CN102682573B - A kind of storm surge disaster early warning system based on time series analysis - Google Patents
A kind of storm surge disaster early warning system based on time series analysis Download PDFInfo
- Publication number
- CN102682573B CN102682573B CN201210093064.1A CN201210093064A CN102682573B CN 102682573 B CN102682573 B CN 102682573B CN 201210093064 A CN201210093064 A CN 201210093064A CN 102682573 B CN102682573 B CN 102682573B
- Authority
- CN
- China
- Prior art keywords
- data
- early warning
- disaster
- real
- monitoring
- 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.)
- Expired - Fee Related
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of storm surge disaster early warning system based on time series analysis, including database server, early warning and alert model analysis, aid decision-making system displaying, Web server and management user.Described database server storage Historical Monitoring data, real-time monitoring materials data, Fundamental Geographic Information System document data base, emergency preplan data, correlation computations model data and early warning data.Described monitoring materials data and early warning data are time series data.After described early warning and alert model analysis mainly carries out pretreatment to data, time series data is carried out Piecewise Linear Representation and reaches the purpose of dimension compression, and then carry out Similarity matching with Historical Monitoring data, and make disaster alarm according to Similarity matching result.Described aid decision-making system shows decision-making assistant information based on geographical graphic information, and is shown to manage subscription client by the Web server disposed.
Description
Technical field
The present invention relates to a kind of Marine Storm Genesis tide early warning system based on time series analysis, particularly one make full use of Historical Monitoring data current Monitoring Data is analyzed, pre-warning system and method.
Background technology
Along with the fast development of global economy, climate change is frequent, causes global ocean acidifying, sea level rise, and Oceanic disasters take place frequently.Oceanic disasters specifically include that storm tide, tsunami, wave and Coastal erosion, red tide etc., wherein occupy the first at China's storm tide occurrence frequency and the disaster that causes, the loss caused accounts for more than the 60% of Oceanic disasters loss, exceedes the land disasters such as earthquake in terms of casualties.
Present stage, the method for Oceanic disasters forecast uses Numerical Prediction Method substantially.Numerical Prediction Method solves the equation group describing Oceanic disasters phenomenon to the method making Oceanic disasters forecast mainly by electronic computer large-scale, quick.The amount of budget of its prediction process is huge, time-consumingly grows and consumes more resource.In numerical forecast, due to some little yardsticks or close to little yardstick move cannot definite reflecting in forecast model, the determination of the Model Parameter adding Numerical Prediction Method lacks objective and accurate method, thus result in the accuracy predicted the outcome and reduce.
Simultaneously in Numerical Prediction Method, the foundation of model is disaster data based on history, and data are fewer, and complication system simulated by this single model set up based on Small Sample Database is highly difficult.It is thus desirable on existing valuable historical summary, use the computer technology of science that this natural disaster carries out forecasting and warning, preferably provide technical support for government decision.
Summary of the invention
It is an object of the invention to provide a kind of storm surge disaster early warning system based on time series analysis, make full use of Historical Monitoring data, storm tide is forecast, early warning.
In order to realize object above, the present invention adopts the following technical scheme that realization:
A kind of storm surge disaster early warning system based on time series analysis, the long-range Monitoring Data of real-time reception, and Monitoring Data sequence is carried out early warning analysis, carry out early warning and aid decision according to analysis result.It is characterized in that, including Database Systems, Early-warning Model analysis, aid decision-making system displaying, Web server and management user.After early warning and alert model analysis module mainly carries out pretreatment to the observation data in data base, time series data is carried out Piecewise Linear Representation and reaches the purpose of dimension compression, and then Real-time Monitoring Data and Historical Monitoring data are carried out Similarity matching, and make disaster alarm according to Similarity matching result.If Monitoring Data reaches threshold value of warning, observation data and the historical data information that matches are stored in early warning document data base by early warning and alert model analysis module.Aid decision-making system is to show decision-making assistant information based on geographical graphic information, it is simulated disaster showing and emergency preplan generation including calling early warning data, emergency preplan data, the typhoon data calling monitoring in real time are shown, the analog data of aid decision-making system and emergency preplan data are also stored in early warning document data base, and Map Services and data are shown to the client of management user by the Web server of deployment.
Described database server storage Historical Monitoring data, real-time monitoring materials data, Fundamental Geographic Information System document data base, emergency preplan data, correlation computations model data and early warning data.Described monitoring materials data and early warning data are time series data.Described monitoring materials data and early warning data are time series data.Historical Monitoring document data base includes storing history typhoon title, typhoon actual measurement and forecast data, position, total water level and astronomical tide bit data, forecast data and disaster loss grade data are surged in Historical Storm Surges Round actual measurement.The Real-time Monitoring Data of monitoring materials data base's timing receipt remote data acquisition system transmission in real time, arranges database file and automatically extends with table contraction with the real-time typing adapting to data.Fundamental Geographic Information System data library storage Fundamental Geographic Information Data, the remote sensing image data provided including road and the spatial data of settlement place, attribute data and ESRI company of the U.S..Emergency preplan data library storage history typhoon prediction scheme and design prediction scheme, Historical Storm Surges Round prediction scheme and design prediction scheme.Correlation computations model data library storage is for choosing disaster index, Storm Surge Disaster simulation, the model of disaster's degree and the expertise being directed to.Matching result data that early warning data library storage Early-warning Model analysis obtains, the condition of a disaster Simulation is assessed data, disaster's degree data, the data in early warning document data base store in emergency preplan document data base after early warning releases.
Described aid decision-making system is shown and is included this storm surge disaster the condition of a disaster Simulation is assessed, grade assessment, typhoon track displaying and the reasoning prediction scheme result according to history the condition of a disaster emergency preplan.The condition of a disaster Simulation is assessed is the information returned for early warning, carry out the condition of a disaster simulation and submergence ratio, the displaying of depth of the water submerging with this monitoring time series data for boundary condition, and obtain this disaster loss grade assessment result according to the result reasoning of similarity measurement and be sent to manage user.
Described Web server returns to manage user by WebServices transmission XML format data.
Alert, after receiving early warning, is issued early warning report by described management user.It is sent to government website, mobile terminal of mobile telephone, offshore vessel mounted terminal and Decision Control center by Internet, leader expert the condition of a disaster is done trace analysis.
First above-mentioned Early-warning Model analysis is that Real-time Monitoring Data and Historical Monitoring data are carried out data prediction, Monitoring Data and normal Monitoring Data when in Historical Monitoring document data base the most to be separated, storm surge disaster occurs, extract tide level data and be analyzed.For normal Monitoring Data, according to selecting the part data in wherein storm tide multiple season as case data, Monitoring Data when occurring for Historical Storm Surges Round disaster, the most all as case data.Next to that the Historical Monitoring data in data base and Real-time Monitoring Data are carried out time series linear expression, it is achieved the dimensionality reduction of data and compression.It is the method using Time Series Similarity coupling again, with the time series data in case database, Real-time Monitoring Data is carried out similarity mate, distance value according to similarity measurement and judgment threshold set in advance, determine whether disaster is carried out early warning.
To in the seasonal effect in time series similarity analysis of ocean, two key issues are first had to need to solve.One is how to represent time series, and another is how to measure seasonal effect in time series similarity.How the two key issue solves to decide efficiency and the accuracy of algorithm.Time series data has the features such as higher-dimension, complexity, magnanimity and noise jamming, is directly analyzed not only difficulty in raw monitored sequence big, and impact calculates and the performance of the upper aspect of storage, but also affects the accuracy of algorithm.Therefore the present invention is first with the main fluctuation characteristic of seasonal effect in time series method for expressing extraction time sequence, to time series Dimensionality Reduction and compression, redescribes time series on higher level.For time series, the present invention represents that method uses the slope method for expressing of distinguished point based, concretely comprise the following steps:
(1) sequence preset timeIf ri、ri+1For i-th record in R and i+1 record, the numerical value the former with the latter in R is subtracted each other, obtain new sequence P, as follows:
Pi=ri+1-ri
(2) take advantage of wanting two-by-two before and after the numerical value in time series P, obtain new sequence S, as follows:
S=Pi*Pi+1
(3) these index values are added 1, it is possible to index value is corresponding with the sequence index value in R, the Local Extremum that corresponding point is in R by the index position of negative value in record S；
(4) amplification in time series P is less than to the point of a more than x and time difference, it is also added in the sequence of characteristic point, wherein x and a is according to the threshold parameter obtained after expertise and actual monitoring time series calibration, optimization, it is also possible to inputted by user；
(5) index position of zero in sequential S is found, the index value that search obtained is each adds 1, judge the subsegment sequence occurring zero continuously, if occurring that the time number of times of zero is more than m continuously, then there is the initial index position of zero in record, and this point is also characterized a little, and this point is added people's characteristic point set, wherein m is that m can also be inputted by user according to the threshold parameter obtained after expertise and actual monitoring time series calibration, optimization；
(6) utilize above-mentioned algorithm, obtain the characteristic point set of a sequential, then time series is divided into n-1 section by the set of this feature point, and n is characterized sum a little.Now, time series can be described by n straightway, and its straightway sequence M represents, M be an a length of k 3 yuan of vector M={ in MK, MX, ML}, M, the slope of i-th straightway is by MKiRepresenting, the abscissa of starting point is by MXiRepresenting, the projected length at time shaft of straightway is by MLiRepresent.
In Early-warning Model is analyzed, the present invention, according to similarity the matching analysis result, sends early warning in two stages.First stage is with the normal Monitoring Data of history same period, Monitoring Data to be done similarity mate, if the distance value of similarity measurement is all less than first stage judgment threshold, does not the most do early warning；If at least 1 record exceedes first stage judgment threshold, then enter second stage, just Monitoring Data is done similarity with all disaster data in disaster prediction scheme storehouse and is mated, if the distance value of similarity measurement is all less than second stage judgment threshold, then records these data and do early warning to administrator；If there being at least one record to exceed second stage judgment threshold, this Monitoring Data and historical disaster data match are then described, the information such as the historical disaster data by Monitoring Data and matched and the associated ratings of historical disaster data, position of surging, astronomical tide, emergency preplan send to administrator, do early warning.
Compared with prior art, the present invention takes full advantage of Historical Monitoring data, mated the rule information finding current monitoring data sequent with the similarity of historical data by current Monitoring Data, and then utilize this real time data to carry out storm surge disaster early warning with the dependency of historical data, relevant aid decision service is provided simultaneously, sends early warning information in time.
Accompanying drawing explanation
Fig. 1 is storm surge disaster early warning system structure chart of the present invention.
Fig. 2 is the flow chart of invention Piecewise Linear Representation of Time Series.
Fig. 3 is FSAe_studyState transition diagram.
Fig. 4 is emergency preplan design route schematic diagram.
Fig. 5 is the composition schematic diagram figure of early warning warning devices of the present invention.
Detailed description of the invention
The invention discloses a kind of storm surge disaster early warning system based on time series analysis, below in conjunction with the accompanying drawings specific embodiment is illustrated.
As it is shown in figure 1, a kind of storm surge disaster early warning system based on time series analysis, the long-range Monitoring Data of real-time reception, and Monitoring Data sequence is carried out early warning analysis, carry out early warning and aid decision according to analysis result.It is characterized in that, including Database Systems, Early-warning Model analysis, aid decision-making system displaying, Web server and management user.After early warning and alert model analysis module mainly carries out pretreatment to the observation data in data base, time series data is carried out Piecewise Linear Representation and reaches the purpose of dimension compression, and then Real-time Monitoring Data and Historical Monitoring data are carried out Similarity matching, and make disaster alarm according to Similarity matching result.If Monitoring Data reaches threshold value of warning, observation data and the historical data information that matches are stored in early warning document data base by early warning and alert model analysis module.Aid decision-making system is to show decision-making assistant information based on geographical graphic information, it is simulated disaster showing and emergency preplan generation including calling early warning data, emergency preplan data, the typhoon data calling monitoring in real time are shown, the analog data of aid decision-making system and emergency preplan data are also stored in early warning document data base, and Map Services and data are shown to the client of management user by the Web server of deployment.
Described database server storage Historical Monitoring data, real-time monitoring materials data, Fundamental Geographic Information System document data base, emergency preplan data, correlation computations model data and early warning data.Described monitoring materials data and early warning data are time series data.Historical Monitoring document data base includes storing history typhoon title, typhoon actual measurement and forecast data, position, total water level and astronomical tide bit data, forecast data and disaster loss grade data are surged in Historical Storm Surges Round actual measurement.
The Real-time Monitoring Data of monitoring materials data base's timing receipt remote data acquisition system transmission in real time, arranges database file and automatically extends with table contraction with the real-time typing adapting to data.Fundamental Geographic Information System data library storage Fundamental Geographic Information Data, the remote sensing image data provided including road and the spatial data of settlement place, attribute data and ESRI company of the U.S..Emergency preplan data library storage history typhoon prediction scheme and design prediction scheme, Historical Storm Surges Round prediction scheme and design prediction scheme.Correlation computations model data library storage is for choosing disaster index, Storm Surge Disaster simulation, the model of disaster's degree and the expertise being directed to.Matching result data that early warning data library storage Early-warning Model analysis obtains, the condition of a disaster Simulation is assessed data, disaster's degree data, the data in early warning document data base store in emergency preplan document data base after early warning releases.
As in figure 2 it is shown, in said system, early warning and alert model is key modules, is mainly realized by procedure below:
(1) initial data is done pretreatment, make part-time sequence (intercepted length should be more short-and-medium than disaster storehouse).
Monitoring Data and normal Monitoring Data when in Historical Monitoring document data base the most to be separated, storm surge disaster occurs, extract tide level data and be analyzed.Process of data preprocessing takes a little starting point as designated length time series data according to fixed length mainly the most on a timeline, and according to equation below, seasonal effect in time series amplitude is carried out standardization processing, is made part-time sequence:
xi=(xi-XMIN)/(XMAX-XMIN)
Wherein, xiFor carrying out normalized value, XMINFor seasonal effect in time series minima, XMAXFor seasonal effect in time series maximum.Apply normalization method at this, the time series data after stipulations maintains the integrity of initial data, and time and memory source needed for excavation are less, excavates more effectively, produces the analysis result of identical (or almost identical).
(2) for normal Monitoring Data, according to selecting the part data in wherein storm tide multiple season as case data, Monitoring Data when occurring for Historical Storm Surges Round disaster, the most all as case data.Historical Monitoring data in data base and Real-time Monitoring Data are carried out time series linear expression, it is achieved the dimensionality reduction of data and compression.For time series, the present invention represents that method uses the slope method for expressing of distinguished point based, concretely comprise the following steps:
1) given length is the time series of nIf ri、ri+1For i-th record in R and i+1 record, the numerical value the former with the latter in R is subtracted each other, obtain new sequence P, as follows:
Pi=ri+1-ri
2) take advantage of wanting two-by-two before and after the numerical value in time series P, obtain new sequence S, as follows:
S=Pi*Pi+1
3) these index values are added 1, it is possible to index value is corresponding with the sequence index value in R by the index position of negative value in record S, and the Local Extremum that corresponding point is in R joins the arrangement set of characteristic pointIn；
4) amplification in time series P is less than to the point of a more than x and time difference, it is also added in the set T of characteristic point, wherein x and a is according to the threshold parameter obtained after expertise and actual monitoring time series calibration, optimization, it is also possible to inputted by user.Determination method for parameter x and a uses verification method based on finite-state automata (FiniteStateAutomaton, FSA).FSA is a kind of important instrument, has in fields such as software design, checking, syntactic analysis, and state recognitions and is extremely widely applied.Specifically comprise the following steps that
Defining 1 cumulative error E: after time series segmentation becomes multistage subsequence, each subsequence is defined as with summation E of the cumulative error of former sequence
Definition 2FSAe_study: FSAe_studyIt is that quintuple form M=(Q, ∑, δ, S, F) state shifts as shown in Figure 2.Wherein:
A) Q={S, q1, q2It it is state set；
B) ∑={ E}；
C) δ: Q × E → Q is state transition function, and definition is such as table 1.By initial state S, when cumulative error meets precision, transfer to state q1Time, computing terminates；Otherwise, when transferring to state q2Time, optimizing fractional parameter a and x, continue segmentation, and calculate cumulative errors value；
D) S ∈ Q is original state；
e)It is final state set, terminates when meeting E ＜ θ (θ is given by expertise).
Table 1FSAe_studyState transition function
5) finding the index position of zero in sequential S, the index value that search obtained is each adds 1, it is judged that occur the subsegment sequence of zero continuously, if occurring that the time number of times of zero is more than m continuously, then there is the initial index position of zero in record, and this point is also characterized a little, and this point is added people's characteristic point set.Wherein m is according to the threshold parameter obtained after expertise and actual monitoring time series calibration, optimization, it is also possible to inputted by user；
6) utilize above-mentioned algorithm, obtain the characteristic point set of a sequential, then time series is divided into n-1 section by the set of this feature point, and n is characterized sum a little.Now, time series can be described by n straightway, and its straightway sequence M represents, M be an a length of k 3 yuan of vector M={ in MK, MX, ML}, M, the slope of i-th straightway is by MKiRepresenting, the abscissa of starting point is by MXiRepresenting, the projected length at time shaft of straightway is by MLiRepresent.After time series data being indicated according to above method, seasonal effect in time series pattern distance can be calculated, sequence is carried out similarity measurement:
Define 3 slope pattern distances: the linear segmented of given sequence represents Mi={ MKi, MXi, MLiAnd Mj={ MKj, MXj, MLj, then MiWith MjPattern distance be defined as:
Definition 4 dynamic mode distances based on slope pattern:
Wherein Dwarp(Mi, Mj) it is the DTW distance of pattern, rest (Mj) represent sequence MjRemove the sequence after the element of end, d (Mi, Mj) it is the slope pattern distance in definition 1.
Aid decision-making system is shown and is included this storm surge disaster the condition of a disaster Simulation is assessed, grade assessment, typhoon track displaying and the reasoning prediction scheme result according to history the condition of a disaster emergency preplan.
Described the condition of a disaster Simulation is assessed is the information returned for early warning, carry out the condition of a disaster simulation and submergence ratio, the displaying of depth of the water submerging with this monitoring time series data for boundary condition, and obtain this disaster loss grade assessment result according to the result reasoning of similarity measurement and be sent to manage user.
Described typhoon track displaying is accessed Fundamental Geographic Information Data and typhoon track data by system by Web server, shows at management user side, and figure displaying, the form of typhoon data including typhoon track are shown and the Flos Rosae Rugosae figure of typhoon wind direction, grade.
As shown in Figure 4, for emergency preplan design route schematic diagram, emergency preplan shows it is to calculate the engineering that should take and managerial measure according to Historical Storm Surges Round disaster analysis and design storm surge disaster analysis, it is simultaneous for devastated, carries out evacuation path analysis based on Fundamental Geographic Information Datas such as house, road, rivers.
Web server returns to manage user by WebServices transmission XML format data, it is also possible to the request of data receiving administrator returns to manage user after data base obtains data.
As it is shown in figure 5, management user is after receiving early warning, alert is issued early warning report.It is sent to government website, mobile terminal of mobile telephone, offshore vessel mounted terminal and Decision Control center by Intemet, leader expert the condition of a disaster is done trace analysis.Real-time release disaster data information service simultaneously.
In sum, the present invention is a kind of storm surge disaster early warning system based on time series analysis, mated the rule information finding current monitoring data sequent with the similarity of historical data by current Monitoring Data, and then utilize this real time data to carry out storm surge disaster early warning with the dependency of historical data, relevant aid decision service is provided simultaneously, sends early warning information by number of ways in time.
The foregoing is only illustrative, rather than be restricted.This specification content should not be construed as limitation of the present invention, and any spirit and scope without departing from the present invention, within being intended to be limited solely by application range.
Claims (4)
1. a storm surge disaster early warning system based on time series analysis, receive remote real time monitoring data, and Real-time Monitoring Data sequence is carried out early warning analysis, early warning and aid decision is carried out according to analysis result, it is characterized in that, including Database Systems, early warning and alert model analysis module, aid decision-making system, Web server and management user；Described Database Systems include Historical Monitoring document data base, real-time monitoring materials data base, Fundamental Geographic Information System document data base, emergency preplan document data base, correlation computations model document data base and early warning document data base；After described early warning and alert model analysis module carries out pretreatment to the observation data in real-time monitoring materials data base and Historical Monitoring document data base, time series data is carried out Piecewise Linear Representation and reaches the purpose of dimension compression, and then Real-time Monitoring Data and Historical Monitoring data are carried out Similarity matching, and make disaster alarm according to Similarity matching result, if Real-time Monitoring Data reaches threshold value of warning, Real-time Monitoring Data and the Historical Monitoring data that matches are stored in early warning document data base by early warning and alert model analysis module；Described aid decision-making system is to show decision-making assistant information based on geographical graphic information, it is simulated disaster showing and emergency preplan generation including calling early warning data, emergency preplan data, the typhoon data calling monitoring in real time are shown, the analog data of aid decision-making system and emergency preplan data are also stored in early warning document data base, and Map Services and data are shown to the client of management user by the Web server of deployment；
Described Historical Monitoring document data base includes storing history typhoon title, typhoon actual measurement and typhoon forecast data, surged in position in Historical Storm Surges Round actual measurement, Historical Storm Surges Round surveys total water level, astronomical tide bit data, astronomical tide forecast data and Historical Storm Surges Round disaster loss grade data；
The Real-time Monitoring Data of described real-time monitoring materials data base's timing receipt remote data acquisition system transmission, arranges database file and automatically extends with table contraction with the real-time typing adapting to data；
Described Fundamental Geographic Information System data library storage Fundamental Geographic Information Data, the remote sensing image data provided including road and the spatial data of settlement place, attribute data and ESRI company of the U.S.；
Described emergency preplan data library storage history typhoon prediction scheme and design prediction scheme, Historical Storm Surges Round prediction scheme and design prediction scheme；
Described correlation computations model data library storage is for choosing disaster index, Storm Surge Disaster simulation, the model of disaster's degree and the expertise being directed to；
Matching result data that described early warning data library storage early warning and alert model analysis module obtains, the condition of a disaster Simulation is assessed data, disaster's degree data, the data in early warning document data base store in emergency preplan document data base after early warning releases；
After described early warning and alert model analysis module mainly carries out pretreatment to data, time series data is carried out Piecewise Linear Representation and reaches the purpose of dimension compression, and then carry out Similarity matching with Historical Monitoring data, and make disaster alarm according to Similarity matching result；
Described aid decision-making system shows decision-making assistant information based on geographical graphic information, and is shown to manage subscription client by the Web server disposed.
A kind of storm surge disaster early warning system based on time series analysis the most according to claim 1, it is characterized in that, aid decision-making system is shown and is included this storm surge disaster the condition of a disaster Simulation is assessed, grade assessment, typhoon track displaying and the reasoning prediction scheme result according to history the condition of a disaster emergency preplan；
Described the condition of a disaster Simulation is assessed is the information returned for early warning, carry out the condition of a disaster simulation and submergence ratio, the displaying of depth of the water submerging with the time series data of real-time monitoring materials data base for boundary condition, and obtain this disaster loss grade assessment result according to the result reasoning of similarity measurement and be sent to manage user.
A kind of storm surge disaster early warning system based on time series analysis the most according to claim 1, it is characterized in that, described management user is after receiving early warning, alert is issued early warning report, it is sent to government website, mobile terminal of mobile telephone, offshore vessel mounted terminal and Decision Control center by Internet, leader expert the condition of a disaster is done trace analysis.
A kind of storm surge disaster early warning system based on time series analysis the most according to claim 1, it is characterized in that, first described early warning and alert model analysis module is that Real-time Monitoring Data and Historical Monitoring data are carried out data prediction, Monitoring Data and normal Monitoring Data when in Historical Monitoring document data base the most to be separated, storm surge disaster occurs, extraction tide level data is analyzed, for normal Monitoring Data, according to selecting the part data in wherein storm tide multiple season as case data, Monitoring Data when Historical Storm Surges Round disaster is occurred, the most all as case data；Next to that the Historical Monitoring data in Historical Monitoring document data base and real-time monitoring materials data base and Real-time Monitoring Data are carried out time series linear expression, it is achieved the dimensionality reduction of data and compression；It is the method using Time Series Similarity coupling again, Real-time Monitoring Data is carried out similarity with the time series of above-mentioned case data and mates, according to distance value and the judgment threshold set in advance of similarity measurement, determine whether disaster is carried out early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210093064.1A CN102682573B (en) | 2012-03-31 | 2012-03-31 | A kind of storm surge disaster early warning system based on time series analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210093064.1A CN102682573B (en) | 2012-03-31 | 2012-03-31 | A kind of storm surge disaster early warning system based on time series analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102682573A CN102682573A (en) | 2012-09-19 |
| CN102682573B true CN102682573B (en) | 2016-08-03 |
Family
ID=46814420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210093064.1A Expired - Fee Related CN102682573B (en) | 2012-03-31 | 2012-03-31 | A kind of storm surge disaster early warning system based on time series analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102682573B (en) |
Families Citing this family (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104077309B (en) * | 2013-03-28 | 2018-05-08 | 日电（中国）有限公司 | A kind of method and apparatus that dimension-reduction treatment is carried out to time series |
| CN103294911B (en) * | 2013-05-23 | 2016-12-28 | 中国人民解放军国防科学技术大学 | A kind of time series similarity value-acquiring method and system |
| CN104298841B (en) * | 2013-07-16 | 2018-04-13 | 浙江贵仁信息科技股份有限公司 | A kind of Flood Forecasting Method and system based on historical data |
| CN104156815B (en) * | 2014-08-06 | 2017-09-29 | 成都国科海博信息技术股份有限公司 | The intelligent method of disposal of emergency event based on time shaft |
| CN104268164A (en) * | 2014-09-09 | 2015-01-07 | 四川九洲电器集团有限责任公司 | Earthquake emergency processing method and system |
| CN105095655B (en) * | 2015-07-17 | 2018-09-04 | 南京信息工程大学 | A kind of perturbation motion method based on adaptive sensitive factor |
| CN112541620B (en) * | 2017-06-20 | 2023-11-03 | 福建省海洋预报台 | Typhoon storm water increasing prediction method and system with high prediction precision and efficiency |
| CN107871140B (en) * | 2017-11-07 | 2021-10-01 | 哈尔滨工程大学 | Slope-based elastic similarity measurement method |
| CN108022415B (en) * | 2017-12-01 | 2020-08-04 | 福建工程学院 | BIM-based alarming method and terminal for land reclamation from sea |
| CN108288367B (en) * | 2017-12-13 | 2019-11-08 | 济南创智电气科技有限公司 | A kind of fast reporting method and system of power grid the condition of a disaster data |
| CN108710623B (en) * | 2018-03-13 | 2021-01-05 | 南京航空航天大学 | Airport departure delay time prediction method based on time series similarity measurement |
| CN108509990A (en) * | 2018-03-29 | 2018-09-07 | 重庆大学 | A kind of sequential key assignments type industrial process data Parallel analytic method |
| CN108932307A (en) * | 2018-06-13 | 2018-12-04 | 浙江大学 | A kind of electric power data feature extracting method based on time series |
| CN108961688B (en) * | 2018-07-13 | 2020-11-03 | 特力惠信息科技股份有限公司 | Geological disaster monitoring and early warning method under support of big data |
| CN109325048B (en) * | 2018-08-23 | 2021-12-07 | 上海海洋大学 | Red tide data query method constructed based on graph model |
| CN109637088A (en) * | 2018-12-29 | 2019-04-16 | 宁波中数云创信息技术有限公司 | A kind of real time early warning method based on big concurrent incremental data |
| CN110377656B (en) * | 2019-06-13 | 2023-04-25 | 中国地质大学深圳研究院 | Storm surge inundation early warning visualization method based on MVC architecture |
| CN110414726A (en) * | 2019-07-15 | 2019-11-05 | 南京灿能电力自动化股份有限公司 | A kind of power quality method for early warning based on Analysis on monitoring data |
| CN110766054B (en) * | 2019-09-23 | 2022-05-10 | 东软集团股份有限公司 | Early warning method and device for fracturing sand plugging, storage medium and equipment |
| CN111125446A (en) * | 2019-12-20 | 2020-05-08 | 北京睦合达信息技术股份有限公司 | Data management platform and data management method |
| JP7310638B2 (en) * | 2020-02-18 | 2023-07-19 | コベルコ建機株式会社 | Disaster countermeasure support server, disaster countermeasure support system and disaster countermeasure support method |
| CN111489041B (en) * | 2020-06-23 | 2020-10-16 | 平安国际智慧城市科技股份有限公司 | Method and device for predicting abnormal emission of pollutants and computer equipment |
| CN112819248A (en) * | 2021-02-26 | 2021-05-18 | 国家海洋局东海预报中心 | Storm surge alarm quality assessment method and device |
| CN113254560B (en) * | 2021-06-08 | 2021-09-28 | 东营市大地勘测地理信息研究院有限公司 | Tidal disaster prediction system and method for oil field beach sea |
| CN113450545B (en) * | 2021-08-31 | 2022-03-15 | 广东新禾道信息科技有限公司 | Natural disaster early warning system and method, cloud platform and storable medium |
| CN113962468A (en) * | 2021-10-29 | 2022-01-21 | 杭州青橄榄网络技术有限公司 | Energy consumption monitoring and statistics-based energy consumption carbon emission management method and system |
| CN114519921A (en) * | 2022-02-24 | 2022-05-20 | 重庆大学 | Modularization landslide monitoring and early warning system based on industry cloud |
| CN114596182B (en) * | 2022-03-09 | 2023-05-16 | 王淑娟 | Government affair management method and system based on big data |
| CN114966854B (en) * | 2022-07-28 | 2022-11-18 | 海南浙江大学研究院 | Single-layer non-static pressure earthquake tsunami early warning system and method |
| CN115330268B (en) * | 2022-10-12 | 2023-12-29 | 华北科技学院(中国煤矿安全技术培训中心) | Comprehensive emergency command method and system for coping with mine disasters |
| CN116128141B (en) * | 2023-02-07 | 2023-08-29 | 国家海洋环境预报中心 | Storm surge prediction method and device, storage medium and electronic equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8983808B2 (en) * | 2008-10-15 | 2015-03-17 | The United States Of America, As Represented By The Secretary Of The Navy | Automated mesh generation and editing tools |
| CN101567124B (en) * | 2009-06-04 | 2012-05-02 | 山东省科学院海洋仪器仪表研究所 | Method for early warning of marine disasters |
| CN101989374B (en) * | 2009-11-09 | 2012-07-18 | 上海海洋大学 | Ocean storm surge disaster early warning system and method thereof |
| CN102394917A (en) * | 2011-10-19 | 2012-03-28 | 上海海洋大学 | Ocean environment monitoring and early warning system |
-
2012
- 2012-03-31 CN CN201210093064.1A patent/CN102682573B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN102682573A (en) | 2012-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102682573B (en) | A kind of storm surge disaster early warning system based on time series analysis | |
| Orton et al. | Flood hazard assessment from storm tides, rain and sea level rise for a tidal river estuary | |
| Mazas et al. | A multi-distribution approach to POT methods for determining extreme wave heights | |
| Torres et al. | Role of hurricane wind models in accurate simulation of storm surge and waves | |
| CN114935759A (en) | Wave field missing value filling method and system based on high-frequency ground wave radar observation | |
| Roberts et al. | A regression-based approach for cool-season storm surge predictions along the New York–New Jersey coast | |
| CN114399235B (en) | Method and system for judging disaster risk level based on rain condition data | |
| Alerskans et al. | A transformer neural network for predicting near‐surface temperature | |
| Wang et al. | CNN-BiLSTM-attention model in forecasting wave height over South-East China Seas | |
| Bodini et al. | Assessing boundary condition and parametric uncertainty in numerical-weather-prediction-modeled, long-term offshore wind speed through machine learning and analog ensemble | |
| CN117371303A (en) | Prediction method for effective wave height under sea wave | |
| Peng et al. | Short‐term wind power prediction based on stacked denoised auto‐encoder deep learning and multi‐level transfer learning | |
| King | Prediction of corrosiveness of sea bed sediments | |
| Vettor et al. | On the accuracy of voluntary observing ship’s records | |
| Foley | Long-term trends in large-scale circulation behaviour and wind storms for North Atlantic islands: a multi-data analysis using ERA-20C and meteorological station data | |
| KR20220071038A (en) | Devices and Methods for Detection and Prediction of Cold Water Mass Using Artificial Intelligence and Satellite Imaging | |
| Lindner | Climatology and variability of tropical cyclones affecting charleston, South Carolina, from 1670 to 1850 | |
| Zhan et al. | A Multimodal Deep Learning Approach for Typhoon Track Forecast by Fusing CNN and Transformer Structures | |
| Peach et al. | Investigating machine learning for virtual wave monitoring | |
| Manian et al. | Using genetic algorithms to optimize bathymetric sampling for predictive model input | |
| Roy et al. | Generation of 100-year-return value maps of maximum significant wave heights with automated threshold value estimation | |
| Iyer | Efficiency of Flash Flood Prediction by XGBoost and Random Forest using 15 minutes & 1 hour time period sensor data. | |
| Guo et al. | Predict typhoon-induced storm surge deviation in a principal component back-propagation neural network model | |
| Asplin et al. | The Canada Coastal Zone Information System for Model-Based Projections of Future Metocean Parameters from Coupled Atmosphere-Ocean Models Under Different Greenhouse Gas Emission Scenarios for Offshore Marine Energy Development in Canada | |
| Boccard | World Cyclonic Pulse |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160803 Termination date: 20190331 |