CN114493005A - Early warning method and system for predicting river flow based on rainfall - Google Patents
Early warning method and system for predicting river flow based on rainfall Download PDFInfo
- Publication number
- CN114493005A CN114493005A CN202210098386.9A CN202210098386A CN114493005A CN 114493005 A CN114493005 A CN 114493005A CN 202210098386 A CN202210098386 A CN 202210098386A CN 114493005 A CN114493005 A CN 114493005A
- Authority
- CN
- China
- Prior art keywords
- historical
- soil
- data
- rainfall
- flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000002689 soil Substances 0.000 claims abstract description 153
- 230000008020 evaporation Effects 0.000 claims abstract description 91
- 238000001704 evaporation Methods 0.000 claims abstract description 91
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 238000001556 precipitation Methods 0.000 claims abstract description 37
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 96
- 230000008595 infiltration Effects 0.000 claims description 18
- 238000001764 infiltration Methods 0.000 claims description 18
- 229920006395 saturated elastomer Polymers 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F1/00—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow
- G01F1/002—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow wherein the flow is in an open channel
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Pure & Applied Mathematics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Emergency Management (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Fluid Mechanics (AREA)
- Bioinformatics & Computational Biology (AREA)
Abstract
The invention provides an early warning method and system for predicting river channel flow based on rainfall, wherein a prediction model is established according to historical flow data, historical rainfall, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data and second historical flow data of branches of each section; secondly, calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain the estimated surface runoff and the estimated underground runoff of each section of the river to be detected; then inputting the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into a flow prediction model to obtain flow prediction data of each section of the river channel to be detected; finally, whether the flow prediction data exceed the early warning value or not is analyzed, and if the flow prediction data exceed the early warning value, an alarm prompt is given; the river channel flow can be early warned more timely.
Description
Technical Field
The invention relates to the technical field of river monitoring, in particular to an early warning method and an early warning system for predicting river flow based on rainfall.
Background
At present, a plurality of research results for researching the relation between the incoming water volume and the rainfall exist at home and abroad. A large part of the rainfall determination is based on surface rainfall. The surface rainfall is a classical hydrology concept, and is an average rainfall in a certain area in a certain period of time, and can objectively reflect the influence of rainfall on the determination of a drainage basin, so that the surface rainfall becomes an important parameter for a flood prevention department to analyze the water condition and forecast flood. The method has many achievements in the aspects of interpolation and estimation methods of the surface rainfall, distribution and evolution characteristics of the surface rainfall, research of a surface rainfall forecasting method and the like. The classical plane rainfall concept is that it is relatively easy to establish the plane rainfall and the influence thereof on the water coming from the power station under the scenes of clear water system, simple terrain and simple climate background. However, under the condition of complex terrain in mountainous areas, the weather and climate are complex and changeable, and often different days exist in ten days, the establishment of the water collecting surface of the drainage basin is relatively difficult, and sometimes rainfall appears in the drainage basin surface, so that the contribution to the runoff yield of the drainage basin is small. Furthermore, from the point of view of business applications, considering the availability of data and algorithms, existing methods of face rainfall calculation like the Thiessen polygon are computationally complex and cannot be done in the absence of points. In addition, starting from the aspect of hydrology, a hydrological model is established to establish the relation between the inflow and the rainfall, and trees are well established in the aspects of a conceptual hydrological model and a distributed hydrological model, such as a common Xinanjiang model, a neural network model and the like, and are also applied in business. However, the method does not well consider the characteristics of complex terrain and rainfall in mountainous areas, and has poor real-time early warning capability on river channel flow. It is therefore desirable to provide a solution to facilitate early warning of river traffic in a more timely manner.
Disclosure of Invention
The invention aims to provide an early warning method and an early warning system for predicting river channel flow based on rainfall, which are used for achieving the technical effect of early warning the river channel flow in time.
In a first aspect, the invention provides an early warning method for predicting river channel flow based on rainfall, which comprises the following steps:
s1, acquiring first historical flow data, historical precipitation, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data and second historical flow data of branches of each section of a riverway to be detected;
s2, calculating according to the historical precipitation, the historical normalized vegetation index, the evaporation capacity of the historical evaporation vessel and the historical soil data to obtain the historical earth surface runoff and the historical underground runoff of each section of the river to be detected;
s3, taking the second historical flow data, the surface runoff and the underground runoff as input, taking the first historical flow data as output, and training through an LSTM model to obtain a flow prediction model of each section of the river channel to be measured;
s4, receiving forecast precipitation, real-time normalized vegetation index and real-time soil detection data of each section of the river channel to be detected and real-time flow detection data of branches of each section;
s5, calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain estimated surface runoff and estimated underground runoff of each section of the river to be detected;
s6, inputting the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into the flow prediction model to obtain flow prediction data of each section of the river channel to be detected;
and S7, analyzing whether the flow prediction data exceed an early warning value, and if the flow prediction data exceed the early warning value, performing alarm prompt.
Further, the implementing step of S2 includes:
s21, calculating a corresponding first leaf area index according to the historical normalized vegetation index of each segment, and calculating a first canopy water capacity according to the first leaf area index;
s22, calculating according to the historical precipitation and the first canopy water capacity to obtain a corresponding first residual water quantity;
s23, calculating first soil saturated water content of each section of the river channel to be detected according to the historical soil data; the historical soil data comprises soil type, soil composition, soil thickness and actual soil water content of each rainfall stage; the rainfall stage comprises before rainfall, during rainfall and after rainfall;
s24, calculating according to the evaporation capacity of the historical evaporation vessel and the water capacity of the canopy to obtain historical canopy evaporation capacity; meanwhile, historical soil evaporation capacity is calculated according to the canopy evaporation capacity, the actual water content of the soil in the rainfall and the evaporation capacity of the historical evaporation vessel;
s25, calculating to obtain first soil moisture infiltration capacity of each rainfall process according to the first soil saturated water content, the actual water content of the soil before rainfall, the residual water amount and the average infiltration capacity of each section of the river channel to be measured;
s26, calculating to obtain the historical soil moisture interception flow according to the actual water content of the soil in the rainy days and the historical soil evaporation amount;
s27, calculating to obtain historical underground runoff according to the historical soil moisture interception amount and the underground water replenishment coefficient;
s28, calculating to obtain historical earth surface runoff according to the first residual water quantity and the first soil moisture infiltration quantity.
Furthermore, the segments are divided according to the geographical environment of the basin where the river to be detected passes.
Further, the S5 further includes:
s51, calculating a corresponding second leaf area index according to the real-time normalized vegetation index, and calculating a second canopy water capacity according to the second leaf area index;
s52, calculating according to the forecast precipitation and the second canopy water capacity to obtain a corresponding second residual water quantity;
s53, calculating second soil saturated water content of each section of the river channel to be detected according to the real-time soil detection data; the real-time soil detection data comprises the current soil type, soil components, soil thickness and estimated soil water content at each rainfall stage; the rainfall stage comprises before rainfall, in rainfall and after rainfall;
s54, calculating according to the evaporation capacity of the current evaporation vessel and the second canopy water capacity to obtain an estimated canopy evaporation capacity; meanwhile, calculating according to the estimated canopy evaporation capacity, the estimated soil water content in the rainfall and the evaporation capacity of the current evaporation vessel to obtain the estimated soil evaporation capacity;
s55, calculating according to the second soil saturated water content, the soil water content before rainfall, the second residual water amount and the average infiltration amount of each section of the river channel to be detected to obtain the second soil water infiltration amount of each rainfall process;
s56, calculating to obtain the estimated soil moisture interception flow according to the estimated soil water content in the rainfall and the estimated soil evaporation amount;
s57, calculating according to the estimated soil moisture interception amount and underground water supply coefficient to obtain estimated underground runoff;
and S58, calculating to obtain the estimated surface runoff according to the second residual water quantity and the second soil moisture infiltration amount.
In a second aspect, the present invention provides an early warning system for predicting river channel flow based on rainfall, including:
the data acquisition module is used for acquiring first historical flow data, historical precipitation, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data and second historical flow data of branches of each section of the river channel to be detected;
the first analysis module is used for calculating according to historical precipitation, the historical normalized vegetation index, the evaporation capacity of the historical evaporation vessel and the historical soil data to obtain historical earth surface runoff and historical underground runoff of each section of the river to be detected;
the modeling module is used for taking the second historical flow data, the surface runoff and the underground runoff as input, taking the first historical flow data as output, and training through an LSTM (least squares metric) model to obtain a flow prediction model of each section of the river to be tested;
the data receiving module is used for receiving forecast precipitation, real-time normalized vegetation indexes, real-time soil detection data and real-time flow detection data of each segmented branch of the river channel to be detected;
the second analysis module is used for calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain estimated surface runoff and estimated underground runoff of each section of the river to be detected;
the output module is used for inputting the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into the flow prediction model to obtain flow prediction data of each section of the river channel to be detected;
and the early warning module is used for analyzing whether the flow prediction data exceeds an early warning value or not, and giving an alarm prompt if the flow prediction data exceeds the early warning value.
The beneficial effects that the invention can realize are as follows: the early warning method for predicting the river flow based on rainfall provided by the invention establishes a prediction model according to historical flow data, historical precipitation, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data and second historical flow data of each segmented branch; secondly, calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain the estimated surface runoff and the estimated underground runoff of each section of the river to be detected; then inputting the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into a flow prediction model to obtain flow prediction data of each section of the river channel to be detected; and finally, analyzing whether the flow prediction data exceeds an early warning value or not, and if the flow prediction data exceeds the early warning value, giving an alarm prompt so as to early warn the flow of the river channel in more time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments of the present invention will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of an early warning method for predicting river channel flow based on rainfall according to an embodiment of the present invention;
fig. 2 is a schematic view of a topological structure of an early warning system for predicting river channel flow based on rainfall according to an embodiment of the present invention.
Icon: 10-an early warning system; 100-a data acquisition module; 200-a first analysis module; 300-a modeling module; 400-a data receiving module; 500-a second analysis module; 600-an output module; 700-early warning module.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a schematic flow chart of an early warning method for predicting river channel flow based on rainfall according to an embodiment of the present invention.
In an implementation manner, an embodiment of the present invention provides an early warning method for predicting river channel flow based on rainfall, which is described in the following.
S1, obtaining first historical flow data, historical precipitation, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data and second historical flow data of branches of each section of a river channel to be detected.
Specifically, the first historical flow data, the historical precipitation amount, the historical normalized vegetation index, the evaporation amount of the historical evaporation vessel, the second historical flow data of the branch of each section, the historical soil data and the like of each section of the river channel to be detected can be obtained from a historical monitoring list of the river channel to be detected. The soil data comprises soil type, soil composition, soil thickness, actual soil water content of each rainfall stage and the like, and can be acquired through field sampling.
Furthermore, the river channel to be tested can be segmented according to the geographic environment, for example, the segmentation can be performed according to the soil type, vegetation type, terrain and the like of the river channel to be tested.
And S2, calculating according to the historical precipitation, the historical normalized vegetation index, the evaporation capacity of the historical evaporation vessel and the historical soil data to obtain the historical earth surface runoff and the historical underground runoff of each section of the river to be detected.
In one embodiment, S2 may be implemented as follows:
s21, calculating a corresponding first leaf area index according to the historical normalized vegetation index of each segment, and calculating a first canopy water capacity according to the first leaf area index.
The specific calculation process can be implemented as follows:
L=a*NDVI-b
Imax=x*L+y
wherein L represents a leaf area index; a and b represent calculation constants corresponding to different types of vegetation, and NDVI represents a normalized vegetation index; i ismaxRepresenting the canopy water capacity; x and y represent constants corresponding to different types of vegetation.
And S22, calculating to obtain a corresponding first residual water amount according to the historical precipitation amount and the first canopy water capacity.
Ps=max(P-(Imax-It-1),0)
Wherein P represents the precipitation amount; i ist-1Representing the residual water amount after evaporation in the previous time period, wherein a time period is from the end of each rainfall to the beginning of the next rainfall; i ismaxRepresenting the canopy water capacity.
S23, calculating first soil saturated water content of each section of the river channel to be detected according to the historical soil data; the historical soil data comprises soil type, soil composition, soil thickness and actual soil water content of each rainfall stage; the rainfall stage comprises before rainfall, during rainfall and after rainfall.
Specifically, the saturated water content of the soil can be calculated according to the soil type, the soil components and the soil thickness to obtain:
θet=-0.25S+0.19C+0.01M+0.01(S×OM)-0.27(C×OM)+0.3
θ(O-e)t=0.28S+0.03C+0.02M-0.02(S×OM)-0.03(C×OM)-0.60(S×C)+0.08
θ(O-e)=θ(O-e)t+0.64θ(O-e)t-0.1
SAT=θe+θ(O-e)-0.1S+0.04
in the above formula, SD represents the soil thickness; s represents the sand content; c represents a clay content; r represents the gravel content; OM represents the organic content; thetaeRepresents the soil moisture at e kilopascals; thetao-eRepresents the soil moisture at 0-e kilopascals; SAT denotes the saturated water content of the soil.
S24, calculating according to the evaporation capacity of the historical evaporation vessel and the water capacity of the canopy to obtain historical canopy evaporation capacity; and meanwhile, calculating to obtain the historical soil evaporation capacity according to the canopy evaporation capacity, the actual water content of the soil in the rainfall and the evaporation capacity of the historical evaporation vessel.
Ep=ETpan*Ke
Ei=min(It,Ep)
In the above formula, ETpanRepresents the evaporation capacity of the evaporation vessel; keExpressing the evaporation conversion coefficient of the evaporation vessel; epRepresenting the converted actual evaporation capacity of the evaporation vessel; i istRepresenting the amount of water remaining after evaporation for the current calculation period.
And S25, calculating to obtain the first soil moisture infiltration capacity of each rainfall process according to the first soil saturated water content, the actual soil water content before rainfall, the residual water amount and the average infiltration capacity of each section of the river channel to be detected.
Pis=min(SAT-SMt-1,Ps,IC)
SMtmp=SMt-1+Pis
In the above formula, SMt-1Representing the interception amount of the soil moisture after the rainfall evaporation in the previous time period; psRepresents the remaining amount of water; IC represents the average runoff yield of the watershed.
And S26, calculating the historical soil moisture interception amount according to the actual water content of the soil in the rainy days and the historical soil evaporation amount.
SMt=SMtmp-Es
In the above formula, SMtmpIndicating the actual water content of the soil in the rain, EsRepresents the soil evaporation amount; SMtShowing the amount of soil water intercepted after evaporation of rainfall.
And S27, calculating to obtain historical underground runoff according to the historical soil moisture interception amount and the underground water replenishment coefficient.
Rg=Kg×SMt
In the above formula, KgRepresenting a groundwater recharge coefficient; rgRepresenting the subsurface runoff volume.
S28, calculating to obtain historical earth surface runoff according to the first residual water quantity and the first soil moisture infiltration quantity.
Rg=Ps-Pis
And S3, taking the second historical flow data, the surface runoff and the underground runoff as input, taking the first historical flow data as output, and training through an LSTM model to obtain a flow prediction model of each section of the river channel to be measured.
And S4, receiving forecast precipitation, real-time normalized vegetation index and real-time soil detection data of the river channel to be detected and real-time flow detection data of each segmented branch.
Illustratively, the forecast precipitation of the river to be measured can be obtained from weather forecast, and the real-time normalized vegetation index can be obtained through telemetering data; real-time soil detection data can be acquired through the arranged soil detection sensor; the real-time flow detection data of each segmented branch can also be obtained by analyzing and calculating the data acquired by the arranged sensors.
And S5, calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain the estimated surface runoff and the estimated underground runoff of each section of the river to be detected.
In one embodiment, S5 is performed as follows:
s51, calculating a corresponding second leaf area index according to the real-time normalized vegetation index, and calculating a second canopy water capacity according to the second leaf area index;
s52, calculating according to the forecast precipitation and the second canopy water capacity to obtain a corresponding second residual water quantity;
s53, calculating second soil saturated water content of each section of the river channel to be detected according to the real-time soil detection data; the real-time soil detection data comprises the current soil type, soil components, soil thickness and estimated soil water content at each rainfall stage; the rainfall stage comprises before rainfall, in rainfall and after rainfall;
s54, calculating according to the evaporation capacity of the current evaporation vessel and the second canopy water capacity to obtain an estimated canopy evaporation capacity; meanwhile, calculating according to the estimated canopy evaporation capacity, the estimated soil water content in the rainfall and the evaporation capacity of the current evaporation vessel to obtain the estimated soil evaporation capacity;
s55, calculating according to the second soil saturated water content, the soil water content before rainfall, the second residual water amount and the average infiltration amount of each section of the river channel to be detected to obtain the second soil water infiltration amount of each rainfall process;
s56, calculating to obtain the estimated soil moisture interception flow according to the estimated soil water content in the rainfall and the estimated soil evaporation amount;
s57, calculating according to the estimated soil moisture interception amount and underground water supply coefficient to obtain estimated underground runoff;
and S58, calculating to obtain the estimated surface runoff according to the second residual water quantity and the second soil moisture infiltration amount.
Specifically, the calculation of the above process may be performed in the manner referred to as S21-S28.
And S6, inputting the estimated earth surface runoff, the estimated earth surface runoff and the real-time flow detection data into the flow prediction model to obtain flow prediction data of each section of the river channel to be detected.
And S7, analyzing whether the flow prediction data exceed an early warning value or not, and if the flow prediction data exceed the early warning value, giving an alarm.
Illustratively, when the flow prediction data exceeds the early warning value, early warning prompt can be performed in the modes of short messages, broadcasting and the like, and related personnel are informed of preparing disaster prevention in time.
Referring to fig. 2, fig. 2 is a schematic view of a topological structure of an early warning system for predicting river channel flow based on rainfall according to an embodiment of the present invention.
In an implementation manner, an embodiment of the present invention further provides an early warning system 10 for predicting river channel flow based on rainfall, where the early warning system 10 includes:
the data acquisition module 100 is configured to acquire first historical flow data, historical precipitation, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data of each section of the river channel to be detected, and second historical flow data of each section of branch;
the first analysis module 200 is used for calculating according to the historical precipitation, the historical normalized vegetation index, the evaporation capacity of the historical evaporation vessel and the historical soil data to obtain the historical earth surface runoff and the historical underground runoff of each section of the river to be detected;
the modeling module 300 is used for taking the second historical flow data, the surface runoff and the underground runoff as input, taking the first historical flow data as output, and obtaining a flow prediction model of each section of the river channel to be tested through training of an LSTM model;
the data receiving module 400 is used for receiving forecast precipitation, real-time normalized vegetation index and real-time soil detection data of each section of the riverway to be detected and real-time flow detection data of branches of each section;
the second analysis module 500 is used for calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain the estimated surface runoff and the estimated underground runoff of each section of the river channel to be detected;
the output module 600 inputs the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into the flow prediction model to obtain flow prediction data of each section of the river channel to be detected;
and the early warning module 700 is used for analyzing whether the flow prediction data exceeds an early warning value or not, and giving an alarm prompt if the flow prediction data exceeds the early warning value.
In summary, the embodiment of the present invention provides an early warning method and system for predicting river channel flow based on rainfall, which establish a prediction model according to historical flow data, historical rainfall, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data, and second historical flow data of each segmented branch; secondly, calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain estimated surface runoff and estimated underground runoff of each section of the river to be detected; then inputting the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into a flow prediction model to obtain flow prediction data of each section of the river channel to be detected; finally, whether the flow prediction data exceed the early warning value or not is analyzed, and if the flow prediction data exceed the early warning value, an alarm prompt is given; the river channel flow can be early warned more timely.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. The early warning method for predicting the river channel flow based on rainfall is characterized by comprising the following steps of:
s1, acquiring first historical flow data, historical precipitation, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data and second historical flow data of branches of each section of a riverway to be detected;
s2, calculating according to the historical precipitation, the historical normalized vegetation index, the evaporation capacity of the historical evaporation vessel and the historical soil data to obtain the historical earth surface runoff and the historical underground runoff of each section of the river to be detected;
s3, taking the second historical flow data, the surface runoff and the underground runoff as input, taking the first historical flow data as output, and training through an LSTM model to obtain a flow prediction model of each section of the river channel to be measured;
s4, receiving forecast precipitation, real-time normalized vegetation index and real-time soil detection data of each section of the river channel to be detected and real-time flow detection data of branches of each section;
s5, calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain estimated surface runoff and estimated underground runoff of each section of the river to be detected;
s6, inputting the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into the flow prediction model to obtain flow prediction data of each section of the river channel to be detected;
and S7, analyzing whether the flow prediction data exceed an early warning value or not, and if the flow prediction data exceed the early warning value, giving an alarm.
2. The method of claim 1, wherein the step of implementing S2 comprises:
s21, calculating a corresponding first leaf area index according to the historical normalized vegetation index of each segment, and calculating a first canopy water capacity according to the first leaf area index;
s22, calculating according to the historical precipitation and the first canopy water capacity to obtain a corresponding first residual water quantity;
s23, calculating first soil saturated water content of each section of the river channel to be detected according to the historical soil data; the historical soil data comprises soil type, soil composition, soil thickness and actual soil water content of each rainfall stage; the rainfall stage comprises before rainfall, in rainfall and after rainfall;
s24, calculating according to the evaporation capacity of the historical evaporation vessel and the water capacity of the canopy to obtain historical canopy evaporation capacity; meanwhile, historical soil evaporation capacity is calculated according to the canopy evaporation capacity, the actual water content of the soil in the rainfall and the evaporation capacity of the historical evaporation vessel;
s25, calculating to obtain first soil moisture infiltration capacity of each rainfall process according to the first soil saturated water content, the actual soil water content before rainfall, the residual water amount and the average infiltration capacity of each section of the river channel to be detected;
s26, calculating to obtain historical soil moisture interception flow according to the actual water content of the soil in rainfall and the historical soil evaporation amount;
s27, calculating to obtain historical underground runoff according to the historical soil moisture interception amount and the underground water replenishment coefficient;
s28, calculating to obtain historical earth surface runoff according to the first residual water quantity and the first soil moisture infiltration quantity.
3. The method of claim 1, wherein the segments are divided according to the geographical environment of the basin through which the river to be tested passes.
4. The method according to claim 2, wherein the S5 further comprises:
s51, calculating a corresponding second leaf area index according to the real-time normalized vegetation index, and calculating a second canopy water capacity according to the second leaf area index;
s52, calculating according to the forecast precipitation and the second canopy water capacity to obtain a corresponding second residual water quantity;
s53, calculating second soil saturated water content of each section of the river channel to be detected according to the real-time soil detection data; the real-time soil detection data comprises the current soil type, soil components, soil thickness and estimated soil water content at each rainfall stage; the rainfall stage comprises before rainfall, in rainfall and after rainfall;
s54, calculating according to the evaporation capacity of the current evaporation vessel and the second canopy water capacity to obtain an estimated canopy evaporation capacity; meanwhile, calculating according to the estimated canopy evaporation capacity, the estimated soil water content in the rainfall and the evaporation capacity of the current evaporation vessel to obtain the estimated soil evaporation capacity;
s55, calculating according to the second soil saturated water content, the soil water content before rainfall, the second residual water amount and the average infiltration amount of each section of the river channel to be detected to obtain the second soil water infiltration amount of each rainfall process;
s56, calculating to obtain the estimated soil moisture interception flow according to the estimated soil water content in the rainfall and the estimated soil evaporation amount;
s57, calculating according to the estimated soil moisture interception amount and underground water supply coefficient to obtain estimated underground runoff;
and S58, calculating to obtain the estimated surface runoff according to the second residual water quantity and the second soil moisture infiltration amount.
5. The utility model provides a warning system based on rainfall prediction river course flow which characterized in that includes:
the data acquisition module is used for acquiring first historical flow data, historical precipitation, historical normalized vegetation index, evaporation capacity of a historical evaporation vessel, historical soil data and second historical flow data of branches of each section of the river channel to be detected;
the first analysis module is used for calculating according to historical precipitation, the historical normalized vegetation index, the evaporation capacity of the historical evaporation vessel and the historical soil data to obtain historical earth surface runoff and historical underground runoff of each section of the river to be detected;
the modeling module is used for taking the second historical flow data, the surface runoff and the underground runoff as input, taking the first historical flow data as output, and training through an LSTM (least squares metric) model to obtain a flow prediction model of each section of the river to be tested;
the data receiving module is used for receiving forecast precipitation, real-time normalized vegetation index and real-time soil detection data of each section of the riverway to be detected and real-time flow detection data of branches of each section;
the second analysis module is used for calculating according to the forecast precipitation, the real-time normalized vegetation index and the real-time soil detection data to obtain estimated surface runoff and estimated underground runoff of each section of the river to be detected;
the output module is used for inputting the estimated surface runoff, the estimated surface runoff and the real-time flow detection data into the flow prediction model to obtain flow prediction data of each section of the river channel to be detected;
and the early warning module is used for analyzing whether the flow prediction data exceeds an early warning value or not, and giving an alarm prompt if the flow prediction data exceeds the early warning value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210098386.9A CN114493005A (en) | 2022-01-27 | 2022-01-27 | Early warning method and system for predicting river flow based on rainfall |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210098386.9A CN114493005A (en) | 2022-01-27 | 2022-01-27 | Early warning method and system for predicting river flow based on rainfall |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114493005A true CN114493005A (en) | 2022-05-13 |
Family
ID=81476668
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210098386.9A Pending CN114493005A (en) | 2022-01-27 | 2022-01-27 | Early warning method and system for predicting river flow based on rainfall |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114493005A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117392811A (en) * | 2023-10-27 | 2024-01-12 | 浙江水文新技术开发经营有限公司 | Hilly rainfall monitoring and early warning system |
CN117473791A (en) * | 2023-12-22 | 2024-01-30 | 水发科技信息(山东)有限公司 | Public data storage management system based on artificial intelligence |
-
2022
- 2022-01-27 CN CN202210098386.9A patent/CN114493005A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117392811A (en) * | 2023-10-27 | 2024-01-12 | 浙江水文新技术开发经营有限公司 | Hilly rainfall monitoring and early warning system |
CN117392811B (en) * | 2023-10-27 | 2024-05-07 | 浙江水文新技术开发经营有限公司 | Hilly rainfall monitoring and early warning system |
CN117473791A (en) * | 2023-12-22 | 2024-01-30 | 水发科技信息(山东)有限公司 | Public data storage management system based on artificial intelligence |
CN117473791B (en) * | 2023-12-22 | 2024-03-29 | 水发科技信息(山东)有限公司 | Public data storage management system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112070286B (en) | Precipitation forecast and early warning system for complex terrain river basin | |
CN114493005A (en) | Early warning method and system for predicting river flow based on rainfall | |
Beck et al. | Improving curve number based storm runoff estimates using soil moisture proxies | |
CN111651885A (en) | Intelligent sponge urban flood forecasting method | |
CN106373070B (en) | A kind of four pre- methods for coping with urban rainstorm waterlogging | |
CN113222283B (en) | Mountain torrent forecasting and early warning method and system based on digital twinning | |
CN102135531A (en) | Method for forecasting blue-green algae water bloom in large-scale shallow lake within 72 hours | |
CN113434565A (en) | Water conservancy flood control drought and waterlogging prevention comprehensive disaster reduction platform system based on CIM platform | |
CN111428942B (en) | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology | |
CN111784976B (en) | Mountain torrent disaster early warning method, device, system and storage medium | |
CN111579004A (en) | Water conservancy monitoring system and method based on Beidou satellite application and storage medium | |
CN115186858A (en) | Transformer substation flood inundation risk early warning method and system based on different influence types | |
CN106771059A (en) | A kind of intellectual monitoring for ecological zone and preventing control method and system | |
CN115879363A (en) | Accumulated water prediction method based on rainfall | |
Engeset et al. | Snow map system for Norway | |
CN113593191A (en) | Visual urban waterlogging monitoring and early warning system based on big data | |
CN115099162A (en) | Correction method for wind field under complex terrain | |
Nandalal et al. | Event based modeling of a watershed using HEC-HMS | |
Nguyen et al. | Design of an automatic hydro-meteorological observation network for a real-time flood warning system: a case study of Vu Gia-Thu Bon river basin, Vietnam | |
CN209417901U (en) | Mountain flood dynamic early-warning system based on soil moisture content real time correction | |
Manaouch et al. | Integrating GIS-based FAHP and WaTEM/SEDEM for identifying potential RWH areas in semi-arid areas | |
Nyayapathi et al. | Drought vulnerability assessment by employing the Geographical Information System and Analytical Hierarchy Process for the Kurnool district of Andhra Pradesh, India | |
Sali et al. | Peatlands monitoring in Malaysia with IoT Systems: Preliminary experimental results | |
Tadrist et al. | Towards Low-Cost IoT and LPWAN-Based flood forecast and monitoring system | |
CN113077080A (en) | Wisdom hydrology analysis application system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |