CN114201570A

CN114201570A - River network water quality monitoring method and device and readable storage medium

Info

Publication number: CN114201570A
Application number: CN202111523702.4A
Authority: CN
Inventors: 陈瑞斌; 曾志辉; 许文龙; 廖海滨; 邢军华
Original assignee: ZTE ICT Technologies Co Ltd
Current assignee: ZTE ICT Technologies Co Ltd
Priority date: 2021-12-14
Filing date: 2021-12-14
Publication date: 2022-03-18

Abstract

The invention provides a method and a device for monitoring river network water quality and a readable storage medium. A method for monitoring river network water quality comprises the steps of obtaining first data of all river monitoring sections; acquiring second data of an enterprise sewage draining exit in the river network; acquiring meteorological data of a river network; acquiring the predicted flow and the predicted water level of all river monitoring sections by adopting a neural network model; and acquiring a simulation result of the river network by adopting a hydrodynamic model and a water quality model. According to the technical scheme, the water environment condition of the river network can be obtained more intuitively by simulating the water environment of the river network, the water environment in the whole river basin range of the river network is monitored comprehensively, and the whole condition of the whole river network is convenient to master.

Description

River network water quality monitoring method and device and readable storage medium

Technical Field

The invention relates to the technical field of monitoring, in particular to a method and a device for monitoring river network water quality and a readable storage medium.

Background

With the development of urbanization and industrialization, more and more industrial wastewater and domestic wastewater are discharged to rivers, reservoirs, lakes and oceans, so that fresh water resources are polluted, and meanwhile, the water resources are more tense. In order to avoid further deterioration of water pollution, water quality supervision is not slow at all.

In the related technology, modeling is often performed according to historical data, the water environment modeling is not prospective, and future data cannot be used for modeling.

Disclosure of Invention

The present invention is directed to solving or improving at least one of the above technical problems.

Therefore, the first purpose of the invention is to provide a method for monitoring the water quality of a river network.

The second purpose of the invention is to provide a river network water quality monitoring device.

The third purpose of the invention is to provide a river network water quality monitoring device.

A fourth object of the present invention is to provide a readable storage medium.

In order to achieve the first object of the invention, the technical scheme of the invention provides a method for monitoring the water quality of a river network, wherein the river network comprises a plurality of rivers, and the monitoring method comprises the following steps: acquiring first data of all river monitoring sections, wherein the first data comprises a first flow, a first water level, salinity and a first pollutant concentration; acquiring second data of a sewage discharge outlet of an enterprise in the river network, wherein the second data comprises a second flow and a second pollutant concentration; acquiring meteorological data of a river network, wherein the meteorological data comprise temperature, wind speed, wind direction and rainfall; based on the first data, acquiring the predicted flow and the predicted water level of all river monitoring sections by adopting a neural network model; and acquiring a simulation result of the river network by adopting a hydrodynamic model and a water quality model based on the first data, the second data, the meteorological data, the predicted flow and the predicted water level, wherein the simulation result comprises a water level simulation result, flow simulation data, a flow field simulation result and a pollutant simulation result.

According to the technical scheme, the simulation of the river network water environment can be carried out by acquiring the obtained first data, the obtained second data, the obtained meteorological data, the predicted flow and the predicted water level and adopting a hydrodynamic model and a water quality model, so that a simulation result is obtained. By simulating the water environment of the river network, the water environment condition of the river network can be obtained more visually, the water environment in the whole river basin range of the river network is monitored more comprehensively, and the whole condition of the whole river network is convenient to master.

In addition, the technical scheme provided by the invention can also have the following additional technical characteristics:

in the above technical solution, before the first data of all river monitoring sections are obtained, the method further includes: acquiring historical data of each river monitoring section in a first time period, wherein the historical data comprises a third flow and a second water level; cleaning historical data, and carrying out normalization processing on the cleaned historical data; regarding the historical data after the normalization processing, taking the data of a plurality of continuous moments as input, and taking the data of the next moment as output to obtain an input data set and an output data set; splitting an input data set and an output data set into a training set, a verification set and a test set; and constructing a deep learning neural network model of each river monitoring section, training the deep learning neural network model by adopting a training set and a verification set corresponding to each river monitoring section, and evaluating the deep learning neural network model by adopting a test set so as to obtain the trained deep learning neural network model of each river monitoring section.

According to the technical scheme, the accuracy of the prediction result of the neural network model can be remarkably improved by acquiring the historical data, cleaning and normalizing the historical data to generate the training set, the verification set and the test set.

In any of the above technical solutions, based on the first data, the method for obtaining the predicted flow and the predicted water level of all river monitoring sections by using the neural network model specifically includes: and acquiring a first flow and a first water level of each river monitoring section at the current moment and a plurality of continuous moments before as input, and inputting the input into the trained deep learning neural network model of the river to obtain the predicted flow and the predicted water level of each river monitoring section.

The river network in the technical scheme comprises a plurality of rivers, the accurate predicted flow and predicted water level of each river monitoring section are obtained by adopting the deep learning neural network model, accurate parameters are provided for the hydrodynamic model and the water quality model, and the accuracy of the output simulation result of the hydrodynamic model and the water quality model is improved.

In any of the above technical solutions, before the hydrodynamic model and the water quality model are used to obtain the simulation result, the method further includes: modeling the river network to obtain a river network generalized diagram; and constructing a hydrodynamic model and a water quality model.

According to the technical scheme, the river network is modeled to obtain a river network generalized diagram, the overall simulation of a plurality of rivers is realized by constructing the river network generalized diagram in the river basin range, the water environment in the whole river basin range of the river network can be comprehensively monitored, and the overall situation of the whole river network can be conveniently mastered.

In any of the above technical solutions, modeling the river network to obtain a generalized diagram of the river network specifically includes: manufacturing a river channel grid based on the river network to obtain a river network generalization file; acquiring river bottom elevation data of a river and making river terrain data; carrying out interpolation processing on the river channel grids and the river channel terrain data; adding dry points to corresponding river channel grids according to actual conditions of the river channels; and adding a thin dam on the corresponding river channel grid according to the actual geographic information.

According to the technical scheme, the overall simulation of a plurality of rivers is realized by constructing a river network generalized diagram in a river basin range, the number of the river network generalized diagram grids is reduced by constructing a one-dimensional river network generalized diagram, and the overall operation speed of the model is improved.

In any of the above technical solutions, the method for monitoring river network water quality further includes: obtaining water level data, flow field data and pollutant concentration data through a hydrodynamic model and a water quality model; converting the water level data, the flow field data and the pollutant concentration data into GeoJson data; based on the GeoJson data, a GIS (Geographic Information System) visualization effect of the water level, a GIS visualization effect of the flow field, and a GIS visualization effect of the pollutant concentration are obtained.

According to the technical scheme, the water level data, the flow field data and the pollutant concentration data are converted to obtain the GIS visual effect of the water level, the GIS visual effect of the flow field and the GIS visual effect of the pollutant concentration, the obtained GIS visual effect can show the water environment more visually, and the whole situation of the whole river network can be mastered conveniently.

In any of the above technical solutions, the first data, the second data, and the meteorological data are respectively acquired through the data interface.

In the technical scheme, the first data, the second data and the meteorological data are acquired through the data interface, and the sensor does not need to be additionally installed to detect and acquire, so that the cost is saved. And moreover, the data is acquired through the data interface, the accuracy of the data source can be improved, and the data acquisition process is fast.

In order to achieve the second object of the present invention, the technical solution of the present invention provides a monitoring device for water quality of a river network, the river network includes a plurality of rivers, the monitoring device includes: the device comprises a first acquisition module, a second acquisition module, a third acquisition module, a prediction module and a simulation module; the method comprises the steps that a first acquisition module acquires first data of all river monitoring sections, wherein the first data comprise a first flow, a water level, salinity and a first pollutant concentration; the second acquisition module acquires second data of the enterprise sewage draining exit in the river network, wherein the second data comprises a second flow and a second pollutant concentration; the third acquisition module acquires meteorological data of the river network, wherein the meteorological data comprises temperature, wind speed, wind direction and rainfall; the prediction module obtains the predicted flow and the predicted water level of all river monitoring sections by adopting a neural network model based on the first data; the simulation module obtains a simulation result of the river network by adopting a hydrodynamic model and a water quality model based on the first data, the second data, the meteorological data, the predicted flow and the predicted water level, wherein the simulation result comprises a water level simulation result, flow simulation data, a flow field simulation result and a pollutant simulation result.

According to the technical scheme, the first acquisition module acquires first data of a river monitoring section, and the prediction module predicts the future flow and the future water level of the monitoring section by adopting a neural network model through the first flow and the first water level in the first data, namely the predicted flow and the predicted water level of the monitoring section. According to the technical scheme, the water level and the flow are predicted through the neural network model, and the accuracy of the predicted value can be obviously improved.

In order to achieve the third object of the present invention, the present invention provides a river network water quality monitoring device, including: the device comprises a memory and a processor, wherein the memory stores programs or instructions, and the processor executes the programs or instructions; wherein, the processor realizes the steps of the river network water quality monitoring method according to any technical scheme of the invention when executing programs or instructions.

The river network water quality monitoring device provided by the technical scheme realizes the steps of the river network water quality monitoring method according to any technical scheme of the invention, so that the river network water quality monitoring device has all the beneficial effects of the river network water quality monitoring method according to any technical scheme of the invention, and the details are not repeated herein.

In order to achieve the fourth object of the present invention, the technical solution of the present invention provides a readable storage medium, which stores a program or instructions, and when the program or instructions are executed, the steps of the method for monitoring river network water quality according to any one of the above technical solutions are implemented.

The readable storage medium provided by the technical scheme realizes the steps of the river network water quality monitoring method according to any technical scheme of the invention, so that the readable storage medium has all the beneficial effects of the river network water quality monitoring method according to any technical scheme of the invention, and the description is omitted.

Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.

Drawings

The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is one of flow charts of a method for monitoring river network water quality according to an embodiment of the invention;

fig. 2 is a second flow chart of a river network water quality monitoring method according to an embodiment of the invention;

fig. 3 is a third flow chart of a river network water quality monitoring method according to an embodiment of the invention;

fig. 4 is a fourth flowchart of a river network water quality monitoring method according to an embodiment of the invention;

fig. 5 is a fifth flowchart of a river network water quality monitoring method according to an embodiment of the invention;

fig. 6 is a sixth flowchart of a river network water quality monitoring method according to an embodiment of the invention;

FIG. 7 is a schematic view of a river network water quality monitoring device according to an embodiment of the present invention;

fig. 8 is a second schematic view of a river network water quality monitoring device according to an embodiment of the invention;

fig. 9 is a seventh flowchart of a river network water quality monitoring method according to an embodiment of the invention;

FIG. 10 is a schematic representation of the results of an illustrative river network modeling according to one embodiment of the present invention;

FIG. 11 is an enlarged partial schematic view of FIG. 10 according to one embodiment of the invention;

FIG. 12 is one of a plurality of schematic water level screenshots of an illustrative river network at different times, according to one embodiment of the invention;

fig. 13 is a second diagram illustrating water level screenshots of an exemplary river network at different times, according to an embodiment of the present invention;

FIG. 14 is a third screenshot of water levels at different times of an illustrative river network, according to one embodiment of the present invention;

FIG. 15 is one of a flow screenshot of an exemplary river network at different times, according to one embodiment of the invention;

fig. 16 is a second example of a flow screenshot of an illustrative river network at different times, according to an embodiment of the present invention;

FIG. 17 is one of a plurality of cross-sectional views of an exemplary river network of pollutants at various times in accordance with one embodiment of the present invention;

fig. 18 is a second screenshot of the pollutant at different times of the illustrative river network, in accordance with one embodiment of the present invention.

Wherein, the correspondence between the reference numbers and the part names in fig. 7 and 8 is:

100: river network water quality monitoring device, 110: first acquisition module, 120: second acquisition module, 130: third acquisition module, 140: prediction module, 150: a simulation module; 200: river network water quality monitoring device, 210: memory, 220: a processor.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.

A method, an apparatus, and a readable storage medium for monitoring river network water quality according to some embodiments of the present invention are described below with reference to fig. 1 to 18.

Example 1:

as shown in fig. 1, the present embodiment provides a method for monitoring water quality in a river network, where the river network includes a plurality of rivers, and the monitoring method includes the following steps:

step S102, acquiring first data of all river monitoring sections, wherein the first data comprises a first flow, a first water level, salinity and a first pollutant concentration;

step S104, acquiring second data of a sewage outlet of an enterprise in the river network, wherein the second data comprises a second flow and a second pollutant concentration;

step S106, acquiring meteorological data of a river network, wherein the meteorological data comprises temperature, wind speed, wind direction and rainfall;

step S108, based on the first data, acquiring the predicted flow and the predicted water level of all river monitoring sections by adopting a neural network model;

and step S110, acquiring a simulation result of the river network by adopting a hydrodynamic model and a water quality model based on the first data, the second data, the meteorological data, the predicted flow and the predicted water level, wherein the simulation result comprises a water level simulation result, flow simulation data, a flow field simulation result and a pollutant simulation result.

The river network comprises a plurality of rivers, each river is provided with a monitoring section, first data of the river monitoring section are obtained, and the future flow and the future water level of the monitoring section are predicted through the first flow and the first water level in the first data by adopting a neural network model, namely the predicted flow and the predicted water level of the monitoring section. In the embodiment, the water level and the flow are predicted through the neural network model, so that the accuracy of the predicted value can be obviously improved.

In this embodiment, the simulation of the river network water environment can be performed by using the hydrodynamic model and the water quality model through the acquired first data, second data, meteorological data, and predicted flow and predicted water level, so as to obtain a simulation result. By simulating the water environment of the river network, the water environment condition of the river network can be obtained more visually, the water environment in the whole river basin range of the river network is monitored more comprehensively, and the whole condition of the whole river network is convenient to master.

In this embodiment, the acquired first data, second data, and meteorological data may be real-time data or past historical data, and when historical data is used, simulation of a passing water environment may be implemented, and when real-time data is used, simulation of a future water environment may be implemented. The embodiment can simulate the water environment in the past or in the future, so that the river network water quality prediction time period is more flexible and the application is more extensive.

Example 2:

as shown in fig. 2, the present embodiment provides a method for monitoring water quality in a river network, and in addition to the technical features of the above embodiment, the present embodiment further includes the following technical features:

before acquiring first data of all river monitoring sections, the method further comprises the following steps:

step S202, obtaining historical data of each river monitoring section in a first time period, wherein the historical data comprises a third flow and a second water level;

step S204, cleaning the historical data, and carrying out normalization processing on the cleaned historical data;

step S206, regarding the historical data after the normalization processing, taking the data of a plurality of continuous moments as input and the data of the next moment as output to obtain an input data set and an output data set;

step S208, the input data set and the output data set are divided into a training set, a verification set and a test set.

Step S210, constructing a deep learning neural network model of each river monitoring section, training the deep learning neural network model by adopting a training set and a verification set corresponding to each river monitoring section, and evaluating the deep learning neural network model by adopting a test set so as to obtain the trained deep learning neural network model of each river monitoring section.

Furthermore, the first time period is a time period greater than or equal to 1 year, the data in the first time period are adopted to construct the neural network model, the sizes of the sample data such as a training set, a verification set and the like of the neural network model can be suitable, and the prediction result of the neural network model is accurate.

Further, the data cleaning is to perform interpolation processing on missing values in the historical data, complement the data, and then perform normalization processing on the historical data. The embodiment can repair incomplete and inaccurate historical data by cleaning the historical data to obtain completed and accurate historical data, and then train the neural network model through the complete and accurate historical data, so that the prediction accuracy of the neural network is improved, and the water level and the flow rate of the monitored cross section are more accurate.

Further, for the history data after the normalization processing, the history data at M consecutive times may be taken as one input x, and the data at M +1 time may be taken as an output y (i.e. a predicted value), and all x1, x2, x3, …, xn, and corresponding predicted values y1, y2, y3, …, yn, are sequentially slid on the history data set. Finally, obtaining an input data set X ═ X1, X2, X3,. xn }, an output data set Y ═ Y1, Y2, Y3, …, yn },

further, the input data set and the output data set are split into a training set, a verification set and a test set, for example, X, Y data are split into the training set, the verification set and the test set according to a ratio of 8:1: 1.

Further, the neural network model is a deep learning neural network model, for example, a long-short term memory artificial neural network (LSTM), EEMD-LSTM, SARIMA-LSTM, a differential Integrated Moving Average Autoregressive model (Arima), and the like may be used.

Further, when the long-short term memory artificial neural network LSTM is used for building a neural network model, parameters can be set: unit is 16, and dropout is 0.5. And training the neural network model by adopting a training set and a verification set, and evaluating the accuracy of the neural network model by using a test set. The trained network weight file may be saved with epochs 1000, batch _ size 32, and learning _ rate 0.01.

In the embodiment, the accuracy of the prediction result of the neural network model can be obviously improved by acquiring the historical data, cleaning and normalizing the historical data to generate the training set, the verification set and the test set.

Example 3:

as shown in fig. 3, the present embodiment provides a method for monitoring water quality in a river network, and in addition to the technical features of the above embodiments, the present embodiment further includes the following technical features:

based on the first data, acquiring the predicted flow and the predicted water level of all river monitoring sections by adopting a neural network model, and specifically comprising the following steps:

step S302, acquiring a first flow and a first water level of each river monitoring section at the current moment and a plurality of continuous moments before as input, and inputting the first flow and the first water level into the trained deep learning neural network model of the river to obtain the predicted flow and the predicted water level of each river monitoring section.

In this embodiment, the trained deep learning neural network model of the river is substituted into the first flow and the first water level of the current moment and the previous continuous moments of the river monitoring section, so as to obtain the predicted flow and the predicted water level of the river monitoring section.

The river network in the embodiment comprises a plurality of rivers, the accurate predicted flow and the predicted water level of each river monitoring section are obtained by adopting the deep learning neural network model, accurate parameters are provided for the hydrodynamic model and the water quality model, and the accuracy of the output simulation result of the hydrodynamic model and the water quality model is improved.

Example 4:

as shown in fig. 4, the present embodiment provides a method for monitoring water quality in a river network, and in addition to the technical features of the above embodiments, the present embodiment further includes the following technical features:

before the hydrodynamic model and the water quality model are adopted to obtain a simulation result, the method further comprises the following steps:

s402, modeling the river network to obtain a river network generalized diagram;

and S404, constructing a hydrodynamic model and a water quality model.

The river network comprises a plurality of rivers, the river network is modeled to obtain a generalized river network diagram, the generalized river network diagram in the river basin range is constructed, the overall simulation of the plurality of rivers is achieved, the water environment in the overall river basin range of the river network can be comprehensively monitored, and the overall situation of the whole river network can be conveniently mastered.

In the related art, the development of mathematical models of hydrodynamic models and water quality models has matured, and a series of software such as MIKE, EFDC, Delft3D, WASP (MIKE, EFDC, Delft3D and WASP all represent software names) and the like are presented for performing numerical simulation of water models. And performing water model numerical simulation by acquiring historical hydrological data of the river as model input, and then performing parameter verification by combining real data and a model prediction result to finally obtain an accurate hydrodynamic model and a water quality model.

Example 5:

as shown in fig. 5, the present embodiment provides a method for monitoring water quality in a river network, and in addition to the technical features of the above embodiments, the present embodiment further includes the following technical features:

modeling the river network to obtain a river network generalized diagram, and specifically comprising the following steps of:

step S502, making a river course grid based on a river course to obtain a river course generalized file;

step S504, river bottom elevation data of a river is obtained, and river terrain data are made;

step S506, performing interpolation processing on the river channel grids and the river channel terrain data;

step S508, adding dry points to corresponding river channel grids according to actual conditions of the river channels;

and step S510, adding a thin dam on the corresponding river channel grid according to the actual geographic information.

Specifically, river network modeling may include:

(1) manufacturing a river channel grid: the grd (file format) river network generalized file is produced by Global Mapper, ArcGIS, Delft3D (Global Mapper, ArcGIS, and Delft3D all represent software names).

(2) Making river terrain data: and collecting river bottom elevation data of the river to manufacture terrain data.

(3) Terrain interpolation: and carrying out interpolation processing on the river channel grids and the topographic data.

(4) Adding dry points: and adding dry points to the corresponding grids according to the actual situation of the river.

(5) Adding a thin dam: and adding a thin dam on the corresponding grid according to the actual geographic information.

In this embodiment, a river network generalized diagram is finally obtained by making river network grids, making river network terrain data, performing interpolation processing on the river network grids and the river network terrain data, adding dry points and adding thin dams.

In the embodiment, the overall simulation of a plurality of rivers is realized by constructing a river network generalized diagram in a river basin range, and the number of the river network generalized diagram grids is reduced by constructing a one-dimensional river network generalized diagram, so that the overall operation speed of the model is increased.

Example 6:

as shown in fig. 6, the present embodiment provides a method for monitoring water quality in a river network, and in addition to the technical features of the above embodiments, the present embodiment further includes the following technical features:

the method for monitoring the river network water quality further comprises the following steps:

step S602, obtaining water level data, flow field data and pollutant concentration data through a hydrodynamic model and a water quality model;

step S604, converting the water level data, the flow field data and the pollutant concentration data into GeoJson data;

and step S606, obtaining a GIS visualization effect of the water level, a GIS visualization effect of the flow field and a GIS visualization effect of the pollutant concentration based on the GeoJson data.

In this embodiment, based on GeoJson (a format for encoding various Geographic data structures) data, a GIS (Geographic Information System) visualization effect of the water level, a GIS visualization effect of the flow field, and a GIS visualization effect of the pollutant concentration are obtained, for example, a folium library may be used to read the GeoJson data respectively, and then html files of the GIS are generated respectively, and the GIS visualization effect of the water level, the GIS visualization effect of the flow field, and the GIS visualization effect of the pollutant concentration may be displayed by opening the html files with a browser. The GIS visualization can be realized by adopting a foldium (a library integrated by a LEAFLET for Python calling) library, or by adopting a GIS library such as a ceium library and a LEAFLET library (a JavaScript integrated library for front-end visualization and a html file calling), and a three-dimensional effect can be shown according to the setting of the river network parameters.

The embodiment obtains the GIS visualization effect of the water level, the GIS visualization effect of the flow field and the GIS visualization effect of the pollutant concentration by converting the water level data, the flow field data and the pollutant concentration data, and the obtained GIS visualization effect can show the water environment more visually and is convenient for mastering the whole condition of the whole river network.

Example 7:

the embodiment provides a method for monitoring river network water quality, which further includes the following technical features in addition to the technical features of the embodiment:

the first data, the second data and the meteorological data are respectively acquired through a data interface.

In this embodiment, the first data may include a first flow rate, a first water level, a salinity, and a first pollutant concentration, and the first data may be acquired through a data interface, and an interface acquisition object may be an automatic monitoring station, a website of an environmental protection agency, and the like.

In this embodiment, the second data may include a second flow rate and a second pollutant concentration, the second data may be acquired through the data interface, and the acquired object may be an environmental protection agency or the like.

In this embodiment, the meteorological data includes temperature, wind speed, wind direction, rainfall, and may be acquired through the data interface, and the acquisition object may be a meteorological bureau or the like.

In this embodiment, first data, second data and meteorological data acquire through data interface, do not need extra installation sensor to detect and acquire, save the cost. And moreover, the data is acquired through the data interface, the accuracy of the data source can be improved, and the data acquisition process is fast.

Example 8:

as shown in fig. 7, the present embodiment provides a monitoring apparatus 100 for water quality of a river network, the river network including a plurality of rivers, the monitoring apparatus 100 including: a first acquisition module 110, a second acquisition module 120, a third acquisition module 130, a prediction module 140, and a simulation module 150.

The first acquisition module 110 acquires first data of all river monitoring sections, wherein the first data comprises a first flow, a water level, salinity and a first pollutant concentration; the second obtaining module 120 obtains second data of the enterprise sewage draining exit in the river network, wherein the second data comprises a second flow rate and a second pollutant concentration; the third obtaining module 130 obtains meteorological data of the river network, wherein the meteorological data comprises temperature, wind speed, wind direction and rainfall; the prediction module 140 obtains the predicted flow and the predicted water level of all river monitoring sections by adopting a neural network model based on the first data; the simulation module 150 obtains a simulation result of the river network by using the hydrodynamic model and the water quality model based on the first data, the second data, the meteorological data, the predicted flow rate, and the predicted water level, wherein the simulation result includes a water level simulation result, flow rate simulation data, a flow field simulation result, and a pollutant simulation result.

The river network comprises a plurality of rivers, each river is provided with a monitoring section, the first acquisition module 110 acquires first data of the river monitoring section, and the prediction module 140 predicts the future flow and the future water level of the monitoring section by adopting a neural network model according to the first flow and the first water level in the first data, namely the predicted flow and the predicted water level of the monitoring section. In the embodiment, the water level and the flow are predicted through the neural network model, so that the accuracy of the predicted value can be obviously improved.

In this embodiment, the simulation module 150 may perform a simulation of the water environment of the river network by using the hydrodynamic model and the water quality model through the acquired first data, second data, meteorological data, and predicted flow and predicted water level obtained through prediction, so as to obtain a simulation result. By simulating the water environment of the river network, the water environment condition of the river network can be obtained more visually, the water environment in the whole river basin range of the river network is monitored more comprehensively, and the whole condition of the whole river network is convenient to master.

Example 9:

as shown in fig. 8, the present embodiment provides a monitoring apparatus 200 for river network water quality, including: a memory 210 and a processor 220, the memory 210 storing programs or instructions, the processor 220 executing the programs or instructions; when executing the program or the instructions, the processor 220 implements the steps of the method for monitoring river network water quality according to any embodiment of the present invention.

Example 10:

the embodiment provides a readable storage medium, which stores a program or instructions, and when the program or instructions are executed by a processor, the steps of the method for monitoring river network water quality in any one of the above embodiments are implemented.

The specific embodiment is as follows:

as shown in fig. 9, the present embodiment provides a method for monitoring water quality of a river network, which relates to the field of water environment management and the field of computer technology, and in particular relates to a method for river water pollution diffusion and river monitoring section early warning and prediction based on a Geographic Information System (GIS) and an EFDC computing engine, wherein the monitoring method includes:

step S702, acquiring real-time data;

the flow, water level, salinity and pollutant concentration data of the monitoring sections of all rivers in the river basin at the current moment are obtained through the interface, and the interface obtaining object can be an automatic monitoring station, a website of an environmental protection agency and the like.

The flow, the pollutant concentration and the like of the enterprise sewage draining exit are obtained through the interface, and the obtained object can be an environmental protection bureau and the like.

The interface is used for acquiring meteorological data, such as temperature, wind speed, wind direction, rainfall and the like, and the acquisition object can be called a meteorological bureau and the like.

Step S704, predicting future flow and future water level;

(1) collecting data: collecting historical hydrological data of rivers in N years (N is more than or equal to 1), including flow, water level and the like;

(2) training a predictive model, comprising:

data cleaning: and carrying out interpolation processing on missing values in the collected data, completing the data, and carrying out normalization processing on the data. Taking the data of M continuous time instants as the data of an x time instant and an M +1 time instant as y (namely a predicted value), and sequentially sliding all the x1, x2, x3,. xn on the data set to obtain the corresponding predicted values y1, y2, y3,. and yn. Finally, an input data set X ═ X1, X2, X3,. xn } is obtained, and an output data set Y ═ Y1, Y2, Y3,. yn }.

Data splitting: and splitting the X and Y data into a training set, a verification set and a test set according to the ratio of 8:1: 1.

Building a deep learning neural network model: using long-short term memory artificial neural network LSTM to build a network, setting parameters: unit is 16, and dropout is 0.5.

Training the LSTM model by using a training set and a verification set, and evaluating the accuracy of the model by using a test set: let epochs 1000, batch _ size 32, and leaving _ rate 0.01. And storing the trained network weight file.

(3) Predicting hydrological data by applying an LSTM model;

inputting data: the data at the current time and M previous times are used as input data x.

And inputting the input data x into the model, wherein the model prediction result is y, namely the predicted hydrologic data result. The input data includes flow rate and water level, and the output result includes future flow rate and future water level (predicted flow rate and predicted water level).

Step S706, performing water model simulation;

(1) river network modeling

Manufacturing a river channel grid: grd river net generalized file made by Globalmapper, Arcgis, Delft3D

Making river terrain data: collecting river bottom elevation data of a river to manufacture terrain data terrain interpolation: interpolating the river course grid and the topographic data

Adding dry points: adding dry points to corresponding grids according to actual conditions of river channels

Adding a thin dam: adding thin dams on corresponding grids according to actual geographic information

(2) Constructing a model;

setting parameters of the hydrodynamic model:

in the efdc. inp file and other material parameter files, the following parameters are set: setting the starting time and the ending time of simulation, the starting water level and the flow of an upstream monitoring section, the starting water level and the flow of a downstream monitoring section, the starting water level and the flow of the upstream monitoring section predicted by a hydrological prediction model (namely a neural network model), the starting water level and the flow of the downstream monitoring section predicted by the hydrological prediction model, the wind speed, the wind direction, the air temperature, the river water temperature and the salinity, the positions of a water inlet and a water outlet, an observation point, the monitoring sections, an output file format and the like.

Setting parameters of a water quality model:

in the water quality model INP file, the following parameters are set: pollutants, initial concentration, time sequence change data of discharge, positions of water inlets and water outlets, observation points, monitoring sections and the like.

Among them, the pollutants may include Kmno4 (permanganate index), Oxy (dissolved oxygen), So2 (sulfur dioxide), and the like.

(3) Running model

Running the efdc.inp file by the model, and generating results of each simulation object of the river after running, wherein the results specifically comprise grid data, water level simulation results, flow simulation data, flow field simulation results and simulation results of each pollutant factor in the river, and the data is stored in the _ cel.

Step S708, visualizing a model result GIS;

(1) hydrodynamic water level data visualization.

And converting water level data generated in the hydrodynamic model and the water quality model into GeoJson data.

And reading the GeoJson data by using a folium library to generate an html file of the GIS.

And opening html by using a browser, and displaying the GIS visualization effect of the water level.

(2) And visualizing hydrodynamic flow field data.

And converting flow field data generated in the hydrodynamic model and the water quality model into GeoJson data.

And opening html by using a browser, and displaying the GIS visualization effect of the flow field.

(3) And visualizing pollutant data of water quality.

And converting pollutant concentration data generated in the hydrodynamic model and the water quality model into GeoJson data.

And opening html by using a browser, and displaying the GIS visualization effect of the concentration of the pollutants.

The water quality monitoring is carried out on a certain river network in local coastal areas of eastern China, and the results are shown in figures 10 to 18, wherein river reach are different, concentration is different, different concentrations are displayed in different colors, the generalized result of the river network is shown in figure 10, the amplification effect of figure 10 is shown in figure 11, and after the amplification of figure 10, grids are clearly visible. For the water level visualization, fig. 12, 13, and 14 are water level screenshots at different times, and the change of the water level is clearly visible through fig. 12 to 14. For the flow visualization, fig. 15 and 16 are flow screenshots at different times, and the change of the flow speed can be clearly seen through fig. 15 and 16. For the visualization of the transport of pollutants, fig. 17 and 18 are screenshots of pollutants at different times, and the change of water quality can be clearly seen through fig. 17 and 18.

After accomplishing above-mentioned visual, the quality of water data of river monitoring section can also be drawed to this embodiment, include:

(1) the data extraction time interval is set to n minutes (n is an integer such as 30 min).

(2) Setting the name of the extracted pollutants.

(3) And recording the grid id corresponding to the cross section according to the monitoring cross sections arranged in the hydrodynamic model and the water quality model.

(4) And extracting corresponding numerical data from pollutant concentration data generated in the visualization of the pollutant data of the water quality according to the name of the substance, the time interval and the grid id, wherein the numerical data is the water quality data of the river monitoring section.

The deep learning neural network model in this embodiment may also be EEMD-LSTM, SARIMA-LSTM, Arima, etc.

In the embodiment, a folium library is used for GIS visualization, and can also be realized by GIS libraries such as ceium and leaflet, and a three-dimensional effect can be shown according to the setting of river network parameters.

The embodiment predicts the future water level and water quantity by using a neural network algorithm, and can simulate the water environment in the past and the future.

The embodiment constructs a river network generalized diagram, combines gis visualization, can dynamically display a model result through an html file, and can comprehensively monitor the water environment (water level, flow field and water quality) change condition of the whole river area range.

In the embodiment, a river network generalized diagram of the whole river area is constructed, the whole river network is monitored, the number of river network grids is controlled by using the one-dimensional river network generalized diagram, and the operation speed of a model for simulating the large-scale water environment is increased.

In the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance; the term "plurality" means two or more unless expressly limited otherwise. The terms "mounted," "connected," "fixed," and the like are to be construed broadly, and for example, "connected" may be a fixed connection, a removable connection, or an integral connection; "coupled" may be direct or indirect through an intermediary. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.

In the description of the present invention, it is to be understood that the terms "upper", "lower", "left", "right", "front", "rear", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or unit must have a specific direction, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.

In the description herein, the description of the terms "one embodiment," "some embodiments," "specific embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring water quality of a river network is characterized in that the river network comprises a plurality of rivers, and the monitoring method comprises the following steps:

acquiring first data of all river monitoring sections, wherein the first data comprises a first flow, a first water level, salinity and a first pollutant concentration;

acquiring second data of the enterprise sewage draining outlets in the river network, wherein the second data comprises a second flow and a second pollutant concentration;

acquiring meteorological data of the river network, wherein the meteorological data comprises temperature, wind speed, wind direction and rainfall;

based on the first data, acquiring the predicted flow and the predicted water level of all the river monitoring sections by adopting a neural network model;

and acquiring a simulation result of the river network by adopting a hydrodynamic model and a water quality model based on the first data, the second data, the meteorological data, the predicted flow and the predicted water level, wherein the simulation result comprises a water level simulation result, flow simulation data, a flow field simulation result and a pollutant simulation result.

2. The method for monitoring the river network water quality according to claim 1, further comprising, before the acquiring first data of all the river monitoring sections:

acquiring historical data of each river monitoring section in a first time period, wherein the historical data comprises a third flow and a second water level;

cleaning the historical data, and carrying out normalization processing on the cleaned historical data;

regarding the historical data after the normalization processing, taking data of a plurality of continuous moments as input, and taking data of the next moment as output to obtain an input data set and an output data set;

splitting the input data set and the output data set into a training set, a validation set and a test set;

and constructing a deep learning neural network model of each river monitoring section, training the deep learning neural network model by adopting the training set and the verification set corresponding to each river monitoring section, and evaluating the deep learning neural network model by adopting the test set so as to obtain the trained deep learning neural network model of each river monitoring section.

3. The river network water quality monitoring method according to claim 2, wherein the step of obtaining the predicted flow and the predicted water level of all the river monitoring sections by using a neural network model based on the first data specifically comprises the steps of:

and obtaining the first flow and the first water level of each river monitoring section at the current moment and a plurality of continuous moments before as input, and inputting the input into the trained deep learning neural network model of the river to obtain the predicted flow and the predicted water level of each river monitoring section.

4. The method for monitoring the water quality of the river network according to claim 1, wherein before the obtaining of the simulation result by using the hydrodynamic model and the water quality model, the method further comprises:

modeling the river network to obtain a river network generalized diagram;

and constructing a hydrodynamic model and a water quality model.

5. The method for monitoring river network water quality according to claim 4, wherein the modeling of the river network to obtain a river network generalized diagram specifically comprises:

manufacturing a river channel grid based on the river network to obtain a river network generalization file;

acquiring river bottom elevation data of the river and making river terrain data;

performing interpolation processing on the river channel grids and the river channel terrain data;

adding dry points to corresponding river channel grids according to actual conditions of the river channels;

and adding a thin dam on the corresponding river channel grid according to the actual geographic information.

6. The method for monitoring the river network water quality according to claim 1, further comprising:

obtaining water level data, flow field data and pollutant concentration data through the hydrodynamic model and the water quality model;

converting the water level data, the flow field data and the pollutant concentration data into GeoJson data;

and obtaining a GIS visualization effect of the water level, a GIS visualization effect of the flow field and a GIS visualization effect of the pollutant concentration based on the GeoJson data.

7. The method for monitoring the water quality of the river network according to any one of claims 1 to 6, wherein the first data, the second data and the meteorological data are acquired through data interfaces respectively.

8. A monitoring device (100) of river network water quality, characterized in that the river network comprises a plurality of rivers, the monitoring device (100) comprises:

a first acquisition module (110), wherein the first acquisition module (110) acquires first data of all river monitoring sections, and the first data comprises a first flow rate, a water level, salinity and a first pollutant concentration;

the second acquisition module (120) acquires second data of a sewage discharge outlet of the enterprise in the river network, wherein the second data comprises a second flow and a second pollutant concentration;

a third obtaining module (130), wherein the third obtaining module (130) obtains meteorological data of the river network, and the meteorological data comprises temperature, wind speed, wind direction and rainfall;

the prediction module (140), the prediction module (140) adopts a neural network model based on the first data to obtain the predicted flow and the predicted water level of all the river monitoring sections;

a simulation module (150), wherein the simulation module (150) obtains a simulation result of the river network by using a hydrodynamic model and a water quality model based on the first data, the second data, the meteorological data, the predicted flow and the predicted water level, and the simulation result includes a water level simulation result, flow simulation data, a flow field simulation result and a pollutant simulation result.

9. A monitoring device (200) for river network water quality, comprising:

a memory (210) storing programs or instructions;

a processor (220) that executes the program or instructions;

wherein the processor (220), when executing the program or instructions, performs the steps of the method for monitoring river network water quality as claimed in any one of claims 1 to 7.

10. A readable storage medium, characterized in that the readable storage medium stores thereon a program or instructions, which when executed by a processor, implements the steps of the method for monitoring river network water quality according to any one of claims 1 to 7.