CN113128105B - Method and device for monitoring sudden river basin water pollution accident - Google Patents
Method and device for monitoring sudden river basin water pollution accident Download PDFInfo
- Publication number
- CN113128105B CN113128105B CN202110349618.9A CN202110349618A CN113128105B CN 113128105 B CN113128105 B CN 113128105B CN 202110349618 A CN202110349618 A CN 202110349618A CN 113128105 B CN113128105 B CN 113128105B
- Authority
- CN
- China
- Prior art keywords
- data
- water quality
- river basin
- analysis model
- water
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000003911 water pollution Methods 0.000 title claims abstract description 50
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 177
- 238000004458 analytical method Methods 0.000 claims abstract description 57
- 238000004088 simulation Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012806 monitoring device Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 abstract description 12
- 238000004364 calculation method Methods 0.000 abstract description 9
- 230000004044 response Effects 0.000 abstract description 5
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 7
- 238000006467 substitution reaction Methods 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012876 topography Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000001994 activation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for monitoring sudden river basin water pollution accidents, wherein the method comprises the following steps: acquiring hydrological data of a monitoring area; inputting basic river basin data into a preset water quality analysis model, and outputting water quality data in a prediction time period; and (3) constructing a preset water quality analysis model based on 3DCNNs, taking output data of the water flow numerical simulation model as a label, and taking corresponding basic river basin data as a sample for training. The method solves the problem that the calculation time of the simulation models such as MIKE and the like is too long, realizes quick prediction on the water quality environment of the river basin, effectively analyzes the future change trend, reduces the time loss, and can improve the response speed of local environmental departments and finally quickly, effectively and accurately treat the water pollution accident of the river basin. In addition, the method can analyze the time variation of the water quality data by utilizing the time sequence attribute of 3DCNNs, and simultaneously add a residual error network unit to analyze the space characteristic variation of the water quality data.
Description
Technical Field
The invention relates to the technical field of computer graphics, in particular to a method and a device for monitoring sudden watershed water pollution accidents.
Background
In recent years, serious emergencies of watershed water pollution are layered, the ecological environment faces serious threat, relevant environmental departments adopt real-time monitoring schemes for water environment pollution accidents, and most of the real-time monitoring schemes use wireless sensor network systems to automatically monitor watershed water quality indexes such as ammonia nitrogen, five-day biochemical oxygen demand (BOD 5), dissolved Oxygen (DO) and the like, and the water quality indexes are packaged and transmitted back to the cloud. Because the water quality data monitored by the sensor system has smaller granularity and high cost, and can not reflect the real-time change condition of the water quality of the outflow region, the water flow numerical simulation models such as MIKE, SWAT and the like are used for simulating the transmission process of dissolved substances and the like in the water environment due to convection and diffusion. The model has wide application in the aspects of river basin water balance, river flow prediction, non-point source pollution control evaluation and the like, has powerful functions, long calculation time and needs professional operation.
Specifically, the existing MIKE and other water flow numerical simulation models are powerful, consume a large amount of time, and cannot rapidly analyze the future change trend of water quality when water pollution emergency occurs.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a method and a device for monitoring sudden river basin water pollution accidents.
The invention provides a method for monitoring sudden river basin water pollution accidents, which comprises the following steps: acquiring hydrological data and meteorological data of a monitoring area as basic watershed data, and increasing granularity of water quality data in time and space; inputting basic river basin data into a preset water quality analysis model, and outputting water quality data in a prediction time period; the basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
According to an embodiment of the present invention, the method for monitoring sudden watershed water pollution accident further includes: obtaining a basic river basin data sample, and inputting the basic river basin data sample into a water flow numerical simulation model to obtain predicted water quality data;
And constructing an initial water quality analysis model based on the 3DCNNs network and the residual error network, taking predicted water quality data as a label, taking the basic river basin data sample as input, and training the initial water quality analysis model to obtain the preset water quality analysis model.
According to an embodiment of the present invention, after obtaining the preset water quality analysis model, the method further includes: and evaluating the water quality analysis model by using the root mean square error and the average absolute error, and if the root mean square error and the average absolute error do not meet the preset conditions, re-selecting the input sample for training.
According to the sudden river basin water pollution accident monitoring method, the basic river basin data comprise topography data, hydrological data and meteorological data of a monitored area.
According to the sudden river basin water pollution accident monitoring method, the topographic data comprise longitude, latitude and altitude data, the hydrologic data comprise water flow, manning coefficients and water quality data, and the meteorological data comprise wind speed data and wind direction data.
According to the sudden river basin water pollution accident monitoring method provided by the embodiment of the invention, the water quality data of the monitoring area is continuously acquired, and the method specifically comprises the following steps: the edge computing gateway continuously acquires water quality data of the monitoring area; correspondingly, the basic river basin data are input into a preset water quality analysis model, and the method specifically comprises the following steps: and inputting the basic river basin data into a water quality analysis model preset in the edge computing gateway.
According to the sudden river basin water pollution accident monitoring method of one embodiment of the invention, after outputting the water quality data of the predicted time period, the method further comprises the following steps: and analyzing the water quality data in the predicted time period to obtain a water quality analysis result.
According to the sudden river basin water pollution accident monitoring method of one embodiment of the invention, after outputting the water quality data of the predicted time period, the method further comprises the following steps: and sending the water quality data and/or the water quality analysis result of the predicted time period to a cloud server for storage. The invention also provides a sudden river basin water pollution accident monitoring device, which comprises: the data acquisition module is used for acquiring hydrological data and meteorological data of the monitoring area; the water quality prediction module is used for inputting the basic river basin data into a preset water quality analysis model and outputting the water quality data of a prediction time period; the basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the steps of any of the sudden river basin water pollution incident monitoring methods described above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a sudden watershed water pollution incident monitoring method as described in any of the above.
According to the method and the device for monitoring the sudden river basin water pollution accident, the replacement model is constructed by the method of 3DCNNs, and the problem that the calculation time of the water flow numerical simulation model such as MIKE and the like is too long is solved. The method can rapidly predict the water quality environment of the river basin, effectively analyze the future change trend of the water quality environment and reduce the time loss, so that the response speed of local field departments can be improved, and finally, the water pollution accident of the river basin can be rapidly, effectively and accurately treated. In addition, the method can analyze the time variation of the water quality data by utilizing the time sequence attribute of 3DCNNs, and simultaneously add a residual error network unit for analyzing the space characteristic variation of the water quality data.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for monitoring sudden river basin water pollution accidents provided by the invention;
FIG. 2 is a second flow chart of the method for monitoring sudden river basin water pollution accidents provided by the invention;
FIG. 3 is a schematic structural view of the sudden river basin water pollution accident monitoring device provided by the invention;
fig. 4 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The existing water quality data has smaller granularity and can not well reflect the water quality condition of the outflow region, so that the local relevant environmental department uses MIKE to construct a water flow numerical simulation model according to the existing basic water quality data set to enlarge the granularity of the water quality data, the data can be obtained in half an hour in time, and the water quality change condition of a certain subarea can be observed in space. However, the existing MIKE water flow numerical simulation model has strong functions, but has low running speed, needs professional operation, and cannot be rapidly analyzed under the emergency of water pollution.
The method and apparatus for monitoring sudden river basin water pollution accidents according to the present invention are described below with reference to fig. 1 to 4. Fig. 1 is a schematic flow chart of a method for monitoring sudden river basin water pollution accidents, provided by the invention, as shown in fig. 1, the method for monitoring sudden river basin water pollution accidents comprises the following steps:
101. Hydrologic data of the monitored area is acquired.
Basic drainage basin data of the drainage basin is collected first, wherein the basic drainage basin data comprises hydrological data and meteorological data. And acquiring hydrologic data according to wireless network sensors and the like of monitoring stations in the monitoring area. The hydrologic data comprise water flow data of the river basin and water quality data monitored by monitoring stations, such as DO, BOD 5, COD, ammonia nitrogen, total phosphorus and other indexes. The meteorological data includes wind direction and wind speed values over the river basin.
102. Inputting basic river basin data into a preset water quality analysis model, and outputting water quality data in a prediction time period; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
The base basin data also includes terrain data for the monitored area, which may be obtained from satellite topography of the basin, including elevation data and latitude and longitude, and weather data and terrain data may be obtained from a geographic database as part of the base basin data.
According to the invention, the water quality monitoring analysis of the whole river basin at different monitoring sites is realized by acquiring the water quality data and the water flow data acquired by the sensors in the region. According to the obtained basic data set, water quality values of different places of the whole river basin at different moments in the future can be obtained through a MIKE water flow numerical simulation model, and the granularity of the data is increased. Then, based on the water quality values at different moments in the future as labels, training a water quality analysis model to obtain the water quality analysis model to replace MIKE and other water flow numerical simulation models.
The water quality data of the watershed is data with time attribute and space attribute, the existing simulation substitution model comprises a radial basis function model, a Kriging model, a wavelet neural network model and the like, only the change trend of water quality at a certain moment can be simulated, the simulation substitution model does not have time sequence attribute, the water quality data can not be analyzed, the time change and the space correlation can not be realized, the substitution model is not comprehensive enough when the water quality environment is analyzed by substituting MIKE water flow numerical model, the error is large, and the simulation analysis can not be accurately performed according to the real-time environment data.
According to the sudden river basin water pollution accident monitoring method provided by the invention, the 3DCNNs method and the residual error network are used for constructing the substitution model, so that the problem that the calculation time of the MIKE 21 water flow numerical simulation model is too long is solved. The method can rapidly predict the water quality environment of the river basin, effectively analyze the future change trend of the water quality environment and reduce the time loss, so that the response speed of local field departments can be improved, and finally, the water pollution accident of the river basin can be rapidly, effectively and accurately treated. In addition, the method can analyze the change of water quality data in time by using the time sequence attribute of 3 DCNNs.
In one embodiment, before inputting the basic watershed data into the preset water quality analysis model, the method further comprises: obtaining a basic river basin data sample, and inputting the basic river basin data sample into a water flow numerical simulation model to obtain predicted water quality data; and constructing an initial water quality analysis model based on the 3DCNNs network and the residual error network, taking predicted water quality data as a label, taking the basic river basin data sample as input, and training the initial water quality analysis model to obtain the preset water quality analysis model.
Before model training, basic river basin data of the river basin are collected at first, water quality data are obtained according to wireless network sensors of monitoring sites and the like, and meteorological data and topographic data are obtained according to a geographic database to serve as the basic river basin data.
Then inputting the basic drainage basin data MIKE to build a water flow numerical simulation model to obtain MIKE output, namely predicted water quality data, taking the MIKE output data and the basic drainage basin data as a sample set, building a substitution model by using a 3DCNNs method and a residual error network, and training and verifying.
Constructing the model of the water flow numerical value MIKE comprises dividing a basic map into N grids according to the river basin topography data, and calculating to obtain a Manning coefficient of each grid, wherein each grid is a place with longitude and latitude. And inputting meteorological data, water flow data, manning coefficients and water quality data of a monitoring station, and calculating MIKE to obtain the water quality value of each grid in a future time period.
Specifically, the basic map can be divided into 39078 grids, water quality data of 39078 grids are obtained through MIKE model calculation, the water quality data are not different, the longitude and latitude of a part of grids are consistent, when a substitution model is constructed, the data are preprocessed firstly, and null data and data with repeated longitude and latitude are deleted. The water quality dataset may be referred to as spatiotemporal data, with both Temporal and Spatial attributes (Spatial). The time-space data is also a plurality of time sequences, each time sequence is generated by different spaces, each time sequence has a time association, the time sequences also have a space association, when the prediction is carried out, the time sequences are firstly divided in time, the space prediction is carried out at each time point, and then the prediction fusion is carried out in time. The invention provides a method for 3DCNNs and a residual error network, namely dividing a research area into grid areas with equidistant length and width in a space dimension, and slicing in a time dimension, namely predicting a value of a certain position point, wherein the value is related to the current space dimension and different position points in different time periods in the past. After 3DCNNs convolution operations, the time information is fully mined, and then a residual network is adopted to further explore the space information. The residual network is combined by two activations and 2D convolution and is superimposed on the 3D convolution layer. At 3 hour intervals in time, namely 12: 00. 15: 00. 18: 00. 21: 00. 00: 00. 3: 00. 6: 00. 9:00, then there are 8 time periods a day, and the time dimension predicts with 8 as a period.
3D CNNs is mainly applied to the fields of video classification, motion recognition and the like, and is changed based on 2DCNN, if 2D CNN is adopted to operate on space-time data, each frame time sequence of the data is generally recognized by CNN, and for a filter, a two-dimensional characteristic diagram is output, multi-channel information is compressed, and the recognition in the mode does not consider inter-frame motion information in a time dimension and cannot capture time sequence information well. Thus, 3D CNNs is used, which composes a cube by stacking a plurality of consecutive frames, and then applying a 3D convolution kernel in the cube. In this structure, each feature map in the convolution layer is connected to a plurality of adjacent consecutive frames in the previous layer, thereby capturing motion information. Thus, the time sequence information in the sequence can be well utilized, and the output of the 3D convolution is still a 3D characteristic diagram. That is, using 3D CNNs can better capture the temporal and spatial characteristic information of the data.
According to the sudden river basin water pollution accident monitoring method, an initial water quality analysis model is built through the 3DCNNs network and the residual error network, and the problem of delay of data analysis of the water flow numerical simulation model can be solved.
In one embodiment, after obtaining the preset water quality analysis model, the method further includes: using a Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) evaluation model, and if the root mean square error and the mean absolute error do not meet a preset condition, re-selecting an input sample for training, wherein the specific definition is as follows:
wherein y pre is the predicted value of the alternative model network, yi is the true value of the water quality index, and N is the number of predicted samples.
In one embodiment, the base basin data includes terrain data, hydrologic data, and meteorological data for the monitored area. The topography data comprise longitude, latitude and elevation data, the hydrologic data comprise water flow, manning coefficients and water quality data, and the meteorological data comprise wind speed data and wind direction data. Fig. 2 is a second schematic flow chart of the method for monitoring sudden river basin water pollution accidents provided by the invention, and the specific application can be seen in the above embodiment and fig. 2.
In one embodiment, the continuously acquiring water quality data of the monitoring area is specifically: the edge computing gateway continuously acquires water quality data of the monitoring area; correspondingly, the basic river basin data are input into a preset water quality analysis model, and the method specifically comprises the following steps: and inputting the basic river basin data into a water quality analysis model preset in the edge computing gateway.
In one embodiment, after outputting the water quality data for the predicted period of time, further comprising: and analyzing the water quality data in the predicted time period to obtain a water quality analysis result. For example, the predicted water quality data is analyzed by an edge computing gateway to obtain a future water quality state.
In one embodiment, after outputting the water quality data for the predicted period of time, further comprising: and sending the water quality data and/or the water quality analysis result of the predicted time period to a cloud server for storage.
Considering that the existing wireless network sensor monitoring system needs to transmit mass data, and the data center is in the cloud, the data is packaged and transmitted through the network to consume a large amount of time, the transmission cost is high, and the data processing cannot embody the effectiveness.
After MIKE model simulation is completed, the output data and the input data are used as sample sets to train a substitute model network, the trained substitute model is transmitted to an edge computing gateway module of a monitoring site, and the edge computing gateway can perform a low-power-consumption high-performance AI algorithm, uplink and downlink of data and communicate with a cloud server. The data collected by the edge computing gateway and the sensor are used for predicting the future change trend of the water quality, any one or both of the water quality data and the analysis result are returned to the cloud, the water quality change trend of different areas is rapidly analyzed when the water pollution emergency occurs, and the response speed of local environmental departments is improved.
The implementation mode of the edge computing gateway is as follows: the artificial intelligent board Jetson Xavier of NVIDIA company and the main board based on the full-scope A64 processor can be embedded into equipment such as a camera and the like, and assembled into PAD for use, so that the operation speed is improved. Jetson Xavier with Tensorflow equipment, can perform a large number of AI algorithms such as image recognition and the like; the motherboard based on the full-lineage A64 is used for data acquisition, wireless network connection, uplink and downlink of data and communication with the cloud.
Main interface of motherboard based on full-lineage A64: the USB interface, the TF card interface, the OTG interface and the serial port; providing an MIPI interface, wherein a maximum supportable 1900x1200 resolution LCD screen; providing a CSI camera interface, and enabling a high-definition camera with the maximum pixel of 500w to input so as to support fixed focus or automatic focusing; the board card integrates a Wifi and Bluetooth 4.0 module, a headset interface, a loudspeaker interface, an independent power supply interface and a micro USB data interface. Small size and stable performance. The main modules are as follows:
1) AXP803, a highly integrated PMIC, requires multi-channel power conversion output for lithium battery applications. It provides a simple and flexible power management solution for the processor to meet increasingly complex and accurate power control requirements.
2) 24 GB DDR3 LSDRAMs.
3) NCEFBS98-16G memory chip IC FORESEE.
4) Ameba CS RTL8721CSM (QFN 68), a high-integration and low-power consumption single chip microcomputer of the Internet of things. The new architecture Armv M KM4 MCU, wi-Fi, bluetooth, combined with ARM, and provides a set of configurable GPIOs, these GPIOs being configured as digital peripherals, applied to different applications and control uses.
5) The GL850G USB HUB controller chip has the characteristics of low power consumption, low temperature, reduced pin count and the like.
According to the sudden river basin water pollution accident monitoring method, the calculation pressure of cloud data center equipment is reduced, the calculation effectiveness is improved, the data processing, analysis and various AI algorithms are realized at the edge of a data source through the edge calculation gateway, the problem of delay of cloud data analysis is solved, the transmission cost is saved, the data quality is improved, the calculation speed is increased, and the time cost is reduced.
The sudden river basin water pollution accident monitoring device provided by the invention is described below, and the sudden river basin water pollution accident monitoring device described below and the sudden river basin water pollution accident monitoring method described above can be correspondingly referred to each other.
Fig. 3 is a schematic structural diagram of a sudden river basin water pollution accident monitoring device provided by the present invention, and as shown in fig. 3, the sudden river basin water pollution accident monitoring device includes: a data acquisition module 301 and a water quality prediction module 302. The data acquisition module 301 is configured to acquire hydrological data of a monitored area; the water quality prediction module 302 is configured to input the basic basin data into a preset water quality analysis model, and output water quality data in a prediction time period; the basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
The embodiment of the device provided by the embodiment of the present invention is for implementing the above embodiments of the method, and specific flow and details refer to the above embodiments of the method, which are not repeated herein.
According to the sudden river basin water pollution accident monitoring device provided by the embodiment of the invention, the replacement model is constructed by the 3DCNNs method, so that the problem that the calculation time of the water flow numerical simulation model such as MIKE and the like is too long is solved. The method can rapidly predict the water quality environment of the river basin, effectively analyze the future change trend of the water quality environment and reduce the time loss, so that the response speed of local field departments can be improved, and finally, the water pollution accident of the river basin can be rapidly, effectively and accurately treated.
Fig. 4 is a schematic structural diagram of an electronic device according to the present invention, as shown in fig. 4, the electronic device may include: processor 401, communication interface (Communications Interface) 402, memory 403 and communication bus 404, wherein processor 401, communication interface 402 and memory 403 complete communication with each other through communication bus 404. Processor 401 may invoke logic instructions in memory 403 to perform a sudden watershed water pollution incident monitoring method comprising: acquiring hydrological data of a monitoring area; inputting basic river basin data into a preset water quality analysis model, and outputting water quality data in a prediction time period; the basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
Further, the logic instructions in the memory 403 may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method of sudden river basin water pollution incident monitoring provided by the above methods, the method comprising: acquiring hydrological data of a monitoring area; inputting basic river basin data into a preset water quality analysis model, and outputting water quality data in a prediction time period; the basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method for sudden river basin water pollution accident monitoring provided by the above embodiments, the method comprising: acquiring hydrological data of a monitoring area; inputting basic river basin data into a preset water quality analysis model, and outputting water quality data in a prediction time period; the basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for monitoring sudden watershed water pollution accidents, comprising the steps of:
acquiring hydrological data of a monitoring area;
Obtaining a basic river basin data sample, and inputting the basic river basin data sample into a water flow numerical simulation model to obtain predicted water quality data;
constructing an initial water quality analysis model based on a 3DCNNs network and a residual error network, taking predicted water quality data as a label, taking a basic river basin data sample as input, and training the initial water quality analysis model to obtain a preset water quality analysis model;
Using the root mean square error and the average absolute error to evaluate a water quality analysis model, and re-selecting an input sample for training if the root mean square error and the average absolute error do not meet preset conditions;
inputting basic river basin data into a preset water quality analysis model, and outputting water quality data in a prediction time period;
The basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
2. The method of claim 1, wherein the topographical data comprises latitude and longitude data, the hydrologic data comprises water flow, manning coefficients, and water quality data, and the meteorological data comprises wind speed data and wind direction data.
3. The method for monitoring sudden watershed water pollution incidents according to claim 1, wherein the continuous acquisition of water quality data of the monitored area is specifically as follows:
the edge computing gateway continuously acquires water quality data of the monitoring area;
correspondingly, the basic river basin data are input into a preset water quality analysis model, and the method specifically comprises the following steps:
and inputting the basic river basin data into a water quality analysis model preset in the edge computing gateway.
4. The method for monitoring sudden watershed water pollution incidents according to claim 3, wherein after outputting the water quality data for the predicted period of time, further comprising:
And analyzing the water quality data in the predicted time period to obtain a water quality analysis result.
5. The method for monitoring sudden watershed water pollution incidents according to claim 3 or 4, wherein after outputting the water quality data for the predicted period of time, further comprising:
and sending the water quality data and/or the water quality analysis result of the predicted time period to a cloud server for storage.
6. A sudden watershed water pollution accident monitoring device, comprising:
the data acquisition module is used for acquiring hydrological data of the monitoring area;
Obtaining a basic river basin data sample, and inputting the basic river basin data sample into a water flow numerical simulation model to obtain predicted water quality data;
constructing an initial water quality analysis model based on a 3DCNNs network and a residual error network, taking predicted water quality data as a label, taking a basic river basin data sample as input, and training the initial water quality analysis model to obtain a preset water quality analysis model;
Using the root mean square error and the average absolute error to evaluate a water quality analysis model, and re-selecting an input sample for training if the root mean square error and the average absolute error do not meet preset conditions;
the water quality prediction module is used for inputting the basic river basin data into a preset water quality analysis model and outputting the water quality data of a prediction time period;
The basic river basin data comprise hydrological data of a preset time period, meteorological data of the preset time period and topographic data of a monitoring area; the preset water quality analysis model is constructed based on 3DCNNs and a residual error network, and is obtained by taking output data of the water flow numerical simulation model as a label and corresponding basic river basin data as a sample for training.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the sudden river basin water pollution incident monitoring method of any one of claims 1 to 5.
8. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the sudden watershed water pollution incident monitoring method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110349618.9A CN113128105B (en) | 2021-03-31 | 2021-03-31 | Method and device for monitoring sudden river basin water pollution accident |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110349618.9A CN113128105B (en) | 2021-03-31 | 2021-03-31 | Method and device for monitoring sudden river basin water pollution accident |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113128105A CN113128105A (en) | 2021-07-16 |
| CN113128105B true CN113128105B (en) | 2024-05-17 |
Family
ID=76774408
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110349618.9A Active CN113128105B (en) | 2021-03-31 | 2021-03-31 | Method and device for monitoring sudden river basin water pollution accident |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128105B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113720425B (en) * | 2021-08-31 | 2024-09-20 | 福建蓝密码物联网科技有限公司 | Water leakage monitoring method and system based on intelligent water meter |
| CN114115401A (en) * | 2021-11-25 | 2022-03-01 | 深圳市地质局 | Water quality hydrology environment perception and water conservancy facility integrated intelligent management system |
| CN114759969A (en) * | 2022-03-07 | 2022-07-15 | 航天行云科技有限公司 | Water and soil quality monitoring method and system for shrimp and rice operation area |
| CN115204060B (en) * | 2022-08-19 | 2023-06-09 | 水利部交通运输部国家能源局南京水利科学研究院 | Quick early warning method and system for multidimensional model of water quality of drinking water source |
| CN116258403B (en) * | 2023-01-19 | 2023-09-15 | 河南省新乡水文水资源勘测局 | Big data-based water quality monitoring and early warning method and system |
| CN116109977B (en) * | 2023-02-12 | 2023-09-01 | 深圳中检联检测有限公司 | Food sanitation detection method, device, equipment and medium based on production environment |
| CN116310831B (en) * | 2023-03-23 | 2023-11-03 | 河南省水利第一工程局集团有限公司 | Big data-based water source environment monitoring method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798467A (en) * | 2017-10-11 | 2018-03-13 | 杭州市环境保护科学研究院 | Water pollution burst accident based on deep learning quickly meet an urgent need assess and decision-making technique |
| CN110487980A (en) * | 2019-06-27 | 2019-11-22 | 江苏亚寰环保科技股份有限公司 | A kind of monitoring water environment analysis system based on artificial intelligence and machine learning algorithm |
| CN111062316A (en) * | 2019-12-16 | 2020-04-24 | 成都之维安科技股份有限公司 | Pollution source wastewater discharge real-time video analysis system based on deep learning technology |
-
2021
- 2021-03-31 CN CN202110349618.9A patent/CN113128105B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798467A (en) * | 2017-10-11 | 2018-03-13 | 杭州市环境保护科学研究院 | Water pollution burst accident based on deep learning quickly meet an urgent need assess and decision-making technique |
| CN110487980A (en) * | 2019-06-27 | 2019-11-22 | 江苏亚寰环保科技股份有限公司 | A kind of monitoring water environment analysis system based on artificial intelligence and machine learning algorithm |
| CN111062316A (en) * | 2019-12-16 | 2020-04-24 | 成都之维安科技股份有限公司 | Pollution source wastewater discharge real-time video analysis system based on deep learning technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113128105A (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113128105B (en) | Method and device for monitoring sudden river basin water pollution accident | |
| CN107703564A (en) | A kind of precipitation predicting method, system and electronic equipment | |
| Shao et al. | Branchy-GNN: A device-edge co-inference framework for efficient point cloud processing | |
| CN114611705A (en) | Data processing method, training method for machine learning, and related device and equipment | |
| Do et al. | Graph-deep-learning-based inference of fine-grained air quality from mobile IoT sensors | |
| Zheng et al. | An eiot system designed for ecological and environmental management of the xianghe segment of china’s grand canal | |
| US20240054339A1 (en) | Method and system for predicting spatio-temporal perception information based on graph neural network | |
| CN111435463A (en) | Data processing method and related equipment and system | |
| CN114221978B (en) | Urban rail transit cloud platform system | |
| CN112801340B (en) | Crowd density prediction method based on multi-level city information unit portraits | |
| CN118535889B (en) | Sea surface temperature prediction method based on multi-scale channel and space-time information fusion | |
| CN113822460A (en) | Traffic flow prediction method and device, electronic equipment and storage medium | |
| CN115083112A (en) | Intelligent early warning emergency management system and deployment method thereof | |
| CN117079148A (en) | Urban functional area identification method, device, equipment and medium | |
| Kiremidjian et al. | A wireless structural monitoring system with embedded damage algorithms and decision support system | |
| CN115468541B (en) | Karst collapse four-dimensional monitoring information system | |
| Wang et al. | C3Meta: a context-aware cloud-edge-end collaboration framework toward green metaverse | |
| CN114818476A (en) | Federal learning system and method applied to service life prediction of rotating machinery equipment | |
| Liu et al. | Growth scale prediction of big data for information systems based on a deep learning SAEP method | |
| Ganchev et al. | Designing a heterogeneous sensor tier for the EMULSION IoT platform | |
| Delnevo et al. | A deep learning approach to anthropogenic load assessment for sustainable coastal tourism | |
| CN110766566A (en) | Intelligent operation and maintenance behavior analysis system based on bidirectional LSTM model | |
| Zhao et al. | Spatio-Temporal Wind Speed Prediction Based on Variational Mode Decomposition. | |
| CN117874498B (en) | Intelligent forestry big data system, method, equipment and medium based on data lake | |
| CN115134816B (en) | Base station flow prediction method based on space-time convolution and multiple time scales |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |