CN110110725A - Typhoon destructiveness range determining method, device, computer equipment and storage medium - Google Patents
Typhoon destructiveness range determining method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110110725A CN110110725A CN201910382117.3A CN201910382117A CN110110725A CN 110110725 A CN110110725 A CN 110110725A CN 201910382117 A CN201910382117 A CN 201910382117A CN 110110725 A CN110110725 A CN 110110725A
- Authority
- CN
- China
- Prior art keywords
- typhoon
- scale
- value
- temperature
- intensity
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Radiation Pyrometers (AREA)
Abstract
The present invention is suitable for field of computer technology, provides a kind of typhoon destructiveness range determining method, device, computer equipment and storage medium, which comprises establishes the Typhoon-scale containing variable element based on history typhoon observation data and calculates regression model;Obtain intensity of typhoon information and center of typhoon location information;Obtain stationary weather satellite infrared observation image;Typhoon cloud top regional temperature figure is generated according to the gray value of pixel each in infrared observation image;Regression model, intensity of typhoon, center of typhoon position and typhoon cloud top regional temperature figure, which are calculated, according to Typhoon-scale determines Typhoon-scale;Typhoon destructiveness range is determined according to Typhoon-scale.Typhoon destructiveness range determining method provided by the invention, Typhoon-scale, which is established, based on history typhoon observation data calculates regression model, after obtaining intensity of typhoon information, center of typhoon location information and stationary weather satellite infrared observation image, can directly, reliably determine Typhoon-scale, so that it is determined that typhoon destructiveness range.
Description
Technical field
The invention belongs to field of computer technology more particularly to a kind of typhoon destructiveness range determining methods, device, calculating
Machine equipment and storage medium.
Background technique
Typhoon is a kind of meteorological disaster, is often born on summer sea level.Typhoon-scale is defined as by meteorologists
The size of the destructive range wind ranges in typhoon periphery, therefore Typhoon-scale is an important indicator for describing typhoon structure, is
A key factor for determining typhoon destructiveness range, for decision of preventing and reducing natural disasters with very important reference significance, platform
Wind scale is bigger, then typhoon destructiveness range is wider, needs to carry out precautionary measures in advance.
But due to the typhoon mainly occurrence and development on ocean, in view of the limitation of monitoring means, related analyzed vortex ruler
The data of degree is seldom.Other than the Atlantic Ocean has aircraft to commence business and observe, other global ocean are directly observed only for typhoon
It is limited to the accidental capture of ship, buoy or island observation station, the Typhoon-scale data in off-lying sea is very deficient.Therefore, mesh
Before can not accomplish to determine Typhoon-scale well, so that the destructive range of typhoon can not be effectively determined.
As it can be seen that existing typhoon observation technology is not possible to quickly and accurately determine Typhoon-scale, so that it is determined that typhoon
Destructive range.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of typhoon destructiveness range determining method, it is intended to solve existing
It is not possible to quickly and accurately determine Typhoon-scale existing for wind observation technology, so that it is determined that the technology of the destructive range of typhoon
Problem.
The embodiments of the present invention are implemented as follows, a kind of typhoon destructiveness range determining method, comprising:
The Typhoon-scale containing variable element, which is established, based on history typhoon observation data calculates regression model, the variable element packet
Include the typhoon cloud top regional temperature under intensity of typhoon, preset condition;
Current intensity of typhoon information and current center of typhoon location information are obtained in real time;
Current quiet meteorological satellite infrared observation image is obtained in real time;
Typhoon cloud top regional temperature figure is generated according to the gray value of each pixel in the stationary weather satellite infrared observation image;
Regression model, intensity of typhoon, center of typhoon position and typhoon cloud top regional temperature figure are calculated according to the Typhoon-scale
Determine Typhoon-scale;
Typhoon destructiveness range is determined according to the Typhoon-scale.
The another object of the embodiment of the present invention is to provide a kind of typhoon destructiveness ranges determination device, comprising:
Typhoon-scale calculates regression model and establishes unit, for establishing the platform containing variable element based on history typhoon observation data
Wind dimension calculation regression model, the variable element include the typhoon cloud top regional temperature under intensity of typhoon, preset condition;
Intensity of typhoon and center location information acquiring unit, for being obtained in current intensity of typhoon information and current typhoon in real time
Heart location information;
Meteorological satellite infrared observation image acquisition unit, for obtaining current quiet meteorological satellite infrared observation image in real time;
Typhoon cloud top regional temperature figure generation unit, for according to each pixel in the stationary weather satellite infrared observation image
Gray value generate typhoon cloud top regional temperature figure;
Typhoon-scale determination unit, for according to the Typhoon-scale calculate regression model, intensity of typhoon, center of typhoon position with
And typhoon cloud top regional temperature figure determines Typhoon-scale;And
Typhoon destructiveness range determination unit, for determining typhoon destructiveness range according to the Typhoon-scale.
The another object of the embodiment of the present invention is to provide a kind of computer equipment, including memory and processor, described
Computer program is stored in memory, when the computer program is executed by the processor, so that the processor executes
The step of typhoon destructiveness range determining method as described above.
The another object of the embodiment of the present invention is to provide a kind of computer readable storage medium, described computer-readable to deposit
Computer program is stored on storage media, when the computer program is executed by processor, so that the processor executes as above
The step of stating the typhoon destructiveness range determining method.
A kind of typhoon destructiveness range determining method provided in an embodiment of the present invention observes data by history typhoon first
It establishes the Typhoon-scale containing variable element and calculates regression model, then obtain current intensity of typhoon information, current typhoon respectively
Center location information and current quiet meteorological satellite infrared observation image, further according to current quiet meteorological satellite infrared observation figure
As the generation typhoon cloud top regional temperature figure of each pixel, by above-mentioned intensity of typhoon information, current center of typhoon location information with
And typhoon cloud top regional temperature figure is input in the Typhoon-scale calculating regression model of foundation and is assured that out the typhoon
Scale, to further determine that the destructive range of the typhoon.A kind of typhoon destructiveness range provided in an embodiment of the present invention
Method is determined, since what be can be convenient gets current intensity of typhoon information, current center of typhoon location information and current quiet
Only meteorological satellite infrared observation image, and calculating regression model according to the Typhoon-scale quickly can directly determine typhoon ruler
Degree further since the Typhoon-scale used calculates regression model is established based on history typhoon observation data, moreover it is possible to have
It ensure that effect the accuracy rate of the Typhoon-scale finally determined.
Detailed description of the invention
Fig. 1 is the step flow chart of typhoon destructiveness range determining method provided in an embodiment of the present invention;
Fig. 2 is the step flow chart of determining typhoon two time scales approach provided in an embodiment of the present invention;
Fig. 3 is the schematic diagram that annulus provided in an embodiment of the present invention defines;
Fig. 4 is the step flow chart provided in an embodiment of the present invention established Typhoon-scale and calculate regression model;
Fig. 5 is the step process provided in an embodiment of the present invention that Typhoon-scale calculating regression model is established based on supporting vector algorithm
Figure;
Fig. 6 is the structural schematic diagram of typhoon destructiveness ranges determination device provided in an embodiment of the present invention;
Fig. 7 is the structural schematic diagram of Typhoon-scale determination unit provided in an embodiment of the present invention;
Fig. 8 is the structural schematic diagram that Typhoon-scale provided in an embodiment of the present invention calculates that regression model establishes unit;
Fig. 9 is the structural schematic diagram that Typhoon-scale provided in an embodiment of the present invention calculates that regression model establishes module.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is appreciated that term " first " used in this application, " second " etc. can be used to describe various elements herein,
But unless stated otherwise, these elements should not be limited by these terms.These terms are only used to by first element and another yuan
Part is distinguished.For example, in the case where not departing from scope of the present application, the first xx script can be known as the 2nd xx script,
And similarly, the 2nd xx script can be known as the first xx script.
The embodiment of the present invention is to solve quickly and accurately determine typhoon ruler existing for existing typhoon observation technology
The technical issues of spending establishes Typhoon-scale calculating regression model by observing data according to history typhoon, and uses and be easier to
Intensity of typhoon information, center of typhoon location information and the stationary weather satellite infrared observation image of acquisition are as the ginseng in model
Number, so that after establishing Typhoon-scale and calculating regression model, it is only necessary to obtain strength information, the center of typhoon position of current typhoon
Confidence breath and stationary weather satellite infrared observation image can quickly and accurately determine the Typhoon-scale of current typhoon.
As shown in Figure 1, in one embodiment it is proposed that a kind of typhoon destructiveness range determining method, specifically can wrap
Include following steps:
Step S102 establishes the Typhoon-scale containing variable element based on history typhoon observation data and calculates regression model.
In embodiments of the present invention, the variable element includes the typhoon cloud top region temperature under intensity of typhoon, preset condition
Degree.
In embodiments of the present invention, the history typhoon observation data include from each meteorological satellite or meteorological department, various countries
The typhoon of preservation observes data.
As a possible embodiments of the invention, the history typhoon observation data include each history typhoon maximum strong
Intensity of typhoon data value, center of typhoon position information value, the same period stationary weather satellite infrared observation data image when spending and
Typhoon destructiveness range data information.
As a possible embodiments of the invention, the typhoon cloud top regional temperature under the preset condition includes multiple rings
The difference of the average value of the average value and adjacent annular region in shape region.
Step S104 obtains current intensity of typhoon information and current center of typhoon location information in real time.
In embodiments of the present invention, the center of typhoon position is shown with longitude and latitude data.
In embodiments of the present invention, since typhoon service center can real-time release intensity of typhoon information and center of typhoon position
Confidence breath, therefore can be by data call from being read in typhoon service center in current intensity of typhoon information and current typhoon
Heart location information.
Step S106 obtains current quiet meteorological satellite infrared observation image in real time.
In embodiments of the present invention, since the infrared observation image that stationary weather satellite can will be observed that is sent to typhoon industry
Business center, therefore likewise, can directly can also be read from typhoon service center by data call corresponding current
Stationary weather satellite infrared observation image.
Step S108 generates typhoon cloud according to the gray value of each pixel in the stationary weather satellite infrared observation image
Push up regional temperature figure.
In embodiments of the present invention, since stationary weather satellite infrared observation figure is substantially exactly to observe earth's surface and cloud top is red
External radiation intensity, and infrared intensity depends on the temperature of object itself, can be one by infrared observation image understanding therefore
The unique hygrogram of kind, and object temperature is higher, then infrared intensity is also bigger, then tone is deeper in infrared observation figure,
Therefore we are assured that the hygrogram in typhoon cloud top region, gray scale by the gray value of each pixel in infrared observation image
Value is higher, i.e. expression tone is deeper, then temperature is higher, shows that typhoon convection current is weaker;And cloud top tone is more shallow, then represents cloud top and get over
Cold, typhoon convection current is stronger.
Step S110 calculates regression model, intensity of typhoon, center of typhoon position and typhoon cloud according to the Typhoon-scale
Top regional temperature figure determines Typhoon-scale.
In embodiments of the present invention, due to Typhoon-scale calculate regression model be substantially Typhoon-scale and intensity of typhoon,
Therefore the functional relation of center of typhoon position and typhoon cloud top regional temperature passes through the intensity of typhoon of acquisition, center of typhoon position
It sets and typhoon cloud top regional temperature can easily determine Typhoon-scale.
As a preferred embodiment of the present invention, further, typhoon cloud top regional temperature can be handled, be wrapped
The temperature value for obtaining multiple annulus using centered on center of typhoon is included as the substitution value of typhoon cloud top regional temperature, is enabled to
Finally determining Typhoon-scale result is more accurate.
Step S112 determines typhoon destructiveness range according to the Typhoon-scale.
In embodiments of the present invention, it since Typhoon-scale is exactly the index for measuring typhoon destructiveness range, is obtaining currently
After the Typhoon-scale of typhoon, it may be convenient to determine the destructive range of the typhoon.
A kind of typhoon destructiveness range determining method provided in an embodiment of the present invention observes data by history typhoon first
It establishes the Typhoon-scale containing variable element and calculates regression model, then obtain current intensity of typhoon information, current typhoon respectively
Center location information and current quiet meteorological satellite infrared observation image, further according to current quiet meteorological satellite infrared observation figure
As the generation typhoon cloud top regional temperature figure of each pixel, by above-mentioned intensity of typhoon information, current center of typhoon location information with
And typhoon cloud top regional temperature figure is input in the Typhoon-scale calculating regression model of foundation and is assured that out the typhoon
Scale, to further determine that the destructive range of the typhoon.A kind of typhoon destructiveness range provided in an embodiment of the present invention
Method is determined, since what be can be convenient gets current intensity of typhoon information, current center of typhoon location information and current quiet
Only meteorological satellite infrared observation image, and calculating regression model according to the Typhoon-scale quickly can directly determine typhoon ruler
Degree further since the Typhoon-scale used calculates regression model is established based on history typhoon observation data, moreover it is possible to have
It ensure that effect the accuracy rate of the Typhoon-scale finally determined.
In one embodiment, as shown in Fig. 2, step S110 can specifically include following steps:
Step S202 obtains the temperature averages of multiple annulus in the regional temperature figure of typhoon cloud top under preset condition.
In embodiments of the present invention, the annulus is the annular region centered on center of typhoon position.
In embodiments of the present invention, the preset condition refers to the annulus apart from center of typhoon position different distance.
As a preferred embodiment of the present invention, the annulus is centered on center of typhoon, at interval of 16km as ring
Band chooses altogether 20 annulus, is successively denoted as T outward by center of typhoon1~T20。
In embodiments of the present invention, for purposes of illustration only, as shown in figure 3, showing the schematic diagram that annulus defines.
Step S204 calculates the difference of the temperature averages of adjacent ring band.
As a preferred embodiment of the present invention, the difference of the temperature averages between each adjacent two annulus is successively calculated
Value can get 19 temperature gaps, successively be denoted as TD outward by center of typhoon1-TD19。
Step S206 is calculated back according to the temperature averages of the multiple annulus, difference, intensity of typhoon and Typhoon-scale
Model is returned to determine Typhoon-scale.
In embodiments of the present invention, the temperature value of multiple belt temperatures is divided by refining typhoon cloud top regional temperature figure
And difference, the temperature changing trend in more specific characterization typhoon region, so that the Typhoon-scale result finally determined is more
It is accurate to add.
As shown in figure 3, being the schematic diagram that the annulus defines.
In embodiments of the present invention, because showing reason, it illustrate only the annulus at the interval 64km.
In one embodiment, as shown in figure 4, step S102 can specifically include following steps:
Step S402 obtains the typhoon observation data information of multiple history typhoons.
In embodiments of the present invention, the typhoon observation data information includes platform of the history typhoon in maximum intensity
Monsoon intensity data value, center of typhoon position information value, same period stationary weather satellite infrared observation data image and typhoon destroy
Property range data information.
Step S404 determines Typhoon-scale sample value according to the typhoon destructiveness range data information.
In embodiments of the present invention, similar to abovementioned steps S112, since Typhoon-scale is to measure typhoon destructiveness range
Index, therefore can also determine by destructive range data information the sample value of Typhoon-scale.
Step S406 is raw according to the gray value of each pixel in the same period stationary weather satellite infrared observation data image
At same period typhoon cloud top regional temperature source map.
In embodiments of the present invention, similar to abovementioned steps S108, it is only in that the object of processing is different, referring specifically to
The explanation of abovementioned steps S108, details are not described herein.
Step S408, the temperature samples for obtaining multiple annulus in the regional temperature source map of typhoon cloud top under preset condition are flat
Mean value.
In embodiments of the present invention, similar to abovementioned steps S202, it is only in that the object of processing is different, referring specifically to
The explanation of abovementioned steps S202, details are not described herein.
Step S410 determines the difference of the temperature samples average value of adjacent ring band.
In embodiments of the present invention, similar to abovementioned steps S204, it is only in that the object of processing is different, referring specifically to
The explanation of abovementioned steps S204, details are not described herein.
Step S412, according to the Typhoon-scale sample value, intensity of typhoon data value, center of typhoon position information value and
Temperature samples average value and temperature samples average value, and Typhoon-scale is established based on supporting vector algorithm and calculates regression model.
For ease of understanding, data instance is observed with history typhoon of the present invention, including 2001 to 2009 terms
Between, GOES-1 satellite to GOES-13 satellite (U.S.'s GOES satellite series), Meteosat-2 satellite to Meteosat-9 satellite
(European MET satellite series), GMS-1 satellite to GMS-5 satellite (Japanese GMS satellite series), MTSAT-1R satellite to MTSAT-
2R satellite (Japanese MT S satellite series) and FY2 satellite (Chinese FY2 satellite series) totally 5 series of satellites to northwest Pacific platform
The typhoon data that the observation data and U.S.'s typhoon warning center of wind retain, it is established that Typhoon-scale calculate and return mould
Type.Wherein the formula of the Typhoon-scale calculating regression model is specific as follows:
R=0.7331*T2-0.9117*T20-0.9941*TD2+1.4146*TD4-1.0698*TD5+1.4507*TD6-1.5519*
TD10+1.4192*TD13+3.3438*Vm +124.9909。
Wherein, R is Typhoon-scale, VmFor intensity of typhoon, calculated by the Typhoon-scale that above-mentioned history experimental data determines
The Typhoon-scale that the formula of regression model finally determines is suitable with the analysis precision that World Meteorological Organization proposes, error 10% ~
Within 20%.
In one embodiment, as shown in figure 5, step S412 can specifically include following steps:
Step S502 establishes the Typhoon-scale containing initiation parameter and determines regression training model.
Step S504, according to the intensity of typhoon data value, center of typhoon position information value, temperature samples average value, temperature
Degree sample mean and the Typhoon-scale determine in regression training model, determine the Typhoon-scale response under conditions present
Value.
It is default to judge whether the difference of the Typhoon-scale response and the Typhoon-scale target value meets by step S506
Condition.When the difference for judging the Typhoon-scale response and the Typhoon-scale target value is unsatisfactory for preset condition,
Execute step S508;When judging that the Typhoon-scale response and the difference of the Typhoon-scale target value meet preset condition
When, execute step S510.
Step S508 adjusts the Typhoon-scale based on back-propagation algorithm and determines parameter in regression training model, and
It is back to the step S504.
Current Typhoon-scale is determined that regression training model is determined as Typhoon-scale and calculates regression model by step S510.
As shown in fig. 6, in one embodiment, providing a kind of typhoon destructiveness ranges determination device, specifically can wrap
It includes:
Typhoon-scale calculates regression model and establishes unit 610, for containing variable element based on the observation data foundation of history typhoon
Typhoon-scale calculate regression model.
In embodiments of the present invention, the variable element includes the typhoon cloud top region temperature under intensity of typhoon, preset condition
Degree.
In embodiments of the present invention, the history typhoon observation data include from each meteorological satellite or meteorological department, various countries
The typhoon of preservation observes data.
As a possible embodiments of the invention, the history typhoon observation data include each history typhoon maximum strong
Intensity of typhoon data value, center of typhoon position information value, the same period stationary weather satellite infrared observation data image when spending and
Typhoon destructiveness range data information.
As a possible embodiments of the invention, the typhoon cloud top regional temperature under the preset condition includes multiple rings
The difference of the average value of the average value and adjacent annular region in shape region.
Intensity of typhoon and center location information acquiring unit 620, for obtaining current intensity of typhoon information in real time and working as
Preceding typhoon center location information.
In embodiments of the present invention, the center of typhoon position is shown with longitude and latitude data.
In embodiments of the present invention, since typhoon service center can real-time release intensity of typhoon information and center of typhoon position
Confidence breath, therefore can be by data call from being read in typhoon service center in current intensity of typhoon information and current typhoon
Heart location information.
Meteorological satellite infrared observation image acquisition unit 630, for obtaining current quiet meteorological satellite infrared observation in real time
Image.
In embodiments of the present invention, since the infrared observation image that stationary weather satellite can will be observed that is sent to typhoon industry
Business center, therefore likewise, can directly can also be read from typhoon service center by data call corresponding current
Stationary weather satellite infrared observation image.
Typhoon cloud top regional temperature figure generation unit 640, for according in the stationary weather satellite infrared observation image
The gray value of each pixel generates typhoon cloud top regional temperature figure.
In embodiments of the present invention, since stationary weather satellite infrared observation figure is substantially exactly to observe earth's surface and cloud top is red
External radiation intensity, and infrared intensity depends on the temperature of object itself, can be one by infrared observation image understanding therefore
The unique hygrogram of kind, and object temperature is higher, then infrared intensity is also bigger, then tone is deeper in infrared observation figure,
Therefore we are assured that the hygrogram in typhoon cloud top region, gray scale by the gray value of each pixel in infrared observation image
Value is higher, i.e. expression tone is deeper, then temperature is higher, shows that typhoon convection current is weaker;And cloud top tone is more shallow, then represents cloud top and get over
Cold, typhoon convection current is stronger.
Typhoon-scale determination unit 650, for according in Typhoon-scale calculating regression model, intensity of typhoon, typhoon
Heart position and typhoon cloud top regional temperature figure determine Typhoon-scale.
In embodiments of the present invention, due to Typhoon-scale calculate regression model be substantially Typhoon-scale and intensity of typhoon,
Therefore the functional relation of center of typhoon position and typhoon cloud top regional temperature passes through the intensity of typhoon of acquisition, center of typhoon position
It sets and typhoon cloud top regional temperature can easily determine Typhoon-scale.
As a preferred embodiment of the present invention, further, typhoon cloud top regional temperature can be handled, be wrapped
The temperature value for obtaining multiple annulus using centered on center of typhoon is included as the substitution value of typhoon cloud top regional temperature, is enabled to
Finally determining Typhoon-scale result is more accurate.
Typhoon destructiveness range determination unit 660, for determining typhoon destructiveness range according to the Typhoon-scale.
In embodiments of the present invention, it since Typhoon-scale is exactly the index for measuring typhoon destructiveness range, is obtaining currently
After the Typhoon-scale of typhoon, it may be convenient to determine the destructive range of the typhoon.
A kind of typhoon destructiveness ranges determination device provided in an embodiment of the present invention observes data by history typhoon first
It establishes the Typhoon-scale containing variable element and calculates regression model, then obtain current intensity of typhoon information, current typhoon respectively
Center location information and current quiet meteorological satellite infrared observation image, further according to current quiet meteorological satellite infrared observation figure
As the generation typhoon cloud top regional temperature figure of each pixel, by above-mentioned intensity of typhoon information, current center of typhoon location information with
And typhoon cloud top regional temperature figure is input in the Typhoon-scale calculating regression model of foundation and is assured that out the typhoon
Scale, to further determine that the destructive range of the typhoon.A kind of typhoon destructiveness range provided in an embodiment of the present invention
Method is determined, since what be can be convenient gets current intensity of typhoon information, current center of typhoon location information and current quiet
Only meteorological satellite infrared observation image, and calculating regression model according to the Typhoon-scale quickly can directly determine typhoon ruler
Degree further since the Typhoon-scale used calculates regression model is established based on history typhoon observation data, moreover it is possible to have
It ensure that effect the accuracy rate of the Typhoon-scale finally determined.
As shown in fig. 7, in one embodiment, the Typhoon-scale determination unit 510 specifically includes:
Belt temperature determining module 711, for obtaining the temperature of multiple annulus in the regional temperature figure of typhoon cloud top under preset condition
Spend average value.
In embodiments of the present invention, the annulus is the annular region centered on center of typhoon position.
In embodiments of the present invention, the preset condition refers to the annulus apart from center of typhoon position different distance.
As a preferred embodiment of the present invention, the annulus is centered on center of typhoon, at interval of 16km as ring
Band chooses altogether 20 annulus, is successively denoted as T outward by center of typhoon1~T20。
In embodiments of the present invention, for purposes of illustration only, as shown in figure 3, showing the schematic diagram that annulus defines.
Adjacent ring band temperature gap computing module 712, the difference of the temperature averages for calculating adjacent ring band.
As a preferred embodiment of the present invention, the difference of the temperature averages between each adjacent two annulus is successively calculated
Value can get 19 temperature gaps, successively be denoted as TD outward by center of typhoon1-TD19。
Typhoon-scale determining module 713, for according to the temperature averages of the multiple annulus, difference, intensity of typhoon with
And Typhoon-scale calculates regression model and determines Typhoon-scale.
In embodiments of the present invention, the temperature value of multiple belt temperatures is divided by refining typhoon cloud top regional temperature figure
And difference, the temperature changing trend in more specific characterization typhoon region, so that the Typhoon-scale result finally determined is more
It is accurate to add.
As shown in figure 8, in one embodiment, the Typhoon-scale calculating regression model is established unit 502 and is specifically included:
History typhoon observes data information and obtains module 811, and the typhoon for obtaining multiple history typhoons observes data information.
In embodiments of the present invention, the typhoon observation data information includes platform of the history typhoon in maximum intensity
Monsoon intensity data value, center of typhoon position information value, same period stationary weather satellite infrared observation data image and typhoon destroy
Property range data information.
Typhoon-scale sample value determining module 812, for determining typhoon according to the typhoon destructiveness range data information
Scale sample value.
In embodiments of the present invention, similar to aforementioned typhoon destructiveness range determination unit 660, since Typhoon-scale is weighing apparatus
The index of typhoon destructiveness range is measured, therefore can also determine the sample value of Typhoon-scale by destructive range data information.
Typhoon cloud top regional temperature source map generation module 813, for according to the infrared sight of same period stationary weather satellite
The gray value of each pixel generates same period typhoon cloud top regional temperature source map in survey data image.
In embodiments of the present invention, similar to aforementioned typhoon cloud top regional temperature figure generation unit 640, it is only in that processing
Object it is different, it is no longer superfluous herein referring specifically to the explanation of aforementioned typhoon cloud top regional temperature figure generation unit 640
It states.
Belt temperature sample mean determining module 814 presets item for obtaining in the regional temperature source map of typhoon cloud top
The temperature samples average value of multiple annulus under part.
In embodiments of the present invention, similar to aforementioned belt temperature determining module 711, it is only in that the object of processing not
Together, referring specifically to the explanation of aforementioned belt temperature determining module 711, details are not described herein.
Adjacent ring band temperature samples difference determining module 815, the difference of the temperature samples average value for determining adjacent ring band
Value.
In embodiments of the present invention, similar to aforementioned adjacent ring band temperature gap determining module 712, it is only in that processing
Object is different, and the explanation referring specifically to aforementioned adjacent ring with temperature gap determining module 712, details are not described herein.
Typhoon-scale calculates regression model and establishes module 816, for being provided according to the Typhoon-scale sample value, intensity of typhoon
Material value, center of typhoon position information value and temperature samples average value and temperature samples average value, and it is based on supporting vector algorithm
It establishes Typhoon-scale and calculates regression model.
For ease of understanding, data instance is observed with history typhoon of the present invention, including 2001 to 2009 terms
Between, GOES-1 satellite to GOES-13 satellite (U.S.'s GOES satellite series), Meteosat-2 satellite to Meteosat-9 satellite
(European MET satellite series), GMS-1 satellite to GMS-5 satellite (Japanese GMS satellite series), MTSAT-1R satellite to MTSAT-
2R satellite (Japanese MT S satellite series) and FY2 satellite (Chinese FY2 satellite series) totally 5 series of satellites to northwest Pacific platform
The typhoon data that the observation data and U.S.'s typhoon warning center of wind retain, it is established that Typhoon-scale calculate and return mould
Type.Wherein the formula of the Typhoon-scale calculating regression model is specific as follows:
R=0.7331*T2-0.9117*T20-0.9941*TD2+1.4146*TD4-1.0698*TD5+1.4507*TD6-1.5519*
TD10+1.4192*TD13+3.3438*Vm +124.9909。
Wherein, R is Typhoon-scale, VmFor intensity of typhoon, calculated by the Typhoon-scale that above-mentioned history experimental data determines
The Typhoon-scale that the formula of regression model finally determines is suitable with the analysis precision that World Meteorological Organization proposes, error 10% ~
Within 20%.
As shown in figure 9, in one embodiment, the Typhoon-scale calculating regression model is established module 816 and is specifically included:
Typhoon-scale determines regression training model foundation secondary module 911, true for establishing the Typhoon-scale containing initiation parameter
Determine regression training model.
Typhoon-scale response determines secondary module 912, for being provided according to the intensity of typhoon data value, center of typhoon position
Material value, temperature samples average value, temperature samples average value and the Typhoon-scale determine in regression training model, determine current
Under the conditions of Typhoon-scale response.
Secondary module 913 is judged, for judging that the difference of the Typhoon-scale response and the Typhoon-scale target value is
It is no to meet preset condition.
Parameter adjusts secondary module 914, judges the Typhoon-scale response and the Typhoon-scale target value for working as
When difference is unsatisfactory for preset condition, the Typhoon-scale is adjusted based on back-propagation algorithm and determines ginseng in regression training model
Number, and be back to the Typhoon-scale response and determine secondary module 912.
Typhoon-scale calculate regression model determine secondary module 915, for when judge the Typhoon-scale response with it is described
When the difference of Typhoon-scale target value meets preset condition, current Typhoon-scale is determined that regression training model is determined as typhoon
Dimension calculation regression model.
In one embodiment it is proposed that a kind of computer equipment, the computer equipment include memory, processor and
It is stored in the computer program that can be run on the memory and on the processor, the processor executes the computer
It is performed the steps of when program
The Typhoon-scale containing variable element, which is established, based on history typhoon observation data calculates regression model, the variable element packet
Include the typhoon cloud top regional temperature under intensity of typhoon, preset condition;
Current intensity of typhoon information and current center of typhoon location information are obtained in real time;
Current quiet meteorological satellite infrared observation image is obtained in real time;
Typhoon cloud top regional temperature figure is generated according to the gray value of each pixel in the stationary weather satellite infrared observation image;
Regression model, intensity of typhoon, center of typhoon position and typhoon cloud top regional temperature figure are calculated according to the Typhoon-scale
Determine Typhoon-scale;
Typhoon destructiveness range is determined according to the Typhoon-scale.
In one embodiment, a kind of computer readable storage medium is provided, is stored on computer readable storage medium
Computer program, when computer program is executed by processor, so that processor executes following steps:
The Typhoon-scale containing variable element, which is established, based on history typhoon observation data calculates regression model, the variable element packet
Include the typhoon cloud top regional temperature under intensity of typhoon, preset condition;
Current intensity of typhoon information and current center of typhoon location information are obtained in real time;
Current quiet meteorological satellite infrared observation image is obtained in real time;
Typhoon cloud top regional temperature figure is generated according to the gray value of each pixel in the stationary weather satellite infrared observation image;
Regression model, intensity of typhoon, center of typhoon position and typhoon cloud top regional temperature figure are calculated according to the Typhoon-scale
Determine Typhoon-scale;
Typhoon destructiveness range is determined according to the Typhoon-scale.
Although should be understood that various embodiments of the present invention flow chart in each step according to arrow instruction successively
It has been shown that, but these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein,
There is no stringent sequences to limit for the execution of these steps, these steps can execute in other order.Moreover, in each embodiment
At least part step may include multiple sub-steps perhaps these sub-steps of multiple stages or stage be not necessarily
Synchronization executes completion, but can execute at different times, and the execution sequence in these sub-steps or stage also need not
Be so successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or
Person alternately executes.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a non-volatile computer and can be read
In storage medium, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, provided herein
Each embodiment used in any reference to memory, storage, database or other media, may each comprise non-volatile
And/or volatile memory.Nonvolatile memory may include that read-only memory (ROM), programming ROM (PROM), electricity can be compiled
Journey ROM(EPROM), electrically erasable ROM(EEPROM) or flash memory.Volatile memory may include random access memory
(RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, such as static state RAM
(SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhanced SDRAM
(ESDRAM), synchronization link (Synchlink) DRAM(SLDRAM), memory bus (Rambus) direct RAM(RDRAM), it is straight
Connect memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of typhoon destructiveness range determining method characterized by comprising
The Typhoon-scale containing variable element, which is established, based on history typhoon observation data calculates regression model, the variable element packet
Include the typhoon cloud top regional temperature under intensity of typhoon, preset condition;
Current intensity of typhoon information and current center of typhoon location information are obtained in real time;
Current quiet meteorological satellite infrared observation image is obtained in real time;
Typhoon cloud top regional temperature figure is generated according to the gray value of each pixel in the stationary weather satellite infrared observation image;
Regression model, intensity of typhoon, center of typhoon position and typhoon cloud top regional temperature figure are calculated according to the Typhoon-scale
Determine Typhoon-scale;
Typhoon destructiveness range is determined according to the Typhoon-scale.
2. typhoon destructiveness range determining method according to claim 1, which is characterized in that described according to Typhoon-scale meter
It is specific to calculate the step of regression model, intensity of typhoon, center of typhoon position and typhoon cloud top regional temperature figure determine Typhoon-scale
Include:
The temperature averages of multiple annulus in the regional temperature figure of typhoon cloud top under preset condition are obtained, the annulus is with typhoon
Annular region centered on center;
Calculate the difference of the temperature averages of adjacent ring band;
Regression model determining table is calculated according to the temperature averages of the multiple annulus, difference, intensity of typhoon and Typhoon-scale
Wind scale.
3. typhoon destructiveness range determining method according to claim 1, which is characterized in that described to be seen based on history typhoon
The step of Typhoon-scale of the measured data foundation containing variable element calculates regression model specifically includes:
The typhoon observation data information of multiple history typhoons is obtained, the typhoon observation data information includes that the history typhoon exists
Intensity of typhoon data value, center of typhoon position information value, the same period stationary weather satellite infrared observation source map when maximum intensity
Picture and typhoon destructiveness range data information;
Typhoon-scale sample value is determined according to the typhoon destructiveness range data information;
Same period typhoon cloud is generated according to the gray value of each pixel in the same period stationary weather satellite infrared observation data image
Push up regional temperature source map;
Obtain the temperature samples average value of multiple annulus in the regional temperature source map of typhoon cloud top under preset condition, the annulus
For the annular region centered on center of typhoon position;
Determine the difference of the temperature samples average value of adjacent ring band;
It is average according to the Typhoon-scale sample value, intensity of typhoon data value, center of typhoon position information value and temperature samples
Value and temperature samples average value, and Typhoon-scale is established based on supporting vector algorithm and calculates regression model.
4. typhoon destructiveness range determining method according to claim 3, which is characterized in that described according to the typhoon ruler
Sample value, intensity of typhoon data value, center of typhoon position information value and temperature samples average value and temperature samples average value are spent,
And the step of Typhoon-scale calculates regression model is established based on supporting vector algorithm and is specifically included:
It establishes the Typhoon-scale containing initiation parameter and determines regression training model;
According to the intensity of typhoon data value, center of typhoon position information value, temperature samples average value, temperature samples average value with
And the Typhoon-scale determines in regression training model, determines the Typhoon-scale response under conditions present;
Judge whether the Typhoon-scale response and the difference of the Typhoon-scale target value meet preset condition;
When the difference for judging the Typhoon-scale response and the Typhoon-scale target value is unsatisfactory for preset condition, it is based on
Back-propagation algorithm adjusts the Typhoon-scale and determines parameter in regression training model, and is back to described according to the typhoon
Intensity data value, center of typhoon position information value, temperature samples average value, temperature samples average value and the Typhoon-scale are true
The step of determining to determine the Typhoon-scale response under conditions present in regression training model;
It, will be current when the difference for judging the Typhoon-scale response and the Typhoon-scale target value meets preset condition
Typhoon-scale determines that regression training model is determined as Typhoon-scale and calculates regression model.
5. a kind of typhoon destructiveness ranges determination device characterized by comprising
Typhoon-scale calculates regression model and establishes unit, for establishing the platform containing variable element based on history typhoon observation data
Wind dimension calculation regression model, the variable element include the typhoon cloud top regional temperature under intensity of typhoon, preset condition;
Intensity of typhoon and center location information acquiring unit, for being obtained in current intensity of typhoon information and current typhoon in real time
Heart location information;
Meteorological satellite infrared observation image acquisition unit, for obtaining current quiet meteorological satellite infrared observation image in real time;
Typhoon cloud top regional temperature figure generation unit, for according to each pixel in the stationary weather satellite infrared observation image
Gray value generate typhoon cloud top regional temperature figure;
Typhoon-scale determination unit, for according to the Typhoon-scale calculate regression model, intensity of typhoon, center of typhoon position with
And typhoon cloud top regional temperature figure determines Typhoon-scale;And
Typhoon destructiveness range determination unit, for determining typhoon destructiveness range according to the Typhoon-scale.
6. a kind of typhoon destructiveness ranges determination device as claimed in claim 5, which is characterized in that the Typhoon-scale determines
Unit includes:
Belt temperature determining module, the temperature for obtaining multiple annulus in the regional temperature figure of typhoon cloud top under preset condition are flat
Mean value, the annulus are the annular region centered on center of typhoon position;
Adjacent ring band temperature gap determining module, the difference of the temperature averages for calculating adjacent ring band;And
Typhoon-scale determining module, for according to the temperature averages of the multiple annulus, difference, intensity of typhoon and typhoon ruler
Degree calculates regression model and determines Typhoon-scale.
7. typhoon destructiveness ranges determination device according to claim 5, which is characterized in that the Typhoon-scale calculates back
The model foundation unit is returned to include:
History typhoon observes data information and obtains module, and the typhoon for obtaining multiple history typhoons observes data information, described
Typhoon observation data information includes intensity of typhoon data value of the history typhoon in maximum intensity, center of typhoon position information
Value, same period stationary weather satellite infrared observation data image and typhoon destructiveness range data information;
Typhoon-scale sample value determining module, for determining Typhoon-scale sample according to the typhoon destructiveness range data information
Value;
Typhoon cloud top regional temperature source map generation module, for according to the same period stationary weather satellite infrared observation source map
The gray value of each pixel generates same period typhoon cloud top regional temperature source map as in;
Belt temperature sample mean determining module is more under preset condition in the regional temperature source map of typhoon cloud top for obtaining
The temperature samples average value of a annulus, the annulus are the annular region centered on center of typhoon position;
Adjacent ring band temperature samples difference determining module, the difference of the temperature samples average value for determining adjacent ring band;And
Typhoon-scale calculates regression model and establishes module, for according to the Typhoon-scale sample value, intensity of typhoon data value, platform
Wind center data value and temperature samples average value and temperature samples average value, and typhoon is established based on supporting vector algorithm
Dimension calculation regression model.
8. typhoon destructiveness ranges determination device according to claim 7, which is characterized in that the Typhoon-scale calculates back
The model building module is returned to include:
Typhoon-scale determines regression training model foundation secondary module, determines back for establishing the Typhoon-scale containing initiation parameter
Return training pattern;
Typhoon-scale response determines secondary module, for according to the intensity of typhoon data value, center of typhoon position information value, temperature
Degree sample mean, temperature samples average value and the Typhoon-scale determine in regression training model, determine under conditions present
Typhoon-scale response;
Secondary module is judged, for judging it is pre- whether the difference of the Typhoon-scale response and the Typhoon-scale target value meets
If condition;
Parameter adjusts secondary module, for being discontented with when the difference for judging the Typhoon-scale response and the Typhoon-scale target value
When the preset condition of foot, the Typhoon-scale is adjusted based on back-propagation algorithm and determines parameter in regression training model, and is returned
It is back to the Typhoon-scale response and determines secondary module;
Typhoon-scale calculates regression model and determines secondary module, judges the Typhoon-scale response and the Typhoon-scale for working as
When the difference of target value meets preset condition, current Typhoon-scale is determined that regression training model is determined as Typhoon-scale and calculates
Regression model.
9. a kind of computer equipment, which is characterized in that including memory and processor, computer journey is stored in the memory
Sequence, when the computer program is executed by the processor, so that the processor perform claim requires any one of 1 to 4 power
Benefit requires the step of typhoon destructiveness range determining method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, when the computer program is executed by processor, so that the processor perform claim requires any one of 1 to 4 right
It is required that the step of typhoon destructiveness range determining method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910382117.3A CN110110725A (en) | 2019-05-09 | 2019-05-09 | Typhoon destructiveness range determining method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910382117.3A CN110110725A (en) | 2019-05-09 | 2019-05-09 | Typhoon destructiveness range determining method, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110110725A true CN110110725A (en) | 2019-08-09 |
Family
ID=67488953
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910382117.3A Pending CN110110725A (en) | 2019-05-09 | 2019-05-09 | Typhoon destructiveness range determining method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110725A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114550007A (en) * | 2022-02-25 | 2022-05-27 | 中山大学 | Typhoon center position offset generation method and typhoon center positioning method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915729A (en) * | 2015-05-26 | 2015-09-16 | 中国科学院深圳先进技术研究院 | Method and system for carrying out processing on environment prediction factor data of typhoon intensity |
CN104932035A (en) * | 2015-05-26 | 2015-09-23 | 中国科学院深圳先进技术研究院 | Typhoon intensity prediction method and system |
CN107330583A (en) * | 2017-06-09 | 2017-11-07 | 哈尔滨工业大学深圳研究生院 | A kind of complete trails typhoon risk analysis method based on statistical dynamics |
-
2019
- 2019-05-09 CN CN201910382117.3A patent/CN110110725A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915729A (en) * | 2015-05-26 | 2015-09-16 | 中国科学院深圳先进技术研究院 | Method and system for carrying out processing on environment prediction factor data of typhoon intensity |
CN104932035A (en) * | 2015-05-26 | 2015-09-23 | 中国科学院深圳先进技术研究院 | Typhoon intensity prediction method and system |
CN107330583A (en) * | 2017-06-09 | 2017-11-07 | 哈尔滨工业大学深圳研究生院 | A kind of complete trails typhoon risk analysis method based on statistical dynamics |
Non-Patent Citations (3)
Title |
---|
XIAOQIN LU 等: "Estimating Tropical Cyclone Size in the Northwestern Pacific from Geostationary Satellite Infrared Images", 《REMOTE SENSING》 * |
华建新: "《全连续式冷连轧机过程控制》", 29 February 2000 * |
杨可明: "《遥感原理与应用》", 30 September 2016 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114550007A (en) * | 2022-02-25 | 2022-05-27 | 中山大学 | Typhoon center position offset generation method and typhoon center positioning method |
CN114550007B (en) * | 2022-02-25 | 2022-08-19 | 中山大学 | Typhoon center position offset generation method and typhoon center positioning method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Krajewski et al. | Real-time flood forecasting and information system for the state of Iowa | |
Ramsankaran et al. | Spatially distributed ice-thickness modelling for Chhota Shigri Glacier in western Himalayas, India | |
CN109668635A (en) | Sea surface temperature fusion method and system | |
Frolov et al. | Improved statistical prediction of surface currents based on historic HF-radar observations | |
Xie et al. | Diagnosis of 3D vertical circulation in the upwelling and frontal zones east of Hainan Island, China | |
Lefévre et al. | A comparison of multiple regression and neural network techniques for mapping in situ pCO2 data | |
CN114139444A (en) | Offshore sea surface temperature inversion method based on machine learning | |
Brakenridge | Flood risk mapping from orbital remote sensing | |
Hassan et al. | Evaluation of daily gridded meteorological datasets over the Niger Delta region of Nigeria and implication to water resources management | |
CN110110725A (en) | Typhoon destructiveness range determining method, device, computer equipment and storage medium | |
Devi et al. | Analyzing precipitation and temperature trends of Kanha and Satpura tiger reserve, central India | |
Zhai et al. | On the variability of wind power input to the oceans with a focus on the subpolar North Atlantic | |
Gobron et al. | Assessment of tide gauge biases and precision by the combination of multiple collocated time series | |
Choukulkar et al. | A modified optimal interpolation technique for vector retrieval for coherent Doppler lidar | |
Olivares-Pulido et al. | Markov chain Monte Carlo and the application to geodetic time series analysis | |
Hemming et al. | Daily subsurface ocean temperature climatology using multiple data sources: new methodology | |
DiNezio et al. | Identifying and estimating biases between XBT and Argo observations using satellite altimetry | |
Martin | Ocean forecasting systems: product evaluation and skill | |
CN112861355B (en) | Sea surface net radiation estimation method and system | |
Suhura et al. | Coastal land use/land cover and shoreline studies for Dakshina Kannada Coast, Karnataka, India | |
Bak et al. | Initialization and setup of the coastal model test bed: STWAVE | |
Reid et al. | Methodology for applying GIS to evaluate hydrodynamic model performance in predicting coastal inundation | |
Blaylock et al. | Assimilating near-surface wind retrievals from high-frequency radars | |
Young et al. | Initialization and Setup of the Coastal Model Test Bed: CSHORE | |
Grašič et al. | Validation of numerically forecast vertical temperature profile with measurements for dispersion modelling |
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 |