CN113868223A - Water quality monitoring method, device and system and readable storage medium - Google Patents
Water quality monitoring method, device and system and readable storage medium Download PDFInfo
- Publication number
- CN113868223A CN113868223A CN202111026757.4A CN202111026757A CN113868223A CN 113868223 A CN113868223 A CN 113868223A CN 202111026757 A CN202111026757 A CN 202111026757A CN 113868223 A CN113868223 A CN 113868223A
- Authority
- CN
- China
- Prior art keywords
- data
- water quality
- model
- quality monitoring
- time
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 312
- 238000012544 monitoring process Methods 0.000 title claims abstract description 257
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 53
- 231100000719 pollutant Toxicity 0.000 claims abstract description 53
- 238000003062 neural network model Methods 0.000 claims abstract description 32
- 238000012806 monitoring device Methods 0.000 claims abstract description 7
- 230000015654 memory Effects 0.000 claims description 18
- 239000000356 contaminant Substances 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000009792 diffusion process Methods 0.000 claims description 4
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000004088 simulation Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 13
- 238000011144 upstream manufacturing Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 7
- 239000003086 colorant Substances 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000012800 visualization Methods 0.000 description 6
- 238000003911 water pollution Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 238000012795 verification Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000019771 cognition Effects 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000010865 sewage Substances 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
Abstract
The invention provides a water quality monitoring method, a water quality monitoring device, a water quality monitoring system and a readable storage medium. Wherein, the water quality monitoring method comprises the following steps: acquiring starting time, ending time and first hydrological data corresponding to the starting time; inputting the starting time, the ending time and the first hydrological data into a first preset model, and generating second hydrological data corresponding to the ending time; acquiring monitoring data and pollutant parameters of a plurality of monitoring points in a target area; and inputting the starting time, the ending time, the monitoring data, the first hydrological data, the second hydrological data and the pollutant parameters into a second preset model to generate a water quality monitoring result corresponding to the target area. According to the technical scheme provided by the invention, the hydrologic data is predicted through the neural network model, the current hydrologic data and the predicted hydrologic data are used as calibration parameters for water quality monitoring, the water quality of the water body in the target area is monitored, and the accuracy of a water quality monitoring result is improved.
Description
Technical Field
The invention relates to the technical field of water quality monitoring, in particular to a water quality monitoring method, a water quality monitoring device, a water quality monitoring system and a readable storage medium.
Background
In the related art, a Delft3D hydrodynamic force-water quality model is adopted to monitor and predict the river water quality, wherein model parameters are calibrated by using historical hydrographic data, however, the hydrographic data are greatly changed every year, and the hydrodynamic force is calibrated by using the historical hydrographic data with a large error, so that the water quality monitoring error is increased.
Disclosure of Invention
The present invention is directed to solving at least the problems of the prior art or the related art.
To this end, a first aspect of the invention provides a water quality monitoring method.
The second aspect of the invention also provides a water quality monitoring device.
The third aspect of the invention also provides a water quality monitoring system.
The fourth aspect of the present invention also provides a readable storage medium.
In view of the above, the first aspect of the present invention provides a water quality monitoring method, including: acquiring starting time, ending time and first hydrological data corresponding to the starting time; inputting the starting time, the ending time and the first hydrological data into a first preset model, and generating second hydrological data corresponding to the ending time; acquiring monitoring data and pollutant parameters of a plurality of monitoring points in a target area; and inputting the starting time, the ending time, the monitoring data, the first hydrological data, the second hydrological data and the pollutant parameters into a second preset model to generate a water quality monitoring result corresponding to the target area.
The water quality monitoring method provided by the invention obtains the starting time and the ending time of water quality monitoring, wherein the starting time can be the current time, and the ending time can be the future time. And acquiring first hydrological data corresponding to the starting time, specifically, the first hydrological data is water level data and/or flow data corresponding to the water quality monitoring target.
And further, inputting the starting time, the ending time and the first hydrologic data into a first preset model, wherein the first preset model is a hydrologic prediction model, predicting future hydrologic data through the hydrologic prediction model to obtain second hydrologic data corresponding to the ending time, and the second hydrologic data is a predicted hydrologic data result.
Further, monitoring data and pollution parameters of a plurality of monitoring points in the target area are obtained, wherein the monitoring points are monitoring sites which are deployed at the upstream and the downstream of the whole water body in the target monitoring area and branch flows. Discrete data of the starting time, the ending time, monitoring data of a monitoring point, pollutant parameters, first hydrological data and second hydrological data obtained by prediction of a first preset model are input into a second preset model, wherein the second preset model can be a Delft3D model, and the Delft3D model can simulate and predict the future water quality of the whole water body in the target area through the discrete data, so that a water quality monitoring result corresponding to the target area is obtained.
Compared with the prior art that only historical hydrological data are used as parameters of a Delft3D model, the water quality monitoring method provided by the invention has the technical problem that the water quality simulation error is large due to the fact that the hydrological data are large in real-time change and the hydrodynamic force is large in error when the historical hydrological data are used for calibrating, and the prediction hydrological data are obtained through a neural network model, and the hydrological data collected in real time and the prediction hydrological data are used as parameters of the Delft3D model to monitor the water quality of the whole water body in a target area. Can accurately grasp that the current time receives which data variable influences more greatly, effectively predict the quality of water situation in the future, improve the precision of water quality monitoring result.
According to the water quality monitoring method provided by the invention, the following additional technical characteristics can be provided:
in the above technical solution, further, the second preset model includes a hydrodynamic model and a water quality model, and the step of inputting the start time, the end time, the monitoring data, the first hydrologic data, the second hydrologic data and the pollutant parameters into the second preset model to generate a water quality monitoring result corresponding to the target area specifically includes: inputting the starting time, the ending time, the monitoring data, the first hydrological data and the second hydrological data into a hydrodynamic model, and generating third hydrological data corresponding to a plurality of preset time points; inputting the third hydrological data and the pollutant parameters into a water quality model to generate water quality pollution results corresponding to a plurality of preset time points; and generating a water quality monitoring result according to the third hydrological data and the water quality pollution result.
In the technical scheme, the second preset model can be a Delft3D model, the Delft3D model comprises a hydrodynamic model and a water quality model, and the hydrodynamic field and the water quality field of the whole water body in the target area are simulated and predicted by inputting hydrological data, monitoring data and discrete data of pollutant parameters of monitoring points of upstream, downstream and tributaries.
Specifically, after obtaining predicted hydrographic data by using the hydrographic prediction model, inputting hydrographic data corresponding to the current time, the predicted hydrographic data, the start time, the end time, and monitoring data of the monitoring points into the hydrodynamic model, and obtaining third hydrographic data of each grid point corresponding to a plurality of preset time points, namely, a water level simulation result and/or a flow simulation result of the whole water body in the target area. Further, when the hydrodynamic model is generated, the output values of the water level data and/or the flow data of each grid point corresponding to one preset time point are immediately input into the water quality model at the preset time point, and the simulation result of the pollutant factor in the target area is obtained by combining the pollutant parameters. And summarizing the generated water level simulation result and/or flow simulation result and the simulation result of the pollutant factor to obtain the water quality monitoring result in the target area. The water quality monitoring method has the advantages that the water power model and the water quality model are synchronously and tightly coupled, future water quality of the whole water body in a target area is monitored, pollution factors of the whole water body are monitored and predicted, theoretical basis is provided for water ecological protection, and powerful support is provided for making scientific and effective water pollution control and treatment schemes.
It is understood that the plurality of preset time points may be set as the time points for extracting the water quality monitoring data according to the start time and the end time, for example, the water quality monitoring time may be determined to be 3 days according to the start time and the end time, and the preset time points for extracting the water quality monitoring results may be set to be extracted once per hour.
In any of the above technical solutions, further, the water quality monitoring method further includes: establishing a first preset model based on the neural network model; acquiring historical hydrological data in a preset time period; filling missing data in the historical hydrological data by adopting a Lagrange interpolation method to obtain the filled complete hydrological data; and training a first preset model according to the complete hydrological data, and optimizing parameters of the first preset model.
In the technical scheme, a first preset model, namely a hydrological prediction model, is established based on a neural network model. And acquiring historical hydrological data in a preset time period from the historical water quality monitoring data, filling missing data in the historical hydrological data by adopting a Lagrange interpolation method to obtain complete historical hydrological data, and carrying out normalization processing on the data. Dividing the filled hydrological data into a training set, a verification set and a test set, training a first preset model according to the training set and the verification set, optimizing parameters of the first preset model, and evaluating the accuracy of the first preset model according to the test set so as to ensure the reliability of the first preset model on the research of the water environment and obtain a final reasonable and accurate hydrological prediction result.
In any of the above technical solutions, further, the neural network model includes: a long-short term memory neural network model, a recurrent neural network model, a back propagation neural network model, or a convolutional neural network model.
In the technical scheme, the first preset model can be established through a plurality of neural network models, such as a long-short term memory neural network model, a cyclic neural network model, a back propagation neural network model and a convolutional neural network model, so that the flexibility and the applicability of the hydrological prediction model construction are effectively improved.
In any of the above technical solutions, further, after generating the water quality monitoring result corresponding to the target area, the method further includes: and (5) visually displaying the water quality monitoring result.
According to the technical scheme, after the water quality monitoring result of the whole water body in the target area is obtained, the visual image layer of the whole water body is output, the water body monitoring section result is displayed, and the positioning query of the water quality simulation monitoring result is supported. The classification state and the pollution condition of the water quality of the whole water body in the target area are dynamically displayed in real time on a three-dimensional space by combining the water quality monitoring result with a visualization technology, so that the real-time evaluation of the current water quality situation is facilitated, the overall cognition and the grasp of the water quality state of the target area are improved, and a decision support is provided for water pollution prevention and treatment.
In any of the above technical solutions, further, the hydrologic data includes at least one of: water level data and flow data; the monitoring data includes at least one of: location data, meteorological data and water temperature data are monitored.
In the technical scheme, the hydrological data comprises water level data and/or flow data, the water level and/or flow of the whole water body at the current time are determined and collected according to items to be monitored in the water quality monitoring target, and then the future water level and/or flow of the water body are predicted, so that the flexibility and the applicability of water quality monitoring are effectively improved. Further, the monitoring data includes monitoring location data, meteorological data, and water temperature data. By flexibly applying the monitoring data, the characteristics which can be provided by the monitoring data are reasonably found, the potential influence of the monitoring data on the water quality monitoring result is fully considered, and the accuracy of the water quality monitoring result is effectively improved.
The meteorological data comprises data such as atmospheric pressure, evapotranspiration, rainfall, cloud cover, wind power, wind speed and the like.
In addition, hydrological data of the current time can be acquired from a website of an automatic monitoring station or a central office through an interface, and meteorological data can be acquired from a meteorological office through an interface.
In any of the above embodiments, further the contaminant parameter comprises at least one of: contaminant species, initial contaminant concentration, and contaminant diffusion coefficient.
In this embodiment, the contaminant parameters include the contaminant type, initial contaminant concentration, and contaminant diffusion coefficient. By flexibly applying pollutant parameters, detection results of all pollutant factors in the whole water body in a target area are obtained, the influence degree of different pollutant factors on water quality is determined, and powerful support is provided for making scientific and effective water pollution control and treatment schemes.
According to a second aspect of the present invention, there is provided a water quality monitoring device comprising: the first acquisition module is used for acquiring the starting time, the ending time and first hydrological data corresponding to the starting time; the first generation module is used for inputting the starting time, the ending time and the first hydrological data into a first preset model and generating second hydrological data corresponding to the ending time; the second acquisition module is used for acquiring monitoring data and pollutant parameters of a plurality of monitoring points in the target area; and the second generation module is used for inputting the starting time, the ending time, the monitoring data, the first hydrologic data, the second hydrologic data and the pollutant parameters into a second preset model to generate a water quality monitoring result corresponding to the target area.
The water quality monitoring device provided by the invention obtains the starting time and the ending time of water quality monitoring, wherein the starting time can be the current time, and the ending time can be the future time. And acquiring first hydrological data corresponding to the starting time, specifically, the first hydrological data is water level data and/or flow data corresponding to the water quality monitoring target.
And further, inputting the starting time, the ending time and the first hydrologic data into a first preset model, wherein the first preset model is a hydrologic prediction model, predicting future hydrologic data through the hydrologic prediction model to obtain second hydrologic data corresponding to the ending time, and the second hydrologic data is a predicted hydrologic data result.
Further, monitoring data and pollution parameters of a plurality of monitoring points in the target area are obtained, wherein the monitoring points are monitoring sites which are deployed at the upstream and the downstream of the whole water body in the target monitoring area and branch flows. Discrete data of the starting time, the ending time, monitoring data of a monitoring point, pollutant parameters, first hydrological data and second hydrological data obtained by prediction of a first preset model are input into a second preset model, wherein the second preset model can be a Delft3D model, and the Delft3D model can simulate and predict the future water quality of the whole water body in the target area through the discrete data, so that a water quality monitoring result corresponding to the target area is obtained.
Compared with the prior art, the water quality monitoring device provided by the invention only uses historical hydrological data as the parameters of the Delft3D model, but the hydrological data is large in real-time change, and the hydrodynamic force is calibrated by using the historical hydrological data to have large errors, so that the technical problem of large water quality simulation errors is solved. Can accurately grasp that the current time receives which data variable influences more greatly, effectively predict the quality of water situation in the future, improve the water quality monitoring precision.
According to a third aspect of the present invention, a water quality monitoring system is provided, which comprises a memory, wherein the memory stores programs or instructions; and the processor is connected with the memory and is configured to execute the program or the instructions to realize the water quality monitoring method provided by the first aspect. Therefore, the water quality monitoring system has all the beneficial effects of the water quality monitoring method provided by the first aspect, and is not repeated herein.
According to a fourth aspect of the present invention, there is provided a readable storage medium having stored thereon a program or instructions which, when executed by a processor, performs the water quality monitoring method set forth in the first aspect. Therefore, the readable storage medium has all the beneficial effects of the water quality monitoring method provided by the first aspect, and redundant description is omitted for avoiding repetition.
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 shows one of the flow diagrams of a water quality monitoring method according to an embodiment of the present invention;
FIG. 2 is a second schematic flow chart of a water quality monitoring method according to an embodiment of the present invention;
FIG. 3 is a third schematic flow chart of a water quality monitoring method according to an embodiment of the present invention;
FIG. 4 is a fourth schematic flow chart of the water quality monitoring method according to the embodiment of the invention;
FIG. 5 is a schematic flow chart of a water quality monitoring method according to an embodiment of the present invention;
FIG. 6 shows one of the schematic diagrams of the water quality monitoring results of the embodiment of the present invention;
FIG. 7 is a second schematic diagram showing the water quality monitoring result according to the embodiment of the present invention;
FIG. 8 is a third diagram showing the water quality monitoring result according to the embodiment of the present invention;
FIG. 9 is a fourth diagram showing the water quality monitoring result according to the embodiment of the present invention;
FIG. 10 is a fifth schematic diagram showing the water quality monitoring results of the embodiment of the present invention;
FIG. 11 shows a sixth schematic diagram of the water quality monitoring results of an embodiment of the present invention;
FIG. 12 shows a seventh schematic diagram of the water quality monitoring results of an embodiment of the present invention;
FIG. 13 shows an eighth schematic diagram of the water quality monitoring results of an embodiment of the present invention;
FIG. 14 shows a ninth schematic diagram of the water quality monitoring results of an embodiment of the present invention;
FIG. 15 is a tenth of a schematic diagram showing the results of water quality monitoring according to an embodiment of the present invention;
FIG. 16 is a block diagram illustrating a long short term memory neural network model in accordance with an embodiment of the present invention;
fig. 17 shows a schematic block diagram of a water quality monitoring apparatus according to an embodiment of the present invention.
Wherein, the correspondence between the reference numbers and the names of the components in fig. 17 is:
1700, 1702 first obtaining module, 1704 first generating module, 1706 second obtaining module, 1708 second generating module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the descriptions in this patent document as to "first", "second", "third", etc. are for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicit to the number of technical features indicated. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of the feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In addition, the technical solutions in the embodiments of the present invention may be combined with each other, but it must be based on the realization of those skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination of technical solutions should not be considered to exist, and is not within the protection scope of the present invention.
Water quality monitoring methods, devices, systems and readable storage media of some embodiments of the invention are described below with reference to fig. 1-17.
Example 1:
as shown in fig. 1, according to an embodiment of the present invention, there is provided a water quality monitoring method including:
102, acquiring starting time, ending time and first hydrological data corresponding to the starting time;
step 104, inputting the starting time, the ending time and the first hydrologic data into a first preset model, and generating second hydrologic data corresponding to the ending time;
and step 108, inputting the starting time, the ending time, the monitoring data, the first hydrologic data, the second hydrologic data and the pollutant parameters into a second preset model, and generating a water quality monitoring result corresponding to the target area.
The water quality monitoring method provided by this embodiment obtains the start time and the end time of water quality monitoring, where the start time may be the current time, and the end time may be the future time. And acquiring first hydrological data corresponding to the starting time, specifically, the first hydrological data is water level data and/or flow data corresponding to the water quality monitoring target.
And further, inputting the starting time, the ending time and the first hydrologic data into a first preset model, wherein the first preset model is a hydrologic prediction model, predicting future hydrologic data through the hydrologic prediction model to obtain second hydrologic data corresponding to the ending time, and the second hydrologic data is a predicted hydrologic data result.
Further, monitoring data and pollution parameters of a plurality of monitoring points in the target area are obtained, wherein the monitoring points are monitoring sites which are deployed at the upstream and the downstream of the whole water body in the target monitoring area and branch flows. Discrete data of the starting time, the ending time, monitoring data of a monitoring point, pollutant parameters, first hydrological data and second hydrological data obtained by prediction of a first preset model are input into a second preset model, wherein the second preset model can be a Delft3D model, and the Delft3D model can simulate and predict the future water quality of the whole water body in the target area through the discrete data, so that a water quality monitoring result corresponding to the target area is obtained.
Compared with the prior art in which only historical hydrographic data are used as Delft3D model parameters, the water quality monitoring method provided by the embodiment has the technical problems that the hydrographic data change greatly in real time, and the hydrodynamic force is calibrated by using the historical hydrographic data to have a large error, so that the water quality simulation error is large, and the technical problems that predicted hydrographic data are obtained through a neural network model, and the hydrographic data and the predicted hydrographic data which are collected in real time are used as the parameters of a Delft3D model to monitor the water quality of the whole water body in a target area are solved. Can accurately grasp that the current time receives which data variable influences more greatly, effectively predict the quality of water situation in the future, improve the water quality monitoring precision.
Further, the hydrological data includes at least one of: water level data and flow rate data. According to the items to be monitored in the water quality monitoring target, the water level and/or the flow of the whole water body at the current time are determined and collected, and then the future water level and/or the future flow of the water body are predicted, so that the flexibility and the applicability of water quality monitoring are effectively improved.
Further, the monitoring data includes monitoring location data, meteorological data, and water temperature data. By flexibly applying the monitoring data, the characteristics which can be provided by the monitoring data are reasonably found, the potential influence of the monitoring data on the water quality monitoring result is fully considered, and the accuracy of the water quality monitoring result is effectively improved.
The meteorological data comprises data such as atmospheric pressure, evapotranspiration, rainfall, cloud cover, wind power, wind speed and the like.
In addition, hydrological data of the current time can be acquired from a website of an automatic monitoring station or a central office through an interface, and meteorological data can be acquired from a meteorological office through an interface.
Further, the contaminant parameter includes at least one of: contaminant species, initial contaminant concentration, and contaminant diffusion coefficient. By flexibly applying pollutant parameters, detection results of all pollutant factors in the whole water body in a target area are obtained, the influence degree of different pollutant factors on water quality is determined, and powerful support is provided for making scientific and effective water pollution control and treatment schemes.
Wherein, the pollutant parameters also comprise the pollutant discharge amount of the enterprise sewage discharge outlet.
Example 2:
as shown in fig. 2, according to an embodiment of the present invention, there is provided a water quality monitoring method including:
and 212, generating a water quality monitoring result according to the third hydrological data and the water quality pollution result.
In this embodiment, the second predetermined model may be a Delft3D model, the Delft3D model includes a hydrodynamic model and a water quality model, and the hydrodynamic field and the water quality field of the whole water body in the target area are simulated and predicted by inputting discrete data of hydrological data, monitoring data and pollutant parameters of monitoring points of upstream, downstream and branch flows.
Specifically, after obtaining predicted hydrographic data by using the hydrographic prediction model, inputting hydrographic data corresponding to the current time, the predicted hydrographic data, the start time, the end time, and monitoring data of the monitoring points into the hydrodynamic model, and obtaining third hydrographic data of each grid point corresponding to a plurality of preset time points, namely, a water level simulation result and/or a flow simulation result of the whole water body in the target area. Further, when the hydrodynamic model is generated, the output values of the water level data and/or the flow data of each grid point corresponding to one preset time point are immediately input into the water quality model at the preset time point, and the simulation result of the pollutant factor in the target area is obtained by combining the pollutant parameters. And summarizing the generated water level simulation result and/or flow simulation result and the simulation result of the pollutant factor to obtain the water quality monitoring result in the target area. The water quality monitoring method has the advantages that the water power model and the water quality model are synchronously and tightly coupled, future water quality of the whole water body in a target area is monitored, pollution factors of the whole water body are monitored and predicted, theoretical basis is provided for water ecological protection, and powerful support is provided for making scientific and effective water pollution control and treatment schemes.
It is understood that the plurality of preset time points may be set as the time points for extracting the water quality monitoring data according to the start time and the end time, for example, the water quality monitoring time may be determined to be 3 days according to the start time and the end time, and the preset time points for extracting the water quality monitoring results may be set to be extracted once per hour.
Example 3:
as shown in fig. 3, according to an embodiment of the present invention, there is provided a water quality monitoring method including:
step 312, inputting the start time, the end time and the first hydrologic data into a first preset model, and generating second hydrologic data corresponding to the end time;
step 314, acquiring monitoring data and pollutant parameters of a plurality of monitoring points in the target area;
and step 316, inputting the starting time, the ending time, the monitoring data, the first hydrologic data, the second hydrologic data and the pollutant parameters into a second preset model, and generating a water quality monitoring result corresponding to the target area.
In this embodiment, a first preset model, i.e., a hydrologic prediction model, is established based on a neural network model. And acquiring historical hydrological data in a preset time period from the historical water quality monitoring data, filling missing data in the historical hydrological data by adopting a Lagrange interpolation method to obtain complete historical hydrological data, and carrying out normalization processing on the data. Dividing the filled hydrological data into a training set, a verification set and a test set, training a first preset model according to the training set and the verification set, optimizing parameters of the first preset model, and evaluating the accuracy of the first preset model according to the test set so as to ensure the reliability of the first preset model on the research of the water environment and obtain a final reasonable and accurate hydrological prediction result.
In a specific embodiment, the long-short term memory neural network is used to build a hydrological prediction model, as shown in fig. 16, the hydrological prediction model is a chain structure of the long-short term memory neural network, the chain structure has 4 neural networks, and parameters of the long-short term memory neural network are set as follows: the size units of the hidden layer in the unit is 16, and the unit number dropout in the neural network is removed from the network is 0.5; training all training samples in the model for epochs 1000; the number of training samples batch-size is 32; the learning rate is 0.01. And taking the set parameters of the long-term and short-term memory neural network as second preset model parameters. Further, collecting N years of historical hydrological data of the water body in the target area, whereinN is more than or equal to 1. And carrying out interpolation processing on missing values in the collected hydrological data, completing the data, and carrying out normalization processing on the data. Taking the continuous M times of data as xnFor example, setting the historical hydrological data of 1 year of the water body in the target area to be collected, wherein the collection starting time is 2019-09-01-00:00, and the data of 4 continuous hours is taken as an xn. Taking the data of M +1 times as a predicted value yn. In the processed historical hydrological data, all x are taken in a sliding mode according to the time sequence1，x2，x3，...，xnCorresponding predicted value y1，y2，y3，...，yn. Finally, the input data set X is obtained as the { X ═ X1，x2，x3，...，xnH, outputting a data set Y ═ Y1，y2，y3，...，yn}. Input data set X and output data set Y are arranged as follows 8: 1: the scale of 1 is divided into a training set, a validation set, and a test set. Training the model using the training set and the validation set, and optimizing the model parameters. And evaluating the model accuracy according to the test set, for example, if the model accuracy reaches 70%, storing the trained model, and if the model accuracy does not reach 70%, selecting more historical hydrological data to train the model again until the model accuracy reaches 70%.
Further, the neural network model includes: a long-short term memory neural network model, a recurrent neural network model, a back propagation neural network model, or a convolutional neural network model. The first preset model can be established through a plurality of neural network models, such as a long-short term memory neural network model, a cyclic neural network model, a back propagation neural network model and a convolution neural network model, so that the flexibility and the applicability of the hydrological prediction model construction are effectively improved.
In addition, the network model also comprises a bidirectional long and short word memory model.
Example 4:
as shown in fig. 4, according to an embodiment of the present invention, there is provided a water quality monitoring method including:
and step 410, visually displaying the water quality monitoring result.
In the embodiment, after the water quality monitoring result of the whole water body in the target area is obtained, the visual image layer of the whole water body is output, the water body monitoring result is displayed, and the positioning query of the water quality simulation monitoring result is supported. The classification state and the pollution condition of the water quality of the whole water body in the target area are dynamically displayed in real time on a three-dimensional space by combining the water quality monitoring result with a visualization technology, so that the real-time evaluation of the current water quality situation is facilitated, the overall cognition and the grasp of the water quality state of the target area are improved, and a decision support is provided for water pollution prevention and treatment.
In a specific embodiment, a Geographic Information System (GIS) technology is used for realizing visual application of a Delft3D model on an electronic map corresponding to a target area, a depth optimization traversal algorithm is used for searching all river channel path names in the target area in the Delft3D model, then the electronic map is used as a base map, all river channel paths are drawn on the map in a covering manner, the water quality spatial distribution state is vividly and visually displayed, and the requirements of a user on the integrated GIS and water environment monitoring System are met. Specifically, as shown in fig. 6, the river water quality monitoring result of the whole water body on the electronic map of the target area is shown, where a "solid line" represents a river, and a "dotted line" represents a street, 5 water quality grades are divided, and the water quality grades correspond to different color components, respectively, and the corresponding water quality grades are determined according to the display color of the river. As shown in fig. 7, the grid water quality monitoring result after the selected area is amplified is shown, where "grid" represents a river channel, and "dotted line" represents a street, 5 water quality grades are divided, and correspond to different color components, respectively, and the water quality grades corresponding to different river channel areas are determined according to the grid color of the area of the amplified river channel. As shown in fig. 8 and 9, for different preset time points, river water level monitoring results of the whole water body on the electronic map of the target area are obtained, where "solid line" represents a river, and "dotted line" represents a street, 6 water level levels are divided, and correspond to different color components, and different river display colors correspond to different water level levels, and a water level change trend is displayed in real time according to the water level colors of the river. As shown in fig. 10 and 11, for different preset time points, river flow monitoring results of the whole water body on the electronic map of the target area are obtained, where a "solid line" represents a river, a "dotted line" represents a street, 6 flow levels are divided, and correspond to different color components, and different river display colors correspond to different flow levels, and a flow change trend is displayed in real time according to the river flow colors. As shown in fig. 12 and 13, for different preset time points, river flow rate monitoring results of the whole water body on the electronic map of the target area are obtained, where a "solid line" represents a river, a "dotted line" represents a street, 6 flow rate levels are divided, and correspond to different color components, and different river display colors correspond to different flow rate levels, and a flow rate variation trend is displayed in real time according to the flow rate colors of the river. As shown in fig. 14 and 15, for different preset time points, river pollution monitoring results of the whole water body on the electronic map of the target area are obtained, where "solid line" represents a river, and "dotted line" represents a street, 6 pollution levels are divided, and correspond to different color components, and different river display colors correspond to different pollution levels, and the water body pollution trend is displayed in real time according to the water quality color of the river.
Example 5:
as shown in fig. 5, according to an embodiment of the present invention, a water quality monitoring method is provided, which includes:
and step 512, extracting water quality data of the river monitoring section in the water quality monitoring result.
In this embodiment, the flow, water level, salinity and pollutant concentration data of all monitoring sections of the river at the starting time are obtained through the interface, wherein the interface obtaining object can be an automatic monitoring station, a website of an environmental protection agency and the like. And acquiring the flow, the pollutant concentration and the like of the sewage draining outlet of the enterprise through the interface, wherein the acquired object can be an environmental protection bureau and the like. And acquiring meteorological data such as temperature, wind speed, wind direction and the like through an interface, wherein the acquisition object can be a meteorological bureau and the like. Further, the data of the starting time is input into the first preset model as input data, and a hydrological data result of the predicted ending time is obtained.
Further, the river course mesh is manufactured, and the method comprises the steps of manufacturing river course boundaries, drawing spline curves and generating meshes. Specifically, river bottom elevation data of a river is collected and manufactured into river terrain data. And carrying out interpolation processing on the river channel grids and the topographic data. And adding dry points to the corresponding grids according to the actual situation of the river. And adding a thin dam on the corresponding grid according to the actual geographic information.
Further, Delft3D model parameters were set. Specifically, in a hydrodynamic model MDF (extension: MDF) file, a start time and an end time of monitoring, a start water level and/or a flow rate of an upstream monitoring section, a start water level and/or a flow rate of a downstream monitoring section, a start water level and/or a flow rate of an upstream monitoring section predicted by a first preset model, a start water level and/or a flow rate of a downstream monitoring section predicted by a first preset model, meteorological data such as wind speed, wind direction, temperature, salinity, gravitational acceleration, water density, air density, wind resistance coefficient, hydrodynamic data such as riverbed roughness, horizontal vortex viscosity coefficient, positions of a water inlet and a water outlet, a monitoring point position and a monitoring section are set as input parameters of the hydrodynamic model, and a hydrodynamic model output file format is set.
Further, in a water quality model INP (extension. INP) file, a start time and an end time that are consistent with the hydrodynamic model, pollutant and initial concentration, dispersion coefficient, positions of a water inlet and a water outlet, a monitoring point position, a monitoring section are set as water quality model input parameters, and a water quality model output file format is set.
Further, after the Delft3D model calculation engine Delft3D-Flow operates by calling the MDF file, water quality monitoring results of each monitored object of the river channel are generated, and the water quality monitoring results specifically include grid data, water level monitoring results, Flow monitoring data, Flow field monitoring results and monitoring results of each pollutant factor in the river.
Further, the hydrodynamic water level data are analyzed, the analyzed hydrodynamic water level data are visual, and the GIS visual effect of the water level can be displayed.
Furthermore, the flow data of the hydrodynamic force is analyzed, the analyzed flow data of the hydrodynamic force is visualized, and the GIS visualization effect of the flow can be displayed.
Furthermore, the hydrodynamic flow field data are analyzed, and the analyzed hydrodynamic flow field data are visualized, so that the GIS visualization effect of the flow field can be displayed.
Furthermore, the pollutant data of the water quality is analyzed, and the analyzed pollutant data of the water quality is visualized, so that the GIS visualization effect of the flow field can be displayed.
Further, the time interval for extracting the water quality data in the water quality monitoring result is set, the time point for extracting the data is determined according to the time interval, for example, the starting time of the water quality monitoring is 2021-09-01-00:00, the ending time is 2021-09-01-24:00, and the time interval for extracting the data can be set to be 30 minutes, that is, the time point is 00:30, 01:00, 01:30, and the like. Setting and extracting pollutant names, recording grid numbers corresponding to the cross sections according to the set monitoring cross sections, and extracting corresponding numerical data from the generated pollutant water quality visualization data according to the material names, the time intervals and the grid numbers, wherein the numerical data are the water quality data of the river monitoring cross sections.
The water quality monitoring method provided by the embodiment uses the deep learning model to predict the hydrological data, so that the construction process of the Delft3D hydrodynamic-water quality model is improved, the simulation result of the Delft3D hydrodynamic-water quality model is combined with the GIS, and the requirements of users on an integrated geographic information system and a water environment simulation system are met.
Example 6:
as shown in fig. 17, according to an embodiment of the second aspect of the present invention, a water quality monitoring apparatus 1700 is provided, including: a first obtaining module 1702, configured to obtain a start time, an end time, and first hydrologic data corresponding to the start time; a first generation module 1704, configured to input the start time, the end time, and the first hydrologic data into a first preset model, and generate second hydrologic data corresponding to the end time; a second obtaining module 1706, configured to obtain monitoring data and pollutant parameters of multiple monitoring points in the target area; and a second generating module 1708, configured to input the start time, the end time, the monitoring data, the first hydrologic data, the second hydrologic data, and the pollutant parameter into a second preset model, and generate a water quality monitoring result corresponding to the target area.
The water quality monitoring apparatus 1700 according to this embodiment acquires a start time and an end time of water quality monitoring through the first acquiring module 1702, where the start time may be a current time, and the end time may be a future time. And acquiring first hydrological data corresponding to the starting time, specifically, the first hydrological data is water level data and/or flow data corresponding to the water quality monitoring target.
Further, the first generation module 1704 inputs the start time, the end time, and the first hydrologic data into a first preset model, where the first preset model is a hydrologic prediction model, and predicts future hydrologic data through the hydrologic prediction model to obtain second hydrologic data corresponding to the end time, which is a predicted hydrologic data result.
Further, the second obtaining module 1706 is used to obtain monitoring data and pollution parameters of multiple monitoring points in the target area, where the monitoring points are monitoring sites deployed upstream, downstream, and tributary of the whole water body in the target monitoring area. Discrete data of the starting time, the ending time, the monitoring data of the monitoring point, the pollutant parameter, the first hydrological data and second hydrological data obtained by prediction of the first preset model are input into a second preset model, wherein the second preset model can be a Delft3D model, and the Delft3D model can simulate and predict the future water quality of the whole water body in the target area through the discrete data and a second generation module 1708, so that a water quality monitoring result corresponding to the target area is obtained.
Compared with the prior art in which only historical hydrographic data are used as Delft3D model parameters, the hydrographic data change greatly in real time, and the hydrodynamic force is calibrated by using the historical hydrographic data to have a large error, so that the technical problem of large water quality simulation error is caused, predicted hydrographic data are obtained through a neural network model, and then the hydrographic data and the predicted hydrographic data acquired in real time are used as the parameters of a Delft3D model to monitor the water quality of the whole water body in a target area. Can accurately grasp that the current time receives which data variable influences more greatly, effectively predict the quality of water situation in the future, improve the water quality monitoring precision.
Example 7:
according to a third aspect of the present invention, a water quality monitoring system is provided, which comprises a memory, wherein the memory stores programs or instructions; and the processor is connected with the memory and is configured to execute the program or the instructions to realize the water quality monitoring method provided by the first aspect.
In this embodiment, a start time and an end time of water quality monitoring are obtained, where the start time may be a current time and the end time may be a future time. And acquiring first hydrological data corresponding to the starting time, specifically, the first hydrological data is water level data and/or flow data corresponding to the water quality monitoring target.
And further, inputting the starting time, the ending time and the first hydrologic data into a first preset model, wherein the first preset model is a hydrologic prediction model, predicting future hydrologic data through the hydrologic prediction model to obtain second hydrologic data corresponding to the ending time, and the second hydrologic data is a predicted hydrologic data result.
Further, monitoring data and pollution parameters of a plurality of monitoring points in the target area are obtained, wherein the monitoring points are monitoring sites which are deployed at the upstream and the downstream of the whole water body in the target monitoring area and branch flows. Discrete data of the starting time, the ending time, monitoring data of a monitoring point, pollutant parameters, first hydrological data and second hydrological data obtained by prediction of a first preset model are input into a second preset model, wherein the second preset model can be a Delft3D model, and the Delft3D model can simulate and predict the future water quality of the whole water body in the target area through the discrete data, so that a water quality monitoring result corresponding to the target area is obtained.
Compared with the prior art that only historical hydrological data are used as parameters of a Delft3D model, the water quality monitoring system provided by the invention has the technical problem that the water quality simulation error is large due to the fact that the hydrological data are large in real-time change and the hydrodynamic force is large in error when the historical hydrological data are used for calibrating, and the prediction hydrological data are obtained through a neural network model, and the hydrological data collected in real time and the prediction hydrological data are used as parameters of the Delft3D model to monitor the water quality of the whole water body in a target area. Can accurately grasp that the current time receives which data variable influences more greatly, effectively predict the quality of water situation in the future, improve the water quality monitoring precision.
Example 8:
in an embodiment of the fourth aspect of the present invention, a readable storage medium is provided, on which a program or instructions are stored, and the program or instructions, when executed by a processor, implement the steps of the water quality monitoring method according to any one of the above technical solutions.
The readable storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
The readable storage medium, the program or the instructions provided by the present invention, when executed by the processor, implement the steps of the water quality monitoring method according to any of the above technical solutions, and therefore the readable storage medium includes all the beneficial effects of the water quality monitoring method according to any of the above technical solutions, and is not described herein again. 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 (10)
1. A water quality monitoring method is characterized by comprising the following steps:
acquiring starting time, ending time and first hydrological data corresponding to the starting time;
inputting the starting time, the ending time and the first hydrological data into a first preset model, and generating second hydrological data corresponding to the ending time;
acquiring monitoring data and pollutant parameters of a plurality of monitoring points in a target area;
and inputting the starting time, the ending time, the monitoring data, the first hydrologic data, the second hydrologic data and the pollutant parameters into a second preset model to generate a water quality monitoring result corresponding to the target area.
2. The water quality monitoring method according to claim 1, wherein the second predetermined model comprises a hydrodynamic model and a water quality model, and the step of inputting the start time, the end time, the monitoring data, the first hydrologic data, the second hydrologic data and the pollutant parameters into the second predetermined model to generate the water quality monitoring result corresponding to the target area specifically comprises:
inputting the starting time, the ending time, the monitoring data, the first hydrologic data and the second hydrologic data into the hydrodynamic model, and generating third hydrologic data corresponding to a plurality of preset time points;
inputting the third hydrological data and the pollutant parameters into the water quality model to generate water quality pollution results corresponding to the plurality of preset time points;
and generating the water quality monitoring result according to the third hydrological data and the water quality pollution result.
3. The water quality monitoring method according to claim 1, further comprising:
establishing a first preset model based on the neural network model;
acquiring historical hydrological data in a preset time period;
filling missing data in the historical hydrological data by adopting a Lagrange interpolation method to obtain filled complete hydrological data;
and training the first preset model according to the complete hydrological data, and optimizing parameters of the first preset model.
4. A water quality monitoring method according to claim 3, characterized in that:
the neural network model includes: a long-short term memory neural network model, a recurrent neural network model, a back propagation neural network model, or a convolutional neural network model.
5. The water quality monitoring method according to claim 1, further comprising, after the generating of the water quality monitoring result corresponding to the target area:
and visually displaying the water quality monitoring result.
6. The water quality monitoring method according to any one of claims 1 to 3,
the hydrological data includes at least one of: water level data and flow data;
the monitoring data includes at least one of: location data, meteorological data and water temperature data are monitored.
7. The water quality monitoring method according to any one of claims 1 to 3,
the contaminant parameter includes at least one of: contaminant species, initial contaminant concentration, and contaminant diffusion coefficient.
8. A water quality monitoring device, comprising:
the first acquisition module is used for acquiring starting time, ending time and first hydrological data corresponding to the starting time;
the first generation module is used for inputting the starting time, the ending time and the first hydrological data into a first preset model and generating second hydrological data corresponding to the ending time;
the second acquisition module is used for acquiring monitoring data and pollutant parameters of a plurality of monitoring points in the target area;
and the second generation module is used for inputting the starting time, the ending time, the monitoring data, the first hydrologic data, the second hydrologic data and the pollutant parameters into a second preset model to generate a water quality monitoring result corresponding to the target area.
9. A water quality monitoring system, comprising:
a memory storing a program or instructions;
a processor connected to the memory, the processor implementing the water quality monitoring method of any one of claims 1 to 7 when executing the program or instructions.
10. A readable storage medium having a program or instructions stored thereon, which when executed by a processor, performs the steps of the water quality monitoring method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111026757.4A CN113868223A (en) | 2021-09-02 | 2021-09-02 | Water quality monitoring method, device and system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111026757.4A CN113868223A (en) | 2021-09-02 | 2021-09-02 | Water quality monitoring method, device and system and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113868223A true CN113868223A (en) | 2021-12-31 |
Family
ID=78989295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111026757.4A Pending CN113868223A (en) | 2021-09-02 | 2021-09-02 | Water quality monitoring method, device and system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113868223A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115936496A (en) * | 2022-11-29 | 2023-04-07 | 中国环境科学研究院 | Water quality prediction model data treatment standardization method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140140361A (en) * | 2013-05-29 | 2014-12-09 | 창원대학교 산학협력단 | Water Quality Forecasting of the River Applying Ensemble Streamflow Prediction |
| CN109615011A (en) * | 2018-12-14 | 2019-04-12 | 河海大学 | A kind of middle and small river short time flood forecast method based on LSTM |
| CN111105061A (en) * | 2018-10-26 | 2020-05-05 | 光大水务科技发展（南京）有限公司 | River water quality prediction method, prediction device and terminal |
| CN111310968A (en) * | 2019-12-20 | 2020-06-19 | 西安电子科技大学 | LSTM neural network circulation hydrological forecasting method based on mutual information |
| CN112182866A (en) * | 2020-09-21 | 2021-01-05 | 武汉大学 | Water quality rapid simulation method and system based on water environment coupling model |
| CN112561134A (en) * | 2020-11-30 | 2021-03-26 | 西安科锐盛创新科技有限公司 | Neural network-based water flow prediction method and device and electronic equipment |
-
2021
- 2021-09-02 CN CN202111026757.4A patent/CN113868223A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140140361A (en) * | 2013-05-29 | 2014-12-09 | 창원대학교 산학협력단 | Water Quality Forecasting of the River Applying Ensemble Streamflow Prediction |
| CN111105061A (en) * | 2018-10-26 | 2020-05-05 | 光大水务科技发展（南京）有限公司 | River water quality prediction method, prediction device and terminal |
| CN109615011A (en) * | 2018-12-14 | 2019-04-12 | 河海大学 | A kind of middle and small river short time flood forecast method based on LSTM |
| CN111310968A (en) * | 2019-12-20 | 2020-06-19 | 西安电子科技大学 | LSTM neural network circulation hydrological forecasting method based on mutual information |
| CN112182866A (en) * | 2020-09-21 | 2021-01-05 | 武汉大学 | Water quality rapid simulation method and system based on water environment coupling model |
| CN112561134A (en) * | 2020-11-30 | 2021-03-26 | 西安科锐盛创新科技有限公司 | Neural network-based water flow prediction method and device and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 倪晋;虞邦义;顾李华;李京兵;: "淮河中游汛期――非汛期洪污调度数学模型", 水利水电技术, no. 07, 20 July 2018 (2018-07-20) * |
| 刘悦忆;赵建世;黄跃飞;施勇;陈炼钢;: "基于蒙特卡洛模拟的水质概率预报模型", 水利学报, no. 01, 15 January 2015 (2015-01-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115936496A (en) * | 2022-11-29 | 2023-04-07 | 中国环境科学研究院 | Water quality prediction model data treatment standardization method |
| CN115936496B (en) * | 2022-11-29 | 2023-09-19 | 中国环境科学研究院 | Water quality prediction model data treatment standardization method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hung et al. | An artificial neural network model for rainfall forecasting in Bangkok, Thailand | |
| Sailor et al. | A neural network approach to local downscaling of GCM output for assessing wind power implications of climate change | |
| Kelleher et al. | Characterizing and reducing equifinality by constraining a distributed catchment model with regional signatures, local observations, and process understanding | |
| CN110646867A (en) | Urban drainage monitoring and early warning method and system | |
| CN105740991A (en) | Climate change prediction method and system for fitting various climate modes based on modified BP neural network | |
| CN112242060B (en) | Traffic flow prediction method and apparatus, computer device, and readable storage medium | |
| CN110334732A (en) | A kind of Urban Air Pollution Methods and device based on machine learning | |
| Refsgaard et al. | Climate change impacts on groundwater hydrology–where are the main uncertainties and can they be reduced? | |
| Sopelana et al. | A continuous simulation approach for the estimation of extreme flood inundation in coastal river reaches affected by meso-and macrotides | |
| Skinner et al. | Global sensitivity analysis of parameter uncertainty in landscape evolution models | |
| CN114201570A (en) | River network water quality monitoring method and device and readable storage medium | |
| KR101575847B1 (en) | System and Method for variability diagnosis modeling of Western North Pacific surface sea temperature using northern hemisphere climatic index | |
| Chirivella Osma et al. | Modelling regional impacts of climate change on water resources: the Júcar basin, Spain | |
| San et al. | Developing flood inundation map using RRI and SOBEK models: a case study of the Bago River Basin, Myanmar | |
| CN114662344A (en) | Atmospheric pollution source tracing prediction method and system based on continuous online observation data | |
| CN113868223A (en) | Water quality monitoring method, device and system and readable storage medium | |
| Banihabib | Performance of conceptual and black-box models in flood warning systems | |
| Reynolds et al. | Definitions of climatological and discharge days: do they matter in hydrological modelling? | |
| CN112287299A (en) | River health change quantitative attribution method, device and system | |
| Tapoglou et al. | Uncertainty estimations in different components of a hybrid ANN–Fuzzy–Kriging model for water table level simulation | |
| Vieira | 738 years of global climate model simulated streamflow in the Nelson-Churchill River Basin | |
| Kirkby | Models in physical geography | |
| CN116933949B (en) | Water quality prediction method and system integrating hydrodynamic model and numerical model | |
| Hou et al. | The effect of large-scale atmospheric uncertainty on streamflow predictability | |
| Shelton | Spatial scale influences on modeled runoff for large watersheds |
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 |