each model is determined, and the most appropriate target distance and the target model with the optimal performance are automatically determined on the basis of the change relation, so that the modeling operation of the target model is carried out on the basis of the current variable information of the target prediction variable at the current missing position point outside the target distance from the current occurrence position point, a more accurate target prediction model can be obtained, the defect of artificial selection or random generation of missing position point modeling is overcome, and the prediction precision and accuracy of the future distribution prediction result are effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of a method for predicting mosquito distribution according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for predicting mosquito distribution according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a mosquito distribution prediction apparatus according to a third embodiment of the present invention;
fig. 4 is a block diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for predicting mosquito distribution according to an embodiment of the present invention, which is applicable to predicting mosquito distribution, and in particular, can be used to analyze influences of climate change and land use change on mosquito distribution. The method may be performed by a mosquito distribution prediction apparatus, which may be implemented by software and/or hardware, integrated in an electronic device. The method specifically comprises the following steps:
s110, acquiring a current appearance position point of a current target mosquito in a preset geographic area, a current missing position point of a current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographic area.
The preset geographic area can be any geographic area which is preset based on business requirements and needs to predict mosquito distribution conditions. For example, the preset geographic area may be the area of the territory of a country, or the area of an asian-european plate. For example, a predetermined geographic area may be set to 25 national regions contained in the southeast Asia and the Western Pacific, the region containing 19 major malaria mosquito vectors with intricate malaria transmission patterns, and the severe environmental and socioeconomic growth problems of the region as well as the staggered influence of population, geographic location, and multiple climate types make the region more susceptible to climate change, which may change the existing distribution pattern of the malaria mosquito vectors in the region, thereby increasing the threat of regional malaria. The target mosquito may be any mosquito vector that transmits an infectious disease, for example, the target mosquito may be, but is not limited to, anopheles macrolepis, etc., which is used to transmit malaria. The current appearance position point may refer to a position point at which the target mosquitoes appear at the current time in the preset geographical area. The current missing location point may refer to a location point where the target mosquitoes do not appear at the current time in the preset geographical area.
Specifically, the current appearance position point and the current missing position point of the target mosquito in the preset geographic area may be obtained through a map project database for recording the target mosquito. For example, when the target mosquito is a mosquito vector for transmitting a malaria infectious disease, the current appearing location point and the current missing location point of the target mosquito in the preset geographic area may be obtained through a malaria map project database website.
The current climate information may refer to the climate information of each current occurrence location point or each current missing location point at the current time or at the previous historical time, which may be obtained from the world climate database. The future climate information may be climate information comprising at least one preset future time period for each currently occurring location point or each currently missing location point in at least one climate change scenario. For example, the climate change scenario may include two, a relatively stable emission scenario RCP4.5 and a severe emission scenario RCP 8.5. The preset future time period may include: 2030s (2020) -2049, 2050s (2040) -2069 and 2070s (2060) -2089). The future climate information can be acquired through meteorological change, agriculture, forestry and food safety websites. The climate information in this embodiment may include values of various climate variables related to temperature and precipitation, such as temperature seasonality, temperature year poor, coldest month minimum temperature, coldest season average temperature, warmest season average temperature, wetest season average temperature, year average temperature, wetest season precipitation, wetest month precipitation, dryest season average temperature, total year precipitation, isothermality, average day poor, wetest month maximum temperature, precipitation seasonal variation coefficient, warmest season precipitation, dryest season precipitation, coolest season precipitation, and dryest month precipitation.
The current land use information may refer to land use information of each current occurrence location point or each current absence location point at a current time or a previous historical time. The future land use information may include land use information for at least one preset future time period for each of the currently occurring location points or each of the currently missing location points under at least one climate change scenario. The current land use information and the future land use information may be acquired through a land use assimilation website. The land use information in this embodiment may include values of various land use variables, such as unit grid pasture occupation ratio, unit grid farmland occupation ratio, unit grid city occupation ratio, unit grid main land occupation ratio, and the like.
And S120, performing univariate modeling based on the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to the target mosquitoes from all the climate variables and all the land utilization variables.
The single variable modeling may refer to modeling by using unique variable information. The target predictive variable may refer to a variable that has an influence on the distribution of target mosquitoes among various climate variables and various land use variables.
Specifically, univariate modeling is carried out according to the numerical value of each climate variable and the numerical value of each land utilization variable of each current occurrence position point and each current deletion position point in a preset geographic area, the model performance corresponding to each constructed climate variable and the model performance corresponding to each land utilization variable are compared, each variable having an important influence effect on target mosquito distribution is determined from each climate variable and each land utilization variable, and the variables are used as target prediction variables.
S130, carrying out modeling operation on at least one prediction model based on variable information of a current occurrence point and variable information of a current missing point generated by different distances from the current occurrence position point, determining a change relation between the distance and the model performance of each model, and determining a target distance and a target model based on the change relation.
Wherein, the current appearance point variable information includes: current variable information of the target predictive variable at the current appearance position point. For example, when the target prediction variables are annual temperature difference, average temperature of the hottest season and unit grid grass ratio, the current occurrence point variable information may be an annual temperature difference value, an average temperature value of the hottest season and a unit grid grass ratio value. The current missing point variable information includes: current variable information for the target predictor variable at the current missing location point each distance away from the current occurrence location point. For each distance, the current missing point variable information may refer to current variable information of the target predictive variable at each current missing position point whose distance from the current appearance position point is equal to or greater than the distance. Wherein the respective distances may be set based on a preset distance interval. For example, if the preset distance interval is 25km, the respective distances may include 25km, 50km, 75km, and so on. For example, the current missing point variable information corresponding to 25km may refer to current variable information of each target predictive variable at each current missing position point 25km or 25km away from the current appearance position point. The predictive model may include, but is not limited to, at least one of a random forest model, an enhanced regression tree model, and a maximum entropy model.
Specifically, for the current missing point variable information corresponding to each distance, based on each current occurrence point variable information and each current missing point variable information corresponding to the distance, a modeling operation may be performed on each prediction model, and the model performance of each prediction model constructed at the distance may be determined. Based on the model performance of each prediction model at each distance, the variation relationship between the distance and the model performance of each model can be drawn, and based on the variation relationship, the influence variation of the distance on the model performance of each model can be determined, so that the most appropriate target distance for modeling can be determined from each distance, and meanwhile, based on the variation relationship, the influence variation of different models on the model performance can be determined, so that the optimal target model can be determined from each prediction model. For example, the modeling data for modeling, that is, the variable information of the current occurrence point and the variable information of the current missing point corresponding to each distance, may be divided to obtain training data (for example, 75% of modeling data) for training the building model and test data (that is, 25% of modeling data) for evaluating the performance of the model. Illustratively, based on the variation relationship, it is possible to select 250km as the target distance and select a random forest as the target model with higher prediction accuracy.
S140, modeling operation of the target model is carried out based on the current variable information of the target prediction variable at the current position and the target missing point variable information corresponding to the target distance, and the modeled target prediction model is obtained.
The target missing point variable information may refer to current variable information of the target prediction variable at each current missing position point whose distance from the current appearance position point is equal to or greater than the target distance. The target prediction model may refer to a model for predicting the distribution of the future target mosquitoes.
Specifically, the modeling operation of the target model can be performed according to the current variable information of the target prediction variable of the target mosquito at the current position and the more accurate target missing point variable information determined in the above steps, so as to construct the more accurate target prediction model.
S150, inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into the target prediction model to predict whether target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
The future variable information may refer to specific values of the target predictive variables at each location point in the preset geographic area in each climate change situation for each preset future time period.
Specifically, for each position point in the preset geographic area, the future variable information of each target prediction variable of the position point in a certain preset future time period under a certain climate change situation may be input into the target prediction model, and based on the output of the target preset model, the probability value that the target mosquitoes may appear in the preset future time period under the certain climate change situation at the position point may be obtained, and the probability value is compared with the preset probability threshold value to determine whether the target mosquitoes appear in the future at the position point. For example, if the probability value of the target mosquitoes appearing at the position point in the future is greater than a preset probability threshold, the prediction result corresponding to the position point is that the target mosquitoes appear at the position point in the preset future time period under the climate change situation; if the probability value of the target mosquitoes appearing at the position point in the future is smaller than the preset probability threshold value, the prediction result corresponding to the position point is that the target mosquitoes do not appear at the position point in the preset future time period under the climate change situation. The preset probability threshold may be manually set in advance based on a service scene, or may be automatically determined based on current climate information, so as to further ensure the accuracy of prediction. For example, the current variable information of the target prediction variable corresponding to each current occurrence position point may be input into the target prediction model to obtain each probability value, and the obtained average value may be used as the preset probability threshold. The embodiment can obtain the future distribution prediction result of the preset geographic area in each preset future time period under each climate change situation, namely the future distribution situation of the target mosquitoes, based on the prediction results of each position point in the preset geographic area in each preset future time period under each climate change situation.
According to the technical scheme of the embodiment of the invention, univariate modeling is carried out on the basis of the current climate information and the current land utilization information at the current appearance position, and the current climate information and the current land utilization information at the current missing position, and the target prediction variable corresponding to the target mosquito is determined from each climate variable and each land utilization variable, so that the variable with an important influence effect can be obtained, and the accuracy of target mosquito distribution prediction is improved. The modeling operation of at least one prediction model is carried out on the basis of the variable information of the current occurrence point and the variable information of the current missing point generated by different distances from the current occurrence position point, the variation relation between the distance and the model performance of each model is determined, and the target distance and the target model are automatically determined on the basis of the variation relation, so that the modeling operation of the target model is carried out on the basis of the current variable information of the target prediction variable at the current missing position point outside the target distance from the current occurrence position point, a more accurate target prediction model can be obtained, the defect of artificial selection or random generation of modeling of the missing position point is avoided, and the prediction precision and accuracy of a future distribution prediction result are effectively improved.
On the basis of the above technical solution, "performing univariate modeling based on the current climate information and the current land utilization information at the current occurrence position, and the current climate information and the current land utilization information at the current deletion position, and determining a target prediction variable corresponding to a target mosquito from each climate variable and each land utilization variable" in S120 may include: performing modeling operation of a univariate preset model on each climate variable and each land utilization variable based on current climate information and current land utilization information at the current position, and current climate information and current land utilization information at the current missing position, and determining the importance degree corresponding to each variable based on the performance evaluation index of the preset model corresponding to each variable after modeling; and determining the variable with the importance degree larger than the preset threshold value as a target prediction variable corresponding to the target mosquito.
Wherein the preset model may be, but is not limited to, a maximum entropy model. The performance evaluation index may be used to evaluate an influence of each variable on an output result of the preset model, and may be, but is not limited to, an AUC (Area Under ROC Curve, Area enclosed by coordinate axes) index. The preset threshold may be a critical threshold for determining whether the variable is important for the prediction model, and optionally, the preset threshold may be 0.7.
Specifically, for each climate variable and each individual land use variable, a modeling operation may be performed on a preset model based on variable information of the variable at each current occurrence position point and each current deletion position point in a preset geographic area, and a performance test may be performed on the built preset model corresponding to the variable to determine a performance evaluation index corresponding to the variable. In this embodiment, the performance evaluation index result corresponding to each variable may be directly determined as the importance degree corresponding to the corresponding variable, for example, an AUC index value corresponding to each preset model that is constructed may be used as the importance degree corresponding to each variable. And determining variables of which AUC index values in the preset model are larger than a preset threshold value as climate variables and land utilization variables which have great influence on target mosquito distribution, and taking the variables as target prediction variables.
For example, determining a variable with a degree of importance greater than a preset threshold as a target prediction variable corresponding to the target mosquito may include: screening out second variables with biological significance from the first variables based on the biological significance of each first variable with the importance degree greater than a preset threshold value to the target mosquitoes; and determining a Pearson correlation coefficient between every two second variables, eliminating the second variable with smaller importance degree in the two second variables of which the Pearson correlation coefficient is larger than a preset coefficient threshold value, and determining each second variable obtained after elimination as a target prediction variable corresponding to the target mosquito.
The first variable may be a climate variable and a land utilization variable which are determined based on a preset model and have a large influence on mosquito distribution among the climate variables and the land utilization variables. The second variable may be a variable that has biological significance in the first variable. The preset coefficient threshold may refer to an evaluation index indicating a correlation between the second variables.
Specifically, a variable having an important biological significance is selected from the first variables determined based on the preset model, and is used as the second variable. The correlation between every two second variables is calculated by utilizing the Pearson correlation coefficient, the second variable with smaller importance degree in the two second variables corresponding to the Pearson correlation coefficient being smaller than the preset coefficient threshold is eliminated by comparing with the preset coefficient threshold, and the residual second variable after elimination is used as a target prediction variable, so that the climate variable and the land utilization variable which more accurately influence the mosquito distribution can be obtained, and the accuracy of distribution prediction is further improved.
For example, in predicting the distribution of malaria mosquito vectors, the first variables determined based on the predetermined model may include (ranked by decreasing importance): the temperature seasonality, the temperature year is poor, the unit grid pasture occupation ratio, the coldest month lowest temperature, the coldest season average temperature, the warmest season average temperature, the wetest season average temperature, the year average temperature, the wetest season rainfall, the wetest month rainfall, the dryest season average temperature, the unit grid farmland occupation ratio, the total year rainfall, the isothermicity, the unit grid city land occupation ratio, the average day is poor, the unit grid main land occupation ratio, the wetest month maximum temperature, the seasonal variation coefficient of the rainfall and the warmest season rainfall are 20 first variables. Based on the biological significance of the malaria mosquito vectors, variables of importance but not biological significance can be further excluded, such as four first variables of seasonal temperature, isothermal temperature, average daily difference, seasonal precipitation coefficient of variation, and the remaining 16 second variables. The correlation between variables is calculated using the pearson correlation coefficient, which need not be calculated since there is no high correlation between land use variables or between climate variables. If the pearson correlation coefficients between the annual temperature difference and the coldest month lowest temperature are both greater than the predetermined coefficient threshold, but the degree of importance (e.g., AUC indicator value) corresponding to the annual temperature difference is greater than the degree of importance (e.g., AUC indicator value) corresponding to the coldest month lowest temperature, the second variable, coldest month lowest temperature, may be excluded. Similarly, each of the second variables remaining after the elimination, i.e., each of the target predicted variables, may include: temperature seasonality, average temperature in the warmest season, precipitation amount in the wetest season, unit grid pasture ratio, unit grid farmland ratio, unit grid city land ratio and unit grid main land ratio.
On the basis of the above technical solution, after S150 "obtaining a future distribution prediction result corresponding to a preset geographic area", the method further includes: determining a future habitability area increase area and a future habitability area decrease area corresponding to the target mosquitoes based on future distribution prediction results corresponding to the preset geographic area and current distribution information corresponding to the target mosquitoes; acquiring population distribution information corresponding to a preset geographic area; based on the population distribution information, the number of exposed population corresponding to the future growing region increase area and the number of exposed population corresponding to the future growing region decrease area are determined.
The population distribution information can be obtained through climate and global dynamic laboratory websites, and comprises population distribution data (SSP1-SSP5) under five shared socioeconomic scenarios, the SSP1 represents a sustainable development path, the SSP2 represents an intermediate path of population development and economic growth, the SSP3 and the SSP4 represent regional competition paths and unequal paths under low development tracks respectively, and the SSP5 represents a development path mainly based on petroleum burning. Wherein, the time of population distribution information selection is consistent with the time point of future climate information selection. The exposure population number may refer to the number of populations affected by the target mosquito distribution area. The future habitat increasing area may refer to an area in which the target mosquitoes do not appear at a certain position point in the preset geographic area at present, but the target mosquitoes appear in the future. The future habitat reduction area may be an area where the target mosquitoes appear at a certain position point in the preset geographical area at present but the target mosquitoes disappear in the future.
Specifically, the future distribution situation of the target mosquitoes is compared with the current distribution situation, a future adapted living area increasing area and a future adapted living area decreasing area of the target mosquitoes are determined, and based on population distribution information of each area in a preset geographic area, the number of exposed population of the future adapted living area increasing area and the number of exposed population of the future adapted living area decreasing area can be respectively counted by using a partition statistical mode, for example, the number of exposed population of the two areas in each preset future time period under each climate change situation is obtained. Through the statistical population exposure, the population exposure change caused by the change of the target mosquito habitability area under the future climate and socioeconomic development scenes can be visually compared, so that the method can be more favorable for the formulation of mosquito media prevention and control related strategies based on the information.
Example two
Fig. 2 is a flowchart of a mosquito distribution prediction method according to a second embodiment of the present invention, and this embodiment describes in detail the determination of the target distance and the target model based on the foregoing embodiments. Wherein explanations of the same or corresponding terms as those of the above embodiments are omitted. As shown in fig. 2, the method for predicting mosquito distribution specifically includes the following steps:
s210, acquiring a current appearance position point of a current target mosquito in a preset geographic area, a current missing position point of a current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographic area.
S220, performing univariate modeling based on the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to target mosquitoes from all climate variables and all land utilization variables.
And S230, determining the distance between each current missing position point and the current appearing position point.
Specifically, a preset number of position points, for example 10000 random points, may be randomly generated on a sub-region where the target mosquitoes do not appear in the preset geographic region, as the current missing position points, and a distance between each current missing position point and the current appearing position point is determined.
And S240, determining the current missing point variable information corresponding to each distance based on the preset distance interval.
The preset distance interval may refer to distance division of each current missing position point according to a certain distance with the current appearing position point as a reference. Illustratively, the preset distance interval is 25 km.
Specifically, the distance determined based on the preset distance interval may be plural. For example, a first distance of 25km, a second distance of 50km, and so on. For each distance, the current missing point variable information may refer to current variable information of the target predictive variable at each current missing position point whose distance from the current appearance position point is equal to or greater than the distance. The current missing point variable information corresponding to each distance can be screened out based on the distance between each current missing position point and the current appearing position point. For example, the current missing point variable information corresponding to 25km may refer to current variable information of each target predictive variable at each current missing location point 25km or 25km away from the current appearance location point.
And S250, performing modeling operation and model performance evaluation on at least one prediction model based on the variable information of the current occurrence point and the variable information of the current missing point corresponding to each distance, and determining the change relationship between the distance and the model performance of each model.
Wherein the prediction model comprises at least one of a random forest model, an enhanced regression tree model, and a maximum entropy model. Specifically, for the current missing point variable information corresponding to each distance, based on each current occurrence point variable information and each current missing point variable information corresponding to the distance, a modeling operation may be performed on each prediction model, and the model performance of each prediction model constructed at the distance may be determined. Based on the model performance of each prediction model at each distance, the variation relationship between each distance and the model performance under each prediction model can be drawn.
And S260, determining a target distance corresponding to the optimal model performance and a target model with the optimal performance based on the variation relation.
Specifically, for each constructed prediction model, the influence change of each distance on the model performance of the model may be determined based on the change relationship, so that the optimal distance corresponding to the prediction model may be determined from each distance, for example, the distance corresponding to the model when the model performance is the highest or when the model performance is stable is determined as the optimal distance, and the optimal distances corresponding to each prediction model are averaged, and the obtained average optimal distance is used as the optimal target distance. For the target distance, the influence of each prediction model on the model performance at the target distance may be changed based on the change relationship, so that an optimal target model may be determined from each prediction model, for example, a prediction model with the highest model performance at the target distance is used as the target model.
S270, modeling operation of the target model is carried out based on the current variable information of the target prediction variable at the current position and the target missing point variable information corresponding to the target distance, and the modeled target prediction model is obtained.
S280, inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into the target prediction model to predict whether target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
According to the technical scheme of the embodiment, the current missing point variable information corresponding to each distance is determined based on the preset distance interval, the modeling operation and the model performance evaluation are performed based on the current occurring point variable information and the current missing point variable information corresponding to each distance, the change relationship between the distance and the model performance of each model is determined, the target distance corresponding to the optimal model performance and the target model with the optimal performance can be automatically and accurately determined based on the change relationship, the defect that missing position points are artificially selected or randomly generated for modeling can be further avoided, and the accuracy of future mosquito distribution prediction is further effectively improved.
The following is an embodiment of the mosquito distribution prediction apparatus provided in the embodiments of the present invention, and the apparatus and the mosquito distribution prediction method of the embodiments belong to the same inventive concept, and details that are not described in detail in the embodiments of the mosquito distribution prediction apparatus may refer to the embodiments of the mosquito distribution prediction method.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a mosquito distribution prediction apparatus according to a third embodiment of the present invention, which is applicable to predicting future mosquito distribution. The specific structure of the mosquito distribution prediction device is as follows: an information acquisition module 310, a target prediction variable determination module 320, a target distance determination module 330, a target prediction model determination module 340, and a prediction result determination module 350.
The information acquisition module 310 is configured to acquire a current occurrence position point of a current occurrence target mosquito in a preset geographic area, a current missing position point of a current non-occurrence target mosquito in the preset geographic area, and current climate information, future climate information, current land utilization information, and future land utilization information corresponding to each position point in the preset geographic area; the target prediction variable determination module 320 is used for performing univariate modeling on the basis of the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to target mosquitoes from all climate variables and all land utilization variables; a target distance determining module 330, configured to perform modeling operation on at least one prediction model based on the variable information of the current occurrence point and the variable information of the current missing point generated at different distances from the current occurrence point, determine a variation relationship between the distance and the model performance of each model, and determine a target distance and a target model based on the variation relationship, where the variable information of the current occurrence point includes: current variable information of the target predictive variable at the current appearance position point, the current missing point variable information including: current variable information of the target predictor variable at the current missing position point outside each distance from the current occurrence position point; the target prediction model determining module 340 is configured to perform modeling operation on a target model based on current variable information of a target prediction variable at a current occurrence position and target missing point variable information corresponding to a target distance, so as to obtain a modeled target prediction model; the prediction result determining module 350 is configured to input future variable information of the target prediction variable corresponding to each location point in the preset geographic area into the target prediction model to predict whether target mosquitoes appear in the future at each location point, and obtain a future distribution prediction result corresponding to the preset geographic area based on output of the target prediction model.
According to the technical scheme of the embodiment of the invention, the target prediction variable is determined by carrying out univariate modeling on the basis of the climate and land utilization information at the current position and the current missing position, so that the variable having an important influence on the prediction model can be determined, and the accuracy of the prediction model can be further improved. The method is characterized in that modeling is carried out based on variable information of a current occurrence point and variable information of a current missing point with different distances, the relation between the distance and a model of each model is determined, and a target distance and a target model are determined, so that modeling can be carried out based on the variable information of the current occurrence point and the variable information of the target missing point, a more accurate target prediction model can be obtained, the defect of artificial selection or random generation of missing position point modeling is overcome, and the prediction precision and accuracy of a future distribution prediction result are effectively improved.
Optionally, the target prediction variable determining module 320 includes:
a model evaluation unit to: performing modeling operation of a univariate preset model on each climate variable and each land utilization variable based on current climate information and current land utilization information at the current position, and current climate information and current land utilization information at the current missing position, and determining the importance degree corresponding to each variable based on the performance evaluation index of the preset model corresponding to each variable after modeling;
and the target predictive variable determining unit is used for determining the variable with the importance degree larger than a preset threshold value as the target predictive variable corresponding to the target mosquito.
Optionally, the preset model is a maximum entropy model; the performance evaluation index is an AUC value of the maximum entropy model.
Optionally, the target prediction variable determining unit includes:
the second variable determination subunit is used for screening out second variables with biological significance from all the first variables based on the biological significance of each first variable with the importance degree greater than a preset threshold value to the target mosquitoes;
and the target predictive variable determining subunit is used for determining a Pearson correlation coefficient between every two second variables, eliminating the second variable with smaller importance degree in the two second variables of which the Pearson correlation coefficient is greater than a preset coefficient threshold value, and determining each second variable obtained after elimination as the target predictive variable corresponding to the target mosquito.
Optionally, the target prediction model determining module 340 includes:
the distance determining unit is used for determining the distance between each current missing position point and the current appearing position point;
the variable information determining unit is used for determining current missing point variable information corresponding to each distance based on a preset distance interval;
the model performance evaluation unit is used for carrying out modeling operation and model performance evaluation on at least one prediction model based on the variable information of the current occurrence point and the variable information of the current missing point corresponding to each distance, and determining the change relation between the distance and the model performance of each model;
and the target model determining unit is used for determining the target distance corresponding to the optimal model performance and the optimal performance target model based on the change relation.
Optionally, the prediction model includes: at least one of a random forest model, an enhanced regression tree model, and a maximum entropy model.
Optionally, the prediction result determining module 350 includes:
the future survival area determining unit is used for determining a future survival area increasing area and a future survival area decreasing area corresponding to the target mosquitoes based on the future distribution prediction result corresponding to the preset geographic area and the current distribution information corresponding to the target mosquitoes;
the population distribution information determining unit is used for acquiring population distribution information corresponding to a preset geographic area;
and the exposed population number determining unit is used for determining the exposed population number corresponding to the future growing area increasing area and the exposed population number corresponding to the future growing area decreasing area based on the population distribution information.
The mosquito distribution prediction device provided by the embodiment of the invention can execute the method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
It should be noted that, in the embodiment of the mosquito distribution prediction apparatus, the units and modules included in the embodiment are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Example four
Fig. 4 is a block diagram of an electronic device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 4 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 4, electronic device 12 is embodied in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown, the network adapter 20 communicates with the other modules of the electronic device 12 over the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implements a mosquito distribution prediction method provided in this embodiment, including:
acquiring a current appearance position point of a current target mosquito in a preset geographic area, a current missing position point of a current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographic area;
performing univariate modeling based on the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to target mosquitoes from all climate variables and all land utilization variables;
carrying out modeling operation of at least one prediction model based on variable information of a current occurrence point and variable information of a current missing point generated by different distances from a current occurrence position point, determining a variation relation between the distance and the model performance of each model, and determining a target distance and a target model based on the variation relation, wherein the variable information of the current occurrence point comprises: current variable information of a target predictor at a current occurrence position point, the current missing point variable information including: current variable information of the target predictor variable at the current missing position point outside each distance from the current occurrence position point;
performing modeling operation on a target model based on current variable information of a target prediction variable at a current position and target missing point variable information corresponding to a target distance to obtain a modeled target prediction model;
and inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into a target prediction model to predict whether target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
Of course, those skilled in the art can understand that the processor may also implement the technical solution of the mosquito distribution prediction method provided in any embodiment of the present invention.
EXAMPLE five
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the mosquito distribution prediction method steps as provided in any embodiment of the present invention, the method including:
acquiring a current occurrence position point of a current target mosquito in a preset geographical area, a current missing position point of a current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographical area;
performing univariate modeling based on the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to target mosquitoes from all climate variables and all land utilization variables;
performing modeling operation of at least one prediction model based on variable information of a current occurrence point and variable information of a current missing point generated by different distances from a current occurrence position point, determining a variation relation between the distance and the model performance of each model, and determining a target distance and a target model based on the variation relation, wherein the variable information of the current occurrence point comprises: current variable information of the target predictive variable at the current appearance position point, the current missing point variable information including: current variable information of the target predictor variable at the current missing position point outside each distance from the current occurrence position point;
performing modeling operation on a target model based on current variable information of a target prediction variable at a current position and target missing point variable information corresponding to a target distance to obtain a modeled target prediction model;
and inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into a target prediction model to predict whether target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It will be understood by those skilled in the art that the modules or steps of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented by program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, or it may be separately fabricated into various integrated circuit modules, or it may be fabricated by fabricating a plurality of modules or steps thereof into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (10)

1. A mosquito distribution prediction method is characterized by comprising the following steps:
acquiring a current appearance position point of a current target mosquito in a preset geographic area, a current missing position point of the current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographic area;
performing univariate modeling based on the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to the target mosquitoes from all climate variables and all land utilization variables;
carrying out modeling operation of at least one prediction model based on variable information of a current occurrence point and variable information of a current missing point generated by different distances from the current occurrence position point, determining a variation relation between the distance and the model performance of each model, and determining a target distance and a target model based on the variation relation, wherein the variable information of the current occurrence point comprises: current variable information of the target predictor variable at the current occurrence position point, the current missing point variable information including: current variable information for the target predictor variable at a current missing location point that is outside each distance from a current occurrence location point;
performing modeling operation on a target model based on the current variable information of the target prediction variable at the current position and the target missing point variable information corresponding to the target distance to obtain a modeled target prediction model;
inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into the target prediction model to predict whether the target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
2. The method of claim 1, wherein the determining a target predictor variable corresponding to the target mosquito from the respective climate variables and the respective land utilization variables based on current climate information and current land utilization information at the current occurrence location point and current climate information and current land utilization information at the current absence location point comprises:
performing modeling operation of a univariate preset model on each climate variable and each land utilization variable based on the current climate information and the current land utilization information at the current appearing position point and the current climate information and the current land utilization information at the current missing position point, and determining the importance degree corresponding to each variable based on the performance evaluation index of the preset model corresponding to each variable after modeling;
and determining the variable with the importance degree larger than a preset threshold value as a target prediction variable corresponding to the target mosquito.
3. The method according to claim 2, wherein the preset model is a maximum entropy model; the performance evaluation index is an AUC value of the maximum entropy model.
4. The method according to claim 2, wherein the determining the variable with the importance degree greater than a preset threshold as the target prediction variable corresponding to the target mosquito comprises:
screening out second variables with biological significance from the first variables based on the biological significance of each first variable with the importance degree larger than a preset threshold value on the target mosquitoes;
determining a Pearson correlation coefficient between every two second variables, excluding the second variable with smaller importance degree from the two second variables with the Pearson correlation coefficient being larger than a preset coefficient threshold value, and determining each second variable obtained after exclusion as a target prediction variable corresponding to the target mosquito.
5. The method of claim 1, wherein the performing at least one predictive model modeling operation based on the variable information of the current occurrence point and the variable information of the current absence point generated at different distances from the current occurrence point, determining a variation relationship between the distance and the model performance of each model, and determining a target distance and a target model based on the variation relationship comprises:
determining a distance between each of the current missing location points and the current occurring location point;
determining current missing point variable information corresponding to each distance based on a preset distance interval;
performing modeling operation and prediction model performance evaluation of at least one prediction model based on the variable information of the current occurrence point and the variable information of the current missing point corresponding to each distance, and determining the change relationship between the distance and the model performance of each prediction model;
and determining the target distance corresponding to the optimal model performance and the optimal performance target model based on the change relation.
6. The method of claim 1, wherein the predictive model comprises: at least one of a random forest model, an enhanced regression tree model, and a maximum entropy model.
7. The method according to any one of claims 1-6, further comprising, after obtaining the future distribution prediction corresponding to the predetermined geographic area:
determining a future growth suiting area increasing area and a future growth suiting area decreasing area corresponding to the target mosquitoes based on the future distribution prediction result corresponding to the preset geographic area and the current distribution information corresponding to the target mosquitoes;
acquiring population distribution information corresponding to the preset geographic area;
determining the number of exposed population corresponding to the future growing region increasing area and the number of exposed population corresponding to the future growing region decreasing area based on the population distribution information.
8. A mosquito distribution prediction device, comprising:
the information acquisition module is used for acquiring a current appearance position point of a current target mosquito in a preset geographic area, a current deletion position point of a current target mosquito, and current climate information, future climate information, current land utilization information and future land utilization information corresponding to each position point in the preset geographic area;
the target prediction variable determination module is used for carrying out univariate modeling on the basis of the current climate information and the current land utilization information at the current appearance position point and the current climate information and the current land utilization information at the current missing position point, and determining target prediction variables corresponding to the target mosquitoes from all climate variables and all land utilization variables;
a target distance determining module, configured to perform modeling operation on at least one prediction model based on variable information of a current occurrence point and variable information of a current missing point generated at a different distance from the current occurrence point, determine a variation relationship between the distance and model performance of each model, and determine a target distance and a target model based on the variation relationship, where the variable information of the current occurrence point includes: current variable information of the target predictor variable at the current occurrence location point, the current missing point variable information including: current variable information for the target predictor variable at a current missing location point that is outside each distance from a current occurrence location point;
the target prediction model determining module is used for carrying out modeling operation on a target model based on the current variable information of the target prediction variable at the current position and the target missing point variable information corresponding to the target distance to obtain a modeled target prediction model;
and the prediction result determining module is used for inputting future variable information of the target prediction variable corresponding to each position point in the preset geographic area into the target prediction model to predict whether the target mosquitoes appear in the future at each position point, and obtaining a future distribution prediction result corresponding to the preset geographic area based on the output of the target prediction model.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the mosquito distribution prediction method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the mosquito distribution prediction method according to any one of claims 1 to 7.
CN202210223156.0A 2022-03-09 2022-03-09 Mosquito distribution prediction method, device, equipment and storage medium Active CN114580178B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210223156.0A CN114580178B (en) 2022-03-09 2022-03-09 Mosquito distribution prediction method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210223156.0A CN114580178B (en) 2022-03-09 2022-03-09 Mosquito distribution prediction method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114580178A CN114580178A (en) 2022-06-03
CN114580178B true CN114580178B (en) 2022-08-30

Family

ID=81773475

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210223156.0A Active CN114580178B (en) 2022-03-09 2022-03-09 Mosquito distribution prediction method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114580178B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116166762A (en) * 2022-12-27 2023-05-26 广东省农业科学院农业经济与信息研究所 Method for generating electronic map of plant diseases and insect pests, unmanned aerial vehicle system and control device
CN116721781B (en) * 2023-07-11 2024-08-20 中国科学院地理科学与资源研究所 Method and device for predicting insect vector infectious disease transmission risk, electronic equipment and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013054005A (en) * 2011-09-06 2013-03-21 Seiko Epson Corp Weather variation information providing system, weather variation information providing method, weather variation information providing program and recording medium
WO2019177620A1 (en) * 2018-03-16 2019-09-19 Ford Motor Company Optimizing and predicting availability of resources in a shared vehicle environment
CN111026823A (en) * 2019-11-27 2020-04-17 北京大学 Resource utilization associated network model planning method based on geographic position data
US10672114B1 (en) * 2017-10-27 2020-06-02 Liberty Mutual Insurance Company Computationally efficient distance-based score approximations
CN111260148A (en) * 2020-02-10 2020-06-09 长江大学 Pine wood nematode invasion risk prediction method based on ecological niche factor model
CN113901348A (en) * 2021-11-10 2022-01-07 江苏省血吸虫病防治研究所 Oncomelania snail distribution influence factor identification and prediction method based on mathematical model

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11068737B2 (en) * 2018-03-30 2021-07-20 Regents Of The University Of Minnesota Predicting land covers from satellite images using temporal and spatial contexts
US20210350295A1 (en) * 2020-05-11 2021-11-11 International Business Machines Corporation Estimation of crop pest risk and/or crop disease risk at sub-farm level

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013054005A (en) * 2011-09-06 2013-03-21 Seiko Epson Corp Weather variation information providing system, weather variation information providing method, weather variation information providing program and recording medium
US10672114B1 (en) * 2017-10-27 2020-06-02 Liberty Mutual Insurance Company Computationally efficient distance-based score approximations
WO2019177620A1 (en) * 2018-03-16 2019-09-19 Ford Motor Company Optimizing and predicting availability of resources in a shared vehicle environment
CN111026823A (en) * 2019-11-27 2020-04-17 北京大学 Resource utilization associated network model planning method based on geographic position data
CN111260148A (en) * 2020-02-10 2020-06-09 长江大学 Pine wood nematode invasion risk prediction method based on ecological niche factor model
CN113901348A (en) * 2021-11-10 2022-01-07 江苏省血吸虫病防治研究所 Oncomelania snail distribution influence factor identification and prediction method based on mathematical model

Non-Patent Citations (8)

* Cited by examiner, † Cited by third party
Title
3S技术简介及在研究蚊及蚊媒传染病分布和控制中的应用;王晓东等;《中国媒介生物学及控制杂志》;20040620(第03期);全文 *
GIS与RS在寄生虫病防治研究中的应用;杨国静等;《中国寄生虫病防治杂志》;20010330(第01期);全文 *
mosquito edge:an edge-intelligent real-time mosquito threat prediction using an lot-enabled hardware system;Shyam Polineni等;《Computer Science》;20220101;全文 *
Spatial distribution estimation of malaria in northern China and its scenarios in 2022,2030,2040 and 2050;Yongze Song;《Malaria Journal》;20160707;全文 *
中国南方稻区褐飞虱灾变分析与预警系统的研究及应用;吴曙雯;《中国优秀博硕士学位论文全文数据库(博士)农业科技辑》;20030315;全文 *
中国蜱类空间分布及其危害预测;赵国平;《中国优秀博硕士学位论文全文数据库(博士)医药卫生科技辑》;20190115;全文 *
基于最大熵模型的中华按蚊潜在分布预测;马爱民 等;《中国媒介生物学及控制杂志》;20141020;全文 *
新疆草地突颊侧琵甲危害空间分析和潜在地理分布预测;李培先;《中国优秀硕士学位论文全文数据库 农业科技辑》;20180115;全文 *

Also Published As

Publication number Publication date
CN114580178A (en) 2022-06-03

Similar Documents

Publication Publication Date Title
CN114580178B (en) Mosquito distribution prediction method, device, equipment and storage medium
Matthews et al. Changes in potential habitat of 147 North American breeding bird species in response to redistribution of trees and climate following predicted climate change
Devictor et al. Distribution of specialist and generalist species along spatial gradients of habitat disturbance and fragmentation
Luo et al. Impacts of climate change on distributions and diversity of ungulates on the Tibetan Plateau
Prieto-Torres et al. Climate change promotes species loss and uneven modification of richness patterns in the avifauna associated to Neotropical seasonally dry forests
Menéndez‐Guerrero et al. Climate change and the future restructuring of Neotropical anuran biodiversity
Buisson et al. Uncertainty in ensemble forecasting of species distribution
Preston et al. Habitat shifts of endangered species under altered climate conditions: importance of biotic interactions
García et al. Calibration of an urban cellular automaton model by using statistical techniques and a genetic algorithm. Application to a small urban settlement of NW Spain
Normand et al. Demography as the basis for understanding and predicting range dynamics
Holloway et al. Incorporating movement in species distribution models: how do simulations of dispersal affect the accuracy and uncertainty of projections?
Vasconcelos et al. Expected impacts of climate change threaten the anuran diversity in the Brazilian hotspots
CN111212383B (en) Method, device, server and medium for determining number of regional permanent population
Cabeza et al. Conservation planning with insects at three different spatial scales
Boria et al. A single‐algorithm ensemble approach to estimating suitability and uncertainty: cross‐time projections for four Malagasy tenrecs
Massimino et al. Projected reductions in climatic suitability for vulnerable British birds
Clement et al. Estimating indices of range shifts in birds using dynamic models when detection is imperfect
Morelli et al. No species is an island: testing the effects of biotic interactions on models of avian niche occupation
Polaina et al. The legacy of past human land use in current patterns of mammal distribution
CN116721781B (en) Method and device for predicting insect vector infectious disease transmission risk, electronic equipment and medium
CN113743673A (en) Power load prediction method during typhoon
CN114708007A (en) Intelligent decomposition method and system for store sales plan
Ribeiro et al. Distribution dynamics of South American savanna birds in response to Quaternary climate change
Matsui et al. Potential impact of climate change on canopy tree species composition of cool-temperate forests in Japan using a multivariate classification tree model
Vuillaume et al. Improving global rainfall forecasting with a weather type approach in Japan

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant