CN114740549A - Method and device for predicting short-term rainfall weather, electronic equipment and readable medium - Google Patents
Method and device for predicting short-term rainfall weather, electronic equipment and readable medium Download PDFInfo
- Publication number
- CN114740549A CN114740549A CN202210381328.7A CN202210381328A CN114740549A CN 114740549 A CN114740549 A CN 114740549A CN 202210381328 A CN202210381328 A CN 202210381328A CN 114740549 A CN114740549 A CN 114740549A
- Authority
- CN
- China
- Prior art keywords
- precipitation
- short
- map
- probability map
- rainfall
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000001556 precipitation Methods 0.000 claims abstract description 303
- 238000012937 correction Methods 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 238000001914 filtration Methods 0.000 claims description 23
- 238000013213 extrapolation Methods 0.000 claims description 19
- 238000010801 machine learning Methods 0.000 claims description 17
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000002592 echocardiography Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 239000006185 dispersion Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/95—Radar or analogous systems specially adapted for specific applications for meteorological use
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/14—Receivers specially adapted for specific applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Environmental & Geological Engineering (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Atmospheric Sciences (AREA)
- Electromagnetism (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for predicting short-term rainfall weather, electronic equipment and a computer readable medium. The method comprises the following steps: respectively generating an observation precipitation probability map, a satellite precipitation probability map and a radar precipitation probability map based on meteorological observation data, a meteorological satellite cloud map and a radar echo map; carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map; inputting the corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map; predicting and/or correcting short-term precipitation weather based on the short-term clinical precipitation plot. The short-term rainfall weather prediction method is combined with meteorological data of various channels to predict the short-term rainfall, the application range of the social meteorological observation data can be expanded, the data sources of the short-term rainfall can be enriched, and the accuracy and precision of the short-term rainfall prediction are improved.
Description
Technical Field
The application relates to the field of weather prediction, in particular to a method and device for predicting short-term rainfall weather, electronic equipment and a computer readable medium.
Background
Precipitation is a phenomenon that water vapor in the atmosphere condenses and then falls to the ground as liquid water or solid water, and generally exists in two forms of rain and snow in nature, and as a very common weather phenomenon, precipitation generally causes certain influence on human production and life, so people pay attention to precipitation weather. The short-term rainfall forecast refers to forecast of rainfall in 0-12 hours in the future, and the forecast is generally fine in time and space and can give a minute-scale and kilometer-scale grid point rainfall forecast.
With the scientific and technological progress and the acceleration of the pace of life and work, people depend on short-term rainfall forecast more and more deeply, a plurality of weather Apps exist in the market and can provide a grid point short-term rainfall forecast service on the scale of minutes and kilometers, a large number of users use the grid point short-term rainfall forecast service, plans and arrangements of life and work are made according to the grid point short-term rainfall forecast service, and a large number of users can also feed back weather phenomena based on artificial observation aiming at wrong short-term rainfall forecast. When a large amount of centralized artificial weather phenomenon feedback exists, it means that the short rainfall forecast service has a serious deviation from the actual weather phenomenon, and the short rainfall forecast correction needs to be performed on the deviated place, so as to avoid the loss of more users caused by the wrong short rainfall forecast. Therefore, it is a basic service for the weather-like App to receive weather feedback from the user and make short-term precipitation corrections accordingly.
At present, the main data source of the short rainfall forecast is meteorological radar data, and a radar echo reflectivity map of 2 hours in the future is presumed according to the current and historical radar echo reflectivity maps, so that the short rainfall is forecasted. In addition, the geostationary orbit meteorological satellite cloud chart can also be used for short-term imminent precipitation forecast, but the accuracy rate is lower than that of the short-term imminent precipitation forecast based on meteorological radar data, and the short-term imminent precipitation forecast can only be used for auxiliary forecast at present. The weather radar data as the core dependence data of the short-term rainfall forecast generally has the following problems: 1. clutter in radar data is more (including meteorological clutter and non-meteorological clutter); 2. echo loss (caused by radar faults, external interference, seasonal factors, meteorological factors and the like) in radar data 3. the radar shutdown time period is longer (particularly in autumn and winter). All the reasons can cause the short-term rainfall forecast error, cause certain negative effects on the production and life of people and generate a large amount of artificial weather feedback.
Therefore, there is a need for a new method, apparatus, electronic device, and computer readable medium for predicting short-term rainfall weather.
The above information disclosed in this background section is only for enhancement of understanding of the background of the application and therefore it may contain information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of this, the application provides a method and a device for predicting short-term rainfall weather, an electronic device and a computer readable medium, which are used for predicting the short-term rainfall by combining meteorological data of various channels, so that the application range of the socialized meteorological observation data can be expanded, the data sources of the short-term rainfall can be enriched, and the accuracy and precision of predicting the short-term rainfall are improved.
Other features and advantages of the present application will be apparent from the following detailed description, or may be learned by practice of the application.
According to an aspect of the present application, a method for predicting short-term rainfall weather is provided, the method comprising: respectively generating an observation precipitation probability map, a satellite precipitation probability map and a radar precipitation probability map based on meteorological observation data, a meteorological satellite cloud map and a radar echo map; carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map; inputting the corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map; predicting and/or correcting short-term precipitation weather based on the short-term clinical precipitation map.
In an exemplary embodiment of the present application, further comprising: acquiring a plurality of short-imminent-live precipitation maps within a first preset time period in the past; correcting the plurality of short-term live precipitation plots; inputting the corrected short-imminent-live precipitation maps into a time-space extrapolation model to generate a short-imminent future precipitation map; and predicting and/or correcting the short-term rainfall weather in the second preset time in the future based on the short-term future rainfall map.
In an exemplary embodiment of the present application, further comprising: training a first machine learning model based on the plurality of corrected historical observation precipitation probability maps, historical satellite precipitation probability maps and historical radar precipitation probability maps to generate the precipitation prediction model; wherein the first machine learning model comprises: a probabilistic graph model of the conditional random field and a deep network model based on deep learning.
In an exemplary embodiment of the present application, includes: training a second machine learning model based on a plurality of corrected historical short-live precipitation maps to generate the spatio-temporal extrapolation model. Wherein the second machine learning model comprises: ConvLSTM model, PredRNN model.
In an exemplary embodiment of the present application, generating an observed precipitation probability map based on meteorological observation data comprises: acquiring uploading data in a third preset time, wherein the uploading data comprises observation station data and user feedback data; filtering the uploaded data; and generating the observation precipitation probability map based on the filtered uploading data.
In an exemplary embodiment of the present application, filtering the uploaded data includes: filtering the observatory data according to a first filtering strategy; and filtering the user feedback data according to a second filtering strategy.
In an exemplary embodiment of the present application, generating the observed precipitation probability map based on the filtered upload data comprises: extracting the spatial position of the filtered uploaded data; performing density clustering on the uploaded data based on the spatial position; distributing credibility weight for the uploaded data based on the result of the density clustering; and generating the observation precipitation probability map based on the uploaded data and the corresponding credibility weight.
In an exemplary embodiment of the present application, performing longitude and latitude correction on the observed precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map includes: projecting the observation rainfall probability map, the satellite rainfall probability map and the radar rainfall probability map according to a preset projection mode to generate an observation rainfall probability projection map, a satellite rainfall probability projection map and a radar rainfall probability projection map; and carrying out longitude and latitude alignment treatment on the observation precipitation probability projection drawing, the satellite precipitation probability projection drawing and the radar precipitation probability projection drawing.
In an exemplary embodiment of the present application, inputting the corrected observed precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map into a precipitation analysis model, and generating a short-term-imminent-live precipitation map, including: inputting the corrected observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model, and calculating and outputting precipitation probabilities of a plurality of grid points by the precipitation analysis model; generating a short-imminent-live precipitation map based on the precipitation probabilities for the plurality of grid points.
In an exemplary embodiment of the application, correcting the plurality of short-lived precipitation maps comprises: correcting the plurality of short-live precipitation maps from a plurality of original short-transient precipitation maps.
According to an aspect of the application, a short-rainfall weather prediction device is proposed, the device comprising: the probability map module is used for respectively generating an observation precipitation probability map, a satellite precipitation probability map and a radar precipitation probability map based on meteorological observation data, a meteorological satellite cloud map and a radar echo map; the correction module is used for carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map; the rainfall map module is used for inputting the corrected observation rainfall probability map, the satellite rainfall probability map and the radar rainfall probability map into a rainfall analysis model to generate a short-imminent-live rainfall map; and the prediction module is used for predicting and/or correcting the short-term rainfall weather based on the short-term clinical rainfall map.
In an exemplary embodiment of the present application, further comprising: the time module is used for acquiring a plurality of short-imminent-live precipitation maps within a first preset time period in the past; a correction module for correcting the plurality of short-imminent-live precipitation maps; the extrapolation module is used for inputting the corrected short imminent actual precipitation maps into a time-space extrapolation model to generate a short imminent future precipitation map; and the correction module is used for predicting and/or correcting the short-term rainfall weather in the second preset time in the future based on the short-term future rainfall map.
According to an aspect of the present application, an electronic device is provided, the electronic device including: one or more processors; storage means for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a method as above.
According to an aspect of the application, a computer-readable medium is proposed, on which a computer program is stored which, when being executed by a processor, carries out the method as above.
According to the method, the device, the electronic equipment and the computer readable medium for forecasting the short-term rainfall weather, an observation rainfall probability map, a satellite rainfall probability map and a radar rainfall probability map are respectively generated based on meteorological observation data, a meteorological satellite cloud map and a radar echo map; carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map; inputting the corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map; the method for predicting and/or correcting the short-term rainfall weather based on the short-term clinical rainfall map is combined with meteorological data of various channels to predict the short-term rainfall, so that the application range of the socialized meteorological observation data can be expanded, the data sources of the short-term rainfall can be enriched, and the accuracy and precision of the prediction of the short-term rainfall are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The drawings described below are only some embodiments of the present application, and other drawings may be derived from those drawings by those skilled in the art without inventive effort.
FIG. 1 is a system block diagram illustrating a method and apparatus for short-rainfall weather prediction, according to an exemplary embodiment.
FIG. 2 is a flow diagram illustrating a method of short-term rainfall weather prediction, according to an example embodiment.
FIG. 3 is a flow chart illustrating a method of short-rainfall weather prediction, according to another exemplary embodiment.
FIG. 4 is a flow chart illustrating a method of short-rainfall weather prediction, according to another example embodiment.
FIG. 5 is a block diagram illustrating a short-rainfall weather prediction device, according to an example embodiment.
FIG. 6 is a block diagram illustrating a short-rainfall weather prediction device, according to another exemplary embodiment.
FIG. 7 is a block diagram illustrating an electronic device in accordance with an example embodiment.
FIG. 8 is a block diagram illustrating a computer-readable medium in accordance with an example embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another. Thus, a first component discussed below may be termed a second component without departing from the teachings of the present concepts. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be appreciated by those skilled in the art that the drawings are merely schematic representations of exemplary embodiments, and that the blocks or processes shown in the drawings are not necessarily required to practice the present application and are, therefore, not intended to limit the scope of the present application.
The inventor of the application considers that the artificial weather feedback is a special social weather observation mode, namely a weather observation mode of manually observing and reporting a weather phenomenon, and other social weather observations further comprise rainfall station observation, automobile windshield wiper observation, traffic and security camera observation and the like. The socialized weather observation has the characteristics of timely observation, accurate observation value, large observation quantity and time-space dispersion, and can correct and supplement short imminent precipitation forecast based on radar data in time by fully utilizing socialized weather observation data. At present, common socialized weather observation mainly includes artificial weather feedback and rainfall station observation, and the use of the common socialized weather observation is limited to correcting the short-term forecast of grid points near an observation point by combining historical experience.
The artificial weather feedback is one of the socialized weather observations, and the other common socialized weather observation is a weather observation station deployed in each province, city, county and county of China, and similar to the artificial weather feedback, the observation can also be used for correcting the short-term rainfall forecast. The social meteorological observation has the advantages of timely observation feedback and accurate observation value (especially data of a meteorological observation station), and has the defect that the observation value is relatively discrete in time and space. Compared with the number of the short-term forecast lattices, the number of the entries of the socialized weather observation is few, and the accurate short-term forecast correction is difficult to accurately carry out only by using the socialized weather observation.
At present, the short-term rainfall forecast correction based on the socialized meteorological observation data mainly adopts a single-point correction method, namely, the short-term rainfall forecast correction is only carried out on lattice points of the short-term rainfall forecast, wherein the lattice points are at observation positions. Or evaluating each observer of the socialized meteorological observations, wherein the area for correcting the short-rainfall forecast is larger when the evaluation of the observer is higher, and the area for correcting the short-rainfall forecast is smaller otherwise, or even the short-rainfall forecast is not corrected. The main problem with this approach is that the correction area due to socialized weather observation is too small.
Based on the analysis, the method is based on the socialized observation data, integrates the geostationary orbit meteorological satellite data, accurately measures and calculates the correction range of the socialized observation data in time and space, avoids correction only in a very small range for pursuing correction accuracy, avoids correction accuracy loss for pursuing a large correction range, and provides a good supplement for lattice-level short-term impending rainfall forecast under the condition of missing or wrong meteorological radar data.
The content of the present application is described in detail below with the aid of specific examples.
FIG. 1 is a system block diagram illustrating a method and apparatus for short-rainfall weather prediction, according to an exemplary embodiment.
As shown in fig. 1, the system architecture 10 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various communication client applications, such as a weather prediction application, an image processing application, an image shooting application, an instant messaging tool, a mailbox client, social platform software, and the like, may be installed on the terminal devices 101, 102, and 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server that provides various services, such as a background management server that provides support for weather observation data transmitted by users using the terminal devices 101, 102, 103. The background management server may analyze the received meteorological observation data, and feed back the processing result (e.g., predicted short-term rainfall weather) to other users.
The server 105 may generate an observed precipitation probability map, a satellite precipitation probability map, a radar precipitation probability map, for example, based on meteorological observation data, a meteorological satellite cloud map, a radar echo map, respectively; the server 105 may, for example, perform latitude and longitude corrections on the observed precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map; the server 105 may, for example, input the corrected observed precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map into a precipitation analysis model to generate a short-lived precipitation map; the server 105 may predict and/or correct short-term precipitation weather, for example, based on the short-term clinical precipitation map.
The server 105 may also, for example, obtain a plurality of short-imminent-live precipitation maps within a first preset time period in the past; the server 105 may also, for example, correct the plurality of short-lived precipitation maps; the server 105 may also, for example, input the corrected plurality of short-term, imminent-live precipitation maps into a spatio-temporal extrapolation model, generating a short-term, imminent-future precipitation map; the server 105 may also predict and/or correct short-term precipitation weather within a second preset time in the future, e.g. based on the short-term future precipitation map.
The server 105 may also train a first machine learning model to generate the precipitation prediction model, e.g., based on a plurality of modified historical observed precipitation probability maps, historical satellite precipitation probability maps, and historical radar precipitation probability maps; wherein the first machine learning model comprises: a probabilistic graph model of the conditional random field and a deep network model based on deep learning.
The server 105 may also train a second machine learning model to generate the spatio-temporal extrapolation model, for example, based on a plurality of corrected historical short-lived precipitation maps. Wherein the second machine learning model comprises: ConvLSTM model, PredRNN model.
The server 105 may be an entity server, or may be composed of a plurality of servers, for example, it should be noted that the method for predicting short-rainfall weather provided in the embodiment of the present application may be executed by the server 105, and accordingly, the short-rainfall weather prediction apparatus may be disposed in the server 105. And the processing end that provides the user with the ability to acquire and transmit the weather observation data is typically located in the terminal devices 101, 102, 103.
FIG. 2 is a flow chart illustrating a method of short-rainfall weather prediction, according to an exemplary embodiment. The method 20 for predicting short-rainfall weather includes at least steps S202 to S208.
As shown in fig. 2, in S202, an observed precipitation probability map, a satellite precipitation probability map, and a radar precipitation probability map are generated based on the weather observation data, the weather satellite cloud map, and the radar echo map, respectively.
In one embodiment, the socialized weather observations over the most recent period of time (e.g., 10 minutes or 15 minutes, etc.) may be read as weather observations and based thereon observed precipitation probability maps may be generated. The specific contents of "generating the observed precipitation probability map based on the meteorological observation data" will be described in detail in the embodiment corresponding to fig. 3.
In one embodiment, a geostationary meteorological satellite cloud map (e.g., wind cloud number 4) may be loaded and a satellite precipitation probability map generated from the meteorological satellite cloud map. In a specific application scenario, there are many methods for generating a satellite precipitation probability map, and for example, the simplest method is to count the relationship between a color value of a cloud on a satellite cloud map and precipitation by using historical data, and then obtain the relationship between the color of the cloud and the precipitation probability; precipitation probability maps may also be generated from satellite clouds, for example using a deep neural network.
In one embodiment, a radar echo map may be loaded and a precipitation probability map based on the radar echoes generated. Under normal conditions, the accuracy of the short-term rainfall forecast based on radar echoes is high, if a large amount of artificial observation is the feedback of rainfall, the radar echoes are possibly missing or the threshold value of judging the rain is higher, and at the moment, a radar echo image before denoising and a lower rain judging threshold value are required to be used for generating a rainfall probability image; if a large amount of feedback that is artificially observed as non-precipitation exists, which indicates that radar echo noise is not completely removed or a rain judging threshold value is lower, a radar echo image subjected to de-drying by the enhanced de-noising model and a high rain judging threshold value can be used for generating a precipitation probability image.
In S204, longitude and latitude correction is performed on the observation precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map. The observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map can be projected according to a preset projection mode to generate an observation precipitation probability projection map, a satellite precipitation probability projection map and a radar precipitation probability projection map; and carrying out longitude and latitude alignment treatment on the observation precipitation probability projection drawing, the satellite precipitation probability projection drawing and the radar precipitation probability projection drawing.
More specifically, different map projection modes and different geographic spatial ranges are generally adopted for observing the precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map, and 3 precipitation probability maps need to be unified on the same map projection mode and need to be aligned on the longitude and latitude.
And in S206, inputting the corrected observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map. The corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map can be input into a precipitation analysis model; the precipitation analysis model outputs precipitation probabilities of a plurality of grid points through calculation; generating a short-imminent-live precipitation map based on the precipitation probabilities for the plurality of lattice points.
In one embodiment, the first machine learning model may be trained to generate the precipitation prediction model based on a plurality of modified historical observed precipitation probability maps, historical satellite precipitation probability maps, and historical radar precipitation probability maps; wherein the first machine learning model comprises: a probabilistic graph model of the conditional random field and a deep network model based on deep learning.
In S208, short-term precipitation weather is predicted and/or corrected based on the short-term clinical precipitation map. It is worth mentioning that the short-term imminent-live rainfall forecast refers to a judgment of whether the current moment is rainfall or not, and when the rainfall forecast is made, the acquired basic data (including radar data, satellite data and the like) all have a certain delay, so that the judgment of the current moment is actually a future rainfall forecast. More specifically, the current short-imminent rainfall map can be corrected through a newly generated short-imminent-live rainfall map, and the rainfall duration of each grid point can be given according to historical experience information to correct the short-imminent-future rainfall forecast.
More specifically, an empirical precipitation time (20 minutes) may be set to correct for short-term future precipitation patterns.
According to the short-term rainfall weather prediction method, an observation rainfall probability map, a satellite rainfall probability map and a radar rainfall probability map are respectively generated based on meteorological observation data, a meteorological satellite cloud map and a radar echo map; carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map; inputting the corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map; the method for predicting and/or correcting the short-term rainfall weather based on the short-term clinical rainfall map is combined with meteorological data of various channels to predict the short-term rainfall, so that the application range of the socialized meteorological observation data can be expanded, the data sources of the short-term rainfall can be enriched, and the accuracy and precision of the prediction of the short-term rainfall are improved.
It should be clearly understood that this application describes how to make and use particular examples, but the principles of this application are not limited to any of the details of these examples. Rather, these principles can be applied to many other embodiments based on the teachings of the present disclosure.
FIG. 3 is a flow chart illustrating a method of short-rainfall weather prediction, according to another exemplary embodiment. The process 30 shown in FIG. 3 is a detailed description of the process S202 "generating an observed precipitation probability map based on meteorological observation data" shown in FIG. 2.
As shown in fig. 3, in S302, upload data in a third preset time is acquired, where the upload data includes observatory data and user feedback data. Socialization imagery observations may be obtained as uploaded data over a recent period of time (e.g., 10 minutes or 15 minutes, etc.).
In S304, the uploaded data is filtered. Filtering the observatory data according to a first filtering strategy; and filtering the user feedback data according to a second filtering strategy.
In a specific embodiment, invalid data in the social meteorological observation data can be filtered out according to a certain rule, and different types of invalid data exist in different social meteorological observation data:
a. for the observation data of the rainfall station, the observation data exceeding a reasonable range are considered as invalid data;
b. for the user manual feedback data, the following rules can be adopted for filtering:
1) filtering out the artificial feedback of the user beyond the common sense (for example, snow is fed back in summer);
2) filtering out manual feedback with regular feedback time (for example, feeding back once every hour at a fixed time, and suspected of being machine feedback);
3) filtering out manual feedback of users who feedback too frequently (too frequent feedback already exceeds the normal need for weather feedback, which is most likely wrong weather);
4) filtering manual feedback of users with low historical feedback accuracy (such users have poor historical credit, and most of weather history tests fed back are wrong);
5) filtering out other feedback that is considered unreasonable (e.g. a group of users who have never fed back weather before, focusing feedback in a region with a low population density for a short time, which may be a malicious attack on the feedback interface).
In S306, the observed precipitation probability map is generated based on the filtered upload data. Extracting the spatial position of the filtered uploaded data; performing density clustering on the uploaded data based on the spatial position; distributing credibility weight for the uploaded data based on the result of the density clustering; and generating the observation precipitation probability map based on the uploaded data and the corresponding credibility weight.
More specifically, the filtered socialized meteorological observation data are subjected to spatial density clustering, and the meteorological observation data in a larger cluster have higher reliability and a larger action range; and conversely, the degree of confidence is slightly smaller, the action range is slightly smaller, and then a precipitation probability map based on the social weather observation data is generated.
FIG. 4 is a flow chart illustrating a method of short-rainfall weather prediction, according to another example embodiment. The flow 40 shown in fig. 4 is a supplementary description of the flow shown in fig. 2.
The short-imminent precipitation correction can only correct short-imminent-live precipitation forecast accurately, and the precipitation duration of each lattice point needs to be estimated when the short-imminent-future precipitation forecast is corrected, so that the precipitation duration is difficult to estimate accurately; the embodiment adopts the idea of extrapolation of the radar echo diagram, extrapolates the corrected short-time real-time rainfall diagram, and then is used for accurately correcting the short-term future rainfall forecast.
As shown in fig. 4, in S402, a plurality of short-imminent-live precipitation plots over a first preset period of time in the past are acquired. And reading meteorological observation data of the past third preset time, and reading a geostationary satellite cloud picture and a radar echo picture of a corresponding time period.
In S404, the plurality of short-lived precipitation maps are corrected. Correcting the plurality of short-live precipitation maps from a plurality of original short-transient precipitation maps. And (4) putting the data into a precipitation analysis model to generate a short-imminent-live precipitation map in a corresponding time period, and correcting the original short-imminent-live precipitation map to obtain a corrected short-imminent-live precipitation map.
The above steps are repeated a plurality of times to generate corrected short-lived precipitation maps for a plurality of successive time periods.
In S406, the corrected short-term imminent-live precipitation maps are input into a spatio-temporal extrapolation model, and a short-term imminent-future precipitation map is generated. And inputting the corrected short-imminent-live precipitation maps into a time-space extrapolation model to generate a short-imminent-future precipitation forecast map.
In one embodiment, a second machine learning model may be trained based on a plurality of corrected historical short-term-live precipitation maps to generate the spatiotemporal extrapolation model. Wherein the second machine learning model comprises: ConvLSTM model, PredRNN model.
In S408, short-term precipitation weather within a second preset time in the future is predicted and/or corrected based on the short-term future precipitation map. And correcting the original short-term rainfall forecast through the short-term future rainfall forecast graph.
The short-term rainfall weather prediction method has the following advantages:
accurately correcting the short-imminent rainfall forecast at the lattice point level by using socialized meteorological observation data; and a filtering strategy based on abnormal weather monitoring, user history monitoring and feedback behavior monitoring is provided, so that the accuracy of the social weather observation data is improved.
Clustering the socialized meteorological observation data in time and space by adopting a density-based clustering method, and generating a precipitation probability map based on socialized meteorological observation according to a clustering result.
Geostationary meteorological satellite data is used in combination with a machine learning model to generate a short-lived precipitation map.
The socialized meteorological observation is used as a very valuable meteorological observation data, is limited by the characteristic of time-space dispersion of the meteorological observation, cannot fully exert the value of the meteorological observation all the time, and can only be used for correcting short-critical-point rainfall forecast in a very small range. The method focuses on the use of the socialized meteorological observation data, combines a geostationary meteorological satellite cloud picture which is not easy to be interfered, and accurately expands the action range of the socialized meteorological observation data, the expansion not only corrects the short clinical scene rainfall forecast, but also generates a short clinical future rainfall forecast picture by using a space-time extrapolation model, gives an accurate result to the time correction range of the socialized meteorological observation data, and greatly expands the use of the socialized meteorological observation in the short clinical lattice point level rainfall forecast.
Those skilled in the art will appreciate that all or part of the steps implementing the above embodiments are implemented as computer programs executed by a CPU. When executed by the CPU, performs the functions defined by the methods provided herein. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.
Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the method according to exemplary embodiments of the present application, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
The following are embodiments of the apparatus of the present application that may be used to perform embodiments of the method of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the embodiments of the method of the present application.
FIG. 5 is a block diagram illustrating a short-rainfall weather prediction device, according to an example embodiment. As shown in fig. 5, the short-rainfall weather prediction device 50 includes: probability map module 502, modification module 504, precipitation map module 506, and prediction module 508.
The probability map module 502 is used for respectively generating an observation precipitation probability map, a satellite precipitation probability map and a radar precipitation probability map based on meteorological observation data, a meteorological satellite cloud map and a radar echo map;
the correction module 504 is configured to perform longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map;
the precipitation map module 506 is configured to input the corrected observed precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map;
the prediction module 508 is configured to predict and/or correct short-term precipitation weather based on the short-term clinical precipitation map.
FIG. 6 is a block diagram illustrating a short-rainfall weather prediction device, according to another example embodiment. As shown in fig. 6, the short-rainfall weather prediction device 60 includes: a time module 602, a correction module 604, an extrapolation module 606, and a correction module 608.
The time module 602 is configured to obtain a plurality of short-imminent-live precipitation maps within a first preset time period in the past;
the correction module 604 is configured to correct the plurality of short-imminent-live precipitation maps;
the extrapolation module 606 is configured to input the corrected multiple short-imminent-live precipitation maps into a spatio-temporal extrapolation model to generate a short-imminent-future precipitation map;
the correction module 608 is configured to predict and/or correct the short-term precipitation weather within the second predetermined time in the future based on the short-term future precipitation map.
According to the short-term rainfall weather prediction device, an observation rainfall probability graph, a satellite rainfall probability graph and a radar rainfall probability graph are respectively generated based on meteorological observation data, a meteorological satellite cloud picture and a radar echo picture; carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map; inputting the corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map; the method for predicting and/or correcting the short-term rainfall weather based on the short-term clinical rainfall map is combined with meteorological data of various channels to predict the short-term rainfall, so that the application range of the socialized meteorological observation data can be expanded, the data sources of the short-term rainfall can be enriched, and the accuracy and precision of the prediction of the short-term rainfall are improved.
FIG. 7 is a block diagram illustrating an electronic device in accordance with an example embodiment.
An electronic device 700 according to this embodiment of the present application is described below with reference to fig. 7. The electronic device 700 shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 7, electronic device 700 is embodied in the form of a general purpose computing device. The components of the electronic device 700 may include, but are not limited to: at least one processing unit 710, at least one memory unit 720, a bus 730 that couples various system components including the memory unit 720 and the processing unit 710, a display unit 740, and the like.
Wherein the storage unit stores program code that can be executed by the processing unit 710 such that the processing unit 710 performs the steps according to various exemplary embodiments of the present application described in the present specification. For example, the processing unit 710 may perform the steps as shown in fig. 2, 3, 4.
The memory unit 720 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)7201 and/or a cache memory unit 7202, and may further include a read only memory unit (ROM) 7203.
The memory unit 720 can also include programs/utilities 7204 having a set (at least one) of program modules 7205, such program modules 7205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 700 may also communicate with one or more external devices 700' (e.g., keyboard, pointing device, bluetooth device, etc.), such that a user can communicate with devices with which the electronic device 700 interacts, and/or any devices (e.g., router, modem, etc.) with which the electronic device 700 can communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interfaces 750. Also, the electronic device 700 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 760. The network adapter 760 may communicate with other modules of the electronic device 700 via the bus 730. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 700, 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.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, as shown in fig. 8, the technical solution according to the embodiment of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiment of the present application.
The software product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with 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 readable storage medium may also be any readable medium that is not a 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 readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The computer readable medium carries one or more programs which, when executed by a device, cause the computer readable medium to perform the functions of: respectively generating an observation precipitation probability map, a satellite precipitation probability map and a radar precipitation probability map based on meteorological observation data, a meteorological satellite cloud map and a radar echo map; carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map; inputting the corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map; predicting and/or correcting short-term precipitation weather based on the short-term clinical precipitation map. The computer readable medium may also perform the following functions: acquiring a plurality of short-imminent-live precipitation maps within a first preset time period in the past; correcting the plurality of short-term live precipitation plots; inputting the corrected short-imminent-live precipitation maps into a time-space extrapolation model to generate a short-imminent future precipitation map; and predicting and/or correcting the short-term rainfall weather in the second preset time in the future based on the short-term future rainfall map.
Those skilled in the art will appreciate that the modules described above may be distributed in the apparatus according to the description of the embodiments, or may be modified accordingly in one or more apparatuses unique from the embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiment of the present application. Exemplary embodiments of the present application are specifically illustrated and described above. It is to be understood that the application is not limited to the details of construction, arrangement, or method of implementation described herein; on the contrary, the intention is to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (14)
1. A method for predicting short-term rainfall weather, comprising:
respectively generating an observation precipitation probability map, a satellite precipitation probability map and a radar precipitation probability map based on meteorological observation data, a meteorological satellite cloud map and a radar echo map;
carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map;
inputting the corrected observed precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map into a precipitation analysis model to generate a short-imminent-live precipitation map;
predicting and/or correcting short-term precipitation weather based on the short-term clinical precipitation map.
2. The method of claim 1, further comprising:
acquiring a plurality of short-imminent-live precipitation maps within a first preset time period in the past;
correcting the plurality of short-lived precipitation maps;
inputting the corrected short-imminent-live precipitation maps into a time-space extrapolation model to generate a short-imminent future precipitation map;
and predicting and/or correcting the short-term rainfall weather in the second preset time in the future based on the short-term future rainfall map.
3. The method of claim 1, further comprising:
training a first machine learning model based on the plurality of corrected historical observation precipitation probability maps, historical satellite precipitation probability maps and historical radar precipitation probability maps to generate the precipitation prediction model;
wherein the first machine learning model comprises: a probabilistic graph model of the conditional random field and a deep network model based on deep learning.
4. The method of claim 2, comprising:
training a second machine learning model based on a plurality of corrected historical short-live precipitation maps to generate the spatio-temporal extrapolation model.
Wherein the second machine learning model comprises: ConvLSTM model, PredRNN model.
5. The method of claim 1, wherein generating an observed precipitation probability map based on meteorological observation data comprises:
acquiring uploading data in a third preset time, wherein the uploading data comprises observation station data and user feedback data;
filtering the uploaded data;
and generating the observation precipitation probability map based on the filtered uploading data.
6. The method of claim 5, wherein filtering the upload data comprises:
filtering the observatory data according to a first filtering strategy;
and filtering the user feedback data according to a second filtering strategy.
7. The method of claim 5, wherein generating the observed precipitation probability map based on the filtered upload data comprises:
extracting the spatial position of the filtered uploaded data;
performing density clustering on the uploaded data based on the spatial position;
distributing credibility weight for the uploaded data based on the result of the density clustering;
and generating the observation precipitation probability map based on the uploaded data and the corresponding credibility weight.
8. The method of claim 1, wherein the modifying the observed precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map by latitude and longitude comprises:
projecting the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map according to a preset projection mode to generate an observation precipitation probability projection map, a satellite precipitation probability projection map and a radar precipitation probability projection map;
and carrying out longitude and latitude alignment treatment on the observation rainfall probability projection graph, the satellite rainfall probability projection graph and the radar rainfall probability projection graph.
9. The method of claim 1, wherein inputting the modified observed precipitation probability map, the satellite precipitation probability map, and the radar precipitation probability map into a precipitation analysis model to generate a short-term-imminent-live precipitation map comprises:
inputting the corrected observed precipitation probability map, the corrected satellite precipitation probability map and the corrected radar precipitation probability map into a precipitation analysis model;
the precipitation analysis model outputs precipitation probabilities of a plurality of grid points through calculation;
generating a short-imminent-live precipitation map based on the precipitation probabilities for the plurality of lattice points.
10. The method of claim 2, wherein correcting the plurality of short-lived precipitation maps comprises:
correcting the plurality of short-onset precipitation maps from a plurality of original short-onset precipitation maps.
11. A short-rainfall weather prediction device, comprising:
the probability map module is used for respectively generating an observation precipitation probability map, a satellite precipitation probability map and a radar precipitation probability map based on meteorological observation data, a meteorological satellite cloud map and a radar echo map;
the correction module is used for carrying out longitude and latitude correction on the observation precipitation probability map, the satellite precipitation probability map and the radar precipitation probability map;
the rainfall map module is used for inputting the corrected observation rainfall probability map, the satellite rainfall probability map and the radar rainfall probability map into a rainfall analysis model to generate a short-imminent-live rainfall map;
and the prediction module is used for predicting and/or correcting the short-term rainfall weather based on the short-term clinical rainfall map.
12. The apparatus of claim 11, further comprising:
the time module is used for acquiring a plurality of short-imminent-live precipitation maps within a first preset time period in the past;
a correction module for correcting the plurality of short-imminent-live precipitation maps;
the extrapolation module is used for inputting the corrected short imminent actual precipitation maps into a time-space extrapolation model to generate a short imminent future precipitation map;
and the correction module is used for predicting and/or correcting the short-term rainfall weather in the second preset time in the future based on the short-term future rainfall map.
13. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-10.
14. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210381328.7A CN114740549B (en) | 2022-04-12 | 2022-04-12 | Short-term precipitation weather prediction method and device, electronic equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210381328.7A CN114740549B (en) | 2022-04-12 | 2022-04-12 | Short-term precipitation weather prediction method and device, electronic equipment and readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114740549A true CN114740549A (en) | 2022-07-12 |
| CN114740549B CN114740549B (en) | 2024-02-06 |
Family
ID=82281917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210381328.7A Active CN114740549B (en) | 2022-04-12 | 2022-04-12 | Short-term precipitation weather prediction method and device, electronic equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114740549B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002328178A (en) * | 2001-04-27 | 2002-11-15 | Nippon Telegr & Teleph Corp <Ntt> | Weather forecasting method, device, program and program recording medium |
| CN109614589A (en) * | 2018-12-28 | 2019-04-12 | 华东交通大学 | The short calculation method for facing precipitation, system, readable storage medium storing program for executing and computer equipment |
| CN109917394A (en) * | 2019-03-13 | 2019-06-21 | 南京信息工程大学 | A kind of short based on weather radar faces intelligent Extrapolation method |
| CN110135654A (en) * | 2019-05-24 | 2019-08-16 | 北京百度网讯科技有限公司 | Method and apparatus for predicting strong convective weather |
| US20200309993A1 (en) * | 2019-03-25 | 2020-10-01 | Yandex Europe Ag | Method of and system for generating weather forecast |
| US20210103051A1 (en) * | 2019-10-04 | 2021-04-08 | International Business Machines Corporation | Predicting weather radar images |
| CN112764129A (en) * | 2021-01-22 | 2021-05-07 | 易天气(北京)科技有限公司 | Method, system and terminal for thunderstorm short-term forecasting |
| CN113075751A (en) * | 2021-03-26 | 2021-07-06 | 国网河南省电力公司电力科学研究院 | Method and system for fusing observation data in short-term forecasting |
| CN114114198A (en) * | 2022-01-27 | 2022-03-01 | 江西省气象信息中心(江西省气象培训中心、江西省农村经济信息中心) | Precipitation data quality control method and device, storage medium and equipment |
| CN114139690A (en) * | 2021-12-09 | 2022-03-04 | 南京邮电大学 | Short-term rainfall prediction method and device |
-
2022
- 2022-04-12 CN CN202210381328.7A patent/CN114740549B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002328178A (en) * | 2001-04-27 | 2002-11-15 | Nippon Telegr & Teleph Corp <Ntt> | Weather forecasting method, device, program and program recording medium |
| CN109614589A (en) * | 2018-12-28 | 2019-04-12 | 华东交通大学 | The short calculation method for facing precipitation, system, readable storage medium storing program for executing and computer equipment |
| CN109917394A (en) * | 2019-03-13 | 2019-06-21 | 南京信息工程大学 | A kind of short based on weather radar faces intelligent Extrapolation method |
| US20200309993A1 (en) * | 2019-03-25 | 2020-10-01 | Yandex Europe Ag | Method of and system for generating weather forecast |
| CN110135654A (en) * | 2019-05-24 | 2019-08-16 | 北京百度网讯科技有限公司 | Method and apparatus for predicting strong convective weather |
| US20210103051A1 (en) * | 2019-10-04 | 2021-04-08 | International Business Machines Corporation | Predicting weather radar images |
| CN112764129A (en) * | 2021-01-22 | 2021-05-07 | 易天气(北京)科技有限公司 | Method, system and terminal for thunderstorm short-term forecasting |
| CN113075751A (en) * | 2021-03-26 | 2021-07-06 | 国网河南省电力公司电力科学研究院 | Method and system for fusing observation data in short-term forecasting |
| CN114139690A (en) * | 2021-12-09 | 2022-03-04 | 南京邮电大学 | Short-term rainfall prediction method and device |
| CN114114198A (en) * | 2022-01-27 | 2022-03-01 | 江西省气象信息中心(江西省气象培训中心、江西省农村经济信息中心) | Precipitation data quality control method and device, storage medium and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 李五生;王洪庆;吴琼;王玉;王烨芳;: "静止卫星云图的云位置偏差及其几何校正", 北京大学学报(自然科学版), no. 05, pages 732 - 736 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114740549B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11555921B2 (en) | Method and apparatus for predicting severe convection weather | |
| US20230194756A1 (en) | Weather-driven multi-category infrastructure impact forecasting | |
| CN107742125B (en) | Deep machine learning to predict and prevent adverse conditions at structural assets | |
| CN108732550B (en) | Method and apparatus for predicting radar echo | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| US9569551B2 (en) | Dynamic modeling of geospatial words in social media | |
| US10564319B2 (en) | Method and system for displaying weather information on a timeline | |
| US20240176045A1 (en) | Nowcasting using generative neural networks | |
| US20240160923A1 (en) | Increasing Accuracy and Resolution of Weather Forecasts Using Deep Generative Models | |
| CN115453541A (en) | Precipitation amount prediction method and device, electronic device and storage medium | |
| US11488083B2 (en) | Risk failure prediction for line assets | |
| CN114594532A (en) | Method and device for predicting cold weather, electronic equipment and computer readable medium | |
| CN114740549B (en) | Short-term precipitation weather prediction method and device, electronic equipment and readable medium | |
| US11493666B2 (en) | System and method for forecasting snowfall probability distributions | |
| Yang et al. | Improving seasonal forecast of summer precipitation in southeastern china using cyclegan deep learning bias correction | |
| KR102666070B1 (en) | Apparatus for providing data-driven parametric insurance and method thereof | |
| CN117151420A (en) | Risk monitoring method, apparatus, device, medium and program product | |
| Westra et al. | Estimating the seasonal predictability of global precipitation: an empirical approach | |
| Salim et al. | A Disparate Disaster: Spatial Patterns of Building Damages and Associated Socio-Economic Factors by 2022 Hurricane Ian |
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 |