TWI720857B - Flooding prediction system and method - Google Patents

Flooding prediction system and method Download PDF

Info

Publication number
TWI720857B
TWI720857B TW109110355A TW109110355A TWI720857B TW I720857 B TWI720857 B TW I720857B TW 109110355 A TW109110355 A TW 109110355A TW 109110355 A TW109110355 A TW 109110355A TW I720857 B TWI720857 B TW I720857B
Authority
TW
Taiwan
Prior art keywords
data
rainfall
flooding
module
rainfall data
Prior art date
Application number
TW109110355A
Other languages
Chinese (zh)
Other versions
TW202137121A (en
Inventor
李文生
洪國展
Original Assignee
多采工程顧問有限公司
多采科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 多采工程顧問有限公司, 多采科技有限公司 filed Critical 多采工程顧問有限公司
Priority to TW109110355A priority Critical patent/TWI720857B/en
Application granted granted Critical
Publication of TWI720857B publication Critical patent/TWI720857B/en
Publication of TW202137121A publication Critical patent/TW202137121A/en

Links

Images

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
    • Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather

Landscapes

  • Alarm Systems (AREA)

Abstract

一種淹水預測系統，包含：資料庫，儲存複數個降雨資料與複數個淹水資料，其中各降雨資料分別關聯於複數個淹水資料其中一者；以及伺服器，存取該資料庫，該伺服器包含：分群模組，自複數個降雨資料中指定複數個第一降雨資料做為第一群組，分群模組根據複數個第一降雨資料產生第一特徵資料，其中複數個第一降雨資料包含第二降雨資料，第二降雨資料關聯於複數個淹水資料中的第一淹水資料；比對模組，根據目標降雨資料與第一特徵資料產生第一比對結果，並根據第一比對結果將目標降雨資料關聯於第一群組，比對模組接著根據目標降雨資料與第一群組中的各第一降雨資料產生第二比對結果，並根據第二比對結果將目標降雨資料關聯於第二降雨資料；以及分析模組，至少根據第一淹水資料以產生淹水分析資料。A flooding prediction system includes: a database storing a plurality of rainfall data and a plurality of flooding data, wherein each rainfall data is respectively associated with one of the plurality of flooding data; and a server, accessing the database, the The server includes: a clustering module, which specifies a plurality of first rainfall data from the plurality of rainfall data as the first group, and the clustering module generates first characteristic data based on the plurality of first rainfall data, of which the plurality of first rainfalls The data includes the second rainfall data, which is related to the first flooding data among the plurality of flooding data; the comparison module generates the first comparison result based on the target rainfall data and the first feature data, and according to the first A comparison result associates the target rainfall data with the first group, and the comparison module then generates a second comparison result based on the target rainfall data and each first rainfall data in the first group, and according to the second comparison result Associating the target rainfall data with the second rainfall data; and the analysis module generates flooding analysis data at least according to the first flooding data.

Description

淹水預測系統及其方法Flooding prediction system and method

本發明係關於一種淹水預測系統及其方法，特別係關於一種透過將降雨資料分群後再進行比對，藉以達到淹水預測的的淹水預測系統及其方法。The present invention relates to a flooding prediction system and method, and more particularly to a flooding prediction system and method that achieves flooding prediction by grouping rainfall data into groups and then comparing them.

目前所使用的淹水預測系統容易因為需考量的因素（例如地形、降雨、地下水等）較多或目標區域的面積龐大而導致系統必須花費較長的計算時間（通常為數小時以上）方可計算出一地區的淹水預測結果。此種耗費計算時間的淹水預測系統在淹水預測上不敷使用。有鑑於此，將需要一種可於較短時間內提供淹水預測結果的淹水預測系統及其方法。The flooding prediction system currently in use is prone to take a long calculation time (usually more than a few hours) due to the large number of factors to be considered (such as terrain, rainfall, groundwater, etc.) or the large area of the target area. Find out the results of flooding prediction in an area. Such a flood prediction system that consumes computational time is not sufficient for flood prediction. In view of this, there will be a need for a flood prediction system and method that can provide flood prediction results in a relatively short period of time.

為了解決上述問題，本發明之一構想在於提供一種可於較短時間內提供淹水預測結果的淹水預測系統及其方法。In order to solve the above-mentioned problems, one idea of the present invention is to provide a flood prediction system and method that can provide flood prediction results in a relatively short time.

基於前揭構想，本發明提供一種淹水預測系統，包含：一資料庫，儲存複數個降雨資料與複數個淹水資料，其中各該降雨資料分別關聯於該複數個淹水資料其中一者；以及一伺服器，存取該資料庫，該伺服器包含：一分群模組，自該複數個降雨資料中指定複數個第一降雨資料做為一第一群組，該分群模組根據該複數個第一降雨資料產生一第一特徵資料，並將該第一特徵資料關聯於該第一群組，其中該複數個第一降雨資料包含一第二降雨資料，該第二降雨資料關聯於該複數個淹水資料中的一第一淹水資料；一比對模組，根據一目標降雨資料與該第一特徵資料產生一第一比對結果，並根據該第一比對結果將該目標降雨資料關聯於該第一群組，該比對模組接著根據該目標降雨資料與該第一群組中的各該第一降雨資料產生一第二比對結果，並根據該第二比對結果將該目標降雨資料關聯於該第二降雨資料；以及一分析模組，至少根據關聯於該第二降雨資料的該第一淹水資料以產生一淹水分析資料；其中該比對模組通訊連接該分群模組與該分析模組。Based on the aforementioned concept, the present invention provides a flooding prediction system, including: a database storing a plurality of rainfall data and a plurality of flooding data, wherein each of the rainfall data is respectively associated with one of the plurality of flooding data; And a server for accessing the database. The server includes: a grouping module, which designates a plurality of first rainfall data from the plurality of rainfall data as a first group, and the grouping module according to the plurality of rainfall data The first rainfall data generates a first feature data, and the first feature data is associated with the first group, wherein the plurality of first rainfall data includes a second rainfall data, and the second rainfall data is associated with the first group. A first flooding data among a plurality of flooding data; a comparison module, which generates a first comparison result based on a target rainfall data and the first characteristic data, and the target according to the first comparison result The rainfall data is associated with the first group, the comparison module then generates a second comparison result according to the target rainfall data and each of the first rainfall data in the first group, and according to the second comparison As a result, the target rainfall data is associated with the second rainfall data; and an analysis module generates a flood analysis data based on at least the first flooding data associated with the second rainfall data; wherein the comparison module The grouping module and the analysis module are communicatively connected.

於本發明之一較佳實施例中，該伺服器包含一目標資料產生模組，根據至少一降雨觀測資料以及至少一降雨預測資料產生該目標降雨資料；其中該比對模組通訊連接該目標資料產生模組。In a preferred embodiment of the present invention, the server includes a target data generation module that generates the target rainfall data based on at least one rainfall observation data and at least one rainfall prediction data; wherein the comparison module is communicatively connected to the target Data generation module.

於本發明之一較佳實施例中，該複數個第一降雨資料包含一第三降雨資料，該第三降雨資料關聯於該複數個淹水資料中的一第二淹水資料；其中該比對模組根據該第二比對結果將該目標降雨資料關聯於該第三降雨資料；其中該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第三降雨資料的該第二淹水資料以產生該淹水分析資料。In a preferred embodiment of the present invention, the plurality of first rainfall data includes a third rainfall data, and the third rainfall data is related to a second flooding data among the plurality of flooding data; wherein the ratio The pairing module associates the target rainfall data with the third rainfall data according to the second comparison result; wherein the analysis module is at least based on the first flooding data associated with the second rainfall data and the first flooding data associated with the second rainfall data. 3. The second flooding data of the rainfall data to generate the flooding analysis data.

於本發明之一較佳實施例中，該分群模組自該複數個降雨資料中指定複數個第四降雨資料做為一第二群組，該分群模組根據該複數個第四降雨資料產生一第二特徵資料，並將該第二特徵資料關聯於該第二群組，其中該複數個第四降雨資料包含一第五降雨資料，該第五降雨資料關聯於該複數個淹水資料中的一第三淹水資料；該比對模組根據該目標降雨資料與該第二特徵資料產生一第三比對結果，並根據該第三比對結果將該目標降雨資料關聯於該第二群組，該比對模組接著根據該目標降雨資料與該第二群組中的各該第四降雨資料產生一第四比對結果，並根據該第四比對結果將該目標降雨資料關聯於該第五降雨資料；該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第五降雨資料的該第三淹水資料以產生該淹水分析資料。In a preferred embodiment of the present invention, the grouping module designates a plurality of fourth rainfall data from the plurality of rainfall data as a second group, and the grouping module generates according to the plurality of fourth rainfall data A second feature data, and the second feature data is associated with the second group, wherein the plurality of fourth rainfall data includes a fifth rainfall data, and the fifth rainfall data is related to the plurality of flooding data A third flooding data of; the comparison module generates a third comparison result based on the target rainfall data and the second characteristic data, and associates the target rainfall data with the second comparison result according to the third comparison result Group, the comparison module then generates a fourth comparison result based on the target rainfall data and each of the fourth rainfall data in the second group, and associates the target rainfall data according to the fourth comparison result In the fifth rainfall data; the analysis module at least generates the flood analysis data based on the first flooding data associated with the second rainfall data and the third flooding data associated with the fifth rainfall data .

於本發明之一較佳實施例中，該伺服器包含一淹水資料產生模組，該淹水資料產生模組根據該複數個降雨資料之每一者以分別產生一對應淹水資料，該淹水資料產生模組並將該對應淹水資料儲存至該資料庫中；其中該對應淹水資料為該複數個淹水資料的其中一者；其中該淹水資料產生模組通訊連接該分群模組。In a preferred embodiment of the present invention, the server includes a flooding data generating module, the flooding data generating module generates a corresponding flooding data according to each of the plurality of rainfall data, the The flooding data generation module and storing the corresponding flooding data in the database; wherein the corresponding flooding data is one of the plurality of flooding data; wherein the flooding data generation module is connected to the group by communication Module.

於本發明之一較佳實施例中，該淹水分析資料包含一區域機率資料，該區域機率資料指示出一區域的一淹水機率；其中該伺服器包含一警示模組，當該淹水機率高於關聯於該區域的一機率門檻值時，該警示模組發出一警示資訊；其中該警示模組通訊連接該分析模組。In a preferred embodiment of the present invention, the flooding analysis data includes an area probability data, the area probability data indicating a flooding probability of an area; wherein the server includes a warning module, when the flooding When the probability is higher than a probability threshold value associated with the area, the warning module sends out a warning message; wherein the warning module is communicatively connected to the analysis module.

於本發明之一較佳實施例中，該區域包含複數個網格區域，其中該分析模組至少根據關聯於該第二降雨資料的該第一淹水資料以產生複數個網格分析資料其分別對應於該複數個網格區域其中一者；其中該分析模組係根據該複數個網格分析資料以產生該區域機率資料。In a preferred embodiment of the present invention, the area includes a plurality of grid areas, wherein the analysis module generates a plurality of grid analysis data at least according to the first flooding data associated with the second rainfall data. Respectively corresponding to one of the plurality of grid regions; wherein the analysis module generates the probability data of the region according to the plurality of grid analysis data.

根據本發明之目的，再提供一種淹水預測方法，應用於一淹水預測系統，該淹水預測系統包含一資料庫以及一伺服器，該資料庫儲存複數個降雨資料與複數個淹水資料，其中各該降雨資料分別關聯於該複數個淹水資料其中一者，該伺服器存取該資料庫；其中淹水預測方法包含：由一伺服器的一分群模組自該複數個降雨資料中指定複數個第一降雨資料做為一第一群組；由該分群模組根據該複數個第一降雨資料產生一第一特徵資料，並將該第一特徵資料關聯於該第一群組，其中該複數個第一降雨資料包含一第二降雨資料，該第二降雨資料關聯於該複數個淹水資料中的一第一淹水資料；由該伺服器的一比對模組根據一目標降雨資料與該第一特徵資料產生一第一比對結果，並根據該第一比對結果將該目標降雨資料關聯於該第一群組；由該比對模組根據該目標降雨資料與該第一群組中的各該第一降雨資料產生一第二比對結果，並根據該第二比對結果將該目標降雨資料關聯於該第二降雨資料；以及由該伺服器的一分析模組至少根據關聯於該第二降雨資料的該第一淹水資料以產生一淹水分析資料。According to the objective of the present invention, a flood prediction method is provided, which is applied to a flood prediction system. The flood prediction system includes a database and a server. The database stores a plurality of rainfall data and a plurality of flooding data. , Wherein each of the rainfall data is respectively associated with one of the plurality of flooding data, and the server accesses the database; wherein the flooding prediction method includes: a clustering module of a server from the plurality of rainfall data Specify a plurality of first rainfall data as a first group; the grouping module generates a first feature data according to the plurality of first rainfall data, and associates the first feature data with the first group , Wherein the plurality of first rainfall data includes a second rainfall data, and the second rainfall data is related to a first flooding data in the plurality of flooding data; a comparison module of the server is based on a The target rainfall data and the first characteristic data generate a first comparison result, and the target rainfall data is associated with the first group according to the first comparison result; the comparison module is based on the target rainfall data and Each of the first rainfall data in the first group generates a second comparison result, and the target rainfall data is associated with the second rainfall data according to the second comparison result; and an analysis performed by the server The module generates a flood analysis data at least according to the first flood data associated with the second rainfall data.

於本發明之一較佳實施例中，該淹水預測方法進一步包含：由該伺服器的一目標資料產生模組根據至少一降雨觀測資料以及至少一降雨預測資料產生該目標降雨資料。In a preferred embodiment of the present invention, the flooding prediction method further includes: generating the target rainfall data based on at least one rainfall observation data and at least one rainfall prediction data by a target data generation module of the server.

於本發明之一較佳實施例中，該複數個第一降雨資料包含一第三降雨資料，該第三降雨資料關聯於該複數個淹水資料中的一第二淹水資料；該淹水預測方法進一步包含：由該比對模組根據該第二比對結果將該目標降雨資料關聯於該第三降雨資料；其中該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第三降雨資料的該第二淹水資料以產生該淹水分析資料。In a preferred embodiment of the present invention, the plurality of first rainfall data includes a third rainfall data, and the third rainfall data is related to a second flooding data of the plurality of flooding data; the flooding data The prediction method further includes: the comparison module associates the target rainfall data with the third rainfall data according to the second comparison result; wherein the analysis module is at least based on the first rainfall data associated with the second rainfall data. The flooding data and the second flooding data associated with the third rainfall data are used to generate the flooding analysis data.

於本發明之一較佳實施例中，該淹水預測方法進一步包含：由該分群模組自該複數個降雨資料中指定複數個第四降雨資料做為一第二群組；由分群模組根據該複數個第四降雨資料產生一第二特徵資料，並將該第二特徵資料關聯於該第二群組，其中該複數個第四降雨資料包含一第五降雨資料，該第五降雨資料關聯於該複數個淹水資料中的一第三淹水資料；由該比對模組根據該目標降雨資料與該第二特徵資料產生一第三比對結果，並根據該第三比對結果將該目標降雨資料關聯於該第二群組；以及由該比對模組根據該目標降雨資料與該第二群組中的各該第四降雨資料產生一第四比對結果，並根據該第四比對結果將該目標降雨資料關聯於該第五降雨資料；其中該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第五降雨資料的該第三淹水資料以產生該淹水分析資料。In a preferred embodiment of the present invention, the flood prediction method further includes: assigning, by the grouping module, a plurality of fourth rainfall data from the plurality of rainfall data as a second group; and the grouping module Generate a second feature data based on the plurality of fourth rainfall data, and associate the second feature data with the second group, wherein the plurality of fourth rainfall data includes a fifth rainfall data, and the fifth rainfall data A third flooding data related to the plurality of flooding data; the comparison module generates a third comparison result according to the target rainfall data and the second characteristic data, and according to the third comparison result The target rainfall data is associated with the second group; and the comparison module generates a fourth comparison result based on the target rainfall data and each of the fourth rainfall data in the second group, and according to the The fourth comparison result associates the target rainfall data with the fifth rainfall data; wherein the analysis module is based on at least the first flooding data associated with the second rainfall data and the fifth rainfall data associated with the The third flood data is used to generate the flood analysis data.

於本發明之一較佳實施例中，該淹水預測方法進一步包含：由該伺服器的一淹水資料產生模組根據該複數個降雨資料之每一者以分別產生一對應淹水資料，並將該對應淹水資料儲存至該資料庫中；其中該對應淹水資料為該複數個淹水資料的其中一者。In a preferred embodiment of the present invention, the flooding prediction method further includes: generating a corresponding flooding data by a flooding data generation module of the server according to each of the plurality of rainfall data; And store the corresponding flooding data in the database; wherein the corresponding flooding data is one of the plural flooding data.

於本發明之一較佳實施例中，該淹水分析資料包含一區域機率資料，該區域機率資料指示出一區域的一淹水機率；該淹水預測方法進一步包含：當該淹水機率高於關聯於該區域的一機率門檻值時，由該伺服器的一警示模組發出一警示資訊。In a preferred embodiment of the present invention, the flooding analysis data includes an area probability data indicating a flooding probability of an area; the flooding prediction method further includes: when the flooding probability is high When a probability threshold is associated with the area, a warning module of the server sends out a warning message.

於本發明之一較佳實施例中，該區域包含複數個網格區域；該淹水預測方法進一步包含：由該分析模組至少根據關聯於該第二降雨資料的該第一淹水資料以產生複數個網格分析資料其分別對應於該複數個網格區域其中一者；以及由該分析模組根據該複數個網格分析資料以產生該區域機率資料。In a preferred embodiment of the present invention, the area includes a plurality of grid areas; the flooding prediction method further includes: using the analysis module at least according to the first flooding data associated with the second rainfall data to Generate a plurality of grid analysis data corresponding to one of the plurality of grid areas; and the analysis module generates the probability data of the area according to the plurality of grid analysis data.

本發明前述各方面及其它方面依據下述的非限制性具體實施例詳細說明以及參照附隨的圖式將更趨於明瞭。The foregoing aspects and other aspects of the present invention will be more clarified based on the detailed description of the following non-limiting specific embodiments and with reference to the accompanying drawings.

請參閱第一圖，其例示說明了根據本發明淹水預測系統一具體實施例的系統架構圖。如第一圖所示實施例，淹水預測系統100包含資料庫110以及伺服器120，伺服器120包含分群模組121、淹水資料產生模組123、比對模組125、分析模組127、警示模組128以及目標資料產生模組129。其中，伺服器120可存取資料庫110。在一具體實施例中，所述伺服器120可存取資料庫110係指伺服器120中的所有模組皆可存取資料庫110。其中，比對模組125連接分群模組121、分析模組127與目標資料產生模組129，淹水資料產生模組123連接分群模組121，警示模組128連接分析模組127。在一具體實施例中，分群模組121並連接分析模組127。在一具體實施例中，以上所述連接為通訊連接。在一具體實施例中，淹水預測系統100包含一或多個處理器，並以硬體與軟體協同運作的方式實施資料庫110、分群模組121、淹水資料產生模組123、比對模組125、分析模組127、警示模組128以及目標資料產生模組129。Please refer to the first figure, which illustrates a system architecture diagram of a specific embodiment of the flood prediction system according to the present invention. As shown in the first embodiment, the flood prediction system 100 includes a database 110 and a server 120. The server 120 includes a grouping module 121, a flood data generating module 123, a comparison module 125, and an analysis module 127. , A warning module 128 and a target data generating module 129. Among them, the server 120 can access the database 110. In a specific embodiment, the server 120 can access the database 110 means that all modules in the server 120 can access the database 110. Among them, the comparison module 125 is connected to the grouping module 121, the analysis module 127 and the target data generating module 129, the flooding data generating module 123 is connected to the grouping module 121, and the warning module 128 is connected to the analysis module 127. In a specific embodiment, the grouping module 121 is connected to the analysis module 127. In a specific embodiment, the above-mentioned connection is a communication connection. In a specific embodiment, the flooding prediction system 100 includes one or more processors, and implements the database 110, the clustering module 121, the flooding data generation module 123, and the comparison in a cooperative manner of hardware and software. Module 125, analysis module 127, warning module 128, and target data generation module 129.

在第一圖所示實施例中，資料庫110儲存複數個降雨資料與複數個淹水資料，其中各降雨資料分別關聯於複數個淹水資料其中一者，伺服器120存取該資料庫。在一具體實施例中，該複數個淹水資料係由淹水資料產生模組123根據複數個降雨資料之每一者以分別產生而得。例如可將該複數個降雨資料之其中一者做為淹水資料產生模組123的輸入資料，藉以由淹水資料產生模組123產生該輸入資料的對應淹水資料。淹水資料產生模組123並可將此對應淹水資料儲存至資料庫110中。淹水資料產生模組123可藉由此方式而根據複數個降雨資料之每一者以分別產生一對應淹水資料，並將此些對應淹水資料儲存至資料庫110中。被儲存至資料庫110中的此些對應淹水資料即為以上所述的複數個淹水資料。在不同具體實施例中，淹水資料產生模組可透過其內的一淹水運算模組以根據降雨資料計算出其所對應的淹水資料，或係可根據降雨資料所對應的歷史淹水資料以得出降雨資料所對應的淹水資料，但不以此為限。在不同具體實施例中，淹水運算模組可為二維漫地流淹水模式模組、中興顧問社所開發的SINOTOPO模組或國家高速網路與計算中心所開發的NCHC-Hydro2D模組等，但不以此為限。在不同具體實施例中，淹水運算模組可使用總變量消減法（Total Variation Diminishing，TVD）或是晶格波茲曼法（Lattice Boltzmann Method，LBM），以根據降雨資料計算出淹水資料，但不以此為限。在其他實施例中，淹水運算模組亦可為任何可根據降雨資料計算出對應的地表淹水情形（即淹水資料）的模組。In the embodiment shown in the first figure, the database 110 stores a plurality of rainfall data and a plurality of flooding data, wherein each rainfall data is respectively associated with one of the plurality of flooding data, and the server 120 accesses the database. In a specific embodiment, the plurality of flooding data are separately generated by the flooding data generation module 123 according to each of the plurality of rainfall data. For example, one of the plural rainfall data can be used as the input data of the flooding data generating module 123, so that the flooding data generating module 123 generates the corresponding flooding data of the input data. The flooding data generating module 123 can store the corresponding flooding data in the database 110. The flood data generating module 123 can generate a corresponding flood data according to each of a plurality of rainfall data in this way, and store the corresponding flood data in the database 110. The corresponding flooding data stored in the database 110 are the plural flooding data described above. In different embodiments, the flooding data generation module can calculate the corresponding flooding data based on the rainfall data through a flooding calculation module in it, or it can be based on the historical flooding corresponding to the rainfall data. The data is based on the inundation data corresponding to the rainfall data, but not limited to this. In different specific embodiments, the flooding calculation module can be a two-dimensional flooding mode module, a SINOTOPO module developed by ZTE Consulting, or a NCHC-Hydro2D module developed by the National High Speed Network and Computing Center. Etc., but not limited to this. In different embodiments, the flooding calculation module can use Total Variation Diminishing (TVD) or Lattice Boltzmann Method (LBM) to calculate flooding data based on rainfall data. , But not limited to this. In other embodiments, the flooding calculation module can also be any module that can calculate the corresponding surface flooding situation (ie, flooding data) based on rainfall data.

在第一圖所示實施例中，分群模組121可自複數個降雨資料中指定複數個第一降雨資料做為第一群組，分群模組121根據該複數個第一降雨資料產生第一特徵資料，並將第一特徵資料關聯於第一群組，其中複數個第一降雨資料包含一第二降雨資料，該第二降雨資料關聯於複數個淹水資料中的第一淹水資料。In the embodiment shown in the first figure, the grouping module 121 can designate a plurality of first rainfall data from the plurality of rainfall data as the first group, and the grouping module 121 generates the first rainfall data according to the plurality of first rainfall data. Feature data, and associate the first feature data with the first group, wherein the plurality of first rainfall data includes a second rainfall data, and the second rainfall data is related to the first flooding data among the plurality of flooding data.

在一具體實施例中，分群模組121係根據不同地區的降雨資料以進行分群。例如可將降雨分布於台北區域之降雨資料分為同一群，將降雨分布於新竹區域之降雨資料分為同一群，以此類推。在一具體實施例中，降雨資料指示出一目標地區的降雨情況。目標地區可包含複數個網格區域。降雨資料至少指示出各個網格區域是否降雨。其中，目標地區中的第一區域（第一區域可例如為台北區域）包含了複數個第一網格區域，目標地區中的第二區域（第二區域可例如為新竹區域）包含了複數個第二網格區域。分群模組121將降雨主要分布在第一網格區域的複數個降雨資料指定為第一群組，並將降雨主要分布在第二網格區域的複數個降雨資料指定為第二群組。在一具體實施例中，降雨資料指示出一目標地區的降雨情況。其中目標地區可包含複數個網格區域。降雨資料指示出各個網格區域是否降雨，或係可進一步指示出各個網格區域的降雨量。如此，分群模組121即可根據各個網格區域的降雨分布相似度及/或各個網格區域的降雨量相似度以將複數個降雨資料進行分群。例如分群模組121可自複數個降雨資料中，將具有極高的降雨分布相似度的複數個第一降雨資料指定為第一群組。分群模組121並可根據此複數個第一降雨資料產生第一特徵資料，藉以代表第一群組的降雨特徵。第一特徵資料可例如為各個網格區域的降雨分布及/或各個網格區域的降雨量。在一具體實施例中，係將複數個第一降雨資料在各網格區域的降雨分布疊合，以產生第一特徵資料。在一具體實施例中，係根據複數個第一降雨資料在各網格區域的降雨量進行計算（例如取其平均值），以產生第一特徵資料。在一具體實施例中，係根據複數個第一降雨資料計算出各個網格區域的降雨次數，藉以產生第一特徵資料。In a specific embodiment, the grouping module 121 performs grouping based on rainfall data in different regions. For example, the rainfall data of the rainfall distribution in the Taipei area can be divided into the same group, and the rainfall data of the rainfall distribution in the Hsinchu area can be divided into the same group, and so on. In a specific embodiment, the rainfall data indicates the rainfall in a target area. The target area may include a plurality of grid areas. The rainfall data at least indicates whether each grid area is raining. Among them, the first area in the target area (the first area may be, for example, the Taipei area) includes a plurality of first grid areas, and the second area in the target area (the second area may be, for example, the Hsinchu area) includes a plurality of The second grid area. The grouping module 121 designates a plurality of rainfall data whose rainfall is mainly distributed in the first grid area as the first group, and designates a plurality of rainfall data whose rainfall is mainly distributed in the second grid area as the second group. In a specific embodiment, the rainfall data indicates the rainfall in a target area. The target area may include a plurality of grid areas. The rainfall data indicates whether each grid area is raining, or the system can further indicate the rainfall of each grid area. In this way, the grouping module 121 can group a plurality of rainfall data according to the rainfall distribution similarity of each grid area and/or the rainfall similarity of each grid area. For example, the grouping module 121 can designate a plurality of first rainfall data with extremely high rainfall distribution similarity from a plurality of rainfall data as the first group. The grouping module 121 can generate first feature data based on the plurality of first rainfall data, so as to represent the rainfall feature of the first group. The first characteristic data may be, for example, the rainfall distribution of each grid area and/or the rainfall of each grid area. In a specific embodiment, the rainfall distribution of a plurality of first rainfall data in each grid area is superimposed to generate the first characteristic data. In a specific embodiment, the calculation is performed based on the rainfall of the plurality of first rainfall data in each grid area (for example, the average value thereof) to generate the first characteristic data. In a specific embodiment, the number of rainfall in each grid area is calculated based on a plurality of first rainfall data, so as to generate the first characteristic data.

在第一圖所示實施例中，目標資料產生模組129可根據一目標地區的至少一降雨觀測資料以及該目標地區的至少一降雨預測資料產生目標降雨資料。在一具體實施例中，目標地區可包含複數個網格區域，目標資料產生模組129係將該至少一降雨觀測資料以及該至少一降雨預測資料在各網格區域的降雨分布疊合，以產生目標降雨資料。在一具體實施例中，目標降雨資料僅指示出各個網格區域是否有降雨。例如若降雨觀測資料或降雨預測資料其中一者在一網格區域有降雨，則目標降雨資料指示出該網格區域有降雨。在一具體實施例中，目標降雨資料進一步指示出各個網格區域的疊合雨量。其中一網格區域的疊合雨量為降雨觀測資料與降雨預測資料在該網格區域上的雨量總合。在一具體實施例中，目標資料產生模組129係將五個降雨觀測資料與一降雨預報資料進行組合以產生目標降雨資料。然應了解，在不同具體實施例中，目標資料產生模組129亦可因應需求而根據不同數目的降雨觀測資料與降雨預報資料產生目標降雨資料。應了解，使用複數個降雨觀測資料以及至少一降雨預測資料以產生目標降雨資料時，該複數個降雨觀測資料可視需求而為時間上連續的降雨觀測資料，或可視需求而為時間上不連續的降雨觀測資料。此外，使用至少一降雨觀測資料以及至少一降雨預測資料以產生目標降雨資料時，可視需求使用時間上連續的降雨觀測資料與降雨預測資料，或可視需求使用時間上不連續的降雨觀測資料與降雨預測資料。In the embodiment shown in the first figure, the target data generation module 129 can generate target rainfall data based on at least one rainfall observation data in a target area and at least one rainfall prediction data in the target area. In a specific embodiment, the target area may include a plurality of grid areas, and the target data generation module 129 superimposes the rainfall distribution of the at least one rainfall observation data and the at least one rainfall prediction data in each grid area to Generate target rainfall data. In a specific embodiment, the target rainfall data only indicates whether there is rainfall in each grid area. For example, if one of the rainfall observation data or the rainfall prediction data has rainfall in a grid area, the target rainfall data indicates that there is rainfall in the grid area. In a specific embodiment, the target rainfall data further indicates the superimposed rainfall of each grid area. The superimposed rainfall in a grid area is the sum of the rainfall observation data and the rainfall forecast data in the grid area. In a specific embodiment, the target data generation module 129 combines five rainfall observation data with one rainfall forecast data to generate target rainfall data. However, it should be understood that in different specific embodiments, the target data generating module 129 can also generate target rainfall data based on different numbers of rainfall observation data and rainfall forecast data according to requirements. It should be understood that when a plurality of rainfall observation data and at least one rainfall prediction data are used to generate target rainfall data, the plurality of rainfall observation data may be continuous rainfall observation data in time, or discontinuous in time depending on demand. Rain observation data. In addition, when at least one rainfall observation data and at least one rainfall prediction data are used to generate target rainfall data, temporally continuous rainfall observation data and rainfall prediction data can be used as needed, or temporally discontinuous rainfall observation data and rainfall can be used as needed Forecast information.

在第一圖所示實施例中，比對模組125可將目標降雨資料與第一特徵資料進行比對，藉以產生第一比對結果。若第一比對結果指出目標降雨資料與第一特徵資料的相似度夠高（例如目標降雨資料與第一特徵資料的相似度達到一相似度門檻值）時，比對模組125根據第一比對結果將該目標降雨資料關聯於該第一群組，比對模組125並接著將目標降雨資料與第一群組中的各個第一降雨資料進行比對，以產生一第二比對結果，藉此即可自第一群組中比對出與目標降雨資料相似的第一降雨資料。在一具體實施例中，比對模組125根據第二比對結果將目標降雨資料關聯於複數個第一降雨資料中的第二降雨資料。應了解，若第一比對結果指出目標降雨資料與第一特徵資料的相似度不夠高（例如目標降雨資料與第一特徵資料的相似度並未達到一相似度門檻值）時，比對模組125根據第一比對結果而不將該目標降雨資料關聯於該第一群組。如此，比對模組125即無需將第一群組中的各個第一降雨資料與目標降雨資料進行比對。藉由此種方式，淹水預測系統100將可大幅降低比對所耗費的時間。In the embodiment shown in the first figure, the comparison module 125 can compare the target rainfall data with the first characteristic data to generate the first comparison result. If the first comparison result indicates that the similarity between the target rainfall data and the first feature data is high enough (for example, the similarity between the target rainfall data and the first feature data reaches a similarity threshold), the comparison module 125 according to the first The comparison result associates the target rainfall data with the first group, and the comparison module 125 then compares the target rainfall data with each of the first rainfall data in the first group to generate a second comparison As a result, the first rainfall data similar to the target rainfall data can be compared from the first group. In a specific embodiment, the comparison module 125 associates the target rainfall data with the second rainfall data among the plurality of first rainfall data according to the second comparison result. It should be understood that if the first comparison result indicates that the similarity between the target rainfall data and the first feature data is not high enough (for example, the similarity between the target rainfall data and the first feature data does not reach a similarity threshold), the comparison model The group 125 does not associate the target rainfall data with the first group according to the first comparison result. In this way, the comparison module 125 does not need to compare each first rainfall data in the first group with the target rainfall data. In this way, the flood prediction system 100 can greatly reduce the time spent in comparison.

在第一圖所示實施例中，當比對模組125比對出與目標降雨資料相似的複數個相似降雨資料後，分析模組127可根據該複數個相似降雨資料所分別對應的淹水資料以產生淹水分析資料。在一具體實施例中，淹水分析資料指示出目標地區的預測淹水狀況。在一具體實施例中，淹水分析資料包含一區域機率資料，該區域機率資料指示出目標地區中的一區域的淹水機率。其中當淹水機率高於關聯於該區域的一機率門檻值時，警示模組128即發出警示資訊。在一具體實施例中，所述目標地區中的一區域為一網格區域。當比對模組125比對出與目標降雨資料相似的複數個相似降雨資料後，分析模組127可根據複數個相似降雨資料分別對應的淹水資料，計算出該網格區域在此複數個對應淹水資料中的淹水次數，藉以產生關聯於該網格區域的區域機率資料。在一具體實施例中，所述目標地區中的一區域包含複數個網格區域。當比對模組125比對出與目標降雨資料相似的複數個相似降雨資料後，分析模組127可根據複數個相似降雨資料分別對應的淹水資料，計算出該區域在此複數個對應淹水資料中的淹水次數，藉以產生關聯於該區域的區域機率資料。在一具體實施例中，所述目標地區中的一區域包含複數個網格區域。複數個相似降雨資料包含一第二降雨資料。分析模組127至少係根據關聯於該第二降雨資料的第一淹水資料以產生複數個網格分析資料，該複數個網格分析資料分別對應於複數個網格區域其中一者。其中分析模組127係根據複數個網格分析資料以產生區域機率資料。In the embodiment shown in the first figure, after the comparison module 125 compares a plurality of similar rainfall data similar to the target rainfall data, the analysis module 127 can respectively correspond to the flooding according to the plurality of similar rainfall data. Data to generate flooding analysis data. In a specific embodiment, the flooding analysis data indicates the predicted flooding status of the target area. In a specific embodiment, the flooding analysis data includes an area probability data, and the area probability data indicates the flooding probability of an area in the target area. Wherein, when the flooding probability is higher than a probability threshold value associated with the area, the warning module 128 sends out warning information. In a specific embodiment, an area in the target area is a grid area. After the comparison module 125 compares a plurality of similar rainfall data that are similar to the target rainfall data, the analysis module 127 can calculate the plurality of similar rainfall data corresponding to the flooding data in the grid area. Corresponding to the flooding times in the flooding data, the regional probability data related to the grid area is generated. In a specific embodiment, an area in the target area includes a plurality of grid areas. After the comparison module 125 compares a plurality of similar rainfall data that are similar to the target rainfall data, the analysis module 127 can calculate the corresponding flooding data of the plurality of similar rainfall data to calculate the corresponding flooding data in the area. The number of flooding in the water data is used to generate regional probability data related to the area. In a specific embodiment, an area in the target area includes a plurality of grid areas. The plurality of similar rainfall data includes a second rainfall data. The analysis module 127 generates a plurality of grid analysis data at least according to the first flooding data associated with the second rainfall data, and the plurality of grid analysis data respectively correspond to one of the plurality of grid areas. The analysis module 127 generates regional probability data based on multiple grid analysis data.

在一具體實施例中，比對模組125比對出的複數個相似降雨資料包含第二降雨資料。因此，分析模組127至少係根據關聯於第二降雨資料的第一淹水資料以產生淹水分析資料。在一具體實施例中，複數個第一降雨資料並包含第三降雨資料，比對模組125比對出的複數個相似降雨資料包含第二降雨資料與第三降雨資料。因此，分析模組127至少係根據關聯於第二降雨資料的第一淹水資料與關聯於第三降雨資料的第二淹水資料以產生淹水分析資料。In a specific embodiment, the plurality of similar rainfall data compared by the comparison module 125 includes the second rainfall data. Therefore, the analysis module 127 at least generates the flood analysis data based on the first flood data associated with the second rainfall data. In a specific embodiment, the plurality of first rainfall data includes the third rainfall data, and the plurality of similar rainfall data compared by the comparison module 125 includes the second rainfall data and the third rainfall data. Therefore, the analysis module 127 at least generates the flood analysis data based on the first flood data associated with the second rainfall data and the second flood data associated with the third rainfall data.

在一具體實施例中，分群模組121自複數個降雨資料中指定複數個第一降雨資料做為第一群組，根據該複數個第一降雨資料產生第一特徵資料，並將第一特徵資料關聯於第一群組。分群模組121自複數個降雨資料中指定複數個第四降雨資料做為第二群組，根據該複數個第四降雨資料產生一第二特徵資料，並將第二特徵資料關聯於第二群組。其中該複數個第一降雨資料包含第二降雨資料，該複數個第四降雨資料包含一第五降雨資料。比對模組125根據目標降雨資料與第一特徵資料產生第一比對結果，並根據第一比對結果將目標降雨資料關聯於第一群組。比對模組125根據目標降雨資料與第二特徵資料產生一第三比對結果，並根據該第三比對結果將該目標降雨資料關聯於該第二群組。接著，比對模組125根據目標降雨資料與第一群組中的各個第一降雨資料產生第二比對結果，並根據第二比對結果將目標降雨資料關聯於第二降雨資料。此外，比對模組125根據目標降雨資料與第二群組中的各個第四降雨資料產生第四比對結果，並根據第四比對結果將目標降雨資料關聯於第五降雨資料。接著，分析模組127至少根據關聯於第二降雨資料的第一淹水資料與關聯於第五降雨資料的第三淹水資料以產生淹水分析資料。In a specific embodiment, the grouping module 121 designates a plurality of first rainfall data as the first group from a plurality of rainfall data, generates first feature data based on the plurality of first rainfall data, and combines the first feature data The data is associated with the first group. The grouping module 121 designates a plurality of fourth rainfall data as the second group from the plurality of rainfall data, generates a second feature data based on the plurality of fourth rainfall data, and associates the second feature data with the second group group. The plurality of first rainfall data includes second rainfall data, and the plurality of fourth rainfall data includes a fifth rainfall data. The comparison module 125 generates a first comparison result according to the target rainfall data and the first characteristic data, and associates the target rainfall data with the first group according to the first comparison result. The comparison module 125 generates a third comparison result according to the target rainfall data and the second characteristic data, and associates the target rainfall data with the second group according to the third comparison result. Then, the comparison module 125 generates a second comparison result according to the target rainfall data and each of the first rainfall data in the first group, and associates the target rainfall data with the second rainfall data according to the second comparison result. In addition, the comparison module 125 generates a fourth comparison result according to the target rainfall data and each fourth rainfall data in the second group, and associates the target rainfall data with the fifth rainfall data according to the fourth comparison result. Then, the analysis module 127 generates flood analysis data at least according to the first flood data associated with the second rainfall data and the third flood data associated with the fifth rainfall data.

請參閱第二圖，其例示說明了分群後之降雨資料一具體實施例的示意圖。如第二圖所示實施例，分群模組將降雨資料進行分群後，儲存在資料庫中的複數個降雨資料可包含第一群組210、第二群組220、第三群組230、第四群組240、第五群組250以及第六群組260。其中第一群組210具有第一特徵資料212其指示出第一群組210的降雨分布，第二群組220具有第二特徵資料222其指示出第二群組220的降雨分布，第三群組230具有第三特徵資料232其指示出第三群組230的降雨分布，第四群組240具有第四特徵資料242其指示出第四群組240的降雨分布，第五群組250具有第五特徵資料252其指示出第五群組250的降雨分布，第六群組260具有第六特徵資料262其指示出第六群組260的降雨分布。其中第一群組210至第六群組260分別包含了複數筆降雨資料。例如第一群組210即包含了第一降雨資料212A、212B、212C等複數個第一降雨資料。Please refer to the second figure, which illustrates a schematic diagram of a specific embodiment of the rainfall data after grouping. As shown in the embodiment shown in the second figure, after the grouping module groups the rainfall data, the plurality of rainfall data stored in the database may include the first group 210, the second group 220, the third group 230, and the first group 210. The fourth group 240, the fifth group 250, and the sixth group 260. The first group 210 has first characteristic data 212 which indicates the rainfall distribution of the first group 210, the second group 220 has second characteristic data 222 which indicates the rainfall distribution of the second group 220, and the third group The group 230 has the third characteristic data 232 which indicates the rainfall distribution of the third group 230, the fourth group 240 has the fourth characteristic data 242 which indicates the rainfall distribution of the fourth group 240, and the fifth group 250 has the first The fifth feature data 252 indicates the rainfall distribution of the fifth group 250, and the sixth group 260 has sixth feature data 262 that indicates the rainfall distribution of the sixth group 260. The first group 210 to the sixth group 260 respectively include a plurality of rainfall data. For example, the first group 210 includes a plurality of first rainfall data such as the first rainfall data 212A, 212B, and 212C.

請參閱第三圖，其例示說明了根據本發明淹水預測方法一具體實施例的流程圖。如第三圖所示實施例，淹水預測方法300係應用於一淹水預測系統，該淹水預測系統包含資料庫以及伺服器，該資料庫儲存複數個降雨資料，該伺服器可存取該資料庫。其中，淹水預測方法300開始於步驟310，由伺服器的淹水資料產生模組根據複數個降雨資料之每一者以分別產生對應的淹水資料，並將該些淹水資料儲存至資料庫中。接著，進行步驟320，由伺服器的分群模組自儲存於資料庫中的複數個降雨資料中，指定複數個第一降雨資料做為第一群組。接著，進行步驟330，由分群模組根據複數個第一降雨資料產生第一特徵資料，並將第一特徵資料關聯於第一群組，其中複數個第一降雨資料中包含第二降雨資料與第三降雨資料，第二降雨資料關聯於複數個淹水資料中的第一淹水資料，第三降雨資料關聯於複數個淹水資料中的第二淹水資料。Please refer to the third figure, which illustrates a flowchart of a specific embodiment of the flood prediction method according to the present invention. As shown in the embodiment shown in Figure 3, the flood prediction method 300 is applied to a flood prediction system. The flood prediction system includes a database and a server. The database stores a plurality of rainfall data and the server can access The database. Wherein, the flood prediction method 300 starts at step 310. The flood data generation module of the server generates corresponding flood data according to each of a plurality of rainfall data, and stores the flood data in the data. In the library. Next, proceed to step 320, where the clustering module of the server designates a plurality of first rainfall data as the first group from the plurality of rainfall data stored in the database. Next, proceed to step 330, the clustering module generates first feature data based on the plurality of first rainfall data, and associates the first feature data with the first group, wherein the plurality of first rainfall data includes the second rainfall data and The third rainfall data, the second rainfall data are related to the first flooding data of the plurality of flooding data, and the third rainfall data is related to the second flooding data of the plurality of flooding data.

接著，進行步驟340，由伺服器的目標資料產生模組根據關聯於一目標地區的至少一降雨觀測資料以及關聯於該目標地區的至少一降雨預測資料產生目標降雨資料。接著，進行步驟350，由伺服器的比對模組根據目標降雨資料與第一特徵資料產生第一比對結果，並根據第一比對結果將目標降雨資料關聯於第一群組。接著，進行步驟360，由比對模組將目標降雨資料與第一群組中的各個第一降雨資料進行比對以產生第二比對結果，並根據第二比對結果將目標降雨資料關聯於第二降雨資料與第三降雨資料。接著，進行步驟370，由伺服器的分析模組至少根據關聯於第二降雨資料的第一淹水資料與關聯於第三降雨資料的第二淹水資料以產生淹水分析資料。其中淹水分析資料包含一區域機率資料，該區域機率資料指示出目標地區中的一區域的一淹水機率。接著，進行步驟370，當淹水機率高於關聯於機率門檻值時，由伺服器的警示模組發出一警示資訊。Next, in step 340, the target data generation module of the server generates target rainfall data based on at least one rainfall observation data associated with a target area and at least one rainfall prediction data associated with the target area. Next, in step 350, the comparison module of the server generates a first comparison result according to the target rainfall data and the first characteristic data, and associates the target rainfall data with the first group according to the first comparison result. Next, proceed to step 360. The comparison module compares the target rainfall data with each of the first rainfall data in the first group to generate a second comparison result, and associates the target rainfall data with the target rainfall data according to the second comparison result. The second rainfall data and the third rainfall data. Then, step 370 is performed, and the analysis module of the server generates flood analysis data based on at least the first flood data associated with the second rainfall data and the second flood data associated with the third rainfall data. The flooding analysis data includes an area probability data, and the area probability data indicates a flooding probability of an area in the target area. Then, proceed to step 370, when the flooding probability is higher than the threshold value associated with the probability, the warning module of the server sends out a warning message.

在一具體實施例中，目標地區中的該區域包含複數個網格區域。淹水預測方法300進一步包含：由分析模組至少根據關聯於第二降雨資料的第一淹水資料與關聯於第三降雨資料的第二淹水資料以產生複數個網格分析資料，該複數個網格分析資料分別對應於複數個網格區域其中一者。淹水預測方法300並進一步包含：由分析模組根據該複數個網格分析資料以產生該區域機率資料。In a specific embodiment, the area in the target area includes a plurality of grid areas. The flooding prediction method 300 further includes: generating a plurality of grid analysis data based on at least the first flooding data associated with the second rainfall data and the second flooding data associated with the third rainfall data by the analysis module. Each grid analysis data corresponds to one of a plurality of grid areas. The flood prediction method 300 further includes: generating the probability data of the area by the analysis module according to the plurality of grid analysis data.

請參閱第四圖，其例示說明了根據本發明淹水預測方法一具體實施例的流程圖。如第四圖所示實施例，淹水預測方法400係應用於一淹水預測系統，淹水預測系統包含資料庫以及伺服器，資料庫儲存複數個降雨資料與複數個淹水資料，其中各個降雨資料分別關聯於複數個淹水資料的其中一者，該伺服器可存取該資料庫。其中，淹水預測方法400開始於步驟410，由伺服器的分群模組自複數個降雨資料中指定複數個第一降雨資料做為第一群組。接著，進行步驟420，由分群模組根據複數個第一降雨資料產生第一特徵資料，並將第一特徵資料關聯於第一群組。其中複數個第一降雨資料包含第二降雨資料，第二降雨資料關聯於複數個淹水資料中的第一淹水資料。接著，進行步驟430，由分群模組自複數個降雨資料中指定複數個第四降雨資料做為第二群組。其中複數個第四降雨資料包含第五降雨資料，第五降雨資料關聯於複數個淹水資料中的一第三淹水資料。接著，進行步驟440，由分群模組根據複數個第四降雨資料產生第二特徵資料，並將第二特徵資料關聯於第二群組。Please refer to the fourth figure, which illustrates a flowchart of a specific embodiment of the flood prediction method according to the present invention. As shown in the embodiment shown in Figure 4, the flood prediction method 400 is applied to a flood prediction system. The flood prediction system includes a database and a server. The database stores multiple rainfall data and multiple flood data, each of which The rainfall data is respectively associated with one of a plurality of flooding data, and the server can access the database. Wherein, the flood prediction method 400 starts at step 410, and the grouping module of the server designates a plurality of first rainfall data as the first group from the plurality of rainfall data. Next, proceed to step 420, the grouping module generates first feature data based on the plurality of first rainfall data, and associates the first feature data with the first group. The plurality of first rainfall data includes the second rainfall data, and the second rainfall data is related to the first flooding data among the plurality of flooding data. Next, proceed to step 430, and the grouping module designates a plurality of fourth rainfall data from the plurality of rainfall data as the second group. The plurality of fourth rainfall data includes fifth rainfall data, and the fifth rainfall data is related to a third flooding data among the plurality of flooding data. Next, proceed to step 440, the grouping module generates second feature data based on the plurality of fourth rainfall data, and associates the second feature data with the second group.

接著，進行步驟450，由伺服器的比對模組根據目標降雨資料與第一特徵資料產生第一比對結果，並根據第一比對結果將目標降雨資料關聯於第一群組。在一具體實施例中，目標降雨資料係由伺服器的目標資料產生模組根據至少一降雨觀測資料以及至少一降雨預測資料所產生而得。接著，進行步驟460，由比對模組根據目標降雨資料與第一群組中的各個第一降雨資料產生第二比對結果，並根據第二比對結果將目標降雨資料關聯於第二降雨資料。接著，進行步驟470，由比對模組根據目標降雨資料與第二特徵資料產生第三比對結果，並根據第三比對結果將目標降雨資料關聯於第二群組。接著，進行步驟480，由比對模組根據目標降雨資料與第二群組中的各個第四降雨資料產生第四比對結果，並根據第四比對結果將目標降雨資料關聯於第五降雨資料。接著，進行步驟490，由伺服器的分析模組至少根據關聯於第二降雨資料的第一淹水資料與關聯於第五降雨資料的第三淹水資料以產生淹水分析資料。Next, proceed to step 450, the comparison module of the server generates a first comparison result according to the target rainfall data and the first characteristic data, and associates the target rainfall data with the first group according to the first comparison result. In a specific embodiment, the target rainfall data is generated by the target data generation module of the server based on at least one rainfall observation data and at least one rainfall prediction data. Next, proceed to step 460, the comparison module generates a second comparison result based on the target rainfall data and each of the first rainfall data in the first group, and associates the target rainfall data with the second rainfall data according to the second comparison result . Next, proceed to step 470, the comparison module generates a third comparison result according to the target rainfall data and the second characteristic data, and associates the target rainfall data with the second group according to the third comparison result. Then, proceed to step 480, the comparison module generates a fourth comparison result based on the target rainfall data and each fourth rainfall data in the second group, and associates the target rainfall data with the fifth rainfall data according to the fourth comparison result . Next, proceed to step 490, where the analysis module of the server generates flood analysis data based on at least the first flood data associated with the second rainfall data and the third flood data associated with the fifth rainfall data.

至此，本發明之淹水預測系統及其方法已經由上述說明及圖式加以說明。然應了解，本發明的各個具體實施例僅是做為說明之用，在不脫離本發明申請專利範圍與精神下可進行各種改變，且均應包含於本發明之專利範圍中。因此，本說明書所描述的各具體實施例並非用以限制本發明，本發明之真實範圍與精神揭示於以下申請專利範圍。So far, the flood prediction system and method of the present invention have been described by the above description and drawings. However, it should be understood that the specific embodiments of the present invention are for illustrative purposes only, and various changes can be made without departing from the scope and spirit of the patent application of the present invention, and should be included in the patent scope of the present invention. Therefore, the specific embodiments described in this specification are not intended to limit the present invention, and the true scope and spirit of the present invention are disclosed in the scope of the following patent applications.

100:淹水預測系統 110:資料庫 120:伺服器 121:分群模組 123:淹水資料產生模組 125:比對模組 127:分析模組 128:警示模組 129:目標資料產生模組 210:第一群組 212:第三特徵資料 212A~212C:第一降雨資料 220:第一群組 222:第二特徵資料 230:第三群組 232:第三特徵資料 240:第四群組 242:第四特徵資料 250:第五群組 252:第五特徵資料 260:第六群組 262:第六特徵資料 300:淹水預測方法 310~380:步驟 400:淹水預測方法 410~490:步驟 100: Flooding prediction system 110: database 120: server 121: Grouping Module 123: Flooding data generation module 125: Comparison module 127: Analysis Module 128: warning module 129: Target data generation module 210: The first group 212: third characteristic data 212A~212C: First rainfall data 220: The first group 222: Second characteristic data 230: third group 232: third characteristic data 240: The fourth group 242: fourth characteristic data 250: Group 5 252: Fifth characteristic data 260: Group Six 262: Sixth Feature Data 300: Flood prediction method 310~380: Step 400: Flood prediction method 410~490: Step

第一圖為本發明淹水預測系統一具體實施例的系統架構圖。The first figure is a system architecture diagram of a specific embodiment of the flood prediction system of the present invention.

第二圖為分群後之降雨資料一具體實施例的示意圖。The second figure is a schematic diagram of a specific embodiment of rainfall data after grouping.

第三圖為本發明淹水預測方法一具體實施例的流程圖。The third figure is a flowchart of a specific embodiment of the flood prediction method of the present invention.

第四圖為本發明淹水預測方法另一具體實施例的流程圖。The fourth figure is a flowchart of another specific embodiment of the flood prediction method of the present invention.

無no

100:淹水預測系統 100: Flooding prediction system

110:資料庫 110: database

120:伺服器 120: server

121:分群模組 121: Grouping Module

123:淹水資料產生模組 123: Flooding data generation module

125:比對模組 125: Comparison module

127:分析模組 127: Analysis Module

128:警示模組 128: warning module

129:目標資料產生模組 129: Target data generation module

Claims (12)

一種淹水預測系統，包含：一資料庫，儲存複數個降雨資料與複數個淹水資料，其中各該降雨資料分別關聯於該複數個淹水資料其中一者；以及一伺服器，存取該資料庫，該伺服器包含：一分群模組，自該複數個降雨資料中指定複數個第一降雨資料做為一第一群組，該分群模組根據該複數個第一降雨資料產生一第一特徵資料，並將該第一特徵資料關聯於該第一群組，其中該複數個第一降雨資料包含一第二降雨資料，該第二降雨資料關聯於該複數個淹水資料中的一第一淹水資料；一比對模組，根據一目標降雨資料與該第一特徵資料產生一第一比對結果，並根據該第一比對結果將該目標降雨資料關聯於該第一群組，該比對模組接著根據該目標降雨資料與該第一群組中的各該第一降雨資料產生一第二比對結果，並根據該第二比對結果將該目標降雨資料關聯於該第二降雨資料；以及一分析模組，至少根據關聯於該第二降雨資料的該第一淹水資料以產生一淹水分析資料；其中該比對模組通訊連接該分群模組與該分析模組；其中該伺服器包含一目標資料產生模組，根據至少一降雨觀測資料以及至少一降雨預測資料產生該目標降雨資料；其中該比對模組通訊連接該目標資料產生模組。 A flooding prediction system includes: a database storing a plurality of rainfall data and a plurality of flooding data, wherein each of the rainfall data is respectively associated with one of the plurality of flooding data; and a server for accessing the The database, the server includes: a clustering module, from the plurality of rainfall data designated a plurality of first rainfall data as a first group, the clustering module generates a first group according to the plurality of first rainfall data A feature data, and the first feature data is associated with the first group, wherein the plurality of first rainfall data includes a second rainfall data, and the second rainfall data is related to one of the plurality of flooding data First flooding data; a comparison module that generates a first comparison result based on a target rainfall data and the first characteristic data, and associates the target rainfall data with the first group according to the first comparison result Group, the comparison module then generates a second comparison result based on the target rainfall data and each of the first rainfall data in the first group, and associates the target rainfall data with the target rainfall data according to the second comparison result The second rainfall data; and an analysis module for generating a flooding analysis data based on at least the first flooding data associated with the second rainfall data; wherein the comparison module is communicatively connected to the grouping module and the Analysis module; wherein the server includes a target data generation module, which generates the target rainfall data based on at least one rainfall observation data and at least one rainfall prediction data; wherein the comparison module is communicatively connected to the target data generation module. 如請求項1所述之淹水預測系統，其中該複數個第一降雨資料包含一第三降雨資料，該第三降雨資料關聯於該複數個淹水資料中的一第二淹水資料；其中該比對模組根據該第二比對結果將該目標降雨資料關聯於該第三降雨資料；其中該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第三降雨資料的該第二淹水資料以產生該淹水分析資料。 The flooding prediction system according to claim 1, wherein the plurality of first rainfall data includes a third rainfall data, and the third rainfall data is related to a second flooding data of the plurality of flooding data; wherein The comparison module associates the target rainfall data with the third rainfall data according to the second comparison result; wherein the analysis module is at least based on the first flooding data associated with the second rainfall data and associated with The second flooding data of the third rainfall data is used to generate the flooding analysis data. 如請求項1所述之淹水預測系統，其中該分群模組自該複數個降雨資料中指定複數個第四降雨資料做為一第二群組，該分群模組根據該複數個第四降雨資料產生一第二特徵資料，並將該第二特徵資料關聯於該第二群組，其中該複數個第四降雨資料包含一第五降雨資料，該第五降雨資料關聯於該複數個淹水資料中的一第三淹水資料；其中該比對模組根據該目標降雨資料與該第二特徵資料產生一第三比對結果，並根據該第三比對結果將該目標降雨資料關聯於該第二群組，該比對模組接著根據該目標降雨資料與該第二群組中的各該第四降雨資料產生一第四比對結果，並根據該第四比對結果將該目標降雨資料關聯於該第五降雨資料；且其中該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第五降雨資料的該第三淹水資料以產生該淹水分析資料。 The flooding prediction system according to claim 1, wherein the grouping module designates a plurality of fourth rainfall data from the plurality of rainfall data as a second group, and the grouping module according to the plurality of fourth rainfall data The data generates a second characteristic data, and associates the second characteristic data with the second group, wherein the plurality of fourth rainfall data includes a fifth rainfall data, and the fifth rainfall data is related to the plurality of flooding A third flooding data in the data; wherein the comparison module generates a third comparison result based on the target rainfall data and the second characteristic data, and associates the target rainfall data with the third comparison result The second group, the comparison module then generates a fourth comparison result based on the target rainfall data and each of the fourth rainfall data in the second group, and then the target according to the fourth comparison result The rainfall data is related to the fifth rainfall data; and wherein the analysis module generates at least the first flooding data related to the second rainfall data and the third flooding data related to the fifth rainfall data to generate The flood analysis data. 如請求項1所述之淹水預測系統，其中該伺服器包含一淹水資料產生模組，該淹水資料產生模組根據該複數個降雨資料之每一者以分別產生一對應淹水資料，該淹水資料產生模組並將該對應淹水資料儲存至該資料庫中；其中該對應淹水資料為該複數個淹水資料的其中一者；其中該淹水資料產生模組通訊連接該分群模組。 The flooding prediction system according to claim 1, wherein the server includes a flooding data generating module, and the flooding data generating module generates a corresponding flooding data according to each of the plurality of rainfall data , The flooding data generating module and storing the corresponding flooding data in the database; wherein the corresponding flooding data is one of the plurality of flooding data; wherein the flooding data generating module communication connection The grouping module. 如請求項1所述之淹水預測系統，其中該淹水分析資料包含一區域機率資料，該區域機率資料指示出一區域的一淹水機率；其中該伺服器包含一警示模組，當該淹水機率高於關聯於該區域的一機率門檻值時，該警示模組發出一警示資訊；其中該警示模組通訊連接該分析模組。 The flooding prediction system according to claim 1, wherein the flooding analysis data includes an area probability data, and the area probability data indicates a flooding probability of an area; wherein the server includes a warning module, when the When the flooding probability is higher than a probability threshold value associated with the area, the warning module sends out a warning message; wherein the warning module is communicatively connected to the analysis module. 如請求項5所述之淹水預測系統，其中該區域包含複數個網格區域，其中該分析模組至少根據關聯於該第二降雨資料的該第一淹水資料以產生複數個網格分析資料其分別對應於該複數個網格區域其中一者；其中該分析模組係根據該複數個網格分析資料以產生該區域機率資料。 The flooding prediction system according to claim 5, wherein the area includes a plurality of grid areas, and the analysis module generates a plurality of grid analyses at least according to the first flooding data associated with the second rainfall data The data respectively correspond to one of the plurality of grid regions; wherein the analysis module generates the probability data of the region based on the plurality of grid analysis data. 一種淹水預測方法，應用於一淹水預測系統，該淹水預測系統包含一資料庫以及一伺服器，該資料庫儲存複數個降雨資料與複數個淹水資料，其中各該降雨資料分別關聯於該複數個淹水資料其中一者，該伺服器存取該資料庫；其中淹水預測方法包含：由一伺服器的一分群模組自該複數個降雨資料中指定複數個第一降雨資料做為一第一群組； 由該分群模組根據該複數個第一降雨資料產生一第一特徵資料，並將該第一特徵資料關聯於該第一群組，其中該複數個第一降雨資料包含一第二降雨資料，該第二降雨資料關聯於該複數個淹水資料中的一第一淹水資料；由該伺服器的一目標資料產生模組根據至少一降雨觀測資料以及至少一降雨預測資料產生一目標降雨資料；由該伺服器的一比對模組根據該目標降雨資料與該第一特徵資料產生一第一比對結果，並根據該第一比對結果將該目標降雨資料關聯於該第一群組；由該比對模組根據該目標降雨資料與該第一群組中的各該第一降雨資料產生一第二比對結果，並根據該第二比對結果將該目標降雨資料關聯於該第二降雨資料；以及由該伺服器的一分析模組至少根據關聯於該第二降雨資料的該第一淹水資料以產生一淹水分析資料。 A flood prediction method applied to a flood prediction system. The flood prediction system includes a database and a server. The database stores a plurality of rainfall data and a plurality of flooding data, wherein each of the rainfall data is respectively associated For one of the plurality of flooding data, the server accesses the database; wherein the flooding prediction method includes: specifying a plurality of first rainfall data from the plurality of rainfall data by a clustering module of a server As a first group; The clustering module generates a first feature data according to the plurality of first rainfall data, and associates the first feature data with the first group, wherein the plurality of first rainfall data includes a second rainfall data, The second rainfall data is associated with a first flooding data among the plurality of flooding data; a target data generation module of the server generates a target rainfall data based on at least one rainfall observation data and at least one rainfall prediction data ; A comparison module of the server generates a first comparison result based on the target rainfall data and the first characteristic data, and associates the target rainfall data with the first group according to the first comparison result ; The comparison module generates a second comparison result based on the target rainfall data and each of the first rainfall data in the first group, and associates the target rainfall data with the target rainfall data according to the second comparison result Second rainfall data; and an analysis module of the server generates a flooding analysis data at least according to the first flooding data associated with the second rainfall data. 如請求項7所述之淹水預測方法，其中該複數個第一降雨資料包含一第三降雨資料，該第三降雨資料關聯於該複數個淹水資料中的一第二淹水資料；其中該淹水預測方法進一步包含：由該比對模組根據該第二比對結果將該目標降雨資料關聯於該第三降雨資料； 其中該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第三降雨資料的該第二淹水資料以產生該淹水分析資料。 The flooding prediction method according to claim 7, wherein the plurality of first rainfall data includes a third rainfall data, and the third rainfall data is related to a second flooding data of the plurality of flooding data; wherein The flood prediction method further includes: associating the target rainfall data with the third rainfall data by the comparison module according to the second comparison result; The analysis module at least generates the flood analysis data based on the first flood data associated with the second rainfall data and the second flood data associated with the third rainfall data. 如請求項7所述之淹水預測方法，進一步包含：由該分群模組自該複數個降雨資料中指定複數個第四降雨資料做為一第二群組；由分群模組根據該複數個第四降雨資料產生一第二特徵資料，並將該第二特徵資料關聯於該第二群組，其中該複數個第四降雨資料包含一第五降雨資料，該第五降雨資料關聯於該複數個淹水資料中的一第三淹水資料；由該比對模組根據該目標降雨資料與該第二特徵資料產生一第三比對結果，並根據該第三比對結果將該目標降雨資料關聯於該第二群組；以及由該比對模組根據該目標降雨資料與該第二群組中的各該第四降雨資料產生一第四比對結果，並根據該第四比對結果將該目標降雨資料關聯於該第五降雨資料；其中該分析模組至少係根據關聯於該第二降雨資料的該第一淹水資料與關聯於該第五降雨資料的該第三淹水資料以產生該淹水分析資料。 The flood prediction method according to claim 7, further comprising: assigning a plurality of fourth rainfall data from the plurality of rainfall data by the grouping module as a second group; and the grouping module according to the plurality of rainfall data. The fourth rainfall data generates a second feature data, and associates the second feature data with the second group, wherein the plurality of fourth rainfall data includes a fifth rainfall data, and the fifth rainfall data is associated with the plurality of A third flooding data among the three flooding data; the comparison module generates a third comparison result based on the target rainfall data and the second characteristic data, and the target rainfall is based on the third comparison result Data is associated with the second group; and the comparison module generates a fourth comparison result based on the target rainfall data and each of the fourth rainfall data in the second group, and according to the fourth comparison As a result, the target rainfall data is associated with the fifth rainfall data; wherein the analysis module is based on at least the first flooding data associated with the second rainfall data and the third flooding data associated with the fifth rainfall data Data to generate the flooding analysis data. 如請求項7所述之淹水預測方法，進一步包含：由該伺服器的一淹水資料產生模組根據該複數個降雨資料之每一者以分別產生一對應淹水資料，並將該對應淹水資料 儲存至該資料庫中；其中該對應淹水資料為該複數個淹水資料的其中一者。 The flooding prediction method according to claim 7, further comprising: generating a corresponding flooding data by a flooding data generation module of the server according to each of the plurality of rainfall data, and combining the corresponding flooding data Flooding information Stored in the database; wherein the corresponding flooding data is one of the plural flooding data. 如請求項7所述之淹水預測方法，其中該淹水分析資料包含一區域機率資料，該區域機率資料指示出一區域的一淹水機率；其中該淹水預測方法進一步包含：當該淹水機率高於關聯於該區域的一機率門檻值時，由該伺服器的一警示模組發出一警示資訊。 The flooding prediction method according to claim 7, wherein the flooding analysis data includes an area probability data, and the area probability data indicates a flooding probability of an area; wherein the flooding prediction method further includes: when the flooding When the water probability is higher than a probability threshold associated with the area, a warning module of the server sends out a warning message. 如請求項11所述之淹水預測方法，其中該區域包含複數個網格區域；該淹水預測方法進一步包含：由該分析模組至少根據關聯於該第二降雨資料的該第一淹水資料以產生複數個網格分析資料其分別對應於該複數個網格區域其中一者；以及由該分析模組根據該複數個網格分析資料以產生該區域機率資料。 The flooding prediction method according to claim 11, wherein the area includes a plurality of grid areas; the flooding prediction method further includes: at least according to the first flooding data associated with the second rainfall data by the analysis module The data is used to generate a plurality of grid analysis data corresponding to one of the plurality of grid regions; and the analysis module generates the probability data of the region according to the plurality of grid analysis data.
TW109110355A 2020-03-26 2020-03-26 Flooding prediction system and method TWI720857B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW109110355A TWI720857B (en) 2020-03-26 2020-03-26 Flooding prediction system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW109110355A TWI720857B (en) 2020-03-26 2020-03-26 Flooding prediction system and method

Publications (2)

Publication Number Publication Date
TWI720857B true TWI720857B (en) 2021-03-01
TW202137121A TW202137121A (en) 2021-10-01

Family

ID=76035837

Family Applications (1)

Application Number Title Priority Date Filing Date
TW109110355A TWI720857B (en) 2020-03-26 2020-03-26 Flooding prediction system and method

Country Status (1)

Country Link
TW (1) TWI720857B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4082686B2 (en) * 2002-12-03 2008-04-30 財団法人河川情報センター Real-time dynamic flood simulation system
TW201638894A (en) * 2014-12-09 2016-11-01 統一電子有限責任公司 Integrated hazard risk management and mitigation system
TWI598851B (en) * 2016-01-28 2017-09-11 桓達科技股份有限公司 Dynamic flood forecasting and warning system
TWI674540B (en) * 2018-08-21 2019-10-11 國家災害防救科技中心 A system for immediate assessment and early warning of industrial and commercial disasters caused by wind and flood

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4082686B2 (en) * 2002-12-03 2008-04-30 財団法人河川情報センター Real-time dynamic flood simulation system
TW201638894A (en) * 2014-12-09 2016-11-01 統一電子有限責任公司 Integrated hazard risk management and mitigation system
TWI598851B (en) * 2016-01-28 2017-09-11 桓達科技股份有限公司 Dynamic flood forecasting and warning system
TWI674540B (en) * 2018-08-21 2019-10-11 國家災害防救科技中心 A system for immediate assessment and early warning of industrial and commercial disasters caused by wind and flood

Also Published As

Publication number Publication date
TW202137121A (en) 2021-10-01

Similar Documents

Publication Publication Date Title
CN107330056A (en) Wind power plant SCADA system and its operation method based on big data cloud computing platform
JP2011118899A (en) Method and system for data distribution in high performance computing cluster
CN102314336B (en) A kind of data processing method and system
CN111428747A (en) Method and device for monitoring dust and dirt condition of air cooling radiating fin
CN112492275B (en) Layout method, device and storage medium of regional monitoring points
TW202133055A (en) Method for establishing system resource prediction and resource management model through multi-layer correlations
KR102219574B1 (en) Method and System for Calculating the Local Climate Type for Urban Micro-climate Environmental Management
CN113177857B (en) Resource elastic allocation method based on typhoon disaster estimation
Krishna An integrated approach for weather forecasting based on data mining and forecasting analysis
AU2018415216B2 (en) Mesoscale data-based automatic wind turbine layout method and device
CN111464775B (en) Monitoring equipment layout rationality determination method and device
Lin et al. Multivariate and propagation graph attention network for spatial-temporal prediction with outdoor cellular traffic
CN106980540B (en) Distributed multi-dimensional discrete data calculation method
TWI720857B (en) Flooding prediction system and method
CN115617279B (en) Distributed cloud data processing method and device and storage medium
CN112215655A (en) Client portrait label management method and system
CN108520178A (en) A kind of Android platform intrusion detection method based on CFSFDP clusters
CN112464276B (en) Privacy protection method for sparse position track
CN110087031B (en) Task allocation method facing cooperative sensing
CN113704750A (en) Network attack detection method and device of distributed power generation system and terminal equipment
CN107908766A (en) A kind of city focus incident dynamic monitoring method and system
CN111046321B (en) Photovoltaic power station operation and maintenance strategy optimization method and device
Bao et al. Trajectory outlier detection based on partition-and-detection framework
CN114884688B (en) Federal anomaly detection method across multi-attribute networks
CN111767567A (en) Social information security management method