CN110211325A - A kind of area road icing high precision monitor early warning system based on meteorological big data - Google Patents
A kind of area road icing high precision monitor early warning system based on meteorological big data Download PDFInfo
- Publication number
- CN110211325A CN110211325A CN201910567666.8A CN201910567666A CN110211325A CN 110211325 A CN110211325 A CN 110211325A CN 201910567666 A CN201910567666 A CN 201910567666A CN 110211325 A CN110211325 A CN 110211325A
- Authority
- CN
- China
- Prior art keywords
- data
- forecast
- meteorological
- observation
- early warning
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
- G08B19/02—Alarm responsive to formation or anticipated formation of ice
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
- G08B29/188—Data fusion; cooperative systems, e.g. voting among different detectors
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The area road icing high precision monitor early warning system based on meteorological big data that the invention discloses a kind of, including hardware running environment is built, live data is collected and analysis, Mesoscale Numerical Forecast tool NONLINEAR CALCULATION, the linearity correction of temperature DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM result, region Surface Temperature Retrieval and area road icing conditions early warning.The beneficial effects of the present invention are: introducing the data of meteorological satellite, the dimension of meteorological measuring is expanded, participates in the Data Assimilation of Numerical Prediction Models, improves the precision of forecast result indirectly；Numerical model DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM is introduced, when gathering forecast result, using sliding training period, weight coefficient changes at any time, improves accuracy；The relationship of temperature, surface temperature, steam under different geographical environments is sought by linear analysis using a variety of representative stations, then from point to surface, improves the accuracy of area road icing conditions prediction.
Description
Technical field
The present invention relates to a kind of monitoring and warning system, specially a kind of area road based on meteorological big data freezes high-precision
Monitoring and warning system is spent, Atmospheric Survey and weather forecasting techniques field are belonged to.
Background technique
With the development and scientific and technological progress of social economy, communications and transportation has become national economy production and people's social life
Important lifeblood, however, the links of communications and transportation are all directly affected by meteorological condition.According to statistics, China is public
Having in the traffic accident of road has the ratio for having 65% in 71%, direct economic loss in 50%, particularly serious traffic accident
In the bad weather generated by bad-weather condition, in winter and early spring, the influence of icy road are especially pronounced.There is road
When icing, since wheel and pavement friction effect weaken significantly, it is easy to skid, stops and do not live vehicle, cause traffic accident.Pedestrian also holds
It easily slips, causes tumble injury, the existing Meteorological Services for icy road, first is that carrying out icy road using automatic weather station
Monitoring, then with detection result carry out early warning；Second is that estimating the road that may occur using the temperature record in weather forecast result
Road freezes.
However for existing Meteorological Services, one, current meteorological observation, mostly Single Point Surveying can not be to big regions
Icy road situation under interior a variety of geographical environments is monitored, although secondly, surface temperature and temperature exist it is preferable related
Relationship, but the influence of the related receptor many factors of the two.The variation of surface temperature is by shadows such as atural object property, dry and wet conditions
It rings, and temperature is influenced by surrounding enviroment.Therefore, the forecast data for only using temperature, can not accurately predict icy road feelings
Condition, thirdly, icy road in addition to surface temperature mutually outside the Pass, it is also related with moisture content, even if also having can there is no precipitation
Icing phenomenon can occur, the moisture content that automatic weather station cannot achieve big region totally monitors.
Summary of the invention
The object of the invention is that providing a kind of area road based on meteorological big data to solve the above-mentioned problems
Icing high precision monitor early warning system.
The present invention is through the following technical solutions to achieve the above objectives: a kind of area road based on meteorological big data freezes
High precision monitor early warning system, comprising the following steps:
Step 1, hardware running environment are built, and the server cluster skill of the ultrahigh speed network based on Infiniband is passed through
Art completes concurrent operation, and solves the bandwidth and capacity problem of data interaction storage, carries out at meteorological data data to meet
A large amount of intensive operations required for managing；
Step 2, live data are collected, are analyzed, and by automatic weather station, obtain real-time dry-bulb temperature (temperature), earth's surface
The meteorological elements such as temperature, icy road, relative temperature, wind speed, precipitation, evaporation capacity, radiation flux, visibility；
Wherein, each website represents a kind of road region classification, and the back or sunny side including mountain area, rivers,lakes and seas are attached
Closely, Plain etc..
Step 3, Mesoscale Numerical Forecast tool (WRF) NONLINEAR CALCULATION, by above-mentioned weather observation data and European mid-term
The GFS numerical forecast mould of the EC Numerical Prediction Models of Climate Prediction Center (ECMWF), Environmental forecasting centre (NECP)
The data importing data pool of formula initial fields, boundary field, then by carrying out Data Assimilation with three-dimensional variational algorithm (3D-Var)；
It is assumed that the observation of meteorological variables is O, and the background value (such as predicted value of average value, numerical model) of the variable
For F, variance σOAnd σF, then obtain a weighted average:
Above-mentioned A is the minimum of following valence function J (S) in fact:
Assuming that there is the measurement S from distinct methods to variable S1、S2..., SN, error ∈n=Sn- S, it is assumed that error be with
Machine, unbiased < ∈nThe error of >=0, and Normal Distribution, n-th of observation falls in ∈nAnd ∈n+d∈nBetween probability be
Error variance:
Have for N number of observation:
If
When I minimalization, maximal possibility estimation is obtained.
By I to SaFirst derivative be zero to obtain:
The maximal possibility estimation of S is the weighted average of Sn, and weight is the inverse of the error variance of each measurement.
As N=2, objective function is introduced:
Wherein, x is situational variables, xbIt is ambient field, x, xbFor N-dimensional vector, yoIt is observation, y is exported by situational variables
Value, y=H (x), H are known as Observation Operators, yo, y be M dimensional vector, B is background error covariance, and O is observation error covariance,
B is N*N matrix, and O is M*M matrix.
Mathematically it can be proved that the best estimate (analysis field) of x is:
X=xb+[B-1+HTO-1H]-1HTO-1(yo-Hxb)
It is the minimal point of objective function, directly asks x extremely difficult, and the minimal point of J is generally found with descent algorithm, is calculated
Gradient formula is:
Wherein,The referred to as tangent linear operator of Observation Operators.
Step 4, temperature DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM result linearity correction, firstly, access 6 groups of temperature forecast results and this pre- call time
Live detection data；Secondly, time series is divided into training period, forecast period by the way of establishing multiple linear regression model；
In training period, the multiple linear regression model of 6 groups of predicted values and observation is established, by using the polynary of predicted value and observation
Linear regression analysis, the weight coefficient of certain 6 groups of forecast results, and finally forecast with 1 group of this weight coefficient acquisition forecast period
As a result；
Wherein, multiple linear regression model
In some given lattice point, for a certain meteorological element of a certain Time effect forecast:
Wherein, O is that the observation of training period is average, aiIt is the weight coefficient for participating in the ith member of set, FiWithPoint
It is not the predicted value and its forecast average value in training period of i-th of mode, N is the mode sum for participating in superset forecast.
Wherein weight coefficient aiIt is calculated and is obtained by the minimum of the error term G in above-mentioned training period equation:
Wherein, N is training period time samples number, St' and Ot' it is the superset of training period and the deviation of observation field respectively,
The operation on the format of each mode of this equation.And the foundation of multi-mode superset forecasting procedure is to rely on error covariance
Matrix, it is mode field deviation F againi' and Fj' establish, therefore, the weight coefficient of each mode is calculated by error matrix C and is obtained:
Wherein, N is training period time samples number, Fi' (t) and Fj' (t) is the pre- of i-th of mode and j-th mode respectively
Report value anomaly, establishes linear algebraic equation.
Wherein,
oi' it is observation anomaly, [CI, j] matrix that is, [ai] be n × n matrix,For the matrix of n × 1, application
Gauss-Jordan null method solves, and obtains substituting into formula.
The numerical forecast data of temperature are substituted into the linear relationship of step 2, are finally inversed by by step 5, region Surface Temperature Retrieval
The surface temperature result of whole region；
Step 6, area road icing conditions early warning, by the numerical forecast data of steam, the surface temperature result of step 5 with
The critical value section of step 2 is compared, and predicts the icy road situation of whole region, and carries out early warning.
Preferably, in order to promote the precision of forecast result indirectly, in the step 2, pass through meteorological satellite, obtain automatic gas
As long wave, the shortwave, steam data of region of standing, and isolate the single-point steam data of site location.
Preferably, in order to obtaining newest forecast result, the step 2 by analytical calculation to real time data
In, the data of collection are real-time transmitted to cloud server by wired or wireless way.
Preferably, in order to improve accuracy of the forecast, in the step 4, training period is sliding training period, and system is continuous
Subsequent live data and forecast result are accessed, contrast verification is able to carry out, newest weight coefficient is obtained, introduces Numerical-Mode
Formula DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM, when gathering forecast result, using sliding training period, weight coefficient changes at any time.
Preferably, for the accuracy of lifting region icy road condition predicting, in the step 4, by linear analysis,
Seek the relationship of temperature, surface temperature, steam under different geographical environments.
It is set the beneficial effects of the present invention are: being somebody's turn to do the area road icing high precision monitor early warning system based on meteorological big data
Meter is reasonable:
(1) data for introducing meteorological satellite expand the dimension of meteorological measuring, participate in the money of Numerical Prediction Models
Material assimilation, improves the precision of forecast result indirectly；
(2) numerical model DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM is introduced, when gathering forecast result, using sliding training period, weight
Coefficient changes at any time, improves accuracy；
(3) temperature, surface temperature, water under different geographical environments are sought by linear analysis using a variety of representative stations
The relationship of vapour, then from point to surface, improve the accuracy of area road icing conditions prediction.
Detailed description of the invention
Fig. 1 is present system flow diagram；
Fig. 2 is surface temperature of the present invention and temperature linear relationship schematic diagram；
Fig. 3 is surface temperature of the present invention and temperature linear relationship schematic diagram；
Fig. 4 is surface temperature of the present invention and temperature linear relationship schematic diagram；
Fig. 5 is meteorological distribution schematic diagram in the embodiment of the present invention；
Fig. 6 is icing probability distribution schematic diagram in the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Please refer to Fig. 1~6, a kind of area road icing high precision monitor early warning system based on meteorological big data, including
Following steps:
Step 1, hardware running environment are built, and the server cluster skill of the ultrahigh speed network based on Infiniband is passed through
Art completes concurrent operation, and solves the bandwidth and capacity problem of data interaction storage, carries out at meteorological data data to meet
A large amount of intensive operations required for managing；
Step 2, live data are collected, are analyzed, and by automatic weather station, obtain real-time dry-bulb temperature (temperature), earth's surface
The meteorological elements such as temperature, icy road, relative temperature, wind speed, precipitation, evaporation capacity, radiation flux, visibility are collected meteorology and are defended
Long wave, shortwave, steam data, the temperature of the automatic weather station in multiple representative places, surface temperature, icy road state of star
And the global number of the live datas of the elements such as relative humidity, precipitation, evaporation capacity, radiation flux, European mid-term Climate Prediction Center
Be worth the initial fields of Forecast Mode ECMWF, ambient field, U.S. environment forecasting centre global numerical Forecast Mode GFS initial fields,
Ambient field, and the single-point steam data of site location are isolated, the data of meteorological satellite are introduced, meteorological measuring is expanded
Dimension, participate in the Data Assimilation of Numerical Prediction Models, improve the precision of forecast result indirectly；
Wherein, each website represents a kind of road region classification, and the back or sunny side including mountain area, rivers,lakes and seas are attached
Closely, Plain etc..
The data of collection are real-time transmitted to cloud server by wired or wireless way, enable the data collected into
Row quickly transmission, and then newest forecast result can be obtained by the analytical calculation to real time data.
Step 3, Mesoscale Numerical Forecast tool (WRF) NONLINEAR CALCULATION, by above-mentioned weather observation data and European mid-term
The GFS numerical forecast mould of the EC Numerical Prediction Models of Climate Prediction Center (ECMWF), Environmental forecasting centre (NECP)
The data importing data pool of formula initial fields, boundary field, then by carrying out Data Assimilation with three-dimensional variational algorithm (3D-Var),
After the completion of Data Assimilation, 3 kinds of physico parametric schemes are chosen, calculate 6 groups of forecast results, each pattern, every group of scheme difference
Calculate 1 group of result；
It is assumed that the observation of meteorological variables is O, and the background value (such as predicted value of average value, numerical model) of the variable
For F, variance σOAnd σF, then obtain a weighted average:
Above-mentioned A is the minimum of following valence function J (S) in fact:
Assuming that there is the measurement S from distinct methods to variable S1、S2..., SN, error ∈n=Sn- S, it is assumed that error be with
Machine, unbiased < ∈nThe error of >=0, and Normal Distribution, n-th of observation falls in ∈nAnd ∈n+d∈nBetween probability be
Error variance:
Have for N number of observation:
If
When I minimalization, maximal possibility estimation is obtained.
By I to SaFirst derivative be zero to obtain:
The maximal possibility estimation of S is the weighted average of Sn, and weight is the inverse of the error variance of each measurement.
As N=2, objective function is introduced:
Wherein, x is situational variables, xbIt is ambient field, x, xbFor N-dimensional vector, yoIt is observation, y is exported by situational variables
Value, y=H (x), H are known as Observation Operators, yo, y be M dimensional vector, B is background error covariance, and O is observation error covariance,
B is N*N matrix, and O is M*M matrix.
Mathematically it can be proved that the best estimate (analysis field) of x is:
X=xb+[B-1+HTO-1H]-1HTO-1(yo-Hxb)
It is the minimal point of objective function, directly asks x extremely difficult, and the minimal point of J is generally found with descent algorithm, is calculated
Gradient formula is:
Wherein,The referred to as tangent linear operator of Observation Operators.
Step 4, temperature DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM result linearity correction, firstly, access 6 groups of temperature forecast results and this pre- call time
Live detection data；Secondly, time series is divided into training period, forecast period by the way of establishing multiple linear regression model；
In training period, the multiple linear regression model of 6 groups of predicted values and observation is established, by using the polynary of predicted value and observation
The relationship of temperature, surface temperature, steam under different geographical environments is sought in linear regression analysis, improves area road icing shape
The accuracy of condition prediction, the weight coefficient of certain 6 groups of forecast results, and it is finally pre- with 1 group of this weight coefficient acquisition forecast period
Report is as a result, training period is sliding training period, and system constantly accesses subsequent live data and forecast result, is able to carry out comparison
Verifying, obtains newest weight coefficient, introduces numerical model DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM, when gathering forecast result, using cunning
Dynamic training period, weight coefficient change at any time, improve accuracy；
Wherein, multiple linear regression model
In some given lattice point, for a certain meteorological element of a certain Time effect forecast:
Wherein, O is that the observation of training period is average, aiIt is the weight coefficient for participating in the ith member of set, FiWithPoint
It is not the predicted value and its forecast average value in training period of i-th of mode, N is the mode sum for participating in superset forecast.
Wherein weight coefficient aiIt is calculated and is obtained by the minimum of the error term G in above-mentioned training period equation:
Wherein, N is training period time samples number, St' and Ot' it is the superset of training period and the deviation of observation field respectively,
The operation on the format of each mode of this equation.And the foundation of multi-mode superset forecasting procedure is to rely on error covariance
Matrix, it is mode field deviation F againi' and Fj' establish, therefore, the weight coefficient of each mode is calculated by error matrix C and is obtained:
Wherein, N is training period time samples number, Fi' (t) and Fj' (t) is the pre- of i-th of mode and j-th mode respectively
Report value anomaly, establishes linear algebraic equation.
Wherein,
oi' it is observation anomaly, [CI, j] matrix that is, [ai] be n × n matrix,For the matrix of n × 1, application
Gauss-Jordan null method solves, and obtains substituting into formula.
The numerical forecast data of temperature are substituted into the linear relationship of step 2, are finally inversed by by step 5, region Surface Temperature Retrieval
The surface temperature result of whole region；
Step 6, area road icing conditions early warning, by the numerical forecast data of steam, the surface temperature result of step 5 with
The critical value section of step 2 is compared, and predicts the icy road situation of whole region, and carries out early warning.
Working principle: when using the area road icing high precision monitor early warning system based on meteorological big data, draw
The data for having entered meteorological satellite expand the dimension of meteorological measuring, participate in the Data Assimilation of Numerical Prediction Models, mention indirectly
The precision of forecast result is risen；Numerical model DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM is introduced, when gathering forecast result, is trained using sliding
Phase, weight coefficient change at any time, improve accuracy；It is sought not using a variety of representative stations by linear analysis
With the relationship of temperature, surface temperature, steam under geographical environment, then from point to surface, the prediction of area road icing conditions is improved
Accuracy.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (5)
1. a kind of area road icing high precision monitor early warning system based on meteorological big data, it is characterised in that: including following
Step:
Step 1, hardware running environment are built, complete by the server cluster technology of the ultrahigh speed network based on Infiniband
At concurrent operation, and the bandwidth and capacity problem of data interaction storage are solved, carries out meteorological data data processing institute to meet
The a large amount of intensive operations needed；
Step 2, live data are collected, are analyzed, and by automatic weather station, obtain real-time dry-bulb temperature, surface temperature, road knot
The meteorological elements such as ice, relative temperature, wind speed, precipitation, evaporation capacity, radiation flux, visibility；
Wherein, each website represents a kind of road region classification, near the back or sunny side, rivers,lakes and seas including mountain area,
Plain；
Step 3, Mesoscale Numerical Forecast tool NONLINEAR CALCULATION, will be in above-mentioned weather observation data and European mid-term weather forecast
The EC Numerical Prediction Models of the heart, the GFS Numerical Prediction Models initial fields in Environmental forecasting centre, boundary field data lead
Enter data pool, then by carrying out Data Assimilation with three-dimensional variational algorithm；
It is assumed that the observation of meteorological variables is O, and the background value of the variable is F, variance σOAnd σF, then obtain a weighting
Average value:
Above-mentioned A is the minimum of following valence function J (S) in fact:
Assuming that there is the measurement S from distinct methods to variable S1、S2..., SN, error ∈n=Sn- S, it is assumed that error is random
, unbiased < ∈nThe error of >=0, and Normal Distribution, n-th of observation falls in ∈nAnd ∈n+d∈nBetween probability be
Error variance:
Have for N number of observation:
If
When I minimalization, maximal possibility estimation is obtained；
By I to SaFirst derivative be zero to obtain:
The maximal possibility estimation of S is the weighted average of Sn, and weight is the inverse of the error variance of each measurement；
As N=2, objective function is introduced:
Wherein, x is situational variables, xbIt is ambient field, x, xbFor N-dimensional vector, yoIt is observation, y is as derived from situational variables
Value, y=H (x), H are known as Observation Operators, yo, y be M dimensional vector, B is background error covariance, and O is observation error covariance, B
For N*N matrix, O is M*M matrix.
Mathematically it can be proved that the best estimate (analysis field) of x is:
X=xb+[B-1+HTO-1H]-1HTO-1(yo-Hxb)
It is the minimal point of objective function, directly asks x extremely difficult, and the minimal point of J is generally found with descent algorithm, calculates gradient
Formula is:
Wherein,The referred to as tangent linear operator of Observation Operators；
Step 4, temperature DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM result linearity correction, firstly, 6 groups of temperature forecast results of access and the pre- fact called time
Detection data；Secondly, time series is divided into training period, forecast period by the way of establishing multiple linear regression model；It is instructing
Practice the phase, the multiple linear regression model of 6 groups of predicted values and observation is established, by using the multiple linear of predicted value and observation
Regression analysis, the weight coefficient of certain 6 groups of forecast results, and with 1 group of final forecast result of this weight coefficient acquisition forecast period；
Wherein, multiple linear regression model
In some given lattice point, for a certain meteorological element of a certain Time effect forecast:
Wherein, O is that the observation of training period is average, aiIt is the weight coefficient for participating in the ith member of set, FiWithIt is respectively
The predicted value of i-th of mode and its forecast average value in training period, N are the mode sums for participating in superset forecast.Wherein
Weight coefficient aiIt is calculated and is obtained by the minimum of the error term G in above-mentioned training period equation:
Wherein, N is training period time samples number, St' and Ot' it is the superset of training period and the deviation of observation field, this side respectively
Journey operation on the format of each mode；And the foundation of multi-mode superset forecasting procedure is to rely on error covariance square
Battle array, it is mode field deviation F againi' and Fj' establish, therefore, the weight coefficient of each mode is calculated by error matrix C and is obtained:
Wherein, N is training period time samples number, Fi' (t) and Fj' (t) is the predicted value of i-th of mode and j-th of mode respectively
Anomaly establishes linear algebraic equation；
Wherein,
oi' it is observation anomaly, [CI, j] matrix that is, [ai] be n × n matrix,For the matrix of n × 1, using Gauss-
Jordan null method solves, and obtains substituting into formula；
The numerical forecast data of temperature are substituted into the linear relationship of step 2 by step 5, region Surface Temperature Retrieval, are finally inversed by entire
The surface temperature result in region；
Step 6, area road icing conditions early warning, by the numerical forecast data of steam, the surface temperature result of step 5 and step
2 critical value section is compared, and predicts the icy road situation of whole region, and carries out early warning.
2. a kind of area road icing high precision monitor early warning system based on meteorological big data according to claim 1,
It is characterized by:, by meteorological satellite, obtaining long wave, shortwave, the steam number of automatic weather station region in the step 2
According to, and the single-point steam data of site location are isolated, the data of meteorological satellite are introduced, the dimension of meteorological measuring is expanded
Degree, participates in the Data Assimilation of Numerical Prediction Models, improves the precision of forecast result indirectly.
3. a kind of area road icing high precision monitor early warning system based on meteorological big data according to claim 1,
It is characterized by: the data of collection are real-time transmitted to cloud server, make to receive by wired or wireless way in the step 2
The data of collection are able to carry out quick transmission, and then can obtain newest forecast by the analytical calculation to real time data and tie
Fruit.
4. a kind of area road icing high precision monitor early warning system based on meteorological big data according to claim 1,
It is characterized by: training period is sliding training period, and system constantly accesses subsequent live data and forecast in the step 4
As a result, it is possible to compare verifying, newest weight coefficient is obtained, numerical model DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM is introduced, to forecast result
When being gathered, using sliding training period, weight coefficient changes at any time, improves accuracy.
5. a kind of area road icing high precision monitor early warning system based on meteorological big data according to claim 1,
It is characterized by:, by linear analysis, seeking the pass of temperature, surface temperature, steam under different geographical environments in the step 4
System improves the accuracy of area road icing conditions prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910567666.8A CN110211325A (en) | 2019-06-27 | 2019-06-27 | A kind of area road icing high precision monitor early warning system based on meteorological big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910567666.8A CN110211325A (en) | 2019-06-27 | 2019-06-27 | A kind of area road icing high precision monitor early warning system based on meteorological big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110211325A true CN110211325A (en) | 2019-09-06 |
Family
ID=67795050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910567666.8A Pending CN110211325A (en) | 2019-06-27 | 2019-06-27 | A kind of area road icing high precision monitor early warning system based on meteorological big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110211325A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110599789A (en) * | 2019-09-17 | 2019-12-20 | 北京心中有数科技有限公司 | Road weather prediction method and device, electronic equipment and storage medium |
| CN110909447A (en) * | 2019-10-19 | 2020-03-24 | 中国电波传播研究所（中国电子科技集团公司第二十二研究所） | High-precision short-term prediction method for ionization layer region |
| CN110941790A (en) * | 2019-09-27 | 2020-03-31 | 成都信息工程大学 | High-resolution numerical value-based low-altitude flight meteorological information processing method for unmanned aerial vehicle |
| CN111986464A (en) * | 2020-07-15 | 2020-11-24 | 遵义同望智能科技有限公司 | System for forecasting road icing based on dynamic method |
| CN112147719A (en) * | 2020-09-29 | 2020-12-29 | 国家海洋环境预报中心 | Storm surge set data forecasting method and device based on GPU parallel computing |
| CN112464567A (en) * | 2020-12-08 | 2021-03-09 | 中国人民解放军国防科技大学 | Intelligent data assimilation method based on variational and assimilative framework |
| CN112884219A (en) * | 2021-02-07 | 2021-06-01 | 上海眼控科技股份有限公司 | Ground icing prediction method and device, electronic equipment and storage medium |
| CN114819501A (en) * | 2022-03-25 | 2022-07-29 | 云南省交通规划设计研究院有限公司 | Road traffic meteorological Internet of things multi-source heterogeneous data processing method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4742388B2 (en) * | 2008-03-28 | 2011-08-10 | 独立行政法人土木研究所 | Road surface condition estimation system at fixed observation points and routes |
| CN103150907A (en) * | 2013-02-06 | 2013-06-12 | 郭忠印 | Highway operation safety-based mobile monitoring and early warning system and method |
| CN105741576A (en) * | 2016-03-25 | 2016-07-06 | 同济大学 | Rainfall-considered bituminous pavement icing early-warning system and method |
| CN106408858A (en) * | 2016-10-12 | 2017-02-15 | 杭州尊鹏信息科技有限公司 | Black ice early warning device and black ice early warning method |
| CN206210048U (en) * | 2016-11-28 | 2017-05-31 | 重庆高略联信智能技术有限公司 | Icy road monitoring and warning system |
| CN107248258A (en) * | 2017-07-28 | 2017-10-13 | 湖北国创高新材料股份有限公司 | A kind of icy road safety early warning device and method for early warning |
| CN108629452A (en) * | 2018-04-28 | 2018-10-09 | 智慧天气风险管理（深圳）有限公司 | A kind of Weather Risk decision-making technique based on multi-mode multi-parameter DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM |
| CN109035681A (en) * | 2018-07-19 | 2018-12-18 | 郭忠印 | A kind of mountainous area highway freezing environment early warning system and method |
-
2019
- 2019-06-27 CN CN201910567666.8A patent/CN110211325A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4742388B2 (en) * | 2008-03-28 | 2011-08-10 | 独立行政法人土木研究所 | Road surface condition estimation system at fixed observation points and routes |
| CN103150907A (en) * | 2013-02-06 | 2013-06-12 | 郭忠印 | Highway operation safety-based mobile monitoring and early warning system and method |
| CN105741576A (en) * | 2016-03-25 | 2016-07-06 | 同济大学 | Rainfall-considered bituminous pavement icing early-warning system and method |
| CN106408858A (en) * | 2016-10-12 | 2017-02-15 | 杭州尊鹏信息科技有限公司 | Black ice early warning device and black ice early warning method |
| CN206210048U (en) * | 2016-11-28 | 2017-05-31 | 重庆高略联信智能技术有限公司 | Icy road monitoring and warning system |
| CN107248258A (en) * | 2017-07-28 | 2017-10-13 | 湖北国创高新材料股份有限公司 | A kind of icy road safety early warning device and method for early warning |
| CN108629452A (en) * | 2018-04-28 | 2018-10-09 | 智慧天气风险管理（深圳）有限公司 | A kind of Weather Risk decision-making technique based on multi-mode multi-parameter DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM |
| CN109035681A (en) * | 2018-07-19 | 2018-12-18 | 郭忠印 | A kind of mountainous area highway freezing environment early warning system and method |
Non-Patent Citations (2)
| Title |
|---|
| 吴凡 等: "江西泰井高速公路道路结冰特征及其预报模型研究", 《江西科学》 * |
| 宋丽萍 等: "哈尔滨市冬季地面温度变化特征及预报模型", 《黑龙江气象》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110599789A (en) * | 2019-09-17 | 2019-12-20 | 北京心中有数科技有限公司 | Road weather prediction method and device, electronic equipment and storage medium |
| CN110599789B (en) * | 2019-09-17 | 2021-04-27 | 北京心中有数科技有限公司 | Road weather prediction method and device, electronic equipment and storage medium |
| CN110941790A (en) * | 2019-09-27 | 2020-03-31 | 成都信息工程大学 | High-resolution numerical value-based low-altitude flight meteorological information processing method for unmanned aerial vehicle |
| CN110909447A (en) * | 2019-10-19 | 2020-03-24 | 中国电波传播研究所（中国电子科技集团公司第二十二研究所） | High-precision short-term prediction method for ionization layer region |
| CN111986464A (en) * | 2020-07-15 | 2020-11-24 | 遵义同望智能科技有限公司 | System for forecasting road icing based on dynamic method |
| CN112147719A (en) * | 2020-09-29 | 2020-12-29 | 国家海洋环境预报中心 | Storm surge set data forecasting method and device based on GPU parallel computing |
| CN112147719B (en) * | 2020-09-29 | 2021-07-27 | 国家海洋环境预报中心 | Storm surge set numerical forecasting method and device based on GPU parallel computing |
| CN112464567A (en) * | 2020-12-08 | 2021-03-09 | 中国人民解放军国防科技大学 | Intelligent data assimilation method based on variational and assimilative framework |
| CN112884219A (en) * | 2021-02-07 | 2021-06-01 | 上海眼控科技股份有限公司 | Ground icing prediction method and device, electronic equipment and storage medium |
| CN114819501A (en) * | 2022-03-25 | 2022-07-29 | 云南省交通规划设计研究院有限公司 | Road traffic meteorological Internet of things multi-source heterogeneous data processing method and system |
| CN114819501B (en) * | 2022-03-25 | 2023-09-15 | 云南省交通规划设计研究院有限公司 | Multi-source heterogeneous data processing method and system for highway traffic meteorological Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110211325A (en) | A kind of area road icing high precision monitor early warning system based on meteorological big data | |
| French et al. | Remote sensing of evapotranspiration over cotton using the TSEB and METRIC energy balance models | |
| Huang et al. | An analytical comparison of four approaches to modelling the daily variability of solar irradiance using meteorological records | |
| CN113919231B (en) | PM2.5 concentration space-time change prediction method and system based on space-time diagram neural network | |
| Bocchiola et al. | Spatial estimation of Snow Water Equivalent at different dates within the Adamello Park of Italy | |
| CN105808819A (en) | Power transmission line ice coating real-time distribution module calculation method | |
| CN105760970A (en) | Method for predicting AQI | |
| CN108090285A (en) | A kind of microclimate observation points distributing method suitable for the monitoring of complicated landform transmission line of electricity disaster caused by a windstorm | |
| CN108154271A (en) | A kind of surface air temperature method of quality control based on spatial coherence and surface fitting | |
| Moser et al. | An initial assessment of radar data assimilation on warm season rainfall forecasts for use in hydrologic models | |
| CN110244387A (en) | A kind of method, apparatus, equipment and storage medium based on Atmospheric Precipitable Water prediction rainy weather | |
| Drage et al. | Atmospheric icing in a coastal mountainous terrain. Measurements and numerical simulations, a case study | |
| CN117009735A (en) | High-strength forest fire occurrence probability calculation method combining BiLSTM and nuclear density estimation | |
| Wild et al. | Regional climate simulation with a high resolution GCM: surface hydrology | |
| Novitasari et al. | Weather parameters forecasting as variables for rainfall prediction using adaptive neuro fuzzy inference system (ANFIS) and support vector regression (SVR) | |
| CN109657988B (en) | Tobacco leaf quality partitioning method based on HASM and Euclidean distance algorithm | |
| Alcott et al. | Snow-to-liquid ratio variability and prediction at a high-elevation site in Utah’s Wasatch Mountains | |
| Haddjeri et al. | Exploring the sensitivity to precipitation, blowing snow, and horizontal resolution of the spatial distribution of simulated snow cover | |
| CN116777079A (en) | Desertification intrusion disaster prediction method based on Bayesian interlayer structure model | |
| LIU et al. | Assessing maize drought hazard for agricultural areas based on the fuzzy gamma model | |
| Jafari et al. | Estimation of reduction factors for combined wind and ice loading of power transmission lines using multivariate scenario sampling | |
| CN113821895B (en) | Method and device for constructing power transmission line icing thickness prediction model and storage medium | |
| CN115598027A (en) | PM based on remote sensing and machine learning technology 2.5 Inversion method | |
| Jiang et al. | Characterizing precipitation uncertainties in a high-altitudinal permafrost watershed of the Tibetan plateau based on regional water balance and hydrological model simulations | |
| CN114111705A (en) | Method for calculating cloud bottom height by using meteorological satellite data |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190906 |