CN106651036A - Air quality forecasting system - Google Patents
Air quality forecasting system Download PDFInfo
- Publication number
- CN106651036A CN106651036A CN201611216042.4A CN201611216042A CN106651036A CN 106651036 A CN106651036 A CN 106651036A CN 201611216042 A CN201611216042 A CN 201611216042A CN 106651036 A CN106651036 A CN 106651036A
- Authority
- CN
- China
- Prior art keywords
- data
- air
- air quality
- monitoring
- model
- 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
- 238000012544 monitoring process Methods 0.000 claims abstract description 81
- 238000009792 diffusion process Methods 0.000 claims abstract description 25
- 238000013468 resource allocation Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 230000007613 environmental effect Effects 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 239000003344 environmental pollutant Substances 0.000 claims description 19
- 231100000719 pollutant Toxicity 0.000 claims description 19
- 238000003915 air pollution Methods 0.000 claims description 16
- 230000007935 neutral effect Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 15
- 210000002569 neuron Anatomy 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 claims description 2
- 230000005284 excitation Effects 0.000 claims description 2
- 210000005036 nerve Anatomy 0.000 claims 2
- 239000003570 air Substances 0.000 description 79
- 230000006870 function Effects 0.000 description 10
- 238000011160 research Methods 0.000 description 6
- 239000000243 solution Substances 0.000 description 6
- 239000012080 ambient air Substances 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 239000000809 air pollutant Substances 0.000 description 2
- 231100001243 air pollutant Toxicity 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000000686 essence Substances 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 239000000926 atmospheric chemistry Substances 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 239000002912 waste gas Substances 0.000 description 1
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
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an air quality forecasting system which comprises an environment quality detection sensor and a cloud computing data processing platform, wherein the environment quality detection sensor is configured at a position of a pollution source and is used for acquiring air monitoring data and transmitting the acquired air monitoring data to a cloud computing data processing platform; and the cloud computing data processing platform is used for receiving the air monitoring data, predicting air quality of a monitored region by adopting an air quality prediction model based on a resource allocation neural network and a smooth support vector regression machine so as to obtain air quality predication data of each monitoring station, pushing the air quality predication data to an associated intelligent terminal, calculating correlation between the monitoring data of the pollution source and the air quality predication data of the monitoring stations according to the air monitoring data of the pollution source and the air quality prediction data of each monitoring station by utilizing a Gaussian point source diffusion model, and carrying out visualized presentation.
Description
Technical field
The application is related to environmental quality monitoring technical field, more particularly to prediction of air quality system.
Background technology
With industrialized continuous development, environmental pollution is also on the rise, the fine particle in air（PM2.5）Concentration is got over
Come higher, national multiple city hazes take place frequently, and the public is constantly lifted for the attention rate of air quality, and current many cities
Ambient air monitoring central site is less, and in addition the level of IT application is not flourishing enough, it is difficult to meets the public and understands air quality in detail
The demand of situation.Substantial increase air monitering site deployment, the importance of extensively development air quality monitoring become increasingly conspicuous, and one
The price of the traditional air quality monitor device of set is very expensive, and building more environmental monitoring websites needs huge fund to throw
Enter, cost is too high.
That what is commonly used in Air Quality Forecast field has statistical method, according to long-term Monitoring Data, sets up statistical fluctuation
Model, model is simple, and service operation is convenient, but lacks solid physical basis；Separately have one to be based on atmospheric physics and material is defeated
The numerical forecast model of fortune model, although physical basis are solid, forecast result is comprehensive, but the border required for pattern, initial strip
Part is difficult to be given, and forecast result precision is not bery high.
The content of the invention
To overcome problem present in correlation technique, this application provides a kind of prediction of air quality system.
According to the first aspect of the embodiment of the present application, there is provided a kind of prediction of air quality system, including：
Environmental quality detection sensor, is configured at pollution sources, for gathering air monitering data, and the air for being gathered is supervised
Data transfer is surveyed to cloud computing data processing platform (DPP)；
Cloud computing data processing platform (DPP), is used for：
Receive the air monitering data；
Using the Air Quality Forecast model based on resource allocation neutral net and Smooth Support Vector Regression machine, to monitored district
The air quality in domain is predicted, and obtains the Air Quality Forecast data of each monitoring station, and Air Quality Forecast data are pushed away
Give the intelligent terminal of association；
According to the air monitering data and the Air Quality Forecast data of each monitoring station of pollution sources, using Gauss point source diffusion mould
Type calculates the correlation between the air monitering data and the Air Quality Forecast data of monitoring station of pollution sources, and carries out visual
Change and show.
The technical scheme that embodiments herein is provided can include following beneficial effect：
The application proposes a neutral net based on resource allocation network and smooth vector regression forecast model, using RAN
The distance criterion and error criterion of neutral net, the dynamic for carrying out hidden node is generated and parameter regulation, and generation can meet error
The minimum neural network structure of requirement, it is to avoid imply node number in network and initial network parameter is difficult to the shortcoming chosen；
Traditional support vector regression is replaced using smooth support vector regression, it is possible to achieve the quality modeling of high-efficient high performance
With control, it is more accurate than traditional algorithm, in hgher efficiency.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
The application can be limited.
Description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the enforcement for meeting the application
Example, and be used to explain the principle of the application together with specification.
Fig. 1 is a kind of structured flowchart of prediction of air quality system of the application according to an exemplary embodiment.
Fig. 2 is a kind of structural representation of resource allocation network of the application according to an exemplary embodiment.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Explained below is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.Conversely, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects described in detail in claims, the application.
It is, only merely for the purpose of description specific embodiment, and to be not intended to be limiting the application in term used in this application.
" one kind ", " described " and " being somebody's turn to do " of singulative used in the application and appended claims is also intended to include majority
Form, unless context clearly shows that other implications.It is also understood that term "and/or" used herein is referred to and wrapped
Containing one or more associated any or all possible combinations for listing project.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used for that same type of information is distinguished from each other out.For example, without departing from
In the case of the application scope, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determining ".
As shown in figure 1, being a kind of structure of prediction of air quality system of the application according to an exemplary embodiment
Block diagram, including environmental quality detection sensor, cloud computing data processing platform (DPP) and intelligent terminal.
Wherein, environmental quality detection sensor, is configured at pollution sources, for gathering air monitering data, and will be adopted
The air monitering data transfer of collection is to cloud computing data processing platform (DPP).
Cloud computing data processing platform (DPP), is used for：
Receive the air monitering data.
Using the Air Quality Forecast model based on resource allocation neutral net and Smooth Support Vector Regression machine, to being supervised
The air quality for surveying region is predicted, and obtains the Air Quality Forecast data of each monitoring station, and by Air Quality Forecast number
According to the intelligent terminal for being pushed to association.
According to the air monitering data and the Air Quality Forecast data of each monitoring station of pollution sources, expanded using Gauss point source
Scattered model calculates the correlation between the Monitoring Data and the Air Quality Forecast data of monitoring station of pollution sources, and carries out visual
Change and show.
The embodiment of the present application proposes and devises based on Internet of Things and the City Air Quality Forecasting of cloud computing and endanger pre-
Alarm system.Cloud platform disclosure satisfy that the forecast of real time access air quality and harm warning data.With real time propelling movement, forecast
The features such as early warning, accuracy, by being sent to intelligent terminal, it is possible to use family is easily browsed by terminals such as smart mobile phones
With the data variation figure for accessing data and image.
The present embodiment proposes a neutral net based on resource allocation network and smooth vector regression forecast model, profit
With the distance criterion and error criterion of RAN neutral nets, dynamic generation and the parameter regulation of hidden node are carried out, generating can be full
The minimum neural network structure of sufficient error requirements, it is to avoid imply node number in network and initial network parameter is difficult to what is chosen
Shortcoming；Traditional support vector regression is replaced using smooth support vector regression, it is possible to achieve the matter of high-efficient high performance
Amount modeling and control, it is more accurate than traditional algorithm, in hgher efficiency.
The present embodiment is based on Gauss point source diffusion model, sets up urban air pollution source emission monitoring data and urban air
The correlation matrix of monitoring data, may be implemented in arbitrarily selected discharge of pollutant sources in the urban area under given meteorological condition
Pollutant levels value contribution rate of the Monitoring Data to each environmental quality monitoring website, and both correlations can be visualized
Analysis.
The embodiment of the present application carries out the Air Quality Forecast in city or region using artificial neural network, it may not be necessary to use
Explicit equation come determine model but according to input data creation model.By burying energy at the nonlinear problem of neutral net
Power and appearance are made an uproar ability, according to different actual conditions, build the Artificial Neural Network Prediction Model under particular case, in experiment and
On the basis of training, network structure is improved, make up the weak point of traditional algorithm, improve the generalization ability of network.It can be ring
Border management work provides some new idea and methods, while can also be to make full use of the magnanimity number in Environmental information management system
According to decision-making foundation is provided, a kind of practicable method is found.
Urban air-quality is monitored and forecast data is a kind of data with time and spatial character, can be in certain journey
Reflect the rule that air quality changes on degree.Input is needed due to setting up large number of environmental air quality monitoring point position
Expense cost is very high, and the monitoring that entirely accurate is carried out to the air pollutant concentration value of extensive area is still infeasible at present, because
This, it is region-wide to obtain to the Monitoring Data of each monitoring site in region and the interpolation of forecast data using interpolation theory and method
The distribution situation of interior air pollutant concentration just becomes feasible, by the air matter of each point position in space in the region that interpolation is obtained
Amount (pollutant levels value) data can also be used as an important evidence for assessing atmosphere quality in the region.
The subject such as the own Jing of research of air pollution diffusion and meteorology, Atmospheric Chemistry is intimately associated and defines new
Section:Air pollution meteorology.From the 50's of last century, air pollution meteorology gradually forms system, occurs in that case mould
Five class models such as type, Gauss model, Lagrangian model, Euler's model, dense gas model.Earliest Gauss model can be predicted
The locally diffusion of little yardstick, subsequently research has obtained the amendment mould for other landform and weather condition based on Gauss model
Type, although up to the present Gauss model remains the basis of most of utility model, but is because that it is based on pollution concentration
Meet Gaussian Profile it is assumed that the precision of simulation and applicable condition are all difficult to deal with air matter under large scale IFR conditions
The forecast of amount.With the development of computer, the research and development to Air Pollution Diffusion Model is mainly carried out with numerical solution.Greatly
Gas contamination can be described with a set of based on hydromechanical math equation, due to the raising of computer capacity, Ke Yizhi
Connect using the method for various numerical solutions to calculate, the key problem of solution is atmospheric turbulance diffusion.Numerical solution model
High precision, can adapt to the meteorological condition of various complexity, but amount of calculation is huge, main at present to transport on high-performance computer
OK, the considerably long calculating time is needed.
The application utilizes and overhead continuous point source Gauss Diffusion Mode is simulated, and calculates under different meteorological conditions,
Pollutant levels value at environmental air quality monitoring point in region, analyzes the phase between air pollution source and air quality monitoring point
Guan Xing, and visual presentation is carried out to this correlation, intuitively characterize different pollution sources in region and different air qualities are supervised
Measuring point influences each other, with good effect.
In sum, carry out based on cloud computing intelligent checking system research, based on artificial neural network surrounding air matter
Research, the visual analyzing of magnanimity environmental air quality monitoring data, the urban air pollution source emissions data of amount forecast model
The research of correlation between urban air-quality Monitoring Data, in correct description and one city of sign or designated area
Ambient air quality situation, the diffusion-condition of pollution sources, between pollution sources and environmental monitoring sites data dependence aspect just
With important theory and practice meaning.This is not only proving how mankind's activity affects ambient air quality this theoretical question
Upper important in inhibiting, and to urban environmental management, Environmental capacity, environmental planning, urban construction, traffic programme and public defend
Industry of making trouble has important actual application value.
The application can monitor the master in air at pollution sources and each monitoring station configuration surroundings quality detection sensor
Want pollution factor, such as PM2.5, NO2, SO2, NH3And the pollutant levels value such as hydrogen sulfide gas.Sensor can pass through GPRS
Wireless Data Transmission is carried out, data receiver and preliminary process are carried out on the server for have public network IP, finally transmitted to cloud meter
Calculate data processing platform (DPP).
In actual applications, it is possible to use wireless sensor node Real-time Collection air quality monitoring data, sent out with wireless
Injection device is transmitted into the mode of real time data Wireless transceiver on main frame.For the complex environment of urban air-quality, can be with
Configuration data collecting unit is responsible for changing the physical quantity information of monitored parameter by AD, is converted to digital quantity, and suitable
When be sent to access point（Such as transfer server）.Access point is by sending synchronised clock information and making transmission timetable
Control the access of each data acquisition unit, it is to avoid the conflict of data receiver occur causes reception failure.Supervised by real-time monitoring
Control, obtains the basic data and real-time dynamic monitoring data of a large amount of ambient air qualities and emphasis air pollution source emission, together
When access point constantly the information for receiving simply processed while receive information, and be sent to cloud platform center
In database, by being shown in cloud platform.
Next the concrete function of cloud computing data processing platform (DPP) is described.
1）Based on artificial neural network and the structure of Smooth Support Vector Regression machine forecast model
One is built with the air monitering data at pollution sources as input, the Air Quality Forecast data of each monitoring station in region
For the artificial neural network and Smooth Support Vector Regression machine forecast model of output.In Air Quality Forecast model, by resource
Distribution network and polynomial smoothing support vector regression model training are obtained.
The model be neutral net based on resource allocation network (RAN Resource Allocation Network) and
Polynomial smoothing support vector regression（PSSVR Polynomial Smooth Support Vector Regression）In advance
Model is surveyed, using the distance criterion and error criterion of RAN neutral nets, the dynamic for carrying out hidden node is generated and parameter regulation,
Generation can meet the minimum neural network structure of error requirements, it is to avoid imply node number in network and initial network parameter is difficult
With the shortcoming chosen, training and the complexity predicted are reduced using the polynomial function of polynomial smoothing SVMs, improved
The degree of accuracy of prediction, this model has the training speed of faster network and the prediction essence of Geng Gao than classical BP neutral nets
Degree.
Resource allocation network (Resource Allocating Network, RAN) is based on RBF (Radical
Basis Function, RBF) single hidden layer feedforward neural network, the network structure of resource allocation network includes input layer, implicit
Layer and output layer.Its thought, as hidden layer neuron node " base ", constitutes hidden layer using RBF；Will input
Layer vector is directly mapped (do not need weights connection) to hidden layer；Hidden layer to output layer is Linear Mapping.RAN neutral nets
Achievable on-line training, by judging novelty condition come dynamic increase hidden node, it is determined that or adjust RBF data
Center, extends the network parameters such as constant, output weights, and generation can meet the minimum neural network structure of error requirements, with complete
Office's approximation properties and preferable generalization ability, are prevented effectively from BP neutral net network structures (hidden node number) and initial network
Parameter is difficult to choose, trains the shortcomings of being easily absorbed in Local Minimum, and its network structure is as shown in Figure 2.
In Fig. 2,i 1 Extremelyi n For input data, hidden layerC 1 ExtremelyC m For neuron node,r 1 （I）Extremelyr m （I）Map for local
Output,w 1 Extremelyw m For connection weight,To export internal threshold,yFor output data.
The excitation function of the neuron node in the hidden layer adopts RBF, using Gaussian function, for J
Individual neuron node, its local mapping output is represented by following formula：
。
The input data of the Air Quality Forecast model be the air monitering data, the Air Quality Forecast model
Output data be Air Quality Forecast data, the output data of the Air Quality Forecast model is calculated by following formula：
2）The learning algorithm of resource allocation network
RAN neutral nets have no hidden node when training starts, and it is to pass through neuron node allocation strategy in training process
Carry out dynamic generation hidden layer with reference to the relevant parameter with regulating networks structure with parameter regulation strategy；The neuron node distributes plan
Slightly by checking training sample to collection, judge whether that meeting novelty condition carrys out one neuron node of dynamically distributes, parameter is adjusted
Section strategy improves neural network accuracy by regulating networks parameter.
Training sample to collection be, whereinBe training sample to concentrate i-th input sample, be corresponding
Output sample, N is training sample to number.RAN algorithms travel through sample to each sample pair for concentrating, when meeting novelty
During condition, as network increases a hidden node；Otherwise carry out network parameter regulation.
To current input sample, ask or the distance with existing hidden node data center in current hidden layer。
For i-th sample pair for checking, novelty condition is:
(1) distance criterion:The nearest data center C of current sample transmission range is more than a value。
Wherein,Referred to as range resolution ratio (referred to as distance), t is the training time.
(2) error criterion：Current sample outputIt is more than certain certain value with the deviation of the output y of neutral net：
Situation 1:When novelty condition (1) and (2) are while satisfaction, then be that hidden layer increases by 1 hidden node.The hidden section that note is newly increased
Point numbering is k, then the hidden node data center is。
Situation 2:When condition (l) and (2) have any one to be unsatisfactory for, network does not increase new hidden node, but passes through
Widrow Hoff LMS algorithm regulating networks parameters, reduce neural network forecast output y with output sampleError.Error meter
Calculating formula is：
Each hidden node in hidden layer and the connection weight of output node are adjusted as follows：
The carrying out of output node side-play amount z is adjusted as follows：
According to gradient descent method, data center is adjusted as follows：
。
3）Smooth Support Vector Regression machine algorithm
SVMs (Support Vector Machine, SVM) is a kind of study based on empirical risk minimization
Method, Generalization Ability is substantially better than some conventional learning algorithmses, and can obtain globally unique optimal solution, solve small sample,
There is distinctive advantage in non-linear and high dimensional pattern identification problem. in numeral identification, Face datection and data mining
It is successfully applied to Deng field.
Using polynomial smoothing support vector regression model（Palynomial Smooth Support Vector
Regression, PSSVR）Model is as object function, unconstrained optimization regression problem model：
。
Wherein,
There is n rank slickness with regard to x.
When n >=2,With second order and above slickness, therefore Newton-Armijo algorithms can solve this
Without constricted regression model.
Newton-Armijo algorithms are to be iterated optimization according to Newton descent directions and Armijo linear searches.This
The great advantage of method is that the speed ratio of convergence is very fast, and due to the inaccurate linear searches of Armijo used in algorithm,
Would not occur the iteration for increasing target function value as classical Newton algorithms.As long as object function second order and
Second order with Smooth can be calculated using this algorithm, and in this kind of smooth function in formula (4.67) except n=1 when
It is single order polynomial smooth function, others can meet condition can be calculated using Newton-Armijo algorithms.Using
Newton-armijo algorithms are iterated optimization, and iterative optimization procedure comprises the steps：
Step 1：Initialization:I=0, the initial point of given algorithmAnd required precision>0；
Step 2：According to formulaCalculateValue, ifThen returnAs a result, otherwise
Continue to calculate；
Step 3：Calculate Hessian matrixes, byObtain Newton descent directionsValue;
Step 4：Using Armijo linear search material calculations.If, takeFor approximate solution and stop, otherwise
Continue, whereinMeet：
, and, here;
Step 5：Order,Go to step 2 to continue executing with.
4）Correlation between the air monitering data of pollution sources and the Air Quality Forecast data of monitoring station and visual
Change
Urban air pollution situation depends primarily on the emission behaviour of pollutant and the diffusivity of air.It is relatively steady in pollution sources
In the case of fixed, pollutant diffusion, migration, flowing and conversion in an atmosphere, wind closely related with meteorological condition at that time
Play an important role to, the diffusion of the meteorological factor to pollutant such as wind speed, inversion layer knot, precipitation.There is precipitation to occur as worked as, or have
When wind, be often conducive to the diffusion of pollutants in air；Otherwise when having mist or wind very little, tend to air dirt occur
Dye increases.
The present embodiment is by the pollutant emission Monitoring Data of air pollution source, urban air-quality Monitoring Data and weather
Situation data, are calculated using Gauss diffusion model of point discharge source and study different air pollution sources to different spatial in city
The pollutant levels of air quality monitoring station's point are calculated, and study contribution rate of the pollution sources to air quality monitoring point, are realized
The visualization of correlation between Area Ambient Air Quality and waste gas of pollutant discharge capacity.
The correlation of the Air Quality Forecast data of air monitering data and each monitoring station at pollution sources, refer to
In the specified time, in designated area, under the conditions of meteorological data, the quantity of the pollution sources in region is that n, the number of monitoring station are
M, the pollutant of j-th monitoring point in the emissions data and m monitoring station of i-th in n pollution sources pollution sources
Corresponding relation between concentration value, forms quantitative relations of the n to m.
The Air Quality Forecast data of each monitoring station（That is to say pollutant levels value）It is various multiple different types of
The coefficient result of pollution source point, by pollutant levels data and the corresponding monitoring point of calculated each monitoring site
True Monitoring Data may have certain error, this is because the data that the monitoring of each monitoring station is obtained are by various inhomogeneities
Concentration value sum of the pollution sources of type at the monitoring station, is by the coefficient result of pollution sources of number of different types.
The theoretical foundation Taylor applied statistical method research atmospheric turbulance diffusion problem of Gauss point source diffusion, with rapid with air
Stream be steady and under uniform assumed condition, take pollution sources for origin, x-axis is mean wind direction；It is assumed that discharging first from origin
Go out a particle, after elapsed time T, it is x=/T that particle leaves the x directions distance of origin, and particle is in the displacement in y directions
It is then time to time change, positive and negative, size change at random.
The model parameter of Gauss diffusion model of point discharge source includes atmospheric stability, air pollution height and contribution rate：
Atmospheric stability
Atmospheric stability refers to the air mass of a certain height of air degree stable in vertical direction, mainly by wind speed, cloud amount
The conventional meteorological watch data such as size and solar radiation situation is determining atmosphere stability grade.It is determined that diffusion parameter it
Before, first have to determine current atmospheric condition, it is that we are roughly divided into A-F totally 6 stability grades this by air.It is followed successively by
Unstable, medium unstable, weak unstable, neutral, weak steady, moderate stable state, according to insolation, wind speed and night sky cloud
Amount situation semi-quantitatively provides stability diffusion rank.
Air pollution height
The parameter air pollution height needed in Gauss Diffusion Mode, refers to effective source height H, and it includes emission source, such as cigarette
The natural height of chimney and air pollution height.
Contribution rate
Contribution rate, it may be determined that each air quality monitoring station's point is mainly related with which pollution sources, and their correlation is big
Little, the discharge capacity management control for pollution sources provides foundation.The parameter represents the pollutant diffusion discharged from a certain pollution sources
All pollution source points are accounted for the percentage of the monitoring station pollutant levels value, to concentration value during monitoring station in order to accurate
Relation between them is described, the present embodiment is defined as the pollutant levels value of monitoring station to bring monitoring body into using those
Concentration value sum of the pollution sources in system at monitoring station.
In the embodiment of the present application, by the air monitering data at pollution sources and the Air Quality Forecast data of each monitoring station
Correlation, and carry out visual presentation, including：
Using air monitering data and default meteorological data as initial data.
According to the initial data, calculate pollution sources using the Gauss diffusion model of point discharge source and be diffused at monitoring station
Air Quality Forecast data, and be written in database.
According to the selection of user, it would be desirable to data be written in XML documents according to XSI forms.
According to the XML documents, using star structure layout correlation is shown.
By taking monitoring station as an example, correlation of the pollution sources to monitoring station is inquired about, it is dirty due to for each monitoring station
The quantity in dye source is dissimilar, in order to make full use of interface shape, makes interface more attractive in appearance, the number to polluting source point
Judged, then different bandwagon effects are provided according to judged result.
First, it is assumed that the number of known pollution source point is 80, based on this data, the algorithm for being given is applicable not only to
Situation of the pollution source point less than or equal to 80, but also be less than or equal to suitable for the quantity with the relevant pollution source point of certain monitoring station
80 situation, the data can meet needs in most cases.
Then, pollution source point and monitoring station are represented using circular pattern, using sort algorithm to each pollution source point and prison
Survey station point is arranged, and using layering thought the pollution sources of different numbers are shown respectively.
From above-described embodiment, by Polluted area large scale deployment environmental quality detection sensor, by backstage
Cloud computing（Data cube）With Detection of Air Quality early warning platform, large-scale air quality monitoring data are analyzed and processed, can be with
Accomplish timely early warning, at utmost reduce the harm to environment.By mass historical data intellectual analysis, it is able to detect that
Pollution course pollutes source with reviewing, and in conjunction with the pollution video record that video frequency pick-up head is shot with video-corder, is more convenient environmental administration's pipe
Reason and rectification, accomplish that law enforcement has evidence.Newest cloud computing detecting system is combined using these characterization factor collectors, can either be solved
Fund input problem, can meet certain certainty of measurement again, and existing air ambient automatic monitoring system forms complementation, meet
Demand of the environmental administration to environmental monitoring, and provide information-based support for the efficiency of executing the environmental law.
Those skilled in the art will readily occur to its of the application after the invention that specification and practice are applied here is considered
Its embodiment.The application is intended to any modification, purposes or the adaptations of the application, these modifications, purposes or
The common knowledge in the art that person's adaptations follow the general principle of the application and do not apply including the application
Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the application and spirit are by following
Claim is pointed out.
It should be appreciated that the application is not limited to the precision architecture for being described above and being shown in the drawings, and
And can without departing from the scope carry out various modifications and changes.Scope of the present application is only limited by appended claim.
The preferred embodiment of the application is the foregoing is only, not to limit the application, all essences in the application
Within god and principle, any modification, equivalent substitution and improvements done etc. should be included within the scope of the application protection.
Claims (8)
1. a kind of prediction of air quality system, it is characterised in that include：
Environmental quality detection sensor, is configured at pollution sources, for gathering air monitering data, and the air for being gathered is supervised
Data transfer is surveyed to cloud computing data processing platform (DPP)；
Cloud computing data processing platform (DPP), is used for：
Receive the air monitering data；
Using the Air Quality Forecast model based on resource allocation neutral net and Smooth Support Vector Regression machine, to monitored district
The air quality in domain is predicted, and obtains the Air Quality Forecast data of each monitoring station, and Air Quality Forecast data are pushed away
Give the intelligent terminal of association；
According to the air monitering data and the Air Quality Forecast data of each monitoring station of pollution sources, using Gauss point source diffusion mould
Type calculates the correlation between the air monitering data and the Air Quality Forecast data of monitoring station of pollution sources, and carries out visual
Change and show.
2. method according to claim 1, it is characterised in that in the Air Quality Forecast model, by resource allocation
Network and polynomial smoothing support vector regression model training are obtained；
Wherein, the network structure of the resource allocation network includes input layer, hidden layer and output layer；Made using RBF
For the base of hidden layer neuron node, hidden layer is constituted；Input layer vector is mapped directly into hidden layer；Hidden layer arrives output layer
It is mapped as Linear Mapping；
Using polynomial smoothing support vector regression model as object function, unconstrained optimization regression problem model is：
。
3. method according to claim 2, it is characterised in that the excitation function of the neuron node in the hidden layer is adopted
With RBF, using Gaussian function, for j-th neuron node, its local mapping output is represented by following formula：
。
4. method according to claim 2, it is characterised in that the input data of the Air Quality Forecast model is described
Air monitering data, the output data of the Air Quality Forecast model is Air Quality Forecast data, and the air quality is pre-
The output data for surveying model is calculated by following formula：
。
5. method according to claim 3, it is characterised in that the resource allocation network is in the training process by nerve
First node distribution strategy and parameter regulation strategy carry out dynamic generation hidden layer with reference to the relevant parameter with regulating networks structure；The god
Jing units node distribution strategy judges whether that meeting novelty condition carrys out one nerve of dynamically distributes by checking training sample to collection
First node, parameter regulation strategy improves neural network accuracy by regulating networks parameter.
6. method according to claim 2, it is characterised in that the polynomial smoothing support vector regression model has
N rank slickness, has 2 rank above slickness when n >=2, and using newton-armijo algorithms optimization is iterated, and iteration is excellent
Change process comprises the steps：
Step 1：Initialization:I=0, the initial point of given algorithmAnd required precision>0；
Step 2：According to formulaCalculateValue, ifThen returnAs a result, otherwise after
It is continuous to calculate；
Step 3：Calculate Hessian matrixes, byObtain Newton descent directionsValue;
Step 4：Using Armijo linear search material calculations.If, takeFor approximate solution and stop, otherwise
Continue, whereinMeet：
, and, here;
Step 5：Order,Go to step 2 to continue executing with.
7. method according to claim 1, it is characterised in that the utilization Gauss diffusion model of point discharge source calculates pollution sources
Correlation between air monitering data and the Air Quality Forecast data of monitoring station, including：
Within a specified time, in designated area, under the conditions of meteorological data, the quantity of the pollution sources in region is n, monitoring station
Number is m, j-th monitoring point in the emissions data and m monitoring station of i-th in n pollution sources pollution sources
Corresponding relation between pollutant levels value, forms quantitative relations of the n to m；
Wherein, in Gauss diffusion model of point discharge source, so that atmospheric turbulance is steady under uniform assumed condition, pollution sources are taken for original
Point, x-axis is mean wind direction；It is assumed that discharging a particle from origin first, after elapsed time T, particle leaves origin
X directions distance is x=/T, and displacement of the particle in y directions is then time to time change, positive and negative, size change at random；Model is joined
Number includes atmospheric stability, air pollution height and contribution rate.
8. method according to claim 1, it is characterised in that the air monitering data according to pollution sources and each monitoring
The Air Quality Forecast data of website, the Monitoring Data of pollution sources and the sky of monitoring station are calculated using Gauss diffusion model of point discharge source
Correlation between makings amount prediction data, and visual presentation is carried out, including：
Using air monitering data and default meteorological data as initial data;
According to the initial data, using the Gauss diffusion model of point discharge source air that pollution sources are diffused at monitoring station is calculated
Prediction of quality data, and be written in database;
According to the selection of user, it would be desirable to data be written in XML documents according to XSI forms；
According to the XML documents, using star structure layout correlation is shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611216042.4A CN106651036A (en) | 2016-12-26 | 2016-12-26 | Air quality forecasting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611216042.4A CN106651036A (en) | 2016-12-26 | 2016-12-26 | Air quality forecasting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106651036A true CN106651036A (en) | 2017-05-10 |
Family
ID=58826913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611216042.4A Pending CN106651036A (en) | 2016-12-26 | 2016-12-26 | Air quality forecasting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106651036A (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107943928A (en) * | 2017-11-21 | 2018-04-20 | 清华大学 | A kind of ozone concentration Forecasting Methodology and system based on space-time data statistical learning |
| CN108562693A (en) * | 2018-01-08 | 2018-09-21 | 郑州易测智能科技有限公司 | A kind of method and its monitoring modular for searching the source of atmospheric pollution |
| CN108681792A (en) * | 2018-05-18 | 2018-10-19 | 环境保护部华南环境科学研究所 | A kind of Air Quality Forecast method and system based on incineration flue gas of household garbage |
| CN109117549A (en) * | 2018-08-08 | 2019-01-01 | 浙江航天恒嘉数据科技有限公司 | A kind of pollutant DIFFUSION PREDICTION method and system |
| CN109359341A (en) * | 2018-09-20 | 2019-02-19 | 佛山科学技术学院 | A kind of city Aerosol particulates diffusion method for tracing |
| CN109444232A (en) * | 2018-12-26 | 2019-03-08 | 苏州同阳科技发展有限公司 | A kind of multichannel intelligent polluted gas monitoring device and diffusion source tracing method |
| CN109636719A (en) * | 2018-11-22 | 2019-04-16 | 北京蛙鸣华清环保科技有限公司 | A kind of multiple dimensioned air quality spatial interpolation methods, system, medium and equipment |
| CN109685246A (en) * | 2018-11-13 | 2019-04-26 | 平安科技（深圳）有限公司 | Environmental data predictor method, device and storage medium, server |
| CN109858696A (en) * | 2019-01-30 | 2019-06-07 | 山东万钢信息科技有限公司 | A kind of city environmental pollution prediction technique and system |
| CN110032612A (en) * | 2019-04-10 | 2019-07-19 | 珠海市岭南大数据研究院 | Information-pushing method and device |
| CN110428104A (en) * | 2019-08-01 | 2019-11-08 | 软通动力信息技术有限公司 | A kind of genes' contamination ratio determines method, apparatus, electronic equipment and storage medium |
| CN110531029A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of device based on environmentally friendly Internet of Things big data prediction air quality trend |
| CN110555551A (en) * | 2019-08-23 | 2019-12-10 | 中南大学 | air quality big data management method and system for smart city |
| CN110610209A (en) * | 2019-09-16 | 2019-12-24 | 北京邮电大学 | Air quality prediction method and system based on data mining |
| CN110659405A (en) * | 2019-09-25 | 2020-01-07 | 南京源堡科技研究院有限公司 | Network information acquisition method based on cloud environment |
| CN110824107A (en) * | 2019-09-29 | 2020-02-21 | 中国人民解放军陆军防化学院 | Air quality forecasting method based on dynamic inversion emission source data |
| CN111025425A (en) * | 2019-11-27 | 2020-04-17 | 东莞理工学院 | Data collection system for meteorological big data analysis |
| CN111079848A (en) * | 2019-12-23 | 2020-04-28 | 哈尔滨理工大学 | Image-based air quality grade evaluation method |
| CN111521754A (en) * | 2020-04-22 | 2020-08-11 | 中国科学院地理科学与资源研究所 | Preliminary investigation and stationing method for soil pollution in coking enterprise site |
| CN111754373A (en) * | 2020-06-03 | 2020-10-09 | 京东城市(北京)数字科技有限公司 | Air quality analysis method and device, electronic equipment and storage medium |
| CN111912749A (en) * | 2020-08-20 | 2020-11-10 | 威海精讯畅通电子科技有限公司 | Air quality monitoring method and system |
| CN112508056A (en) * | 2020-11-13 | 2021-03-16 | 东南大学 | Urban air quality monitoring method based on mobile multi-source perception |
| CN112540159A (en) * | 2020-11-27 | 2021-03-23 | 中广核工程有限公司 | Nuclear power plant atmospheric diffusion prediction correction method, system, medium and electronic equipment |
| CN112711912A (en) * | 2020-12-30 | 2021-04-27 | 许昌学院 | Air quality monitoring and alarming method, system, device and medium based on cloud computing and machine learning algorithm |
| CN113011455A (en) * | 2021-02-02 | 2021-06-22 | 北京数汇通信息技术有限公司 | Air quality prediction SVM model construction method |
| CN113706000A (en) * | 2021-08-19 | 2021-11-26 | 海南绿能环境工程有限公司 | Environment monitoring resource allocation method and system based on Internet of things |
| CN113727214A (en) * | 2021-08-30 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Method, device, equipment and storage medium for inspecting atmospheric pollution |
| CN114048614A (en) * | 2021-11-16 | 2022-02-15 | 中科三清科技有限公司 | Method and device for predicting environmental pollution |
| WO2022052068A1 (en) * | 2020-09-11 | 2022-03-17 | 西门子（中国）有限公司 | Target available model-based environment prediction method and apparatus, program, and electronic device |
| CN114418442A (en) * | 2019-08-14 | 2022-04-29 | 柯灵爱尔(北京)环境技术中心 | Method for selecting pollutant treatment measures |
| CN115097547A (en) * | 2022-07-04 | 2022-09-23 | 湖南省生态环境监测中心 | Atmospheric heavy pollution forecasting method based on combination of numerical mode and statistical analysis |
| RU2796370C1 (en) * | 2022-10-31 | 2023-05-22 | Общество С Ограниченной Ответственностью "Ситиэйр" | System and method for dynamic visualization of environmental pollution |
| TWI808043B (en) * | 2022-11-30 | 2023-07-01 | 桓達科技股份有限公司 | Air pollution detection system and air pollution forecast management method |
| CN118095658A (en) * | 2024-04-24 | 2024-05-28 | 山东林安热能科技有限公司 | Monitoring system for environmental protection engineering |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104596050A (en) * | 2014-12-31 | 2015-05-06 | 东莞市炜奥环保科技有限公司 | Intelligent air purifier remote monitoring system based on cloud platform |
-
2016
- 2016-12-26 CN CN201611216042.4A patent/CN106651036A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104596050A (en) * | 2014-12-31 | 2015-05-06 | 东莞市炜奥环保科技有限公司 | Intelligent air purifier remote monitoring system based on cloud platform |
Non-Patent Citations (3)
| Title |
|---|
| 涂文根 等: "三种训练光滑支持向量分类器方法的比较", 《计算机工程与应用》 * |
| 蒋志方 等: "基于结构优化的 RAN城市环境空气质量预测模型", 《山东大学学报（工学版）》 * |
| 黄华娟 等: "多项式光滑孪生支持向量回归机", 《微电子学与计算机》 * |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107943928B (en) * | 2017-11-21 | 2018-10-30 | 清华大学 | A kind of ozone concentration prediction technique and system based on space-time data statistical learning |
| CN107943928A (en) * | 2017-11-21 | 2018-04-20 | 清华大学 | A kind of ozone concentration Forecasting Methodology and system based on space-time data statistical learning |
| CN108562693A (en) * | 2018-01-08 | 2018-09-21 | 郑州易测智能科技有限公司 | A kind of method and its monitoring modular for searching the source of atmospheric pollution |
| CN108681792A (en) * | 2018-05-18 | 2018-10-19 | 环境保护部华南环境科学研究所 | A kind of Air Quality Forecast method and system based on incineration flue gas of household garbage |
| CN108681792B (en) * | 2018-05-18 | 2021-05-07 | 生态环境部华南环境科学研究所 | Air quality prediction method and system based on household garbage incineration flue gas |
| CN109117549A (en) * | 2018-08-08 | 2019-01-01 | 浙江航天恒嘉数据科技有限公司 | A kind of pollutant DIFFUSION PREDICTION method and system |
| CN109117549B (en) * | 2018-08-08 | 2023-09-05 | 浙江航天恒嘉数据科技有限公司 | Pollutant diffusion prediction method and system |
| CN109359341A (en) * | 2018-09-20 | 2019-02-19 | 佛山科学技术学院 | A kind of city Aerosol particulates diffusion method for tracing |
| CN109685246B (en) * | 2018-11-13 | 2024-04-23 | 平安科技（深圳）有限公司 | Environment data prediction method and device, storage medium and server |
| CN109685246A (en) * | 2018-11-13 | 2019-04-26 | 平安科技（深圳）有限公司 | Environmental data predictor method, device and storage medium, server |
| CN109636719A (en) * | 2018-11-22 | 2019-04-16 | 北京蛙鸣华清环保科技有限公司 | A kind of multiple dimensioned air quality spatial interpolation methods, system, medium and equipment |
| CN109444232A (en) * | 2018-12-26 | 2019-03-08 | 苏州同阳科技发展有限公司 | A kind of multichannel intelligent polluted gas monitoring device and diffusion source tracing method |
| CN109444232B (en) * | 2018-12-26 | 2024-03-12 | 苏州同阳科技发展有限公司 | Multichannel intelligent polluted gas monitoring device and diffusion tracing method |
| CN109858696A (en) * | 2019-01-30 | 2019-06-07 | 山东万钢信息科技有限公司 | A kind of city environmental pollution prediction technique and system |
| CN110032612A (en) * | 2019-04-10 | 2019-07-19 | 珠海市岭南大数据研究院 | Information-pushing method and device |
| CN110428104A (en) * | 2019-08-01 | 2019-11-08 | 软通动力信息技术有限公司 | A kind of genes' contamination ratio determines method, apparatus, electronic equipment and storage medium |
| CN114418442B (en) * | 2019-08-14 | 2022-09-27 | 柯灵爱尔(北京)环境技术中心 | Method for selecting pollutant treatment measures |
| CN114418442A (en) * | 2019-08-14 | 2022-04-29 | 柯灵爱尔(北京)环境技术中心 | Method for selecting pollutant treatment measures |
| CN110531029A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of device based on environmentally friendly Internet of Things big data prediction air quality trend |
| CN110531029B (en) * | 2019-08-16 | 2022-02-25 | 北京慧辰资道资讯股份有限公司 | Device for predicting air quality trend based on environmental protection Internet of things big data |
| CN110555551A (en) * | 2019-08-23 | 2019-12-10 | 中南大学 | air quality big data management method and system for smart city |
| CN110610209A (en) * | 2019-09-16 | 2019-12-24 | 北京邮电大学 | Air quality prediction method and system based on data mining |
| CN110659405A (en) * | 2019-09-25 | 2020-01-07 | 南京源堡科技研究院有限公司 | Network information acquisition method based on cloud environment |
| CN110824107A (en) * | 2019-09-29 | 2020-02-21 | 中国人民解放军陆军防化学院 | Air quality forecasting method based on dynamic inversion emission source data |
| CN111025425A (en) * | 2019-11-27 | 2020-04-17 | 东莞理工学院 | Data collection system for meteorological big data analysis |
| CN111079848B (en) * | 2019-12-23 | 2021-02-12 | 哈尔滨理工大学 | Image-based air quality grade evaluation method |
| CN111079848A (en) * | 2019-12-23 | 2020-04-28 | 哈尔滨理工大学 | Image-based air quality grade evaluation method |
| CN111521754B (en) * | 2020-04-22 | 2021-04-13 | 中国科学院地理科学与资源研究所 | Preliminary investigation and stationing method for soil pollution in coking enterprise site |
| CN111521754A (en) * | 2020-04-22 | 2020-08-11 | 中国科学院地理科学与资源研究所 | Preliminary investigation and stationing method for soil pollution in coking enterprise site |
| CN111754373A (en) * | 2020-06-03 | 2020-10-09 | 京东城市(北京)数字科技有限公司 | Air quality analysis method and device, electronic equipment and storage medium |
| CN111912749A (en) * | 2020-08-20 | 2020-11-10 | 威海精讯畅通电子科技有限公司 | Air quality monitoring method and system |
| WO2022052068A1 (en) * | 2020-09-11 | 2022-03-17 | 西门子（中国）有限公司 | Target available model-based environment prediction method and apparatus, program, and electronic device |
| CN112508056A (en) * | 2020-11-13 | 2021-03-16 | 东南大学 | Urban air quality monitoring method based on mobile multi-source perception |
| CN112508056B (en) * | 2020-11-13 | 2022-04-29 | 东南大学 | Urban air quality monitoring method based on mobile multi-source perception |
| CN112540159A (en) * | 2020-11-27 | 2021-03-23 | 中广核工程有限公司 | Nuclear power plant atmospheric diffusion prediction correction method, system, medium and electronic equipment |
| CN112711912A (en) * | 2020-12-30 | 2021-04-27 | 许昌学院 | Air quality monitoring and alarming method, system, device and medium based on cloud computing and machine learning algorithm |
| CN112711912B (en) * | 2020-12-30 | 2024-03-19 | 许昌学院 | Air quality monitoring and alarming method, system, device and medium based on cloud computing and machine learning algorithm |
| CN113011455A (en) * | 2021-02-02 | 2021-06-22 | 北京数汇通信息技术有限公司 | Air quality prediction SVM model construction method |
| CN113011455B (en) * | 2021-02-02 | 2024-01-05 | 北京数汇通信息技术有限公司 | Air quality prediction SVM model construction method |
| CN113706000A (en) * | 2021-08-19 | 2021-11-26 | 海南绿能环境工程有限公司 | Environment monitoring resource allocation method and system based on Internet of things |
| CN113727214A (en) * | 2021-08-30 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Method, device, equipment and storage medium for inspecting atmospheric pollution |
| CN114048614A (en) * | 2021-11-16 | 2022-02-15 | 中科三清科技有限公司 | Method and device for predicting environmental pollution |
| CN115097547A (en) * | 2022-07-04 | 2022-09-23 | 湖南省生态环境监测中心 | Atmospheric heavy pollution forecasting method based on combination of numerical mode and statistical analysis |
| RU2799893C1 (en) * | 2022-10-28 | 2023-07-13 | федеральное государственное автономное образовательное учреждение высшего образования "Национальный исследовательский университет "Высшая школа экономики" | System for predicting the spatial distribution of harmful substances in the atmospheric air |
| RU2796370C1 (en) * | 2022-10-31 | 2023-05-22 | Общество С Ограниченной Ответственностью "Ситиэйр" | System and method for dynamic visualization of environmental pollution |
| TWI808043B (en) * | 2022-11-30 | 2023-07-01 | 桓達科技股份有限公司 | Air pollution detection system and air pollution forecast management method |
| CN118095658A (en) * | 2024-04-24 | 2024-05-28 | 山东林安热能科技有限公司 | Monitoring system for environmental protection engineering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651036A (en) | Air quality forecasting system | |
| Peng et al. | Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning | |
| Liao et al. | Deep learning for air quality forecasts: a review | |
| Wang et al. | Temperature error correction based on BP neural network in meteorological wireless sensor network | |
| Chen | Prediction algorithm of PM2. 5 mass concentration based on adaptive BP neural network | |
| CN106650825B (en) | Motor vehicle exhaust emission data fusion system | |
| CN110346517B (en) | Smart city industrial atmosphere pollution visual early warning method and system | |
| CN110232471B (en) | Rainfall sensor network node layout optimization method and device | |
| CN105740991A (en) | Climate change prediction method and system for fitting various climate modes based on modified BP neural network | |
| Yu et al. | Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment | |
| Xu et al. | Fine-grained prediction of PM2. 5 concentration based on multisource data and deep learning | |
| CN112163367B (en) | Firefly algorithm and cellular automaton fused city expansion simulation prediction method | |
| CN105243435A (en) | Deep learning cellular automaton model-based soil moisture content prediction method | |
| CN110346518B (en) | Traffic emission pollution visualization early warning method and system thereof | |
| Ye et al. | Short-term prediction of available parking space based on machine learning approaches | |
| CN110555551A (en) | air quality big data management method and system for smart city | |
| CN115775085B (en) | Digital twinning-based smart city management method and system | |
| Zou et al. | Air quality prediction based on a spatiotemporal attention mechanism | |
| CN113011455B (en) | Air quality prediction SVM model construction method | |
| CN110533239A (en) | A kind of smart city air quality high-precision measuring method | |
| CN106096246B (en) | Aerosol optical depth method of estimation based on PM2.5 and PM10 | |
| CN113987912A (en) | Pollutant on-line monitoring system based on geographic information | |
| Lin et al. | Building autocorrelation-aware representations for fine-scale spatiotemporal prediction | |
| Zhang et al. | Spatio-temporal digraph convolutional network-based taxi pickup location recommendation | |
| Zhang et al. | Urban traffic flow prediction model based on BP artificial neural network in Beijing area |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170510 |
|
| WD01 | Invention patent application deemed withdrawn after publication |