Flood risk assessment system and method based on multi-source data fusion

Abstract

The invention discloses a flood risk assessment system and method based on multi-source data fusion, and belongs to the technical field of flood risk assessment. Based on the longitudinal curve length of the river, a water level detection sensor is placed on the river, and segmented areas are constructed; obtaining average riverbed settlement data and water level data, and calculating a water level risk value and a settlement risk value; calculating a comprehensive risk value of all segmented areas at the node of the e-th data acquisition period; calculating an average risk value in all data acquisition periods, and analyzing and judging an early warning level; according to the method, the riverbed settlement sensors are buried in the segmented areas, and the data acquisition period is unified, so that the synchronism and consistency of the water level and the settlement data are ensured, and the accuracy of data fusion is improved; the comprehensive risk value is calculated based on the water level and the settlement risk value, the flood risk can be dynamically quantified, and the risk fluctuation can be effectively captured; and finally, through comprehensive evaluation, the early warning level is accurately judged, and a scientific basis is provided for flood control decision.

Description

Technical Field

[0001] The present invention relates to the technical field of flood risk assessment, and in particular to a flood risk assessment system and method based on multi-source data fusion. Background Art

[0002] Flood risk assessment is an important area related to public safety. With the frequent occurrence of extreme weather events caused by climate change, the threat of flood disasters is increasing. Existing flood risk assessment methods mainly rely on a single data source, such as water level monitoring data or meteorological data. Although these methods are effective in specific scenarios, they often ignore the combined impact of other important factors, such as riverbed subsidence, terrain characteristics and river hydrological characteristics. Especially in complex river environments, a single data source is often difficult to fully reflect the potential flood risks, resulting in greater uncertainty in the assessment results. In addition, with the development of technology, satellite remote sensing technology and Internet of Things sensors are gradually applied to flood monitoring, but the existing assessment methods still lack an effective multi-source data fusion mechanism and cannot give full play to the advantages of these advanced technologies.

[0003] The shortcomings of existing technologies are that a single data source cannot accurately capture the dynamic changes in flood risks, especially the lack of consideration of key variables such as riverbed subsidence that have a direct impact on flood occurrence; in addition, existing risk assessment methods are mostly based on static models and fail to respond to changes in real-time data in a timely manner; at the same time, assessment methods based on a single data source cannot fully quantify the correlation and interaction between the data, resulting in assessment results that are difficult to fully reflect the true risk of floods; in this context, multi-source data fusion technology has become a new research trend, which can more comprehensively and dynamically assess flood risks by integrating data from different sources. Summary of the invention

[0004] The purpose of the present invention is to provide a flood risk assessment system and method based on multi-source data fusion to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A flood risk assessment method based on multi-source data fusion, the method comprising the following steps: using satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map; placing a water level detection sensor on the river based on the longitudinal curve length of the river; forming a segmented area between two adjacent water level detection sensors; burying a riverbed settlement sensor in the segmented area to obtain average riverbed settlement data; obtaining water level data collected by the water level detection sensor and unifying the data collection cycle; calculating the water level risk value and the settlement risk value at the e-th data collection cycle node in the segmented area; calculating the comprehensive risk value of all segmented areas at the e-th data collection cycle node based on the water level risk value and the settlement risk value; calculating the average risk value in all data collection cycles based on the comprehensive risk value, and analyzing and judging the warning level.

[0007] As a preferred solution of the flood risk assessment method based on multi-source data fusion described in the present invention, satellite remote sensing is used to collect river distribution conditions, establish a two-dimensional river plane map, and construct a river database set based on the two-dimensional river plane map, denoted as RV = {RV i |i∈[1,I]}, where RV i represents the i-th river, and I represents the total number of rivers.

[0008] River Based RV i The longitudinal curve length in the river RV i Place N water level detection sensors on the surface and construct a water level detection sensor set WS = {WS n |n∈[1,N]}, where WS n represents the nth water level detection sensor, and N represents the total number of water level detection sensors.

[0009] As a preferred solution of the flood risk assessment method based on multi-source data fusion described in the present invention, based on the water level monitoring sensor in the river RV i The location on the river RV i Segmented, and two adjacent water level detection sensors WS n and WS n+1 A segment area is formed between them, denoted as RSA(WS n |WS n+1 ), the first lateral dimension of the segmented area is the water level detection sensor WS n River RV i The river width of the location, the second lateral dimension of the segmented area is the water level detection sensor WS n+1 River RV i The river width at the position, the longitudinal scale of the segmented area is the length of the river curve between the first lateral scale and the second lateral scale.

[0010] In the segment area RSA (WS n |WS n+1 ) is buried in the riverbed settlement sensor, which is used to monitor the settlement data of the riverbed and obtain the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data, denoted as CJ[RSA(WS n |WS n+1 )].

[0011] Get the water level data collected by the water level detection sensor, denoted as HL n ; Unify the data collection cycle, and synchronously collect segmented area RSA (WS) in the same data collection cycle n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] and average water level data HL[RSA(WS n |WS n+1 )], the average water level data HL[RSA(WS n |WS n+1 )] indicates two adjacent water level detection sensors WS n and WS n+1 Collected water level data HL n and HL n+1 The average value of .

[0012] As a preferred solution of the flood risk assessment method based on multi-source data fusion described in the present invention, at the e-th data collection cycle node, the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] is recorded as the average riverbed settlement cycle data CJ e [RSA(WS n |WS n+1 )], segment area RSA (WS n |WS n+1 ) within the average water level data HL[RSA(WS n |WS n+1 )] is recorded as the average water level cycle data HL e [RSA(WS n |WS n+1 )].

[0013] Calculate the segmented region RSA (WS n |WS n+1) within the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], the calculation formula is as follows:

[0014]

[0015] Among them, HLR e [RSA(WS n |WS n+1 )] represents the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], β represents the preset risk factor, HL safe Indicates the preset warning water level, δ HL A coefficient indicating the preset water level sensitivity.

[0016] In the present invention, HL e [RSA(WS n |WS n+1 )] indicates the segment area RSA (WS n |WS n+1 ) is compared with the warning water level HL safe By comparison, the risk value of water level exceeding the warning line is calculated, δ HL Used to control the sensitivity of water level changes to risk, higher δ HL The value will make the water level change have a greater impact on the risk value; the formula quantifies the impact of river water level on flood risk through normalization of water level data and dynamic adjustment of exponential adjustment; through this calculation method, the risk fluctuations of river water level can be captured more effectively.

[0017] Calculate the segmented region RSA (WS n |WS n+1 ) at the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], the calculation formula is as follows:

[0018]

[0019] Among them, CJR e [RSA(WS n |WS n+1 )] represents the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WSn |WS n+1 )], α represents the preset adjustment coefficient, K CJ represents the normalization factor of the preset riverbed settlement, Indicates the preset segment area RSA (WS n |WS n+1 )’s geographical characteristics attenuation coefficient.

[0020] In the present invention, CJ e [RSA(WS n |WS n+1 )] is composed of segment area RSA (WS n |WS n+1 ) The actual measured values ​​collected by the riverbed sedimentation sensors are converted into risk values ​​by dividing them by a normalization factor K CJ To eliminate the scale differences between different regions, the logarithmic function ln is used to smooth the changes in risk values ​​to prevent extreme values ​​from having too much impact on the results, and the attenuation factor It represents the geographic attenuation effect. This formula quantifies the impact of riverbed subsidence on flood risk by comprehensively considering riverbed subsidence data and geographic attenuation effect, making the risk value more representative. Through this risk calculation method, it is possible to more accurately assess the contribution of riverbed subsidence to flood risk in each area, while avoiding excessive deviation in assessment results due to individual extreme values.

[0021] Based on the water level risk value HLR e [RSA(WS n |WS n+1 )] and the settlement risk value

[0022] CJR e [RSA(WS n |WS n+1 )], calculate the comprehensive risk value of all segmented areas at the e-th data collection cycle node, and the calculation formula is: Among them, ω HL and ω CJ are the preset river water level and land subsidence risk weights, R e [RSA(WS n |WS n+1 )] represents the comprehensive risk value of all segmented areas at the e-th data collection cycle node.

[0023] In the present invention, the weight ω HL and ω CJUsed to adjust the weights of ground subsidence and river water level risks in the overall assessment, the formula integrates the water level risk values ​​and subsidence risk values ​​of all segmented areas within a single data collection cycle, and provides a more comprehensive flood risk assessment through dynamic weight adjustment. Through this integration method, a comprehensive risk assessment result for all segmented areas can be obtained within a single data collection cycle, which is helpful to formulate long-term disaster prevention measures.

[0024] As a preferred solution of the flood risk assessment method based on multi-source data fusion described in the present invention, based on the comprehensive risk value R of all segmented areas at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], calculate the average risk value in the entire data collection period, the calculation formula is as follows:

[0025]

[0026] in, It represents the average risk value in all data collection cycles, and E represents the total number of data collection cycles.

[0027] Preset risk threshold The first warning level and the second warning level, and the first warning level is greater than the second warning level, if the comprehensive risk value within the data collection period The flood risk level during the data collection period is judged to be low and no warning is triggered; if It is determined that the flood risk level within the data collection period triggers the second-level warning level; if It is determined that the flood risk level during this data collection period is high, triggering the first-level warning level.

[0028] A flood risk assessment system based on multi-source data fusion includes: a river data construction module, a river water level and riverbed settlement monitoring module, a comprehensive risk assessment module and a flood risk warning module.

[0029] The river data construction module uses satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map; based on the longitudinal curve length of the river, a water level detection sensor is placed on the river.

[0030] The river water level and riverbed settlement monitoring module forms a segmented area between two adjacent water level detection sensors; a riverbed settlement sensor is buried in the segmented area to obtain average riverbed settlement data; and water level data collected by the water level detection sensor is obtained to unify the data collection cycle.

[0031] The comprehensive risk assessment module calculates the water level risk value and the settlement risk value at the e-th data collection cycle node in the segmented area; based on the water level risk value and the settlement risk value, calculates the comprehensive risk value of all segmented areas at the e-th data collection cycle node.

[0032] The flood risk warning module calculates the average risk value in the entire data collection period based on the comprehensive risk value, analyzes and determines the warning level.

[0033] Furthermore, the river data construction module also includes a two-dimensional river plan unit and a water level detection sensor arrangement unit.

[0034] The two-dimensional river plane map unit uses satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map. Based on the two-dimensional river plane map, a river database set is constructed, which is recorded as RV = {RV i |i∈[1,I]}, where RV i represents the i-th river, and I represents the total number of rivers.

[0035] The water level detection sensor arrangement unit, based on the river RV i The longitudinal curve length in the river RV i Place N water level detection sensors on the surface and construct a water level detection sensor set WS = {WS n |n∈[1,N]}, where WS n represents the nth water level detection sensor, and N represents the total number of water level detection sensors.

[0036] Furthermore, the river water level and riverbed settlement monitoring module also includes a river segmentation unit and a riverbed settlement and water level data acquisition unit.

[0037] The river segmentation unit is based on the water level monitoring sensor in the river RV i The location on the river RV i Segmented, and two adjacent water level detection sensors WS n and WS n+1 A segment area is formed between them, denoted as RSA(WS n |WS n+1 ), the first lateral dimension of the segmented area is the water level detection sensor WS n River RV i The river width of the location, the second lateral dimension of the segmented area is the water level detection sensor WS n+1 River RV i The river width at the position, the longitudinal scale of the segmented area is the length of the river curve between the first lateral scale and the second lateral scale.

[0038] The riverbed settlement and water level data acquisition unit is located in the segmented area RSA (WS n |WS n+1 ) is buried in the riverbed settlement sensor, which is used to monitor the settlement data of the riverbed and obtain the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data, denoted as CJ[RSA(WS n |WS n+1 )]; obtain the water level data collected by the water level detection sensor, recorded as HL n ; Unify the data collection cycle, and synchronously collect segmented area RSA (WS) in the same data collection cycle n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] and average water level data HL[RSA(WS n |WS n+1 )], the average water level data HL[RSA(WS n |WS n+1 )] indicates two adjacent water level detection sensors WS n and WS n+1 Collected water level data HL n and HL n+1 The average value of .

[0039] Furthermore, the comprehensive risk assessment module also includes a water level and subsidence risk calculation unit and a segmented area comprehensive risk unit.

[0040] The water level and subsidence risk calculation unit, at the e-th data collection cycle node, respectively divides the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] is recorded as the average riverbed settlement cycle data CJ e [RSA(WS n |WS n+1 )], segment area RSA (WS n |WS n+1 ) within the average water level data HL[RSA(WS n |WS n+1 )] is recorded as the average water level cycle data HL e [RSA(WS n |WS n+1 )]; Calculate the segment area RSA (WS n |WS n+1) within the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )] water level risk value HLR e [RSA(WS n |WS n+1 )]; Calculate the segment area RSA (WS n |WS n+1 ) at the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WS n |WS n+1 )] e [RSA(WS n |WS n+1 )].

[0041] The segmented area comprehensive risk unit is based on the water level risk value HLR e [RSA(WS n |WS n+1 )] and the settlement risk value CJR e [RSA(WS n |WS n+1 )], calculate the comprehensive risk value R of all segmented areas at the e-th data collection cycle node e [RSA(WS n |WS n+1 )].

[0042] Furthermore, the flood risk warning module also includes an average risk value calculation unit and a warning level determination unit.

[0043] The average risk value calculation unit is based on the comprehensive risk value R of all segmented areas at the e-th data collection period node. e [RSA(WS n |WS n+1 )], calculate the average risk value in the entire data collection period

[0044]

[0045] The warning level determination unit presets a risk threshold The first warning level and the second warning level, and the first warning level is greater than the second warning level, if the comprehensive risk value within the data collection period The flood risk level during the data collection period is judged to be low and no warning is triggered; if It is determined that the flood risk level within the data collection period triggers the second-level warning level; if It is determined that the flood risk level during this data collection period is high, triggering the first-level warning level.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in a flood risk assessment system and method based on multi-source data fusion provided by the present invention, river distribution is collected through satellite remote sensing and water level sensors are placed to establish a two-dimensional river plan, thereby realizing accurate monitoring of river water levels and construction of spatial data sets; by burying riverbed settlement sensors in segmented areas and unifying the data collection cycle, the synchronization and consistency of water level and settlement data are ensured, and the accuracy of data fusion is improved; the comprehensive risk value calculated based on the water level and settlement risk value can dynamically quantify flood risks and effectively capture risk fluctuations; and finally, through comprehensive evaluation, the warning level is accurately judged to provide a scientific basis for flood control decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0048] Figure 1 It is a schematic diagram of the steps of a flood risk assessment method based on multi-source data fusion of the present invention;

[0049] Figure 2 It is a structural schematic diagram of a flood risk assessment system based on multi-source data fusion of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 In the first embodiment, a flood risk assessment method based on multi-source data fusion is provided, and the method comprises the following steps:

[0052] Step S1: using satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plan; placing water level detection sensors on the river based on the longitudinal curve length of the river.

[0053] Specifically, the distribution of rivers is collected by satellite remote sensing, a two-dimensional river plane map is established, and a river database set is constructed based on the two-dimensional river plane map, which is recorded as RV = {RV i |i∈[1,I]}, where RVi represents the i-th river, and I represents the total number of rivers.

[0054] Further, based on river RV i The longitudinal curve length in the river RV i Place N water level detection sensors on the surface and construct a water level detection sensor set WS = {WS n |n∈[1,N]}, where WS n represents the nth water level detection sensor, and N represents the total number of water level detection sensors.

[0055] Step S2: forming a segmented area between two adjacent water level detection sensors; burying a riverbed settlement sensor in the segmented area to obtain average riverbed settlement data; obtaining water level data collected by the water level detection sensor and unifying the data collection cycle.

[0056] Specifically, based on water level monitoring sensors in river RV i The location on the river RV i Segmented, and two adjacent water level detection sensors WS n and WS n+1 A segment area is formed between them, denoted as RSA(WS n |WS n+1 ), the first lateral dimension of the segmented area is the water level detection sensor WS n River RV i The river width of the location, the second lateral dimension of the segmented area is the water level detection sensor WS n+1 River RV i The river width at the position, the longitudinal scale of the segmented area is the length of the river curve between the first lateral scale and the second lateral scale.

[0057] Furthermore, in the segment area RSA (WS n |WS n+1 ) is buried in the riverbed settlement sensor, which is used to monitor the settlement data of the riverbed and obtain the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data, denoted as CJ[RSA(WS n |WS n+1 )], the average riverbed settlement data is obtained by segmented area RSA (WS n |WS n+1 ) is calculated based on the settlement data collected by all riverbed settlement sensors buried in the river.

[0058] Furthermore, the water level data collected by the water level detection sensor is obtained, which is recorded as HL n; Unify the data collection cycle, and synchronously collect segmented area RSA (WS) in the same data collection cycle n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] and average water level data HL[RSA(WS n |WS n+1 )], the average water level data HL[RSA(WS n |WS n+1 )] indicates two adjacent water level detection sensors WS n and WS n+1 Collected water level data HL n and HL n+1 The average value of .

[0059] Step S3: Calculate the water level risk value and the settlement risk value at the e-th data collection cycle node in the segmented area; based on the water level risk value and the settlement risk value, calculate the comprehensive risk value of all segmented areas at the e-th data collection cycle node.

[0060] Specifically, at the e-th data collection cycle node, the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] is recorded as the average riverbed settlement cycle data CJ e [RSA(WS n |WS n+1 )], segment area RSA (WS n |WS n+1 ) within the average water level data HL[RSA(WS n |WS n+1 )] is recorded as the average water level cycle data HL e [RSA(WS n |WS n+1 )].

[0061] Further, the segment area RSA (WS n |WS n+1 ) within the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], the calculation formula is as follows:

[0062]

[0063] Among them, HLRe [RSA(WS n |WS n+1 )] represents the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], β represents the preset risk factor, HL safe Indicates the preset warning water level, δ HL A coefficient indicating the preset water level sensitivity.

[0064] For example, assuming the risk factor β is 0.5, the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )] is 5, the warning water level HL safe is 6, the coefficient of water level sensitivity δ HL = 1, substitute it into the formula to calculate the water level risk value HLR e [RSA(WS n |WS n+1 )] is 0.42.

[0065] Calculate the segmented region RSA (WS n |WS n+1 ) at the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], the calculation formula is as follows:

[0066]

[0067] Among them, CJR e [RSA(WS n |WS n+1 )] represents the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], α represents the preset adjustment coefficient, K CJ represents the normalization factor of the preset riverbed settlement, Indicates the preset segment area RSA (WS n |WS n+1 )’s geographical characteristic attenuation coefficient.

[0068] For example, assuming that the adjustment coefficient α is 0.5, the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WSn |WS n+1 )] is 3, the normalization coefficient of riverbed settlement K CJ =2, the geographical characteristic attenuation coefficient =0, substitute it into the formula to calculate the settlement risk value CJR e [RSA(WS n |WS n+1 )]for

[0069] Furthermore, based on the water level risk value HLR e [RSA(WS n |WS n+1 )] and the settlement risk value CJR e [RSA(WS n |WS n+1 )], calculate the comprehensive risk value of all segmented areas at the e-th data collection cycle node, and the calculation formula is: Among them, ω HL and ω CJ are the preset river water level and land subsidence risk weights, R e [RSA(WS n |WS n+1 )] represents the comprehensive risk value of all segmented areas at the e-th data collection cycle node.

[0070] For example, assuming that the total number of water level detection sensors N is 3 in the first data collection cycle, ω HL and ω CJ 0.4 and 0.5 respectively, and the comprehensive risk value R is calculated by substituting them into the formula e [RSA(WS n |WS n+1 )] is 0.463.

[0071] Step S4: Based on the comprehensive risk value, calculate the average risk value in the entire data collection cycle, analyze and determine the warning level.

[0072] Specifically, based on the comprehensive risk value R of all segmented areas at the e-th data collection period node e [RSA(WS n |WS n+1 )], calculate the average risk value in the entire data collection period, the calculation formula is as follows:

[0073]

[0074] in, It represents the average risk value in all data collection cycles, and E represents the total number of data collection cycles.

[0075] Furthermore, the risk threshold is preset The first warning level and the second warning level, and the first warning level is greater than the second warning level, if the comprehensive risk value within the data collection period The flood risk level during the data collection period is judged to be low and no warning is triggered; if It is determined that the flood risk level within the data collection period triggers the second-level warning level; if It is determined that the flood risk level during this data collection period is high, triggering the first-level warning level.

[0076] For example, assuming E is 4, the risk threshold is 0.5, and the average risk value is calculated by substituting it into the formula is 0.465, then the comprehensive risk value in the first data collection cycle is It is determined that the flood risk level during this data collection period is low and no warning is triggered.

[0077] See also Figure 2 In the second embodiment of the present invention, a flood risk assessment system based on multi-source data fusion is provided, the system comprising: a river data construction module, a river water level and riverbed settlement monitoring module, a comprehensive risk assessment module and a flood risk warning module.

[0078] The river data construction module uses satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map; based on the longitudinal curve length of the river, a water level detection sensor is placed on the river.

[0079] The river water level and riverbed settlement monitoring module forms a segmented area between two adjacent water level detection sensors; a riverbed settlement sensor is buried in the segmented area to obtain average riverbed settlement data; and water level data collected by the water level detection sensor is obtained to unify the data collection cycle.

[0080] The comprehensive risk assessment module calculates the water level risk value and the settlement risk value at the e-th data collection cycle node in the segmented area; based on the water level risk value and the settlement risk value, calculates the comprehensive risk value of all segmented areas at the e-th data collection cycle node.

[0081] The flood risk warning module calculates the average risk value in the entire data collection period based on the comprehensive risk value, analyzes and determines the warning level.

[0082] Furthermore, the river data construction module also includes a two-dimensional river plan unit and a water level detection sensor arrangement unit.

[0083] The two-dimensional river plane map unit uses satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map. Based on the two-dimensional river plane map, a river database set is constructed, which is recorded as RV = {RV i |i∈[1,I]}, where RV i represents the i-th river, and I represents the total number of rivers.

[0084] The water level detection sensor arrangement unit, based on the river RV i The longitudinal curve length in the river RV i Place N water level detection sensors on the surface and construct a water level detection sensor set WS = {WS n |n∈[1,N]}, where WS n represents the nth water level detection sensor, and N represents the total number of water level detection sensors.

[0085] Furthermore, the river water level and riverbed settlement monitoring module also includes a river segmentation unit and a riverbed settlement and water level data acquisition unit.

[0086] The river segmentation unit is based on the water level monitoring sensor in the river RV i The location on the river RV i Segmented, and two adjacent water level detection sensors WS n and WS n+1 A segment area is formed between them, denoted as RSA(WS n |WS n+1 ), the first lateral dimension of the segmented area is the water level detection sensor WS n River RV i The river width of the location, the second lateral dimension of the segmented area is the water level detection sensor WS n+1 River RV i The river width at the position, the longitudinal scale of the segmented area is the length of the river curve between the first lateral scale and the second lateral scale.

[0087] The riverbed settlement and water level data acquisition unit is located in the segmented area RSA (WS n |WS n+1 ) is buried in the riverbed settlement sensor, which is used to monitor the settlement data of the riverbed and obtain the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data, denoted as CJ[RSA(WS n |WS n+1 )]; obtain the water level data collected by the water level detection sensor, recorded as HL n; Unify the data collection cycle, and synchronously collect segmented area RSA (WS) in the same data collection cycle n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] and average water level data HL[RSA(WS n |WS n+1 )], the average water level data HL[RSA(WS n |WS n+1 )] indicates two adjacent water level detection sensors WS n and WS n+1 Collected water level data HL n and HL n+1 The average value of .

[0088] Furthermore, the comprehensive risk assessment module also includes a water level and subsidence risk calculation unit and a segmented area comprehensive risk unit.

[0089] The water level and subsidence risk calculation unit, at the e-th data collection cycle node, respectively divides the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] is recorded as the average riverbed settlement cycle data CJ e [RSA(WS n |WS n+1 )], segment area RSA (WS n |WS n+1 ) within the average water level data HL[RSA(WS n |WS n+1 )] is recorded as the average water level cycle data HL e [RSA(WS n |WS n+1 )]; Calculate the segment area RSA (WS n |WS n+1 ) within the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )] water level risk value HLR e [RSA(WS n |WS n+1 )]; Calculate the segment area RSA (WS n |WS n+1 ) at the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WSn |WS n+1 )] e [RSA(WS n |WS n+1 )].

[0090] The segmented area comprehensive risk unit is based on the water level risk value HLR e [RSA(WS n |WS n+1 )] and the settlement risk value CJR e [RSA(WS n |WS n+1 )], calculate the comprehensive risk value R of all segmented areas at the e-th data collection cycle node e [RSA(WS n |WS n+1 )].

[0091] Furthermore, the flood risk warning module also includes an average risk value calculation unit and a warning level determination unit.

[0092] The average risk value calculation unit is based on the comprehensive risk value R of all segmented areas at the e-th data collection period node. e [RSA(WS n |WS n+1 )], calculate the average risk value in the entire data collection period

[0093] The warning level determination unit presets a risk threshold The first warning level and the second warning level, and the first warning level is greater than the second warning level, if the comprehensive risk value within the data collection period The flood risk level during the data collection period is judged to be low and no warning is triggered; if It is determined that the flood risk level within the data collection period triggers the second-level warning level; if It is determined that the flood risk level during this data collection period is high, triggering the first-level warning level.

[0094] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0095] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A flood risk assessment method based on multi-source data fusion, characterized in that: The method comprises the following steps: Step S1: using satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map; placing water level detection sensors on the river based on the longitudinal curve length of the river; Step S2: forming a segmented area between two adjacent water level detection sensors; burying a riverbed settlement sensor in the segmented area to obtain average riverbed settlement data; obtaining water level data collected by the water level detection sensor and unifying the data collection cycle; Step S3: Calculate the water level risk value and the settlement risk value at the e-th data collection cycle node in the segmented area; based on the water level risk value and the settlement risk value, calculate the comprehensive risk value of all segmented areas at the e-th data collection cycle node; Step S4: Based on the comprehensive risk value, calculate the average risk value in the entire data collection cycle, analyze and determine the warning level.

2. A flood risk assessment method based on multi-source data fusion according to claim 1, characterized in that: The specific implementation process of step S1 includes the following steps: Satellite remote sensing is used to collect river distribution conditions and establish a two-dimensional river plane map. Based on the two-dimensional river plane map, a river database set is constructed, which is denoted as RV = {RV i |i∈[1,I]}, where RV i represents the i-th river, and I represents the total number of rivers; River Based RV i The longitudinal curve length in the river RV i Place N water level detection sensors on the surface and construct a water level detection sensor set WS = {WS n |n∈[1,N]}, where WS n represents the nth water level detection sensor, and N represents the total number of water level detection sensors.

3. A flood risk assessment method based on multi-source data fusion according to claim 2, characterized in that: The specific implementation process of step S2 includes the following steps: Water level monitoring sensor based on river RV i The location on the river RV i Segmented, and two adjacent water level detection sensors WS n and WS n+1 A segment area is formed between them, denoted as RSA(WS n |WS n+1 ), the first lateral dimension of the segmented area is the water level detection sensor WS n River RV i The river width of the location, the second lateral dimension of the segmented area is the water level detection sensor WS n+1 River RV i The width of the river at the position, the longitudinal dimension of the segmented area is the length of the river curve between the first transverse dimension and the second transverse dimension; In the segment area RSA (WS n |WS n+1 ) is buried in the riverbed settlement sensor, which is used to monitor the settlement data of the riverbed and obtain the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data, denoted as CJ[RSA(WS n |WS n+1 )]; Get the water level data collected by the water level detection sensor, denoted as HL n ; Unify the data collection cycle, and synchronously collect segmented area RSA (WS) in the same data collection cycle n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] and average water level data HL[RSA(WS n |WS n+1 )], the average water level data HL[RSA(WS n |WS n+1 )] indicates two adjacent water level detection sensors WS n and WS n+1 Collected water level data HL n and HL n+1 The average value of .

4. A flood risk assessment method based on multi-source data fusion according to claim 3, characterized in that: The specific implementation process of step S3 includes the following steps: At the e-th data collection cycle node, the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] is recorded as the average riverbed settlement cycle data CJ e [RSA(WS n |WS n+1 )], segment area RSA (WS n |WS n+1 ) within the average water level data HL[RSA(WS n |WS n+1 )] is recorded as the average water level cycle data HL e [RSA(WS n |WS n+1 )]; Calculate the segmented region RSA (WS n |WS n+1 ) within the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], the calculation formula is as follows: Among them, HLR e [RSA(WS n |WS n+1 )] represents the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], β represents the preset risk factor, HL safe Indicates the preset warning water level, δ HL A coefficient indicating the preset water level sensitivity; Calculate the segmented region RSA (WS n |WS n+1 ) at the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], the calculation formula is as follows: Among them, CJR e [RSA(WS n |WS n+1 )] represents the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WS n |WS n+1 )], α represents the preset adjustment coefficient, K CJ represents the normalization factor of the preset riverbed settlement, Indicates the preset segment area RSA (WS n |WS n+1 )’s geographical characteristics attenuation coefficient; Based on the water level risk value HLR e [RSA(WS n |WS n+1 )] and the settlement risk value CJR e [RSA(WS n |WS n+1 )], calculate the comprehensive risk value of all segmented areas at the e-th data collection cycle node, and the calculation formula is: Among them, ω HL and ω CJ are the preset river water level and land subsidence risk weights, R e [RSA(WS n |WS n+1 )] represents the comprehensive risk value of all segmented areas at the e-th data collection cycle node.

5. A flood risk assessment method based on multi-source data fusion according to claim 4, characterized in that: The specific implementation process of step S4 includes the following steps: Based on the comprehensive risk value R of all segmented areas at the e-th data collection period node e [RSA(WS n |WS n+1 )], calculate the average risk value in the entire data collection period, the calculation formula is as follows: in, It represents the average risk value in all data collection cycles, and E represents the total number of data collection cycles; Preset risk threshold The first warning level and the second warning level, and the first warning level is greater than the second warning level, if the comprehensive risk value within the data collection period The flood risk level during the data collection period is judged to be low and no warning is triggered; if It is determined that the flood risk level within the data collection period triggers the second-level warning level; if It is determined that the flood risk level during this data collection period is high, triggering the first-level warning level.

6. A flood risk assessment system based on multi-source data fusion, characterized in that: The system includes: a river data construction module, a river water level and riverbed settlement monitoring module, a comprehensive risk assessment module and a flood risk warning module; The river data construction module uses satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map; based on the longitudinal curve length of the river, a water level detection sensor is placed on the river; The river water level and riverbed settlement monitoring module forms a segmented area between two adjacent water level detection sensors; a riverbed settlement sensor is buried in the segmented area to obtain average riverbed settlement data; the water level data collected by the water level detection sensor is obtained to unify the data collection cycle; The comprehensive risk assessment module calculates the water level risk value and the settlement risk value at the e-th data collection cycle node in the segmented area; based on the water level risk value and the settlement risk value, calculates the comprehensive risk value of all segmented areas at the e-th data collection cycle node; The flood risk warning module calculates the average risk value in the entire data collection period based on the comprehensive risk value, analyzes and determines the warning level.

7. The flood risk assessment system based on multi-source data fusion according to claim 6 is characterized by: The river data construction module also includes a two-dimensional river plan view unit and a water level detection sensor arrangement unit; The two-dimensional river plane map unit uses satellite remote sensing to collect river distribution conditions and establish a two-dimensional river plane map. Based on the two-dimensional river plane map, a river database set is constructed, which is recorded as RV = {RV i |i∈[1,I]}, where RV i represents the i-th river, and I represents the total number of rivers; The water level detection sensor arrangement unit, based on the river RV i The longitudinal curve length in the river RV i Place N water level detection sensors on the surface and construct a water level detection sensor set WS = {WS n |n∈[1,N]}, where WS n represents the nth water level detection sensor, and N represents the total number of water level detection sensors.

8. The flood risk assessment system based on multi-source data fusion according to claim 7 is characterized by: The river water level and riverbed settlement monitoring module also includes a river segmentation unit and a riverbed settlement and water level data acquisition unit; The river segmentation unit is based on the water level monitoring sensor in the river RV i The location on the river RV i Segmented, and two adjacent water level detection sensors WS n and WS n+1 A segment area is formed between them, denoted as RSA(WS n |WS n+1 ), the first lateral dimension of the segmented area is the water level detection sensor WS n River RV i The river width of the location, the second lateral dimension of the segmented area is the water level detection sensor WS n+1 River RV i The width of the river at the position, the longitudinal dimension of the segmented area is the length of the river curve between the first transverse dimension and the second transverse dimension; The riverbed settlement and water level data acquisition unit is located in the segmented area RSA (WS n |WS n+1 ) is buried in the riverbed settlement sensor, which is used to monitor the settlement data of the riverbed and obtain the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data, denoted as CJ[RSA(WS n |WS n+1 )]; obtain the water level data collected by the water level detection sensor, recorded as HL n ; Unify the data collection cycle, and synchronously collect segmented area RSA (WS) in the same data collection cycle n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] and average water level data HL[RSA(WS n |WS n+1 )], the average water level data HL[RSA(WS n |WS n+1 )] indicates two adjacent water level detection sensors WS n and WS n+1 Collected water level data HL n and HL n+1 The average value of .

9. The flood risk assessment system based on multi-source data fusion according to claim 8, characterized in that: The comprehensive risk assessment module also includes a water level and subsidence risk calculation unit and a segmented area comprehensive risk unit; The water level and subsidence risk calculation unit, at the e-th data collection cycle node, respectively divides the segmented area RSA (WS n |WS n+1 ) within the average riverbed settlement data CJ [RSA (WS n |WS n+1 )] is recorded as the average riverbed settlement cycle data CJ e [RSA(WS n |WS n+1 )], segment area RSA (WS n |WS n+1 ) within the average water level data HL[RSA(WS n |WS n+1 )] is recorded as the average water level cycle data HL e [RSA(WS n |WS n+1 )]; Calculate the segment area RSA (WS n |WS n+1 ) within the average water level cycle data HL at the e-th data collection cycle node e [RSA(WS n |WS n+1 )] water level risk value HLR e [RSA(WS n |WS n+1 )]; Calculate the segment area RSA (WS n |WS n+1 ) at the average riverbed settlement cycle data CJ at the e-th data collection cycle node e [RSA(WS n |WS n+1 )] e [RSA(WS n |WS n+1 )]; The segmented area comprehensive risk unit is based on the water level risk value HLR e [RSA(WS n |WS n+1 )] and the settlement risk value CJR e [RSA(WS n |WS n+1 )], calculate the comprehensive risk value R of all segmented areas at the e-th data collection cycle node e [RSA(WS n |WS n+1 )].

10. A flood risk assessment system based on multi-source data fusion according to claim 9, characterized in that: The flood risk warning module also includes an average risk value calculation unit and a warning level determination unit; The average risk value calculation unit is based on the comprehensive risk value R of all segmented areas at the e-th data collection period node. e [RSA(WS n |WS n+1 )], calculate the average risk value in the entire data collection period The warning level determination unit presets a risk threshold The first warning level and the second warning level, and the first warning level is greater than the second warning level, if the comprehensive risk value within the data collection period The flood risk level during the data collection period is judged to be low and no warning is triggered; if It is determined that the flood risk level within the data collection period triggers the second-level warning level; if It is determined that the flood risk level during this data collection period is high, triggering the first-level warning level.

Images