CN117671507B - River water quality prediction method combining meteorological data - Google Patents
River water quality prediction method combining meteorological data Download PDFInfo
- Publication number
- CN117671507B CN117671507B CN202410116722.7A CN202410116722A CN117671507B CN 117671507 B CN117671507 B CN 117671507B CN 202410116722 A CN202410116722 A CN 202410116722A CN 117671507 B CN117671507 B CN 117671507B
- Authority
- CN
- China
- Prior art keywords
- preset area
- water quality
- data
- image data
- certain
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 234
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000002159 abnormal effect Effects 0.000 claims abstract description 123
- 238000013136 deep learning model Methods 0.000 claims abstract description 26
- 230000004927 fusion Effects 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims description 59
- 238000012163 sequencing technique Methods 0.000 claims description 21
- 238000012216 screening Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000010295 mobile communication 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
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 239000012286 potassium permanganate Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a river water quality prediction method combining meteorological data, which comprises the following steps: fusing the first meteorological data into a first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fusing the second meteorological data into a second water quality data sequence to obtain a second target prediction data sequence; respectively inputting the first target predicted data sequence and the second target predicted data sequence into a preset deep learning model, and respectively outputting a first water quality predicted result corresponding to an abnormal preset area and a second water quality predicted result corresponding to a certain preset area by the deep learning model; and calculating the water quality prediction result of another preset area according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity. The water quality of each area of the whole river can be rapidly predicted.
Description
Technical Field
The invention belongs to the technical field of river water quality prediction, and particularly relates to a river water quality prediction method combining meteorological data.
Background
According to the basis of different theories, the water environment prediction can be divided into a mechanistic prediction method and a non-mechanistic prediction method. The mechanistic prediction method is based on the internal and external operation evolution rules of the water environment, and relates to a comprehensive prediction method of a plurality of subjects such as dynamics, ecology, chemistry and the like, and finally, the mutual relation among the elements is represented through a model. Common models are: the WASP model, UAL model, MIKE model, GWLF model and the like, and the method requires a great deal of expertise, has high requirements on data acquisition quality, and has an unsatisfactory prediction effect. The non-mechanistic prediction method is a black box method, and based on the correlation theory of probability statistics, a model is built aiming at a specific water environment, so that the method has a good prediction effect, and is also widely applied to water quality prediction of the water environment. Traditional probability statistical methods have difficulty modeling such complex dependencies. At present, the application of an artificial intelligence method represented by deep learning in the prediction of the surface water environment index is greatly developed.
However, in the whole river prediction process, the water quality monitoring data of each section of the river needs to be obtained, and the river water quality is predicted according to the water quality monitoring data of each section of the river, and the method faces the phenomenon that effective water quality monitoring data cannot be acquired when a water quality monitoring device is damaged, so that the prediction accuracy is reduced or even cannot be predicted, and if a plurality of sections need to be predicted, the operation is that all corresponding water quality monitoring data are input into a model to be identified, so that the prediction efficiency is low.
Disclosure of Invention
The invention provides a river water quality prediction method combining meteorological data, which is used for solving the technical problems that when a water quality monitoring device is damaged, effective water quality monitoring data cannot be acquired, so that prediction accuracy is reduced and even cannot be predicted, and if a plurality of areas are required to be predicted, the operation is to identify all input models of corresponding water quality monitoring data, so that the prediction efficiency is low.
In a first aspect, the present invention provides a river water quality prediction method in combination with meteorological data, comprising:
acquiring image data in a plurality of preset areas, and judging whether abnormal image data exists in each image data;
if the abnormal image data exist, screening the abnormal image data, and defining a preset area where the abnormal image data exist as an abnormal preset area;
Acquiring certain image data of a certain preset area and other image data of another preset area adjacent to the certain preset area;
Acquiring a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculating a ratio of the first similarity to the second similarity;
Acquiring first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data are located, and second water quality data and second weather data of each detection point in a preset area where certain image data are located;
Sequencing the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area respectively to obtain a first water quality data sequence and a second water quality data sequence;
Fusing the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fusing the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence;
Respectively inputting the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model, wherein the deep learning model respectively outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area;
and calculating the water quality prediction result of the other preset area according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity.
In a second aspect, the present invention provides a river water quality prediction system incorporating meteorological data, comprising:
The judging module is configured to acquire image data in a plurality of preset areas and judge whether abnormal image data exists in each image data or not;
The screening module is configured to screen out abnormal image data if the abnormal image data exist, and define a preset area where the abnormal image data are located as an abnormal preset area;
A first acquisition module configured to acquire certain image data of a certain preset area and another image data of another preset area adjacent to the certain preset area;
A calculation module configured to acquire a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculate a ratio of the first similarity to the second similarity;
The second acquisition module is configured to acquire first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data are located, and second water quality data and second weather data of each detection point in a preset area where certain image data are located;
the sequencing module is configured to sequence the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area respectively to obtain a first water quality data sequence and a second water quality data sequence;
The fusion module is configured to fuse the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fuse the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence;
the output module is configured to input the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model respectively, and the deep learning model outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area respectively;
and the prediction module is configured to predict the water quality result of the other preset area according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity.
In a third aspect, there is provided an electronic device, comprising: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the river water quality prediction method in combination with meteorological data of any of the embodiments of the present invention.
In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program, the program instructions, when executed by a processor, cause the processor to perform the steps of the river water quality prediction method in combination with meteorological data of any of the embodiments of the present invention.
According to the river water quality prediction method combining meteorological data, the first target prediction data sequence and the second target prediction data sequence are respectively input into the preset deep learning model, the deep learning model respectively outputs the first water quality prediction result corresponding to the abnormal preset area and the second water quality prediction result corresponding to a certain preset area, and the water quality prediction result of the other preset area is calculated according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity, so that the water quality of each area of the whole river can be rapidly predicted, and the water quality results of continuous sections of the river can be accurately obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a river water quality prediction method combined with meteorological data according to an embodiment of the present invention;
FIG. 2 is a heat map of water quality index correlation according to an embodiment of the present invention;
FIG. 3 is a block diagram showing a river water quality prediction system with meteorological data according to an embodiment of the present invention;
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. 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.
Referring to fig. 1, a flow chart of a river water quality prediction method combining meteorological data according to the present application is shown.
As shown in fig. 1, the river water quality prediction method combined with meteorological data specifically includes the following steps:
Step S101, acquiring image data in a plurality of preset areas, and judging whether abnormal image data exists in each image data.
In the step, before river water quality prediction is performed, a camera is placed at a target position near the water flow to be detected and used for shooting image data of the water flow to be detected, or an unmanned aerial vehicle carrying the camera is used for shooting the image data of the water flow to be detected along the water flow direction. And identifying each image data through the image identification model, so that whether abnormal image data exist in each image data can be identified. For example, the water turbidity in each image data is used as a judging basis, and whether the current image data has abnormal image data with the water turbidity larger than a preset threshold value or the water turbidity larger than the historical image data is judged.
The image recognition model for recognizing each image data is a neural network model which is usually used for training and verifying by using the historical image data of each preset area, and the obtained image recognition model. And will not be described in detail herein.
In a specific embodiment, if the data do not exist, screening out initial remote sensing image data, and defining a preset area where the initial remote sensing image data are located as a standard preset area, wherein the initial remote sensing image data are first remote sensing image data acquired based on river flow direction; acquiring certain remote sensing image data of a certain preset area and other remote sensing image data of another preset area adjacent to the certain preset area; and acquiring a third similarity between one remote sensing image data and the initial remote sensing image data and a fourth similarity between the other remote sensing image data and the initial remote sensing image data, and calculating the ratio of the third similarity to the fourth similarity.
Step S102, if the abnormal image data exist, the abnormal image data are screened out, and a preset area where the abnormal image data exist is defined as an abnormal preset area.
Step S103, obtaining a certain image data of a certain preset area and another image data of another preset area adjacent to the certain preset area.
In the step, acquiring a certain remote sensing image data of a certain preset area; taking the position of the abnormal preset area as an origin, taking the river flow direction as a positive direction, and acquiring another remote sensing image data of another preset area adjacent to the certain preset area when the position direction from the certain preset area to the abnormal preset area is the positive direction, wherein the position direction from the other preset area to the certain preset area is the positive direction; when the position direction from one preset area to the abnormal preset area is a negative direction, acquiring the other remote sensing image data of the other preset area adjacent to the one preset area, wherein the position direction from the other preset area to the one preset area is a negative direction.
For example, the position of the abnormal preset area a is used as the origin, and the river flow direction is positive from left to right. At this time, a certain preset area B on the right side of the abnormal preset area a is acquired, the preset area adjacent to the left side of the certain preset area B is another preset area C, the preset area adjacent to the right side of the certain preset area B is another preset area D, and at this time, a certain image data of the certain preset area B and another image data of another preset area D adjacent to the certain preset area are selected to be acquired. Because, when the abnormality preset area a is abnormal, for example, a pollution source exists in the abnormality preset area a, the pollution level of the whole river is gradually reduced by the pollution source according to the river flow direction, and at this time, if the water quality result of the abnormality preset area a with high relative pollution level is detected, the water quality result of the adjacent other preset area D is predicted, so that the predicted result is more accurate. For example, if the water quality result of a certain preset area B is normal, it can be accurately predicted that the water quality result of another preset area D is normal when only one pollution source of the abnormal preset area a exists, but it cannot be predicted whether the water quality result of another preset area C is normal or abnormal.
Step S104, obtaining a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculating a ratio of the first similarity to the second similarity.
In the step, gray scale processing, definition processing and filtering processing are carried out on certain image data and abnormal image data, then a VGGNet network model is adopted to carry out image recognition on the processed certain image data and abnormal image data, a first characteristic quantity corresponding to the certain image data and a second characteristic quantity corresponding to the abnormal image data are respectively obtained, and then the first characteristic quantity and the second characteristic quantity are subjected to difference to obtain the first similarity between the certain image data and the abnormal image data. A second similarity between the other image data and the abnormal image data can also be obtained.
Step S105, acquiring first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data is located, and second water quality data and second weather data of each detection point in a preset area where the certain image data is located.
In this step, water quality data includes, but is not limited to: water temperature, pH, dissolved oxygen, potassium permanganate, ammonia nitrogen, total phosphorus, total nitrogen, conductivity, turbidity and other indexes. Meteorological data includes, but is not limited to: air temperature, atmospheric pressure, humidity, wind speed, dew point temperature, precipitation amount and other indexes.
In a specific embodiment, the pearson correlation coefficient is used to perform correlation analysis on the water quality data, and the index with high correlation is screened to improve the prediction efficiency, wherein the correlation heat of each water quality index is shown in fig. 2. The expression for performing correlation analysis on the water quality data is as follows:
，
In the method, in the process of the invention, Is the pearson correlation coefficient,/>For the quantity of water quality data,/>Is the ith value of a water quality data,For/>Average value of/(I)Is the ith value of another item of water quality data,/>For/>Average value of/(I)Is the standard deviation of X,/>Is the standard deviation of Y.
Step S106, sorting the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area to obtain a first water quality data sequence and a second water quality data sequence.
In the step, first position information of each detection point in an abnormal preset area and second position information of each detection point in a certain preset area are respectively obtained; sequencing each first position information and each second position information based on the river flow direction to obtain a first sequencing result and a second sequencing result; sequencing the first water quality data of each detection point in the abnormal preset area according to the first sequencing result to obtain a first water quality data sequence, and sequencing the second water quality data of each detection point in a certain preset area according to the second sequencing result to obtain a second water quality data sequence.
Step S107, fusing the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fusing the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence.
In the step, judging whether first water quality data and first meteorological data corresponding to each detection point in the abnormal preset area in the same time period exist or not; if the first water quality data and the first meteorological data corresponding to a certain detection point in the same time period exist, splicing the first water quality data and the first meteorological data corresponding to the certain detection point to obtain target prediction data of the certain detection point; if the first water quality data or the first meteorological data corresponding to a certain detection point in the same time period does not exist, filling the first water quality data or the first meteorological data corresponding to the certain detection point by adopting a linear interpolation method, and splicing the first water quality data and the first meteorological data corresponding to the certain detection point after filling to obtain target prediction data of the certain detection point.
It should be noted that, the expression of the first water quality data or the first air image data corresponding to a certain filling detection point by adopting the linear interpolation method is as follows:
，
In QUOTE />Representing time variable QUOTE/> />Indicating an index value QUOTE/> />At QUOTE />Between QUOTE/> />Representing the insertion value, at QUOTE/> />Between them.
Step S108, inputting the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model, where the deep learning model outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area, respectively.
In this step, the preset deep learning model is a CNN-BiLSTM deep learning model. The data combination comprises water quality data and meteorological data, and the data set is divided into a training data set, a verification data set and a test data set according to the proportion of 7:1.5:1.5; and training the CNN-BiLSTM deep learning model by adopting a sliding window technology, wherein the window size is set to be 8, and obtaining the finally trained deep learning model.
Step S109, calculating a water quality prediction result of the other preset area according to the first water quality prediction result, the second water quality prediction result, and the ratio of the first similarity to the second similarity.
In this step, the expression for calculating the water quality prediction result of another preset area is:
,
In the method, in the process of the invention, For the water quality prediction result of another preset area,/>For the second water quality prediction result of a certain preset area,/>For the first water quality prediction result of the abnormal preset area,/>Is the ratio of the first similarity to the second similarity.
For example, the entire river includes a preset area a, a preset area B, a preset area C, a preset area D, a preset area E, a preset area F, and a preset area G in this order with the river direction as the positive direction. When the preset area A is abnormal, the user needs to acquire the water quality results of the preset area B, the preset area C, the preset area D, the preset area E, the preset area F and the preset area G, and parameters required in the water quality prediction result process of another preset area can be calculated. For example, the first water quality prediction result of the preset area a, the second water quality prediction result of the preset area B, and the first similarity of the image between the preset area B and the preset area a are obtained, the second similarity of the image between the preset area C and the preset area a can be directly calculated, and then the third water quality prediction result of the preset area C can be directly calculated, and the water quality prediction results of the preset area D, the preset area E, the preset area F and the preset area G are calculated.
If the preset area B, the preset area C, the preset area D and the preset area E need to be accurately predicted, then only the water quality data and the meteorological data of the preset area B and the preset area D need to be obtained through the method, and the water quality prediction results corresponding to the preset area B, the preset area C, the preset area D and the preset area E can be obtained rapidly.
In summary, according to the method disclosed by the application, the first target prediction data sequence and the second target prediction data sequence are respectively input into the preset deep learning model, the deep learning model respectively outputs the first water quality prediction result corresponding to the abnormal preset area and the second water quality prediction result corresponding to a certain preset area, and the water quality prediction result of the other preset area is calculated according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity, so that the water quality of each area of the whole river can be rapidly predicted, and the water quality results of continuous sections of areas of the river can be accurately obtained.
Referring to FIG. 3, a block diagram of a river water quality prediction system incorporating meteorological data according to the present application is shown.
As shown in fig. 3, the river water quality prediction system 200 includes a judging module 210, a screening module 220, a first obtaining module 230, a calculating module 240, a second obtaining module 250, a sorting module 260, a fusion module 270, an output module 280, and a prediction module 290.
The judging module 210 is configured to acquire image data in a plurality of preset areas and judge whether abnormal image data exists in each image data; the screening module 220 is configured to screen out abnormal image data if the abnormal image data exists, and define a preset area where the abnormal image data exists as an abnormal preset area; a first obtaining module 230 configured to obtain certain image data of a certain preset area and another image data of another preset area adjacent to the certain preset area; a calculation module 240 configured to acquire a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculate a ratio of the first similarity to the second similarity; a second obtaining module 250, configured to obtain first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data is located, and second water quality data and second weather data of each detection point in a preset area where the certain image data is located; the sequencing module 260 is configured to sequence the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area respectively to obtain a first water quality data sequence and a second water quality data sequence; the fusion module 270 is configured to fuse the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fuse the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence; the output module 280 is configured to input the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model respectively, where the deep learning model outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area respectively; a prediction module 290 configured to predict a water quality result of the another preset area according to the first water quality prediction result, the second water quality prediction result, and a ratio of the first similarity to the second similarity.
It should be understood that the modules depicted in fig. 3 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 3, and are not described here again.
In other embodiments, the present invention further provides a computer readable storage medium, on which a computer program is stored, where the program instructions, when executed by a processor, cause the processor to perform the river water quality prediction method combined with meteorological data in any of the above method embodiments;
as one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
acquiring image data in a plurality of preset areas, and judging whether abnormal image data exists in each image data;
if the abnormal image data exist, screening the abnormal image data, and defining a preset area where the abnormal image data exist as an abnormal preset area;
Acquiring certain image data of a certain preset area and other image data of another preset area adjacent to the certain preset area;
Acquiring a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculating a ratio of the first similarity to the second similarity;
Acquiring first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data are located, and second water quality data and second weather data of each detection point in a preset area where certain image data are located;
Sequencing the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area respectively to obtain a first water quality data sequence and a second water quality data sequence;
Fusing the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fusing the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence;
Respectively inputting the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model, wherein the deep learning model respectively outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area;
and calculating the water quality prediction result of the other preset area according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity.
The computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created from the use of river water quality prediction systems in combination with meteorological data, and the like. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes memory remotely located relative to the processor, which may be connected to the river water quality prediction system in combination with the meteorological data via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 4, where the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 4. Memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications of the server and data processing by running non-volatile software programs, instructions and modules stored in the memory 320, i.e., implements the river water quality prediction method of the above-described method embodiments in combination with meteorological data. The input device 330 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the river water quality prediction system in combination with meteorological data. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As an embodiment, the electronic device is applied to a river water quality prediction system combined with meteorological data, and is used for a client, and includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
acquiring image data in a plurality of preset areas, and judging whether abnormal image data exists in each image data;
if the abnormal image data exist, screening the abnormal image data, and defining a preset area where the abnormal image data exist as an abnormal preset area;
Acquiring certain image data of a certain preset area and other image data of another preset area adjacent to the certain preset area;
Acquiring a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculating a ratio of the first similarity to the second similarity;
Acquiring first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data are located, and second water quality data and second weather data of each detection point in a preset area where certain image data are located;
Sequencing the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area respectively to obtain a first water quality data sequence and a second water quality data sequence;
Fusing the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fusing the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence;
Respectively inputting the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model, wherein the deep learning model respectively outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area;
and calculating the water quality prediction result of the other preset area according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity.
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 such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of 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 river water quality prediction method combining meteorological data, comprising:
acquiring image data in a plurality of preset areas, and judging whether abnormal image data exists in each image data;
if the abnormal image data exist, screening the abnormal image data, and defining a preset area where the abnormal image data exist as an abnormal preset area;
Acquiring certain image data of a certain preset area and other image data of another preset area adjacent to the certain preset area, wherein the acquiring the certain image data of the certain preset area and the other image data of the other preset area adjacent to the certain preset area comprises the following steps:
acquiring certain image data of a certain preset area;
Taking the position of an abnormal preset area as an origin, taking the river flow direction as a positive direction, and acquiring another image data of another preset area adjacent to the certain preset area when the position direction from the certain preset area to the abnormal preset area is the positive direction, wherein the position direction from the other preset area to the certain preset area is the positive direction;
When the position direction from the certain preset area to the abnormal preset area is a negative direction, acquiring another image data of another preset area adjacent to the certain preset area, wherein the position direction from the other preset area to the certain preset area is a negative direction;
Acquiring a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculating a ratio of the first similarity to the second similarity;
Acquiring first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data are located, and second water quality data and second weather data of each detection point in a preset area where certain image data are located;
Sequencing the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area respectively to obtain a first water quality data sequence and a second water quality data sequence;
Fusing the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fusing the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence;
Respectively inputting the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model, wherein the deep learning model respectively outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area;
and calculating the water quality prediction result of the other preset area according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity.
2. The method for predicting river water quality in combination with meteorological data of claim 1, wherein after judging whether there is abnormal image data in each image data, the method further comprises:
if the data do not exist, screening out initial image data, and defining a preset area where the initial image data are located as a standard preset area, wherein the initial image data are first image data acquired based on river flow direction;
Acquiring certain image data of a certain preset area and other image data of another preset area adjacent to the certain preset area;
and acquiring a third similarity between the certain image data and the initial image data and a fourth similarity between the other image data and the initial image data, and calculating a ratio of the third similarity to the fourth similarity.
3. The river water quality prediction method based on meteorological data according to claim 1, wherein the step of respectively sorting the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area to obtain a first water quality data sequence and a second water quality data sequence comprises the steps of:
Respectively acquiring first position information of each detection point in an abnormal preset area and second position information of each detection point in a certain preset area;
Sequencing each first position information and each second position information based on the river flow direction to obtain a first sequencing result and a second sequencing result;
Sequencing the first water quality data of each detection point in the abnormal preset area according to the first sequencing result to obtain a first water quality data sequence, and sequencing the second water quality data of each detection point in a certain preset area according to the second sequencing result to obtain a second water quality data sequence.
4. The method of claim 1, wherein the fusing the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target predicted data sequence, and fusing the second meteorological data into the second water quality data sequence to obtain a second target predicted data sequence comprises:
judging whether first water quality data and first meteorological data corresponding to all detection points in the abnormal preset area in the same time period exist or not;
If the first water quality data and the first meteorological data corresponding to a certain detection point in the same time period exist, splicing the first water quality data and the first meteorological data corresponding to the certain detection point to obtain target prediction data of the certain detection point;
If the first water quality data or the first meteorological data corresponding to a certain detection point in the same time period does not exist, filling the first water quality data or the first meteorological data corresponding to the certain detection point by adopting a linear interpolation method, and splicing the first water quality data and the first meteorological data corresponding to the certain detection point after filling to obtain target prediction data of the certain detection point.
5. The river water quality prediction method in combination with meteorological data of claim 1, wherein the expression for calculating the water quality prediction result of the other preset area is:
,
In the method, in the process of the invention, For the water quality prediction result of another preset area,/>A second water quality prediction result for a certain preset area,For the first water quality prediction result of the abnormal preset area,/>Is the ratio of the first similarity to the second similarity.
6. A river water quality prediction system incorporating meteorological data, comprising:
The judging module is configured to acquire image data in a plurality of preset areas and judge whether abnormal image data exists in each image data or not;
The screening module is configured to screen out abnormal image data if the abnormal image data exist, and define a preset area where the abnormal image data are located as an abnormal preset area;
a first obtaining module configured to obtain certain image data of a certain preset area and another image data of another preset area adjacent to the certain preset area, wherein the obtaining the certain image data of the certain preset area and the another image data of another preset area adjacent to the certain preset area includes:
acquiring certain image data of a certain preset area;
Taking the position of an abnormal preset area as an origin, taking the river flow direction as a positive direction, and acquiring another image data of another preset area adjacent to the certain preset area when the position direction from the certain preset area to the abnormal preset area is the positive direction, wherein the position direction from the other preset area to the certain preset area is the positive direction;
When the position direction from the certain preset area to the abnormal preset area is a negative direction, acquiring another image data of another preset area adjacent to the certain preset area, wherein the position direction from the other preset area to the certain preset area is a negative direction;
A calculation module configured to acquire a first similarity between the certain image data and the abnormal image data and a second similarity between the other image data and the abnormal image data, and calculate a ratio of the first similarity to the second similarity;
The second acquisition module is configured to acquire first water quality data and first weather data of each detection point in an abnormal preset area where the abnormal image data are located, and second water quality data and second weather data of each detection point in a preset area where certain image data are located;
the sequencing module is configured to sequence the first water quality data of each detection point in the abnormal preset area and the second water quality data of each detection point in a certain preset area respectively to obtain a first water quality data sequence and a second water quality data sequence;
The fusion module is configured to fuse the first meteorological data into the first water quality data sequence based on a preset fusion rule to obtain a first target prediction data sequence, and fuse the second meteorological data into the second water quality data sequence to obtain a second target prediction data sequence;
the output module is configured to input the first target prediction data sequence and the second target prediction data sequence into a preset deep learning model respectively, and the deep learning model outputs a first water quality prediction result corresponding to the abnormal preset area and a second water quality prediction result corresponding to the certain preset area respectively;
and the prediction module is configured to predict the water quality result of the other preset area according to the first water quality prediction result, the second water quality prediction result and the ratio of the first similarity to the second similarity.
7. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410116722.7A CN117671507B (en) | 2024-01-29 | 2024-01-29 | River water quality prediction method combining meteorological data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410116722.7A CN117671507B (en) | 2024-01-29 | 2024-01-29 | River water quality prediction method combining meteorological data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117671507A CN117671507A (en) | 2024-03-08 |
| CN117671507B true CN117671507B (en) | 2024-05-10 |
Family
ID=90073451
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410116722.7A Active CN117671507B (en) | 2024-01-29 | 2024-01-29 | River water quality prediction method combining meteorological data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117671507B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112379070A (en) * | 2020-11-09 | 2021-02-19 | 安庆中春自动化技术有限公司 | River course water environment environmental protection administers pollution sources monitoring management system based on big data |
| WO2021217859A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Target anomaly identification method and apparatus, and electronic device and storage medium |
| CN114723188A (en) * | 2022-06-09 | 2022-07-08 | 广东盈峰科技有限公司 | Water quality prediction method, device, computer equipment and storage medium |
| CN115146874A (en) * | 2022-08-03 | 2022-10-04 | 电子科技大学 | River water quality prediction method based on multi-graph convolution network |
| CN115829120A (en) * | 2022-11-29 | 2023-03-21 | 中国环境科学研究院 | Water quality prediction early warning system based on machine learning method |
| CN115983493A (en) * | 2023-02-13 | 2023-04-18 | 重庆大学 | Water quality prediction method based on multitask learning and deep learning model |
| CN116466058A (en) * | 2023-06-15 | 2023-07-21 | 上海博取仪器有限公司 | Water quality detection data processing method, water quality evaluation system, equipment and medium |
| CN117273203A (en) * | 2023-09-05 | 2023-12-22 | 内蒙古工业大学 | Water quality prediction method and system based on GAT-transducer time sequence model |
-
2024
- 2024-01-29 CN CN202410116722.7A patent/CN117671507B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021217859A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Target anomaly identification method and apparatus, and electronic device and storage medium |
| CN112379070A (en) * | 2020-11-09 | 2021-02-19 | 安庆中春自动化技术有限公司 | River course water environment environmental protection administers pollution sources monitoring management system based on big data |
| CN114723188A (en) * | 2022-06-09 | 2022-07-08 | 广东盈峰科技有限公司 | Water quality prediction method, device, computer equipment and storage medium |
| CN115146874A (en) * | 2022-08-03 | 2022-10-04 | 电子科技大学 | River water quality prediction method based on multi-graph convolution network |
| CN115829120A (en) * | 2022-11-29 | 2023-03-21 | 中国环境科学研究院 | Water quality prediction early warning system based on machine learning method |
| CN115983493A (en) * | 2023-02-13 | 2023-04-18 | 重庆大学 | Water quality prediction method based on multitask learning and deep learning model |
| CN116466058A (en) * | 2023-06-15 | 2023-07-21 | 上海博取仪器有限公司 | Water quality detection data processing method, water quality evaluation system, equipment and medium |
| CN117273203A (en) * | 2023-09-05 | 2023-12-22 | 内蒙古工业大学 | Water quality prediction method and system based on GAT-transducer time sequence model |
Non-Patent Citations (3)
| Title |
|---|
| Research on water environmental indicators prediction method based on EEMD decomposition with CNN‑BiLSTM;Zhaohua Wang et al.;《Scientifc Reports》;20240119;第1-11页 * |
| Spatial prediction ofwater quality variables along amain river channel, in presence of pollution hotspots;L.D. Rizo-Decelis et al.;《Science of the Total Environment》;20170629;第276-290页 * |
| 基于LSTM深度学习的水产养殖水质预测模型研究及系统实现;李祥铜;《中国优秀硕士学位论文全文数据库 农业科技辑 》;20240115;D052-120 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117671507A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111754042A (en) | Atmospheric pollutant concentration prediction method and device based on Gaussian regression | |
| CN116359218B (en) | Industrial aggregation area atmospheric pollution mobile monitoring system | |
| CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN115995056A (en) | Automatic bridge disease identification method based on deep learning | |
| CN116310850B (en) | Remote sensing image target detection method based on improved RetinaNet | |
| CN117892915A (en) | Commodity carbon label generation method and system based on accounting unit | |
| CN116702090A (en) | Multi-mode data fusion and uncertain estimation water level prediction method and system | |
| CN117977576A (en) | Platform load prediction method based on multi-scale historical load data | |
| CN115983497A (en) | Time sequence data prediction method and device, computer equipment and storage medium | |
| CN118351380A (en) | Weather detection method based on multi-mode data fusion framework | |
| CN113553577B (en) | Unknown user malicious behavior detection method and system based on hypersphere variational automatic encoder | |
| CN116977834B (en) | Method for identifying internal and external images distributed under open condition | |
| CN117391257A (en) | Road congestion condition prediction method and device | |
| CN117671507B (en) | River water quality prediction method combining meteorological data | |
| CN117269742A (en) | Method, device and medium for evaluating health state of circuit breaker in high-altitude environment | |
| CN113989632A (en) | Bridge detection method and device for remote sensing image, electronic equipment and storage medium | |
| CN116630909B (en) | Unmanned intelligent monitoring system and method based on unmanned aerial vehicle | |
| CN114399788B (en) | Object detection method and system | |
| CN118196567B (en) | Data evaluation method, device, equipment and storage medium based on large language model | |
| CN117798498B (en) | Method and system for automatically adjusting welding abnormality of intelligent laser welding machine | |
| CN118275309B (en) | Online monitoring system and method for condensable particles in industrial exhaust flue gas | |
| KR20240136875A (en) | Determining whether a given input record of measurement data is covered by the training of a trained machine learning model | |
| CN118364951A (en) | Power transmission line early warning method and device under typhoon disaster and computer equipment | |
| CN117854280A (en) | Traffic flow prediction method, traffic flow prediction device, electronic equipment and readable storage medium | |
| CN116168263A (en) | Training method of mountain fire smoke detection model and mountain fire smoke identification method |
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 |