CN112684130A - Watershed water quality prediction method and device and computer readable storage medium - Google Patents
Watershed water quality prediction method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN112684130A CN112684130A CN202011321750.0A CN202011321750A CN112684130A CN 112684130 A CN112684130 A CN 112684130A CN 202011321750 A CN202011321750 A CN 202011321750A CN 112684130 A CN112684130 A CN 112684130A
- Authority
- CN
- China
- Prior art keywords
- data
- watershed
- water quality
- prediction model
- sample data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the disclosure provides a watershed water quality prediction method and device and a computer readable storage medium, and belongs to the field of water quality prediction. The watershed water quality prediction method comprises the following steps: acquiring a sample data set of a watershed; carrying out one-hot code preprocessing on the sample data set of the watershed to obtain preprocessed intermediate sample data; inputting the intermediate sample data into a preset target prediction model; the intermediate sample data is predicted through the target prediction model to obtain the target water quality data.
Description
Technical Field
The invention relates to the field of computers, in particular to a watershed water quality prediction method and device and a computer-readable storage medium.
Background
The watershed water quality prediction method generally uses a machine learning algorithm, such as KNN, linear regression, logistic regression, support vector machine, etc., and can meet part of the requirements. However, the machine learning algorithm is limited by the requirement of the input data type, and can only be a numerical value type, and on the premise, text data with large influence weight on the water quality of the watershed cannot be processed; in addition, the basin environment is complex, an algorithm which can well fit the requirements of basin water quality prediction is difficult to find, and a common machine learning algorithm is used for establishing a plurality of models in a universal method, so that the method is troublesome and complex.
Disclosure of Invention
The main purpose of the embodiments of the present disclosure is to provide a watershed water quality prediction method and apparatus, and a computer-readable storage medium, so as to reduce the cost of constructing a prediction model and improve the accuracy of predicted water quality data.
In order to achieve the above object, a first aspect of the embodiments of the present disclosure provides a watershed water quality prediction method, including:
acquiring a sample data set of a watershed;
carrying out one-hot code preprocessing on the sample data set of the watershed to obtain preprocessed intermediate sample data;
inputting the intermediate sample data into a preset target prediction model;
and receiving target water quality data predicted by the prediction model according to the intermediate sample data.
In some embodiments, the sample data set of the watershed includes text data, and the performing unique hot code preprocessing on the sample data set of the watershed to obtain preprocessed intermediate sample data includes:
acquiring the text data;
acquiring historical data;
and carrying out one-hot code encoding preprocessing on the historical data according to the text data to obtain the intermediate sample data.
In some embodiments, the textual data includes weather data.
In some embodiments, the sample data set of the watershed is cleaned to obtain cleaned watershed intermediate data; and taking the cleaned watershed intermediate data as the data for preprocessing the unique hot code.
In some embodiments, the watershed intermediate data comprises at least one of: the method comprises the following steps of cleaning the basin intermediate data to obtain cleaned basin intermediate data, wherein the cleaning comprises null data, repeated data, abnormal range data and external data acquired through a weather interface, and at least one of the following steps is included:
cleaning the null value data to obtain the cleaned basin intermediate data;
cleaning the repeated data to obtain the cleaned watershed intermediate data;
cleaning the abnormal range data to obtain the cleaned watershed intermediate data;
and cleaning the external data to obtain the cleaned watershed intermediate data.
In some embodiments, the intermediate sample data comprises sample water quality data, the method further comprising: constructing the target prediction model specifically comprises the following steps:
constructing an initial prediction model according to the sample water quality data;
and inputting the sample water quality data into the initial prediction model for training to obtain the target prediction model.
In some embodiments, the intermediate sample data further comprises test water quality data, the method further comprising: and evaluating the target prediction model according to the test water quality data.
In some embodiments, the method further comprises:
deploying the target prediction model to an application platform, wherein the application platform is at least one of the following: an application database or an application management platform.
In order to achieve the above object, a second aspect of the embodiments of the present disclosure provides a watershed water quality prediction apparatus, including:
the acquisition module is used for acquiring a sample data set of the watershed;
the preprocessing module is used for carrying out one-hot code preprocessing on the sample data set of the watershed to obtain preprocessed intermediate sample data;
the input module is used for inputting the intermediate sample data into a preset target prediction model;
and the receiving module is used for receiving the target water quality data predicted by the prediction model according to the intermediate sample data.
To achieve the above object, a third aspect of the embodiments of the present disclosure provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform: the method as described above.
According to the watershed water quality prediction method and device and the computer-readable storage medium provided by the embodiment of the disclosure, the sample data set of the watershed is subjected to the one-hot code preprocessing by obtaining the sample data set of the watershed to obtain the preprocessed intermediate sample data, the intermediate sample data is input into the preset target prediction model, the intermediate sample data is predicted by the target prediction model to obtain the target water quality data, only the target prediction model needs to be built, a plurality of models do not need to be built, the cost for building the model is reduced, and the accuracy of the predicted water quality data is improved.
Drawings
Fig. 1 is a flowchart of a watershed water quality prediction method according to a first embodiment of the disclosure.
Fig. 2 is a flowchart of step 102 in fig. 1.
Fig. 3 is a flowchart of a watershed water quality prediction method according to a second embodiment of the disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. The terms first, second and the like in the description and in the claims, and the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.
First, several terms referred to in the present application are resolved:
PH (pundus hydrogenii, PH): the degree of acidity and alkalinity of the aqueous solution is described and is expressed in terms of pH. In the thermodynamic standard, an aqueous solution having a pH of 7 is neutral, acidic when the pH is less than 7, and basic when the pH is greater than 7.
K nearest neighbor (K-nearest neighbor, KNN) algorithm: the method is a classification algorithm and is one of the methods in the data mining classification technology. Where K nearest neighbors means that each sample can be represented by the nearest K neighbors. The neighbor algorithm is a method for classifying each record in the data set.
Linear regression: the method is a statistical analysis method for determining the interdependent quantitative relationship between two or more variables by using regression analysis in mathematical statistics, and is widely applied. Expressed in the form y ═ w' x + e, e is a normal distribution with an error following a mean value of 0.
And (3) logistic regression: the method is a generalized linear regression analysis model and is commonly used in the fields of data mining, automatic disease diagnosis, economic prediction and the like.
A support vector machine: the classifier is developed by a generalized port algorithm (generalized portrait algorithm) in pattern recognition, and is a generalized linear classifier (generalized linear classifier) for binary classification of data in a supervised learning (super learning) mode, and a decision boundary of the classifier is a maximum margin hyperplane for solving a learning sample.
tf. keras. model: the defined network structure is encapsulated into an object for training, testing and forecasting.
tf. kers. layers: implementing classes of common neural network operations such as convolution, batch normalization, etc. These operations require management of weights, losses, updates, and inter-layer connections.
Nonlinear activation function Relu: used for improving the expression capability of the neural network model.
Softmax function: when the method is used in a multi-classification process, the output of a plurality of neurons is mapped into a (0,1) interval, so that multi-classification is realized.
Watershed environmental remediation has been a hot and worthy of research problem. According to a relevant machine learning algorithm, the watershed water quality, such as the change of pH, residual chlorine, turbidity, ammonia nitrogen, conductivity and dissolved oxygen, is predicted in advance, and a watershed water quality abnormity alarm is generated, so that scientific basis is provided for further improving the environment supervision capability of workers, promoting the adjustment of industrial structures, strengthening the upgrading and reconstruction of sewage treatment plants, developing watershed comprehensive treatment, optimizing a cross-boundary section ecological compensation mechanism, water quality mutation and other countermeasures for improving water quality.
The watershed water quality prediction method is realized by a multi-purpose machine learning algorithm, such as a KNN algorithm, a linear regression, a logistic regression, a support vector machine and the like, and can meet part of requirements on the premise of simple requirements and small data volume due to simple realization and low cost. However, the machine learning algorithm is limited by the requirement of the input data type, and can only be data of a numerical value type, and on the premise, text data with large influence weight on the water quality of the watershed cannot be processed; in addition, the basin environment is complex, an algorithm which can well fit the requirements of basin water quality prediction is difficult to find, and a common machine learning algorithm is utilized to establish a plurality of models in a universal method, so that the method is complex and troublesome.
Based on the above problems, the embodiments of the present disclosure provide a watershed water quality prediction method and apparatus, an electronic device, and a computer-readable storage medium, and specifically, the following embodiments are described to first describe the watershed water quality prediction method in the embodiments of the present disclosure.
The watershed water quality prediction method provided by the embodiment of the disclosure can be applied to a terminal, a server side and software running in the terminal or the server side. In some embodiments, the terminal may be a smartphone, tablet, laptop, desktop computer, smart watch, or the like; the server side can be configured into an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and cloud servers for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN (content delivery network) and big data and artificial intelligence platforms; the software may be an application or the like that implements a watershed water quality prediction method, but is not limited to the above form.
Fig. 1 is an optional flowchart of a watershed water quality prediction method provided in an embodiment of the present disclosure, where the method in fig. 1 includes steps 101 to 104. The watershed water quality prediction method is applied to outdoor communication equipment.
102, carrying out one-hot code preprocessing on a sample data set of a watershed to obtain preprocessed intermediate sample data;
and 104, receiving target water quality data predicted by the target prediction model according to the intermediate sample data.
In some embodiments, the source of the sample data set of the watershed may be obtained through a sensor or a weather interface, and the implementation of the present disclosure is not limited. The sample data set of the watershed may include numerical data or text data, and the present disclosure is not limited in implementation.
Typically, the sample data set of the watershed acquired by the sensor is numerical data, which may be, for example, pH, residual chlorine, turbidity, ammonia nitrogen, conductivity, dissolved oxygen, or instantaneous speed of water flow, etc., i.e., the sensor may be a data sensor. The sensors are generally deployed at key nodes along the flow field, and the sensors can regularly acquire the numerical data according to preset time intervals. Under the condition that network abnormality and sensor abnormality do not occur, the sample data set of the watershed acquired by the sensor is relatively stable, and the method is very suitable for machine learning or neural network modeling.
The method comprises the steps that a weather data interface needs to be called through a sample data set of a basin acquired through a weather interface, historical weather data of a water quality monitoring point position needs to be acquired, the historical weather data can be text data such as weather, and the historical weather data can also be numerical data such as temperature and rainfall.
In some embodiments, if the sample data set of the watershed includes text data, step 102 includes steps 201 to 203:
and 203, carrying out one-hot code encoding preprocessing on the historical data according to the text data to obtain intermediate sample data.
In some embodiments, the textual data includes at least weather data. Wherein the weather data has obvious classification characteristics.
Specifically, the description is given by taking weather data as an example, where the weather data includes a weather type; step 201 includes counting weather types, setting the weather types as List1, and regarding List1, List1 is [ "clear", "cloudy", "rainy", "thunderstorm with hail", "sleet", "light rain", "medium rain", "heavy rainstorm", "extra heavy rainstorm", "snow storm", "small snow", "medium snow", "heavy snow", "fog", "sleet", "sand storm-medium rain", "medium rain-heavy rain", "heavy rain-heavy rainstorm", "heavy rain-extra heavy rainstorm", "small snow-medium snow", "medium snow-heavy snow", "heavy snow-heavy snow", "floating dust", "sand raising", "strong sand storm", "haze ].
In some embodiments, the historical data of step 202 includes historical weather data in a preset time period, the historical weather data includes historical weather types, and the historical weather data acquired in the preset time period is set to List2, and for List2, there is List2 [ "fine", "cloudy", "thunderstorm", "cloudy", "light rain", "cloudy", "heavy rain", … … ]. The data in the List2 may be equal to the data in the List2, and the data in the List2 may also be smaller than the data in the List2, which is not limited in the embodiments of the present disclosure.
In some embodiments, step 203 comprises: each weather type appearing in List2 is one-hot coded according to the order of the positions where the types appear in Li st 1. For example, "sunny" in List2, whose one-hot code is coded 100000000000000000000000000000000, and "negative" one-hot code in List2 is coded 001000000000000000000000000000000. Assuming that there are N types in the List2, N unique codes of the weather data appear after the processing in step 203. And finishing the encoding preprocessing of the one-hot code by the weather data for constructing the target prediction model. Similarly, other text data can be preprocessed by one-hot code coding according to the steps.
In some embodiments, the watershed water quality prediction method further comprises:
cleaning the sample data set of the basin to obtain cleaned basin intermediate data; and taking the cleaned intermediate data of the watershed as the data for carrying out the one-hot code preprocessing.
In some embodiments, the watershed intermediate data comprises at least one of: the method comprises the following steps of obtaining null data, repeated data, abnormal range data and external data acquired through a weather interface, wherein the intermediate data of the flow field is cleaned to obtain the cleaned intermediate data of the flow field, and the method at least comprises the following steps:
cleaning the null data to obtain cleaned basin intermediate data;
cleaning the repeated data to obtain cleaned basin intermediate data;
cleaning the abnormal range data to obtain cleaned basin intermediate data;
and cleaning the external data to obtain cleaned basin intermediate data.
The abnormal range data is cleaned, the data ranges of different labels are different, and range definition can be performed by referring to national standards and actual historical acquisition values.
And cleaning the external data acquired through the weather interface, for example, displaying irregular text content or comparing weather, and verifying the reliability of the rainfall data.
The intermediate data of the basin subjected to cleaning treatment is numerical data, and after the numerical data is cleaned by the numerical data, special pretreatment is not required. Since the text data cannot be directly used for modeling of the neural network, the text data needs to be preprocessed in step 102.
In some embodiments, the intermediate sample data includes sample water quality data, referring to fig. 3, the watershed water quality prediction method further includes: constructing a target prediction model, specifically comprising steps 301 to 302:
301, constructing an initial prediction model according to sample water quality data;
In some embodiments, the intermediate sample data further includes test water quality data, and the watershed water quality prediction method further includes:
and step 303, evaluating the target prediction model according to the test water quality data.
Specifically, in step 301, the embodiment of the present disclosure samples tf.keras.model and tf.keras.layers to construct, introduces the nonlinear activation function Relu, and finally normalizes the original output of the model by the Softmax function. The model of the invention inputs a vector (here, a straightened historical data vector group) and outputs a one-dimensional or multi-dimensional vector which respectively represents the one-to-one correspondence relationship between the predicted value and the target water quality label
Specifically, in step 302, the historical data set is input into an initial prediction model for training, so as to obtain a target prediction model, and the prediction value of the model is calculated through the prediction model. The embodiment of the disclosure adopts the cross entropy in tf.keras.loss as a loss function to evaluate the loss condition between the predicted value and the true value of the model. Loss function minimization is the objective of the disclosed embodiments to evaluate, and therefore the disclosed embodiments require calculating the derivative of the loss function with respect to the model variables, passing the found derivative values into the optimizer tf.
Specifically, in step 303, an evaluator tf, keras, metrics is used to evaluate the performance of the model on the test water quality data, and the evaluator tf, keras, metrics can compare the prediction result of the prediction model with the real result and output the ratio of the correctly predicted sample number to the total sample number.
In step 104, a text vector (here, a straightened historical data vector group) is input into the target prediction model, the target prediction model outputs a one-dimensional or multi-dimensional target vector, and the text vector input into the target prediction model and the multi-dimensional items output by the target prediction model respectively represent the one-to-one correspondence relationship between predicted values and target water quality data.
In some embodiments, the watershed water quality prediction method further comprises:
deploying the target prediction model to an application platform, the application platform being at least one of: an application database or an application management platform.
Specifically, the constructed target prediction model is deployed to the corresponding application platform. In practical application, the characteristic data acquired at regular time is input into a target prediction model for prediction, whether the acquired characteristic data is valid or not is judged, and if the acquired characteristic data is valid, prediction is performed through the target prediction model, so that target water quality data can be predicted. And finally, pushing the predicted target water quality data to an application database or an application management platform, thereby realizing the monitoring of the intermediate data of the drainage basin.
The embodiment of the disclosure is a watershed water quality prediction method based on a neural network, and the neural network can be used for various algorithms theoretically, so that a plurality of modeling costs of machine learning are reduced, namely the cost for constructing a plurality of target prediction models is reduced. In addition, the word vector conversion is carried out on the text data which is difficult to process by the machine learning algorithm through the one-hot codes, the target prediction model for predicting the watershed water quality is established by utilizing the neural network, and the robustness and the accuracy of the watershed water quality prediction model are enhanced. In addition, the text data are preprocessed through the one-hot codes, the text data with larger influence weight are converted into the text vectors which can be used for neural network model training, and then the target prediction model for predicting the watershed water quality is established through the neural network, so that the watershed water quality can be conveniently predicted.
The embodiment of the present disclosure further provides another drainage basin water quality prediction apparatus, which can implement the drainage basin water quality prediction method, and the apparatus includes:
the acquisition module is used for acquiring a sample data set of the watershed;
the preprocessing module is used for preprocessing the sample data set of the watershed by the one-hot code to obtain preprocessed intermediate sample data;
the input module is used for inputting the intermediate sample data into a preset target prediction model;
and the receiving module is used for receiving the target water quality data predicted by the prediction model according to the intermediate sample data.
The disclosed embodiment also provides a watershed water quality prediction device of yet another embodiment, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the above-described method steps 101 to 104 in fig. 1, method steps 201 to 203 in fig. 2, and method steps 301 to 303 in fig. 3 are implemented.
An embodiment of the present disclosure further provides an electronic device, including:
at least one memory;
at least one processor;
at least one program;
the programs are stored in a memory, and a processor executes the at least one program to implement the method for address retrieval described above in the present application. The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a Personal Digital Assistant (PDA for short), a vehicle-mounted computer and the like.
The embodiment of the disclosure also provides a computer-readable storage medium, and the computer-executable instructions are used for executing the watershed water quality prediction method.
According to the watershed water quality prediction method, the watershed water quality prediction device, the electronic equipment and the computer-readable storage medium, the sample data set of the watershed is subjected to unique hot code preprocessing to obtain preprocessed intermediate sample data, the intermediate sample data is input into a preset target prediction model, the intermediate sample data is predicted through the target prediction model to obtain target water quality data, only the target prediction model needs to be built, multiple models do not need to be built, the cost of building the models is reduced, and the accuracy of predicting the water quality data is improved. The embodiment of the disclosure is a watershed water quality prediction method based on a neural network, and the neural network can be used for various algorithms theoretically, so that a plurality of modeling costs of machine learning are reduced, namely the cost for constructing a plurality of target prediction models is reduced. In addition, the word vector conversion is carried out on the text data which is difficult to process by the machine learning algorithm through the one-hot codes, and the robustness and the accuracy of the watershed water quality prediction model are enhanced by establishing the target prediction model for predicting the watershed by utilizing the neural network. In addition, the text data are preprocessed through the one-hot codes, the text data with larger influence weight are converted into the text vectors which can be used for neural network model training, and then the target prediction model for predicting the watershed water quality is established through the neural network, so that the watershed water quality can be conveniently predicted.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The embodiments described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation to the technical solutions provided in the embodiments of the present disclosure, and it is obvious to those skilled in the art that the technical solutions provided in the embodiments of the present disclosure are also applicable to similar technical problems with the evolution of technology and the emergence of new application scenarios.
It will be understood by those skilled in the art that the watershed water quality prediction methods shown in fig. 1-3 are not limiting of the disclosed embodiments and may include more or fewer steps than those shown, or some of the steps may be combined, or different steps.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also 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 the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing programs, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The preferred embodiments of the present disclosure have been described above with reference to the accompanying drawings, and therefore do not limit the scope of the claims of the embodiments of the present disclosure. Any modifications, equivalents and improvements within the scope and spirit of the embodiments of the present disclosure should be considered within the scope of the claims of the embodiments of the present disclosure by those skilled in the art.
Claims (10)
1. A watershed water quality prediction method is characterized by comprising the following steps:
acquiring a sample data set of a watershed;
carrying out one-hot code preprocessing on the sample data set of the watershed to obtain preprocessed intermediate sample data;
inputting the intermediate sample data into a preset target prediction model;
and receiving target water quality data predicted by the target prediction model according to the intermediate sample data.
2. The method according to claim 1, wherein the sample data set of the watershed includes text data, and the performing unique hot code preprocessing on the sample data set of the watershed to obtain preprocessed intermediate sample data includes:
acquiring the text data;
acquiring historical data;
and carrying out one-hot code encoding preprocessing on the historical data according to the text data to obtain the intermediate sample data.
3. The method of claim 2, wherein the textual data comprises weather data.
4. The method of claim 1, further comprising: cleaning the sample data set of the watershed to obtain cleaned watershed intermediate data; and taking the cleaned watershed intermediate data as the data for preprocessing the unique hot code.
5. The method of claim 4, wherein the watershed intermediate data comprises at least one of: the method comprises the following steps of cleaning the basin intermediate data to obtain cleaned basin intermediate data, wherein the cleaning comprises null data, repeated data, abnormal range data and external data acquired through a weather interface, and at least one of the following steps is included:
cleaning the null value data to obtain the cleaned basin intermediate data;
cleaning the repeated data to obtain the cleaned watershed intermediate data;
cleaning the abnormal range data to obtain the cleaned watershed intermediate data;
and cleaning the external data to obtain the cleaned watershed intermediate data.
6. The method of claim 1, wherein the intermediate sample data comprises sample water quality data, the method further comprising: constructing the target prediction model specifically comprises the following steps:
constructing an initial prediction model according to the sample water quality data;
and inputting the sample water quality data into the initial prediction model for training to obtain the target prediction model.
7. The method of claim 6, wherein the intermediate sample data further comprises test water quality data, the method further comprising: and evaluating the target prediction model according to the test water quality data.
8. The method according to any one of claims 1 to 7, further comprising:
deploying the target prediction model to an application platform, wherein the application platform is at least one of the following: an application database or an application management platform.
9. A watershed water quality prediction device is characterized by comprising:
the acquisition module is used for acquiring a sample data set of the watershed;
the preprocessing module is used for carrying out one-hot code preprocessing on the sample data set of the watershed to obtain preprocessed intermediate sample data;
the input module is used for inputting the intermediate sample data into a preset target prediction model;
and the receiving module is used for receiving the target water quality data predicted by the prediction model according to the intermediate sample data.
10. A computer-readable storage medium having computer-executable instructions stored thereon for causing a computer to perform:
the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011321750.0A CN112684130A (en) | 2020-11-23 | 2020-11-23 | Watershed water quality prediction method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011321750.0A CN112684130A (en) | 2020-11-23 | 2020-11-23 | Watershed water quality prediction method and device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112684130A true CN112684130A (en) | 2021-04-20 |
Family
ID=75446674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011321750.0A Pending CN112684130A (en) | 2020-11-23 | 2020-11-23 | Watershed water quality prediction method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112684130A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358021A (en) * | 2017-06-01 | 2017-11-17 | 华南理工大学 | DO prediction model establishment method based on BP neural network optimization |
| CN107688871A (en) * | 2017-08-18 | 2018-02-13 | 中国农业大学 | A kind of water quality prediction method and device |
| CN110610261A (en) * | 2019-08-23 | 2019-12-24 | 广东奥博信息产业股份有限公司 | Water body dissolved oxygen prediction method based on neural network |
| CN110991474A (en) * | 2019-10-12 | 2020-04-10 | 未鲲(上海)科技服务有限公司 | Machine learning modeling platform |
| CN111367961A (en) * | 2020-02-27 | 2020-07-03 | 西安交通大学 | Time sequence data event prediction method and system based on graph convolution neural network and application thereof |
| CN111458471A (en) * | 2019-12-19 | 2020-07-28 | 中国科学院合肥物质科学研究院 | Water area detection early warning method based on graph neural network |
| CN111524353A (en) * | 2020-04-28 | 2020-08-11 | 中国计量大学 | Method for traffic text data for speed prediction and travel planning |
| CN111553468A (en) * | 2020-05-15 | 2020-08-18 | 南京大学 | Method for accurately predicting effluent quality of sewage treatment plant |
| CN111639748A (en) * | 2020-05-15 | 2020-09-08 | 武汉大学 | Watershed pollutant flux prediction method based on LSTM-BP space-time combination model |
-
2020
- 2020-11-23 CN CN202011321750.0A patent/CN112684130A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358021A (en) * | 2017-06-01 | 2017-11-17 | 华南理工大学 | DO prediction model establishment method based on BP neural network optimization |
| CN107688871A (en) * | 2017-08-18 | 2018-02-13 | 中国农业大学 | A kind of water quality prediction method and device |
| CN110610261A (en) * | 2019-08-23 | 2019-12-24 | 广东奥博信息产业股份有限公司 | Water body dissolved oxygen prediction method based on neural network |
| CN110991474A (en) * | 2019-10-12 | 2020-04-10 | 未鲲(上海)科技服务有限公司 | Machine learning modeling platform |
| CN111458471A (en) * | 2019-12-19 | 2020-07-28 | 中国科学院合肥物质科学研究院 | Water area detection early warning method based on graph neural network |
| CN111367961A (en) * | 2020-02-27 | 2020-07-03 | 西安交通大学 | Time sequence data event prediction method and system based on graph convolution neural network and application thereof |
| CN111524353A (en) * | 2020-04-28 | 2020-08-11 | 中国计量大学 | Method for traffic text data for speed prediction and travel planning |
| CN111553468A (en) * | 2020-05-15 | 2020-08-18 | 南京大学 | Method for accurately predicting effluent quality of sewage treatment plant |
| CN111639748A (en) * | 2020-05-15 | 2020-09-08 | 武汉大学 | Watershed pollutant flux prediction method based on LSTM-BP space-time combination model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lv et al. | Deep learning combined wind speed forecasting with hybrid time series decomposition and multi-objective parameter optimization | |
| Galelli et al. | An evaluation framework for input variable selection algorithms for environmental data-driven models | |
| Wang et al. | A compound framework for wind speed forecasting based on comprehensive feature selection, quantile regression incorporated into convolutional simplified long short-term memory network and residual error correction | |
| Bin et al. | Regression model for appraisal of real estate using recurrent neural network and boosting tree | |
| Sundararajan et al. | Regression and generalized additive model to enhance the performance of photovoltaic power ensemble predictors | |
| CN115169724A (en) | Runoff prediction method based on space-time graph convolutional neural network | |
| CN114565124A (en) | Ship traffic flow prediction method based on improved graph convolution neural network | |
| CN115587666A (en) | Load prediction method and system based on seasonal trend decomposition and hybrid neural network | |
| Wegayehu et al. | Multivariate streamflow simulation using hybrid deep learning models | |
| CN113360848A (en) | Time sequence data prediction method and device | |
| CN111882157A (en) | Demand prediction method and system based on deep space-time neural network and computer readable storage medium | |
| CN112766603A (en) | Traffic flow prediction method, system, computer device and storage medium | |
| CN112911533B (en) | Temperature detection system based on remove end App | |
| CN112684130A (en) | Watershed water quality prediction method and device and computer readable storage medium | |
| CN116702090A (en) | Multi-mode data fusion and uncertain estimation water level prediction method and system | |
| CN117009785A (en) | Security monitoring method, device, server and system | |
| CN116226748A (en) | Multi-label co-occurrence network discrimination-based electricity stealing type detection method and system | |
| CN115217152A (en) | Method and device for predicting opening and closing deformation of immersed tunnel pipe joint | |
| CN114399101A (en) | TCN-BIGRU-based gas load prediction method and device | |
| CN114915563A (en) | Network flow prediction method and system | |
| CN116910667B (en) | Communication tower abnormal state analysis method and system based on decision algorithm | |
| Alamgeer et al. | Data Mining with Comprehensive Oppositional Based Learning for Rainfall Prediction. | |
| CN117155706B (en) | Network abnormal behavior detection method and system | |
| CN113379125B (en) | Logistics storage sales prediction method based on TCN and LightGBM combined model | |
| Jun-Gang | Time-Series Prediction Research Based on Combined Prophet-LSTM Models |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210420 |
|
| RJ01 | Rejection of invention patent application after publication |