CN115169691A - Pollution factor emission prediction system and method based on artificial intelligence and storage medium - Google Patents
Pollution factor emission prediction system and method based on artificial intelligence and storage medium Download PDFInfo
- Publication number
- CN115169691A CN115169691A CN202210792481.9A CN202210792481A CN115169691A CN 115169691 A CN115169691 A CN 115169691A CN 202210792481 A CN202210792481 A CN 202210792481A CN 115169691 A CN115169691 A CN 115169691A
- Authority
- CN
- China
- Prior art keywords
- pollution factor
- pollution
- concentration value
- prediction
- historical
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The invention relates to the technical field of environmental monitoring, in particular to a pollution factor emission prediction system, a method and a storage medium based on artificial intelligence, wherein the method comprises the following steps: s100, acquiring a historical hour concentration value of a pollution factor of a monitored object; s200, judging whether the historical hour concentration value of the pollution factor is an abnormal value or not; if not, storing the historical hour concentration value of the pollution factor into a data set; s300, selecting a historical hour concentration value of the pollution factor in a data set within a preset time period, and constructing a training sample subset; s400, predicting the emission data of the pollution factors through a prediction model according to the data in the training sample subset, and generating a prediction result vector; s500, judging whether the vector of the prediction result is in an error range; if yes, storing the prediction model and the parameters; if not, adjusting the parameters of the prediction model. By adopting the scheme, the accuracy of the prediction model can be improved, and the emission data of the pollution factors can be predicted.
Description
Technical Field
The invention relates to the technical field of environmental monitoring, in particular to a pollution factor emission prediction system and method based on artificial intelligence and a storage medium.
Background
In recent years, with the rapid development of society, the pressure on the environment is increasing, and some serious pollution emission problems seriously threaten the health of people. In order to be able to cope with possible pollution situations in a timely manner, the prediction of the pollutant emissions becomes of particular importance. The current research on pollution emission prediction mainly includes atmosphere and river pollution prediction based on fuzzy theory, statistical theory, linear theory and the like, and the prediction algorithm mainly comprises a grey prediction model, a time series analysis model, a correlation analysis model, a historical average and weighted average model and the like. Although the model can realize the prediction of the pollution emission, the pollution emission working condition under the open domain condition is extremely unstable, the factors influencing the pollution emission are numerous, and the reliability of the model training data is low, so that the accuracy of the prediction model is influenced, and the prediction effect is poor.
Disclosure of Invention
The invention provides a pollution factor emission prediction system, a method and a storage medium based on artificial intelligence, which can improve the reliability of model training data, thereby improving the accuracy of a prediction model, and more accurately predicting the emission data of pollution factors so as to take pollution emission standard exceeding preventive measures in a targeted and timely manner.
In order to achieve the above object, the basic scheme of the invention is as follows:
the pollution factor emission prediction method based on artificial intelligence comprises the following steps:
s100, acquiring a historical hour concentration value of a pollution factor of a monitored object;
s200, judging whether the historical hour concentration value of the pollution factor is an abnormal value or not; if not, storing the historical hour concentration value of the pollution factor into a data set;
s300, selecting a historical hour concentration value of the pollution factor in a data set within a preset time period, and constructing a training sample subset;
s400, predicting the emission data of the pollution factors through a prediction model according to the data in the training sample subset, and generating a prediction result vector;
s500, judging whether the vector of the prediction result is in an error range; if yes, storing the prediction model and the parameters; if not, adjusting the parameters of the prediction model.
The principle and the advantages of the invention are as follows: whether the acquired historical hour concentration value of the pollution factor is an abnormal value or not is judged, and the historical hour concentration value which is not the abnormal value is stored in a database, so that the abnormal data can be primarily screened, and the reliability of model training data is improved. And then selecting the historical hour concentration value of the pollution factor in the data set within a preset time period, and constructing a training sample subset, thereby increasing the randomness of data selection. And predicting the emission data of the pollution factors by the data in the training sample subset through a prediction model, judging whether the vector of the prediction result is in an error range, and adjusting the parameters of the prediction model according to the error range, thereby obtaining the prediction model with more accurate prediction result and the prediction result conforming to the true value. In conclusion, by adopting the scheme, the effect of improving the accuracy of the prediction model can be achieved by improving the reliability and the randomness of the model training data, so that the emission data of the pollution factors can be more accurately predicted, and the pollution emission standard exceeding preventive measures can be pertinently and timely taken.
Further, S200 includes the steps of:
s201, judging whether the historical hour concentration value of the pollution factor exceeds a preset concentration range; if yes, executing S202; if not, executing S203;
s202, judging that the historical hour concentration value of the pollution factor is an abnormal value, and not storing the historical hour concentration value of the pollution factor;
s203, judging whether the historical hour concentration value of the pollution factor is an abnormal value, and storing the historical hour concentration value of the pollution factor into a data set.
Has the beneficial effects that: whether the historical hour concentration value of the pollution factor exceeds the preset concentration range or not is judged, whether the historical hour concentration value of the pollution factor is an abnormal value or not is judged, and if the historical hour concentration value of the pollution factor is the abnormal value, storage is not carried out, so that the reliability of the data set is improved.
Further, in S200, a historical hour concentration value of the pollution factor at the t hour is randomly obtained, and it is determined whether the historical hour concentration value is an abnormal value.
Has the advantages that: and the randomness of data selection is improved by randomly acquiring the historical hour concentration value of the pollution factor at the t hour.
Further, the preset time period is from the tth hour to the t + a hour;
in S300, an overlapping sliding window with the width of a and the single sliding distance of 1 data is adopted to obtain the historical hour concentration value of the pollution factor in a preset time period.
Has the advantages that: by adopting the scheme, the structural characteristics of continuous dynamic change of the pollution on-line monitoring data can be well guaranteed, the constructed training sample subset contains the pollution factor emission characteristics under all pollution emission working conditions to the maximum extent, and the precision of a subsequently trained pollution factor emission prediction model is improved.
Further, S300 includes the steps of:
s301, selecting historical hour concentration values of pollution factors in a data set within a preset time period, and constructing a training set;
s302, judging whether the data in the training set contains respectively complete 24-hour continuous data of four quarters; if yes, executing S303; if not, returning to S301 to expand the training set;
and S303, randomizing the data in the training set to generate a plurality of training sample subsets.
Has the advantages that: by adopting the scheme, pollution factor emission characteristics under different weather environments can be well considered, the accuracy of a pollution factor emission prediction model trained subsequently is further improved, and data concentrated by training is randomized again, so that the generated training sample subset has stronger randomness.
Further, S500 includes the steps of:
s501, calculating the error of a prediction result vector;
s502, calculating the standard deviation of the vector error of the prediction result according to the error of the vector of the prediction result;
s503, judging whether the standard deviation of the vector error of the prediction result is smaller than a standard deviation threshold value; if yes, judging that the vector of the prediction result is in an error range; if not, judging that the prediction result vector is not in the error range.
Has the advantages that: whether the predicted result vector is in the error range is judged by calculating the standard deviation of the error of the predicted result vector and judging whether the error is smaller than the standard deviation threshold value, so that whether the accuracy of the predicted result meets the standard can be accurately judged, and the prediction model can be adjusted and optimized subsequently.
Further, the method also comprises the following steps:
s600, acquiring a real-time hourly concentration value of the pollution factor of the monitored object;
s700, according to the real-time hour concentration value of the pollution factor, predicting the emission data of the pollution factor through a stored prediction model.
Has the advantages that: and predicting the emission data of the pollution factors through the stored prediction model so as to pertinently and timely take the pollution emission overproof preventive measures.
The pollution factor emission prediction system based on artificial intelligence uses the pollution factor emission prediction method based on artificial intelligence.
Has the advantages that: whether the acquired historical hour concentration value of the pollution factor is an abnormal value or not is judged, and the historical hour concentration value which is not the abnormal value is stored in a database, so that the abnormal data can be primarily screened, and the reliability of model training data is improved. And then selecting the historical hour concentration value of the pollution factor in the data set within a preset time period, and constructing a training sample subset, thereby increasing the randomness of data selection. And predicting the emission data of the pollution factors by the data in the training sample subset through a prediction model, judging whether the vector of the prediction result is in an error range, and adjusting the parameters of the prediction model according to the error range, so that the prediction model with more accurate prediction result and the prediction result conforming to a true value is obtained. In conclusion, by adopting the scheme, the effect of improving the accuracy of the prediction model can be achieved by improving the reliability and the randomness of the model training data, so that the emission data of the pollution factors can be more accurately predicted, and the pollution emission standard exceeding preventive measures can be pertinently and timely taken.
An artificial intelligence based pollution factor emission prediction storage medium storing computer executable instructions which, when executed, implement the artificial intelligence based pollution factor emission prediction method described above.
Has the advantages that: whether the acquired historical hour concentration value of the pollution factor is an abnormal value or not is judged, and the historical hour concentration value which is not the abnormal value is stored in a database, so that the abnormal data can be primarily screened, and the reliability of model training data is improved. And then selecting a data set, wherein the historical hour concentration value of the pollution factor in a preset time period, and constructing a training sample subset, thereby increasing the randomness of data selection. And predicting the emission data of the pollution factors by the data in the training sample subset through a prediction model, judging whether the vector of the prediction result is in an error range, and adjusting the parameters of the prediction model according to the error range, thereby obtaining the prediction model with more accurate prediction result and the prediction result conforming to the true value. In conclusion, by adopting the scheme, the effect of improving the accuracy of the prediction model can be achieved by improving the reliability and the randomness of the model training data, so that the emission data of the pollution factors can be more accurately predicted, and the pollution emission standard exceeding preventive measures can be pertinently and timely taken.
Drawings
Fig. 1 is a flow chart of a pollution factor emission prediction method based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
The following is further detailed by way of specific embodiments:
example 1:
example 1 is substantially as shown in figure 1:
the pollution factor emission prediction method based on artificial intelligence comprises the following steps:
firstly, starting an algorithm system;
s100, obtaining a monitorHistorical hourly concentration values x of different contamination factors i (i =1,2,3.. N) of a test object delta (delta =1,2,3 \8230n) (δ，i) 。
The pollution factors comprise dissolved oxygen, suspended matters, five-day biochemical oxygen demand, chemical oxygen demand, permanganate index, total organic carbon, barium, boron, cobalt, molybdenum, tin, total mercury, alkyl mercury, total cadmium, total chromium, hexavalent chromium, total arsenic, total lead, total nickel, total copper, total zinc, total manganese, total iron, total silver, total beryllium, total selenium, copper, zinc, selenium, arsenic, mercury, cadmium, lead, total nitrogen, ammonia nitrogen, kjeldahl nitrogen, nitrite, nitrate, total phosphorus, cyanide, fluoride, sulfide, chloride, sulfate, petroleum, volatile phenol and organic nitrogen in a wastewater online monitoring system, and monitoring of carbon dioxide, methane, trichloromonofluoromethane, dichlorodifluoromethane, trichlorotrifluoroethane, arsenic, beryllium and compounds thereof, cadmium, lead and compounds thereof, lead, mercury and compounds thereof, mercury, nickel and compounds thereof, tin and compounds thereof, ammonia (ammonia), nitrogen oxides, nitric oxide, nitrogen dioxide, carbon monoxide, cyanide, fluoride, chlorine, hydrogen chloride, sulfur dioxide, hydrogen sulfide, phenols, dichloromethane, trichloromethane, tetrachloromethane, dibromochloromethane, bromodichloromethane, bromomethane, tribromomethane, chloroethane, cyclohexane, n-hexane, n-heptane, vinyl chloride, propylene, hydrocarbons, non-methane total hydrocarbons, chloromethane, benzene, toluene, ethylbenzene, ethyl acetate, vinyl acetate, methanol, formaldehyde, total suspended particulate matter, particulate matter inhalable particulate matter PM10, particulate matter PM2.5, submicron particulate matter PM1.0, soot, sulfuric acid mist, chromic acid, carbon disulfide, and the like in an exhaust gas on-line monitoring system in a subject δ (δ =1,2,3 \\\\ 8230n).
When model training is carried out, according to actual requirements, namely a prediction model of which pollution factor needs to be trained, historical hour concentration values of corresponding pollution factors are obtained for training.
S200, judging whether the historical hour concentration value of the pollution factor is an abnormal value or not; if not, storing the historical hour concentration value of the pollution factor into a data set.
In this embodiment, to promote data selectionObtaining randomness, and randomly obtaining historical hour concentration value x of pollution factors at the t hour (δ,i,t) And judging whether the historical hour concentration value is an abnormal value or not.
S200 includes the following steps:
s201, judging the historical hour concentration value x of the pollution factor at the t hour (δ,i , t) Whether the concentration exceeds a preset concentration range or not; if yes, executing S202; if not, S203 is executed.
In this embodiment, the predetermined concentration range is [ α ] (δ,i,1) ,α (δ,i,2) ]Wherein α is (δ,i,1) 、α (δ,i,2) The values of the monitoring objects delta are manually set by combining the industries h to which the monitoring objects delta belong, the monitoring levels j and the monitoring factors I, the industries to which the monitoring objects delta belong are classified according to the classification standard of the environmental protection industry, and the monitoring levels are divided into 3 levels including I, II and III, as shown in the table 1:
table 1 reference table for limiting parameter value
| Serial number | The industry h | Monitoring level j | Monitoring factor i | α (δ,i,1) | α (δ,i,2) |
| 1 | Industry 1 | I | Factor 1 | ε (1,1,1,1) | ε (1,1,1,2) |
| 2 | Industry 1 | I | Factor 2 | ε (1,1,2,1) | ε (1,1,2,2) |
| …… | …… | …… | …… | …… | …… |
| n | Industry i | j stage | Factor i | ε (h,j,i,1) | ε (h,j,i,2) |
S202, judging that the historical hour concentration value of the pollution factor is an abnormal value, not storing the historical hour concentration value of the pollution factor, and directly entering S300. The abnormal value screening and judging are not based on a unified standard, but are based on the industry to which the monitored object delta belongs, the monitoring level and the individuation and fine screening and judging of the specific monitored factor i.
S203, judging that the historical hour concentration value of the pollution factor is not an abnormal value, storing the historical hour concentration value of the pollution factor into a data set, and then entering S300.
S300, selecting a historical hour concentration value of the pollution factor in a data set within a preset time period, and constructing a training sample subset; the preset time period is from the tth hour to the t + a hour.
S300 includes the steps of:
s301, selecting historical hourly concentration values of pollution factors in a data set in a preset time period, and constructing a training set X (δ,i,a) (ii) a Specifically, a historical hour concentration value of the pollution factor in a preset time period is obtained by adopting an overlapped sliding window with the width of a and the single sliding distance of 1 datum. Therefore, the structural characteristics of continuous dynamic change of pollution online monitoring data can be well guaranteed, the constructed training sample subset contains the pollution factor emission characteristics under all pollution emission working conditions to the maximum extent, and the accuracy of a subsequently trained pollution factor emission prediction model is improved.
S302, judging whether the data in the training set contain respectively complete 24-hour continuous data in one day in four seasons of spring, summer, autumn and winter; if yes, executing S303; if not, returning to S301 to expand the training set; therefore, pollution factor emission characteristics in different weather environments can be well considered, and the accuracy of a subsequently trained pollution factor emission prediction model is further improved.
S303, randomizing the data in the training set to generate a plurality of training sample subsets X (δ,i,a,q) (q＝1,2,3…m)。
S304, judging whether the training sample subsets with the data fragment quantity smaller than mu exist in the m training sample subsets (mu is set manually), if yes, returning to S303 to carry out randomization again, otherwise, entering S400; therefore, the method can better avoid that the number of the established training sample subset data fragments is less and the accuracy of the model prediction result obtained by subsequent training is influenced.
S400, according to data in the m training sample subsets, emission data of pollution factors are predicted through a prediction model, and m prediction result vectors C are generated n (n =1,2,3 \8230m), and specifically, a random forest algorithm decision tree model f (X) is adopted for prediction.
S500, judging whether the vector of the prediction result is in an error range; if yes, storing the prediction model and the parameters; if not, adjusting the parameters of the prediction model.
S500 includes the steps of:
s501, calculating the error of a prediction result vector;
(n＝1，2，3…m；T n a vector constructed for the corresponding true value).
S502, calculating the standard deviation of m predicted result vector errors according to the error of the predicted result vector
Wherein the content of the first and second substances,
is the arithmetic mean of the m prediction error.
S503, judging whether the standard deviation S of the vector error of the prediction result is smaller than a standard deviation threshold value Y; if yes, judging that the vector of the prediction result is in an error range; if not, the prediction result vector is judged not to be in the error range.
S504, when the vector of the prediction result is in the error range, storing the prediction model and the parameters; and when the prediction result vector is not in the error range, adjusting the parameters of the prediction model. Specifically, parameters of a random forest algorithm decision tree model f (X) are adjusted in a multilayer nested loop traversal mode with a stride length omega (omega is manually set), wherein the parameters comprise the number alpha of trees in a forest, the maximum depth beta of the trees, training samples gamma which are contained in each sub-node after the nodes are branched, and the minimum training samples rho which can be branched by one node; the first layer of circulation is the number alpha of trees in the forest, the second layer of circulation is the maximum depth beta of the trees, the third layer of circulation is a training sample gamma which is contained in each sub node after the nodes are branched, and the fourth layer of circulation is a minimum training sample rho which can be branched by one node; and returning to the step S10 to continue the training test after the parameter adjustment is finished once.
And S505, judging whether to continue model training of the next pollution factor, if so, increasing the sequence number of the pollution factor by 1 (i.e. i = i + 1), returning to S100, and otherwise, entering S506.
S506, all model training is completed, and the process goes to S600.
S600, acquiring a real-time hour concentration value of the pollution factor of the monitored object.
S700, according to the real-time hour concentration value of the pollution factor, predicting the emission data of the pollution factor through a stored prediction model.
S700 includes the steps of:
s701, reading an hour 'concentration value' sequence X of a pollution factor i of a monitoring object delta online monitoring system in time periods (t-a) -t in real time by adopting an overlapped sliding window with the width of a and the single sliding distance of 1 datum (δ,i,t,a) Inputting a prediction model f (X) of the factor i;
s702: outputting the discharge concentration predicted value x of the pollution factor i at the moment t +1 (δ,i,t+1) ；
S703: judgment of x (δ,i,t+1) Whether the concentration exceeds a preset concentration range or not; if yes, executing S706; if not, go to S704.
S704: judgment of x (δ,i,t+1) If the value is greater than the preset threshold value p, executing S705; if not, executing S706;
s705: the system starts a prediction alarm that the pollution factor i exceeds the standard, and executes S706;
s706: judging whether to continue predicting the next pollution factor, if so, increasing the serial number of the pollution factor by 1 (i = i + 1), returning to S701, and if not, executing S707;
s707: the system stops running.
The pollution factor emission prediction system based on artificial intelligence uses the pollution factor emission prediction method based on artificial intelligence.
An artificial intelligence based pollution factor emission prediction storage medium storing computer executable instructions which, when executed, implement the artificial intelligence based pollution factor emission prediction method described above.
The pollution factor emission prediction method based on artificial intelligence can be stored in a readable storage medium if the pollution factor emission prediction method is realized in the form of a software functional unit and is sold or used as an independent product. Based on such understanding, all or part of the flow in the method according to the above embodiments may be implemented by a computer program, which may be stored in a readable storage medium and used by a processor to implement the steps of the above method embodiments. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The readable medium may include: any entity or device capable of carrying said computer program code, a recording medium, a usb-disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a Read-only memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, etc.
The foregoing are merely exemplary embodiments of the present invention, and no attempt is made to show structural details of the invention in more detail than is necessary for the fundamental understanding of the art, the description taken with the drawings making apparent to those skilled in the art how the several forms of the invention may be embodied in practice with the teachings of the invention. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (9)
1. The pollution factor emission prediction method based on artificial intelligence is characterized by comprising the following steps: the method comprises the following steps:
s100, acquiring a historical hour concentration value of a pollution factor of a monitored object;
s200, judging whether the historical hour concentration value of the pollution factor is an abnormal value or not; if not, storing the historical hour concentration value of the pollution factor into a data set;
s300, selecting a historical hour concentration value of the pollution factor in a data set within a preset time period, and constructing a training sample subset;
s400, predicting the emission data of the pollution factors through a prediction model according to the data in the training sample subset, and generating a prediction result vector;
s500, judging whether the vector of the prediction result is in an error range; if yes, storing the prediction model and the parameters; if not, adjusting the parameters of the prediction model.
2. The artificial intelligence based pollution factor emission prediction method according to claim 1, wherein: s200 includes the following steps:
s201, judging whether the historical hour concentration value of the pollution factor exceeds a preset concentration range; if yes, executing S202; if not, executing S203;
s202, judging that the historical hour concentration value of the pollution factor is an abnormal value, and not storing the historical hour concentration value of the pollution factor;
s203, judging whether the historical hour concentration value of the pollution factor is an abnormal value, and storing the historical hour concentration value of the pollution factor into a data set.
3. The artificial intelligence based pollution factor emission prediction method according to claim 1, wherein: in S200, a historical hour concentration value of the pollution factor in the t hour is randomly acquired, and whether the historical hour concentration value is an abnormal value or not is judged.
4. The artificial intelligence based pollution factor emission prediction method according to claim 3, wherein: the preset time period is from the tth hour to the t + a hour;
in S300, an overlapping sliding window with the width of a and the single sliding distance of 1 data is adopted to obtain the historical hour concentration value of the pollution factor in a preset time period.
5. The artificial intelligence based pollution factor emission prediction method according to claim 1, wherein: s300 includes the steps of:
s301, selecting historical hourly concentration values of pollution factors in a data set in a preset time period, and constructing a training set;
s302, judging whether the data in the training set contains respectively complete 24-hour continuous data of four quarters; if yes, executing S303; if not, returning to S301 to expand the training set;
and S303, randomizing the data in the training set to generate a plurality of training sample subsets.
6. The artificial intelligence based pollution factor emission prediction method according to claim 1, wherein: s500 includes the steps of:
s501, calculating the error of a prediction result vector;
s502, calculating the standard deviation of the vector error of the prediction result according to the error of the vector of the prediction result;
s503, judging whether the standard deviation of the vector error of the prediction result is smaller than a standard deviation threshold value; if yes, judging that the vector of the prediction result is in an error range; if not, judging that the prediction result vector is not in the error range.
7. The artificial intelligence based pollution factor emission prediction method according to claim 1, wherein: further comprising the steps of:
s600, acquiring a real-time hourly concentration value of the pollution factor of the monitored object;
s700, according to the real-time hour concentration value of the pollution factor, predicting the emission data of the pollution factor through a stored prediction model.
8. Pollution factor discharges prediction system based on artificial intelligence, its characterized in that: the artificial intelligence based pollution factor emission prediction method according to any one of the preceding claims 1 to 7 is used.
9. An artificial intelligence-based pollutant factor emission prediction storage medium for storing computer-executable instructions, characterized in that: the computer-executable instructions, when executed, implement the artificial intelligence based pollution factor emission prediction method of any one of the preceding claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210792481.9A CN115169691A (en) | 2022-07-05 | 2022-07-05 | Pollution factor emission prediction system and method based on artificial intelligence and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210792481.9A CN115169691A (en) | 2022-07-05 | 2022-07-05 | Pollution factor emission prediction system and method based on artificial intelligence and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115169691A true CN115169691A (en) | 2022-10-11 |
Family
ID=83491345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210792481.9A Pending CN115169691A (en) | 2022-07-05 | 2022-07-05 | Pollution factor emission prediction system and method based on artificial intelligence and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115169691A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117457098A (en) * | 2023-10-27 | 2024-01-26 | 生态环境部南京环境科学研究所 | Method, device, medium and equipment for early warning pollution accidents of drinking water source area of cross-boundary area |
-
2022
- 2022-07-05 CN CN202210792481.9A patent/CN115169691A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117457098A (en) * | 2023-10-27 | 2024-01-26 | 生态环境部南京环境科学研究所 | Method, device, medium and equipment for early warning pollution accidents of drinking water source area of cross-boundary area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Air quality early-warning system for cities in China | |
| Arhami et al. | Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations | |
| US20180029900A1 (en) | A Method for Effluent Total Nitrogen-based on a Recurrent Self-organizing RBF Neural Network | |
| Xie et al. | Freshwater algal bloom prediction by support vector machine in macau storage reservoirs | |
| CN108052793B (en) | Mobile pollution source emission concentration prediction method based on fuzzy weighted ELM | |
| CN109190865B (en) | Water quality index evaluation method, prediction method and water area water quality grade evaluation method | |
| CN109344971B (en) | Effluent ammonia nitrogen concentration prediction method based on adaptive recursive fuzzy neural network | |
| CN114858976A (en) | Intelligent analysis method and system for atmospheric quality of industrial park | |
| CN115169691A (en) | Pollution factor emission prediction system and method based on artificial intelligence and storage medium | |
| CN112149902B (en) | Subway short-time arrival passenger flow prediction method based on passenger flow characteristic analysis | |
| CN114037163A (en) | Sewage treatment effluent quality early warning method based on dynamic weight PSO (particle swarm optimization) optimization BP (Back propagation) neural network | |
| Pires et al. | Optimization of artificial neural network models through genetic algorithms for surface ozone concentration forecasting | |
| CN114266384A (en) | Method and device for rapidly predicting typhoon path based on fusion model | |
| Sakarkar et al. | Comparative study of ambient air quality prediction system using machine learning to predict air quality in smart city | |
| CN114822709A (en) | Method and device for analyzing multi-granularity accurate cause of atmospheric pollution | |
| CN110542748B (en) | Knowledge-based robust effluent ammonia nitrogen soft measurement method | |
| CN116090710B (en) | Management method, system, electronic equipment and medium for enterprise pollution discharge permission | |
| Hu et al. | Performance of ensemble‐learning models for predicting eutrophication in Zhuyi Bay, Three Gorges Reservoir | |
| CN112634113A (en) | Polluted waste gas correlation analysis method based on dynamic sliding window | |
| CN116227692A (en) | Crop heavy metal enrichment risk quantification method, system and storable medium | |
| CN115545316A (en) | Atmospheric ozone prediction method based on deep learning hybrid model | |
| Mu et al. | An improved effective approach for urban air quality forecast | |
| CN114970813A (en) | Dissolved oxygen concentration data restoration and prediction method | |
| Kokatnoor et al. | Deducing Water Quality Index (WQI) by Comparative Supervised Machine Learning Regression Techniques for India Region | |
| Coles et al. | The analysis of extreme pollution levels: a case study |
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 |