Very short-term air pollution forecast

Abstract

A method in a data processing system comprising a processor and a memory for predicting air pollution, wherein the memory comprises instructions that are executed by the processor to configure the processor to implement an air pollution prediction mechanism, wherein the method comprises: detecting, by the air pollution prediction mechanism, one or more air pollution monitoring stations correlated with a prediction point, from a plurality of air pollution monitoring stations, wherein the prediction point is one of the air pollution monitoring stations, wherein each of the plurality of air pollution monitoring stations is arranged separately from a source of pollution, wherein determining the one or more air pollution monitoring stations correlated with a prediction point comprises: detecting, by the air pollution prediction mechanism,a set of air pollution monitoring stations from the plurality of air pollution monitoring stations located within a predetermined distance around the forecast point; for each of the set of air pollution monitoring stations, determine, by the air pollution forecasting mechanism, a diffusion velocity s of a pollutant from the air pollution monitoring station Mi to the forecast point M using the wind speed ws and the wind direction wd; calculate, by the air pollution forecasting mechanism, an angle Θ between a direction of a line from monitoring station Mi and the forecast point M with respect to the wind direction wd at location Mi by the data processing system; calculate, by the air pollution forecasting mechanism,a movement velocity v of the pollutant using the diffusion velocity s from the monitoring station Mi to the prediction point M through the data processing system using: v=s+ws*cosΘ; Determining a degree of influence of Dide's pollutant from the monitoring station Mi to the prediction point M through the data processing system using: Di=Q2πvσyσzexp[−12(y2σy2t+z2σz2t)−k2t] where Q is the pollution value of Mi, v is the movement velocity, σy is the diffusion parameter on the y-axis (a fixed value), σz is the diffusion parameter on the z-axis, in particular a fixed value, y is the distance between Mi and M on the y-axis, z is the distance between Mi and M on the z-axis, t is the duration in hours, and k is the decay factor, which in particular is a predefined factor; Determining, by which Air pollution prediction mechanism, whether the detected degree of impact is larger than a threshold DT of the degree of impact,through the data processing system; and in response to the fact that the detected degree of influence is greater than a threshold DT of the degree of influence, adding the air pollution monitoring station Mi to the one or more air pollution monitoring stations correlated with the forecast point M, for the one or more air pollution monitoring stations correlated with the forecast point, detecting, through the air pollution prediction mechanism, one or more patterns of the forecast point, historical patterns of the forecast point associated with the one or more patterns of the forecast point, and one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the forecast point, through the data processing system; and providing, through the air pollution prediction mechanism,a pollution forecast based on one or more patterns of the forecast point, the historical patterns of the forecast point associated with the one or more patterns of the forecast point, and the one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the forecast point.

Description

BACKGROUND

[0001] The present application relates generally to an improved data processing device and method and, more specifically, to mechanisms for very short-term air pollution forecasting.

[0002] Air pollution is the introduction of particles, biological molecules, or other harmful substances into the Earth's atmosphere, causing illness, human death, damage to other living organisms such as food crops, or to the natural or built environment. Air pollution can originate from anthropogenic sources, meaning an effect or thing resulting from human activity, or from natural sources. Some of the most important anthropogenic sources include: traffic, coal burning, industrial manufacturing, and dust emissions.

[0003] The Earth's atmosphere is a complex, natural, gaseous system essential for life on Earth. The ozone hole, caused by air pollution, has been recognized as a threat to human health and the Earth's ecosystems. Some current countermeasures to combat anthropogenic forms of air pollution include traffic control, restrictions or limits on industrial production, and technological improvements. SUMMARY

[0004] This summary is provided to introduce, in simplified form, a selection of concepts that are described in more detail below. This summary is not intended to identify key factors or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter.

[0005] In an illustrative embodiment, a method for predicting air pollution is provided in a data processing system. The illustrative embodiment identifies one or more air pollution monitoring stations from a plurality of such stations that are correlated with a prediction point. For the one or more air pollution monitoring stations correlated with the prediction point, the illustrative embodiment identifies one or more patterns of the prediction point, historical patterns of the prediction point associated with the one or more patterns of the prediction point, and one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the prediction point.The illustrative embodiment provides a pollution forecast based on the one or more patterns of the forecast point, the historical patterns of the forecast point associated with the one or more patterns of the forecast point, and the one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the forecast point.

[0006] In other illustrative embodiments, a computer program product is provided that includes a computer-usable or -readable medium containing a computer-readable program. When the computer-readable program is executed on a data processing unit, it causes the data processing unit to perform various individual and combinations of the operations described above with respect to the illustrative embodiment of the method.

[0007] In a further embodiment, a system / device is provided. The system / device may include one or more processors and a memory connected to the one or more processors. The memory may contain instructions which, when executed by the one or more processors, cause the one or more processors to perform various individual and combinations of the operations described above with regard to the illustrative embodiment of the method.

[0008] These and other features and advantages of the present invention are described in detail in the following exemplary embodiments of the present invention or will become apparent to those skilled in the art. List of characters

[0009] The invention, as well as a preferred use and further aims and advantages thereof, are best understood by reference to the following detailed description of illustrative embodiments, when read together with the accompanying drawings, in which: Fig. 1 is an exemplary diagram of a distributed data processing system in which aspects of the illustrative embodiments can be implemented; Fig. 2 is an exemplary block diagram of a data processing unit in which aspects of the illustrative embodiments can be implemented; Fig. 3 represents a functional block diagram of a mechanism for very short-term air pollution forecasting according to an illustrative embodiment; Fig. 4A presents an example of a pollution curve and extracted shape parameters for a prediction point M during a selected period according to an illustrative embodiment; Fig. 4B presents an example of a historical pollution curve for the forecast point M according to an illustrative embodiment; Fig. 5 represents an overarching operational plan of the operation carried out by a very short-term air pollution forecasting mechanism according to an illustrative embodiment; Fig. 6 represents the operation performed by the mechanism for very short-term air pollution forecasting when correlating air pollution monitoring stations in a plurality of air pollution monitoring stations with a forecast point according to an illustrative embodiment; The Fig. 7A and Fig. 7B represent the operation performed by the mechanism for very short-term air pollution forecasting upon detection of one or more patterns according to an illustrative embodiment; and Fig. 8 represents the operation performed by the mechanism for a very short-term air pollution forecast when providing a very short-term air pollution forecast according to an illustrative embodiment. DETAILED DESCRIPTION

[0010] As we age, the human body becomes less able to compensate for the effects of environmental pollution. Air pollution can worsen heart disease and stroke, lung diseases such as chronic obstructive pulmonary disease (COPD) and asthma, and diabetes. Such pollution leads to increased medication use, more visits to healthcare providers, more emergency room and hospital admissions, and even death. Ozone and particulate matter (PM), particularly pollution with small fine particles known as PM2.5, have the greatest potential to negatively impact the health of older adults. Particulate matter pollution has been linked to premature death, heart rhythm disorders and heart attacks, asthma attacks, and the development of chronic bronchitis. Ozone can exacerbate respiratory illnesses even at low levels.

[0011] Therefore, air pollution forecasting is important for reducing air pollution, improving the quality of life for urban populations who regularly experience poor air quality and high levels of pollution, and so on. Current air pollution data, ozone forecasts, public health data, and data on the environmental impacts of air pollution are used to generate daily, weekly, or other forecasts and actions that individuals and businesses can take to protect themselves from or reduce air pollution. However, air pollution can change by the minute due to changes in wind direction, temperature, current pollution levels, or other factors. Therefore, the illustrative embodiments provide mechanisms for very short-term air pollution forecasting, predicting pollution levels for the next few hours, for example, 1 to 6 hours.The mechanisms of the illustrative embodiments utilize intrinsic meteorological and pollutant diffusion relationships between monitoring stations to predict air pollution on an hourly basis. Using current pollution levels detected by a plurality of air pollution monitoring stations, the mechanisms use meteorological and pollutant diffusion relationships associated with each monitoring station to identify correlated monitoring stations. Once a set of correlated monitoring stations has been identified, the mechanisms detect air pollution patterns and, in particular, pollution events, such as a fire causing a spike in pollution, an unexpected chemical release by a company causing pollution, or similar occurrences.Subsequently, the mechanisms provide a very short-term forecast of air pollution for the identified area and other areas that may be affected by air pollution for the next few hours by detecting pollution patterns.

[0012] Before discussing the various aspects of the illustrative embodiments, it should be noted that the term "mechanism" is used throughout this description to refer to elements of the present invention that perform various operations, functions, and the like. As used herein, a "mechanism" may be an implementation of the functions or aspects of the illustrative embodiments in the form of a device, a procedure, or a computer program product. In the case of a procedure, the procedure is implemented by one or more units, devices, computers, data processing systems, or the like.In a computer program product, the logic represented by computer code or instructions embodied in or on the computer program product is executed by one or more hardware units to implement the functionality or perform the operations associated with the specific "mechanism." Consequently, the mechanisms described herein may be implemented as specialized hardware, software running on general-purpose hardware, software instructions stored on a medium such that the instructions are readily executable by specialized or general-purpose hardware, a procedure or method for performing the functions, or any combination thereof.

[0013] The present description and the present claims may use the terms "one," "at least one," and "one or more" with regard to certain features and elements of the illustrative embodiments. It should be noted that these terms and expressions are intended to indicate that at least one of the respective feature or element is present in the respective illustrative embodiment, but that more than one may also be present. That is to say, these terms / expressions are not intended to limit the description or the claims to the presence of a single feature / element, nor do they require the presence of multiple such features / elements. On the contrary, these terms / expressions require only a single feature / element, with the possibility of multiple such features / elements falling within the scope of the description and the claims.

[0014] Furthermore, it should be noted that the following description uses several different examples for various elements of the illustrative embodiments to further illustrate exemplary implementations of the illustrative embodiments and to aid in understanding the mechanisms of the illustrative embodiments. These examples are not intended to be limiting and do not exhaust the various possibilities for implementing the mechanisms of the illustrative embodiments. It will be apparent to those skilled in the art, in light of the present description, that numerous other alternative implementations for these various elements exist that may be used in addition to or instead of the examples provided herein without departing from the essence or scope of the present invention.

[0015] Therefore, the illustrative embodiments can be used in many different types of data processing environments. To provide a framework for describing the specific elements and functionality of the illustrative embodiments, the following sections will be presented. Fig. 1 and Fig. 2 are provided as exemplary environments in which aspects of the illustrative embodiments can be implemented. It should be noted that the Fig. 1 and Fig. Figure 2 serves only as examples and is not intended to assert or imply any limitation regarding the environments in which aspects or embodiments of the present invention may be implemented. Numerous modifications can be made to the environments shown without altering the essence and scope of the present invention.

[0016] Fig. Figure 1 presents a graphical representation of an exemplary distributed data processing system in which aspects of the illustrative embodiments can be implemented. A distributed data processing system 100 It can include a network of computers in which aspects of the illustrative embodiments can be implemented. The distributed data processing system 100 contains at least one network 102 , which is the medium used to provide data transmission links between different units and computers within the distributed data processing system 100 are interconnected. The network 102 This can include connections such as wired and wireless data transmission links or fiber optic cables.

[0017] In the example shown, a server 104 and a server 106together with a storage unit 108 with the network 102 Furthermore, clients 110, 112, and 114 are also connected to the network. 102 connected. With these clients 110 , 112 and 114 This could include, for example, personal computers, network computers, or similar devices. In the example shown, the server represents... 104 the clients 110 , 112 and 114 data items such as boot files, operating system images, and applications. In the example shown, the clients are... 110 , 112 and 114 to clients of the server 104 The distributed data processing system 100 May include additional servers, clients, and other units not shown.

[0018] In the example shown, the distributed data processing system is... 100around the internet, whereby the network 102 It represents a worldwide network of networks and gateways that use the Transmission Control Protocol / Internet Protocol (TCP / IP) suite of protocols to exchange data. At the heart of the Internet is a central connection of high-speed data transmission links between main nodes or host computers, consisting of thousands of commercial, governmental, educational, and other computer systems that relay data and messages. Naturally, the distributed data processing system can 100 It can also be implemented in such a way that it includes a number of different network types, such as an intranet, a local area network (LAN), a wide area network (WAN), or the like. As stated above, Fig. 1 is meant as an example and not as an architectural limitation of different embodiments of the present invention, and therefore the respective ones in Fig. The elements shown in Figure 1 are not considered to be limiting with regard to the environments in which the illustrative embodiments of the present invention can be implemented.

[0019] As in Fig. As shown in 1, one or more of the data processing units, e.g. the server, can be used. 104, specifically designed to implement a mechanism for very short-term air pollution forecasting. The design of the data processing unit may include the provision of application-specific hardware, firmware, or the like to facilitate the execution of the operations and the generation of the outputs described herein with respect to the illustrative embodiments. Alternatively, the design of the data processing unit may also include the provision of software applications stored in one or more memory units and accessed in the memory of a data processing unit such as a server. 104are loaded to cause one or more hardware processors of the data processing unit to execute the software applications that configure the processors to perform the operations and produce the outputs described herein with respect to the illustrative embodiments. Furthermore, any combination of application-specific hardware, firmware, software applications running on hardware, or the like may be used without deviating from the essence and scope of the illustrative embodiments.

[0020] It should be noted that once the data processing unit is designed in one of these ways, it becomes a specialized data processing unit specifically designed to implement the mechanisms of the illustrative embodiments, and is not a general-purpose data processing unit. Furthermore, as described below, implementing the mechanisms of the illustrative embodiments enhances the functionality of the data processing unit and provides a practical and concrete result that facilitates very short-term air pollution forecasting.

[0021] As noted above, the mechanisms of the illustrative embodiments utilize specially designed data processing units or systems to perform the operations for very short-term air pollution forecasting. These data processing units or systems may include various hardware elements that are specifically designed, either through hardware design, software design, or a combination of both, to implement one or more of the systems / subsystems described herein. Fig. Figure 2 is a block diagram of only one exemplary data processing system in which aspects of the illustrative embodiments can be implemented. In a data processing system 200 This is an example of a computer, such as a server. 104 in Fig. 1, in which computer-usable program code or instructions implementing the processes and aspects of the illustrative embodiments of the present invention are located and / or can be executed to achieve the operation, output and external effects of the illustrative embodiments as described herein.

[0022] In the example shown, the data processing system uses 200 a hub architecture that includes a Northbridge and Storage Control Unit Hub (NB / MCH) 202 and a Southbridge and Input / Output (I / O) control unit hub (SB / ICH) 204 Includes one processing unit. 206 , a main memory 208 and a 210 graphics processor are included with the NB / MCH 202 connected. The graphics processor 210 can be connected to the NB / MCH via an Accelerated Graphics Port (AGP). 202 be connected.

[0023] In the example shown, an adapter is used. 212 for a local area network (LAN) with the SB / ICH 204 connected. An audio adapter 216 , a keyboard and mouse adapter 220 , a modem 222 , a read-only memory (ROM) 224, a hard disk drive (HDD) 226, a CD-ROM drive 230 , Connections for universal serial buses (USB) and other data transmission connections 232 and PCI / PCIe units 234 are connected via a bus 238 and a bus 240 with the SB / ME 204 connected. PCI / PCIe units can include, for example, Ethernet adapters, expansion cards, and PC cards for notebook computers. Unlike PCIe, PCI uses a card bus control unit. Regarding the ROM 224 For example, it could be a basic input / output flash system (BIOS).

[0024] The HDD 226and the CD-ROM drive 230 are via the bus 240 with the SB / ME 204 connected. The HDD 226 and the CD-ROM drive 230 They can, for example, use an Integrated Drive Electronics (IDE) or a Serial Advanced Technology Attachment (SATA) interface. A Super I / O (SIO) unit 236 can be used with the SB / ICH 204 be connected.

[0025] An operating system is installed on the processing unit. 206 executed. The operating system coordinates the control of various components within the data processing system. 200 in Fig. 2 and makes them available. The client operating system can be a standard operating system such as Microsoft. ® Windows 7 ®An object-oriented programming system, such as the Java™ programming system, can be executed together with the operating system and provides calls to the operating system from Java™ programs or applications that run in the data processing system. 200 be carried out.

[0026] The server in the data processing system can be... 200 for example, an IBM eServer™ computer system. ® , a computer system based on a Power™ processor or similar, running the Advanced Interactive Executive (AIX) operating system ® ) or the Linux operating system ® is executed. In the data processing system 200 It could be a symmetric multiprocessor (SMP) system, which has a large number of processors in the processing unit. 206 It includes. Alternatively, a single-processor system can be used.

[0027] Commands for the operating system, the object-oriented programming system, and applications or programs are located on storage units such as the HDD. 226 and can be executed by the processing unit 206 into main memory 208 The processes for illustrative embodiments of the present invention can be performed by the processing unit. 206 This is done using computer-usable program code that resides in a memory such as main memory. 208 , the ROM 224 or in one or more peripheral units 226 and 230 may be located.

[0028] A bus system, such as the bus 238 or the bus 240 , as they are in Fig. The two diagrams shown can consist of one or more buses. The bus system can, of course, be implemented using any type of data transmission structure or architecture that enables the transfer of data between different components or units connected to the structure or architecture. A data transmission unit such as a modem, for example, can be used. 222 or the network adapter 212 from Fig. 2 can include one or more units used for transmitting and receiving data. For example, a storage unit could be main memory. 208 , the ROM 224 or a cache memory, such as that found in the NB / MCH 202 in Fig. 2 can be found.

[0029] As mentioned above, in some illustrative embodiments the mechanisms of the illustrative embodiments can be implemented as application-specific hardware, firmware or the like, or application software, which is located in a storage unit such as the HDD. 226 stored and placed in a memory such as main memory. 208 be loaded to be processed by one or more hardware processors, such as the processing unit. 206 or the like. In that respect, the in Fig. 2. The data processing unit shown is specifically designed to implement the mechanisms of the illustrative embodiments and specifically designed to perform the operations and generate the outputs with regard to the very short-term air pollution forecast described below.

[0030] Experts can see that the hardware in Fig. 1 and Fig. 2 may vary depending on the implementation. Other internal hardware or peripheral units, such as flash memory, equivalent non-volatile memory, optical disk drives, and the like, may be used in addition to or instead of those specified in Fig. 1 and Fig. The hardware shown in Figure 2 can be used. Furthermore, the processes of the illustrative embodiments can be applied to a different multiprocessor data processing system than the aforementioned SMP system without deviating from the essence and scope of the present invention.

[0031] Furthermore, the data processing system can 200The data processing system may take the form of any number of different data processing systems, including client data processing units, server data processing units, a tablet computer, a laptop computer, a telephone or other data transmission unit, a personal digital assistant (PDA), or the like. In some illustrative examples, the data processing system may be... 200 It is a portable data processing unit equipped with flash memory to provide non-volatile storage for, for example, operating system files and / or user-generated data. Essentially, the data processing system can be... 200 without architectural restrictions, it can be any known or subsequently developed data processing system.

[0032] Fig. Figure 3 presents a functional block diagram of a mechanism for very short-term air pollution forecasting according to an illustrative embodiment. A mechanism 300 For very short-term air pollution forecasting, an air pollution data acquisition logic is used. 302 , a weather data acquisition logic 304, a logic 306 for detecting correlated air pollution monitoring stations, an air pollution pattern detection logic 308 and an air pollution prediction logic 310 The air pollution data collection logic 302 It collects air quality data from multiple air pollution monitoring stations. 312 and a forecast point M 313. Forecast point M 313 is a location for which a forecast has been requested, i.e., a selected air pollution monitoring station. 312This air quality data includes specific levels of pollutants and other substances in the atmosphere from sources such as factories, vehicles, and other activities that release pollutants into the atmosphere. These pollutants and other substances may include carbon monoxide, lead, nitrogen oxides, volatile organic compounds, particulate matter, sulfur dioxide, carbon dioxide, methane, nitrogen oxides, fluorinated greenhouse gases, and the like. The air pollution data collection logic 302 stores the recorded air quality data based on a single air pollution monitoring station and the recording time in an air quality data structure. 314 in the storage 316 Similarly, the weather data acquisition logic captures 304 Weather data from a multiple of weather monitoring stations 318and a forecast point M 313. Weather data includes wind speed and direction, air temperature, relative humidity, air pressure, precipitation, visibility, dew point, solar radiation, and the like. The weather data acquisition logic 304 stores the recorded weather data based on a single weather monitoring station and the recording time in a weather data structure 320 in the storage 316 .

[0033] Using the collected data, the logic recognizes 306 to detect correlated air pollution monitoring stations two or more air pollution monitoring stations of the air pollution monitoring stations 312, which are correlated with a selected forecast point M 313, using an affective pollution model. To detect two or more air pollution monitoring stations correlated with a selected forecast point M 313, the logic 306 for detecting correlated air pollution monitoring stations detects those air pollution monitoring stations (M1, M2, M3, ..., M n ) the air pollution monitoring stations 312 , located within a distance D around the forecast point M 313. For each of the detected air pollution monitoring stations (M1, M2, M3, ..., M n ) appreciates the logic 306To identify correlated air pollution monitoring stations, a degree of influence Di on the forecast point M 313 at time T is determined, corresponding to a pollutant concentration, wind speed, wind direction, and the like at time T, based on a physical diffusion model. More precisely, for each of the identified air pollution monitoring stations (M1, M2, M3, ..., M3), a degree of influence Di on the forecast point M313 at time T is determined. n ) recognizes the logic 306 To identify correlated air pollution monitoring stations, a diffusion velocity s of the pollutant from the air pollution monitoring station M is required. i to the forecast point M 313 using the wind speed w s and the wind direction w d The diffusion velocity s is based on the observed wind speed w. s at the air pollution monitoring station M ias well as on one or more eddy coefficients determined by the detected wind speed w s and the air temperature can be determined.

[0034] Using the calculated diffusion rate s, the logic calculates 306 To detect correlated air pollution monitoring stations, an angle Θ is measured between the location M. i and M and based on the wind direction at the location M i and calculates the velocity v of the pollutant using the diffusion velocity s of M i to M using the following equation: v = s + w s * cos Θ .

[0035] The logic then recognizes 306 To identify correlated air pollution monitoring stations, the degree of influence D i of the pollutant from M i to M using the following formula: D i = Q 2 π ν σ y σ z exp [ − 1 2 ( y 2 σ y 2 t + z 2 σ z 2 t ) − k 2 t ] where Q is the pollution value of M iv is the speed of motion, σ y The diffusion parameter on the y-axis (a fixed value) is σ. z The diffusion parameter on the z-axis (a fixed value) is , y is the distance between M i and M on the y-axis, z is the distance between M i and M is on the z-axis, t is the duration in hours (e.g. 1 hour, 2 hours, 3 hours ... etc.) and k is the decay factor, which may be a predefined factor.

[0036] Using the identified degree of influence D i The logic determines 306 to detect correlated air pollution monitoring stations, whether the detected degree of influence D i is greater than a threshold value DT of the degree of influence. If the detected degree of influence D i The logic is that if the value is not greater than a threshold DT of the degree of influence, then... 306to detect correlated air pollution monitoring stations to the nearest detected air pollution monitoring stations (M1, M2, M3, ..., M n ) about. If the recognized degree of influence D i If the value is greater than a threshold DT of the degree of influence, the logic adds 306 to identify correlated air pollution monitoring stations, the air pollution monitoring station M i to a list of correlated air pollution monitoring stations 322 in addition, which are related to the forecast point M 313.

[0037] With the list of identified correlated air pollution monitoring stations 322 analyzes the air pollution pattern detection logic 308 Data relating to forecast point M 313 and the air pollution monitoring stations in the list of correlated air pollution monitoring stations 322are used to identify one or more patterns. For forecast point M 313, the air pollution pattern recognition logic recognizes 308 the associated weather data and pollution data within a period T p from the weather data structure 320 or the air quality data structure 314 For the period T p The air pollution pattern recognition logic recognizes the prediction point M 313. 308 a current shape pattern of the pollution data and extracts the shape parameters such as a number of rises, a number of falls, a degree of rises, a degree of falls, an average amplitude, a duration and magnitude of change of the rise, a duration and magnitude of change of the fall, a detected maximum value, a detected minimum value, or the like. Fig. Figure 4A presents an example of a pollution curve and extracted shape parameters for a prediction point M during a selected period according to an illustrative embodiment. For the detected pollution curve 402 extracts the air pollution pattern detection logic 308 Form parameters such as duration and scope of change 404 of an increase, a duration and a magnitude of change 406 of waste, a recognized maximum value 408 and a recognized minimum value 410 .

[0038] The air pollution pattern detection logic uses the extracted shape parameters to search. 308 the air quality data structure 314 based on historical pollution data belonging to the forecast point M 313, which shows a similarly shaped pattern to that of the identified pollution curve 402 exhibit. Fig. Figure 4B presents an example of a historical pollution curve for forecast point M according to an illustrative embodiment. As illustrated, the air pollution pattern recognition logic extracts the 308 the shape parameters from the pollution curve 412, from which four recognizable shape patterns 414 , 416 , 418 and 420 a rise is followed by a fall. The air pollution pattern recognition logic then calculates... 308 a similarity Sm to each of the shape patterns 414 , 416 , 418 and 420 according to the example based on the duration and extent of the increase, the duration and extent of the decrease, the identified maximum value and the identified minimum value with those of the duration and extent of the change 404 of the increase, duration and extent of change 406 of the waste, of the recognized maximum value 408, of the recognized minimum value 410 That is, for each of the extracted shape parameters, i.e., the duration and extent of change of the increase, the duration and extent of change of the decrease, the detected maximum value and the detected minimum value of the shape pattern. 414 , 416 , 418 and 420 and the duration and scope of the changes 404 of the increase, its duration and extent of change 406 of the waste, the recognized maximum value 408, the recognized minimum value 410 , which the pollution curve 402 The air pollution pattern recognition logic determines which ones belong to it. 308 a difference between the duration and extent of the increase, the duration and extent of the decrease, the detected maximum value and the detected minimum value.

[0039] The air pollution pattern detection logic 308subtracts the percentage of the difference from a perfect match of 100 percent, which in the illustrative embodiment results in a similarity Sm of 55 percent for the shape pattern 414 , of 45 percent for the shape pattern 416 , of 62 percent for the shape pattern 418 and 80 percent for the shape pattern 420 This results in the following: The air pollution pattern recognition logic then determines... 308 The air pollution pattern recognition logic determines whether the calculated similarity Sm is greater than a predefined similarity threshold SmT. For the one or more shape patterns where the similarity Sm is greater than a predefined similarity threshold SmT, the logic identifies the pattern. 308 from the historical pollution curve 412 a historical pollution value pH at time T p +h 422, which will be used for a later forecast.

[0040] After the forecast point M 313 has been analyzed, the air pollution pattern detection logic analyzes 308 each air pollution monitoring station in the list of correlated air pollution monitoring stations 322 This means that for each air pollution monitoring station, the air pollution pattern detection logic recognizes 308 the associated weather data and pollution data within a period T p from the weather data structure 320 or the air quality data structure 314 For the period T p Every air pollution monitoring station uses air pollution pattern detection logic. 308 the extracted shape parameters that correspond to the pollution curve 402 belonging to the air quality data structure 314to search for corresponding shape patterns in the data belonging to the correlated air pollution monitoring station. For each detected shape pattern, the air pollution pattern recognition logic calculates 308 a similarity Smi according to the example based on the duration and extent of change of the increase, the duration and extent of change of the decrease, the detected maximum value and the detected minimum value with those of the duration and extent of change 404 of the increase, duration and extent of change 406 of the waste, of the recognized maximum value 408 , of the recognized minimum value 410 That is, for each of the extracted shape parameters, i.e., the duration and magnitude of the increase, the duration and magnitude of the decrease, the detected maximum and minimum values ​​from the correlated air pollution monitoring station, and the duration and magnitude of the decrease. 404of the increase, its duration and extent of change 406 of the waste, the recognized maximum value 408 , the recognized minimum value 410 , which the pollution curve 402 The air pollution pattern recognition logic determines which ones belong to it. 308 A difference between the duration and magnitude of the increase, the duration and magnitude of the decrease, the detected maximum value, and the detected minimum value. The air pollution pattern detection logic. 308 subtracts the percentage difference from a perfect match of 100 percent and determines whether the calculated similarity Smi is greater than a given similarity threshold SmT.

[0041] For one or more shape patterns in the correlated air pollution monitoring station where the similarity Smi is greater than a predefined similarity threshold, the air pollution pattern recognition logic recognizes308 the air pollution monitoring station belongs to an area where it can be predicted that the pollution level p will be the same as the historical pollution level ph at time T p +h is close. The air pollution pattern detection logic 308 repeats the process for each air pollution monitoring station in the list of correlated air pollution monitoring stations 322 After all air pollution monitoring stations in the list of correlated air pollution monitoring stations 322 The air pollution pattern detection logic has been analyzed. 308 the calculated similarity Sm of the historical pollution curve that lies above the similarity threshold SmT, the similarity Smi of each detected air pollution monitoring station in the list of correlated air pollution monitoring stations 322, which is above the similarity threshold SmT, and the pollution value pH at time T p +h out.

[0042] To provide a very short-term air pollution forecast, the air pollution forecast logic uses 310 the similarity Sm of the historical pollution curve that is above the similarity threshold SmT, which is with the detected pollution curve 402 of the forecast point M 313 correlated, and the similarity Smi of each detected air pollution monitoring station in the list of correlated air pollution monitoring stations 322 , to assign a weight w j to calculate for each detected air pollution monitoring station. To assign a weighting w jTo calculate, for a similar period Tj according to the similarity Sm in the period Tj, from which Smj is derived, and the similarity Smi in the period Tj, from which Smij is derived, uses the air pollution prediction logic. 310 the following equation: w j = S m j * ∏ S m i j ∑ j = 1 n S m j * ∏ S m i j .

[0043] The air pollution prediction logic then says 310 a pollution value p t+h for the correlated air pollution monitoring stations 322 at time T p +h using the following equation beforehand: p t + h = ∑ j = 1 n w j p j .

[0044] In this way, the air pollution prediction logic 310By using searches for historical pollution curves that exhibit a similar pattern to the weighted averages of the currently detected pollution levels, it is possible to predict pollution for the next 1 hour, 2 hours, 3 hours, etc., based on one or more detected similar historical pollution curves. If the air pollution prediction logic 310 For example, it recognizes a historical pollution curve from the past that corresponds to the currently detected pollution levels (e.g., pH). 1, If the forecast for 1 hour is similar to ph2, ph3, then the forecast for 1 hour is ph4, the forecast for 2 hours is ph5 and so on, thus allowing an assignment to any historical pollution pattern rather than a specific pollution pattern.

[0045] The present invention may be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium (or media) containing computer-readable program instructions that cause a processor to execute aspects of the present invention.

[0046] The computer-readable storage medium can be a physical unit capable of maintaining and storing instructions for use by an instruction execution unit. For example, the computer-readable storage medium can be an electronic storage unit, a magnetic storage unit, an optical storage unit, an electromagnetic storage unit, a semiconductor storage unit, or any suitable combination thereof, without limitation.A non-exhaustive list of more specific examples of computer-readable storage media includes the following: a portable computer floppy disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically coded unit such as punched cards or raised structures in a groove on which instructions are recorded, or any suitable combination of the above.As used herein, a computer-readable storage medium is not to be interpreted as per se transitory signals, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves that propagate through a waveguide or other transmission media (e.g., light pulses passing through an optical fiber cable), or electrical signals that are transmitted through a line.

[0047] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium over a network, such as the internet, a local area network, a wide area network, and / or a wireless network, to individual data processing units or to an external computer or storage device. The network may include copper transmission cables, fiber optic transmission lines, wireless transmission systems, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each data processing unit receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage on a computer-readable storage medium within the respective data processing unit.

[0048] The computer-readable program instructions for performing operations of the present invention may be assembly instructions, instructions of an instruction-set architecture (ISA), machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or either source code or object code written in any combination of one or more programming languages, including an object-oriented programming language such as Java, Smalltalk, C++ or the like, and conventional process-oriented programming languages ​​such as the programming language "C" or similar programming languages.The machine-readable program instructions can be executed entirely on the user's computer, partly on the user's computer as a standalone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer via any type of network, such as a local area network (LAN) or a wide area network (WAN), or the connection can be established with an external computer (for example, via the internet using an internet service provider).In some embodiments, electronic circuits such as programmable logic circuits, field-programmable gate arrays (FPGAs) or programmable logic arrays (PLAs) can execute the computer-readable program instructions by inserting state data of the computer-readable program instructions to adapt the electronic circuits in such a way that aspects of the present invention are carried out.

[0049] Aspects of the present invention are described herein with reference to flowcharts and / or block diagrams of processes, devices (systems), and computer program products according to embodiments of the invention. It is understood that each block of the flowcharts and / or block diagrams and combinations of blocks in the flowcharts and / or block diagrams can be implemented by computer-readable program instructions.

[0050] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or any other programmable data processing device to create a machine such that the instructions executed through the processor of the computer or other programmable data processing device create a means of implementing the functions / operations specified in the block or blocks of the flowcharts and / or block diagrams.These computer-readable program instructions can also be stored in a computer-readable storage medium capable of controlling a computer, programmable data processing device and / or other units to function in a particular manner, such that the computer-readable storage medium in which instructions are stored comprises an article of manufacture containing instructions that implement aspects of the function / operation specified in the block or blocks of the flowcharts and / or block diagrams.

[0051] The computer-readable program instructions can also be loaded onto a computer, other programmable data processing device or other unit in such a way as to cause a series of steps of an operation to be carried out on the computer, other programmable device or other unit in such a way as to produce a computer-implemented process such that the instructions executed on the computer, other programmable device or other unit implement the functions / operations specified in the block(s) of the flowchart(s) and / or block diagrams.

[0052] Fig. Figure 5 presents a general flowchart of the operation performed by a very short-term air pollution forecasting mechanism according to an illustrative embodiment. At the start of the operation, the very short-term air pollution forecasting mechanism acquires air quality data from a plurality of air pollution monitoring stations and a forecast point (step 5). 502 The mechanism for very short-term air pollution forecasting also incorporates weather data from a plurality of weather monitoring stations (step 1). 504 The mechanism for very short-term air pollution forecasting performs a check for correlations between air pollution monitoring stations from the majority of air pollution monitoring stations and the forecast point (step 1). 506For those air pollution monitoring stations that correlate with the forecast point, the very short-term air pollution forecasting mechanism recognizes one or more forecast point patterns, historical forecast point patterns, and air pollution monitoring station patterns related to the forecast point pattern (step 508 Subsequently, the very short-term air pollution forecasting mechanism provides a very short-term pollution forecast based on the detected patterns (step ). 510 ), whereby the process repeats itself based on a predetermined prediction cycle.

[0053] Fig. 6 represents the operation performed by the mechanism for very short-term air pollution forecasting when correlating air pollution monitoring stations in a plurality of air pollution monitoring stations with a forecast point according to an illustrative embodiment, as described in step 504 from Fig. 5 described. Using air quality data based on a single air pollution monitoring station and the recording time, and weather data based on a single air pollution monitoring station and the recording time, the very short-term air pollution forecasting mechanism identifies two or more of the majority of air pollution monitoring stations that are correlated with each other using an affective pollution model. At the start of the operation, the very short-term air pollution forecasting mechanism identifies the respective air pollution monitoring stations (M1, M2, M3, ..., M1). n ) the majority of air pollution monitoring stations located within a distance D around the forecast point M (step 602 ). For each of the detected air pollution monitoring stations (M1, M2, M3, ..., M nThe mechanism for very short-term air pollution forecasting estimates a degree of influence Di on the forecast point M at time T, corresponding to a pollutant concentration, wind speed, wind direction, and the like at time T, based on a physical diffusion model. More precisely, for each of the identified air pollution monitoring stations (M1, M2, M3, ..., M3), n ) the mechanism for a very short-term air pollution forecast detects a diffusion rate s of the pollutant from the air pollution monitoring station M i to the forecast point M using the wind speed w s and the wind direction w d (Step 604 The diffusion velocity s is based on the observed wind speed w. s at the air pollution monitoring station M ias well as on one or more eddy coefficients determined by the detected wind speed w s and the air temperature can be determined.

[0054] Using the calculated diffusion velocity s, the mechanism for very short-term air pollution forecasting calculates an angle Θ between the location M i and M and based on the wind direction at the location M i (Step 606 ) and calculates the velocity v of the pollutant using the diffusion velocity s of M i to M (step 608 ) using the following equation: v = s + w s * cos Θ .

[0055] The mechanism then identifies the degree of influence D for a very short-term air pollution forecast. i of the pollutant from M i to M (step 610 ) using the following formula: D i = Q 2 π ν σ y σ z exp [ − 1 2 ( y 2 σ y 2 t + z 2 σ z 2 t ) − k 2 t ] where Q is the pollution value of Mi v is the speed of motion, σ y The diffusion parameter on the y-axis (a fixed value) is σ. z The diffusion parameter on the z-axis (a fixed value) is , y is the distance between M i and M on the y-axis, z is the distance between M i and M is on the z-axis, t is the duration in hours (e.g. 1 hour, 2 hours, 3 hours ... etc.) and k is the decay factor, which may be a predefined factor.

[0056] Using the identified degree of influence D i The mechanism for very short-term air pollution forecasting determines whether the detected degree of influence D i greater than a threshold DT of the degree of influence (step 612 ). If the detected degree of influence Di in step 612If the threshold DT of the degree of influence is not greater than a threshold value, the mechanism for a very short-term air pollution forecast determines whether another detected air pollution monitoring station to be analyzed (M1, M2, M3, ..., M) is required. n ) is present (step 614 ). If in step 614 another identified air pollution monitoring station to be analyzed (M1, M2, M3, ..., M n If present, the operation returns to step 604 back. If the detected degree of influence Di in step 612 If the threshold DT of the degree of influence is greater than a certain threshold, the mechanism for very short-term air pollution forecasting adds the air pollution monitoring station M. i to a list of correlated air pollution monitoring stations associated with forecast point M (step 616 ), and then the operation proceeds step by step 614about. If in step 614 No further identified air pollution monitoring stations to be analyzed (M1, M2, M3, ..., M) n The operation ends when ) are present.

[0057] The Fig. 7A and Fig. 7B represents the operation performed by the mechanism for very short-term air pollution forecasting upon detection of one or more patterns according to an illustrative embodiment, as described in step 506 of Fig. As described in section 5, at the start of the operation, the mechanism for a very short-term air pollution forecast recognizes the associated weather and pollution data for the forecast point M within a period T. p from the weather data structure or the air quality data structure (step 702 ). For the period T pAt the prediction point M, the mechanism for very short-term air pollution forecasting recognizes a current shape pattern of the pollution data (step 704 ) and extracts the shape parameters (step 706) such as a number of rises, a number of falls, a degree of rises, a degree of falls, an average amplitude, a rise duration and magnitude of change, a fall duration and magnitude of change, a detected peak, a detected minimum, or the like. Using the extracted shape parameters, the very short-term air pollution forecasting mechanism searches the air quality data structure for historical pollution data associated with forecast point M that have a similarly shaped pattern to that of the current shape pattern associated with forecast point M, thereby forming a set of similarly shaped patterns (step 708).

[0058] The mechanism then calculates a similarity Sm of each similarly shaped pattern in a set of similarly shaped patterns for a very short-term air pollution forecast (step ).710 The mechanism for a very short-term air pollution forecast subtracts the percentage difference from a perfect 100 percent match (step ). 712 ) and determines whether the calculated similarity Smi is greater than a given similarity threshold SmT (step 714 ). If in step 714 If the calculated similarity Sm is greater than a predefined similarity threshold SmT, the mechanism for very short-term air pollution forecasting recognizes a historical pollution value ph at time T from the historical pollution curve. p +h (step 716 ), which is used for a later prediction. If in step 714 the calculated similarity Sm is not greater than a predefined similarity threshold SmT, or from step 716The mechanism for very short-term air pollution forecasting determines whether another similarly shaped pattern to analyze exists in the historical pollution data (step 718 ). If in step 718 If another similarly shaped pattern is present, the operation returns to step 708 back.

[0059] If in step 718 If no other similarly shaped pattern is present, the mechanism for a very short-term air pollution forecast recognizes the associated weather and pollution data for each air pollution monitoring station within a period T. p from the weather data structure or the air quality data structure (step 720 ). For the period T pFor each air pollution monitoring station, the mechanism for very short-term air pollution forecasting uses the extracted shape parameters belonging to the current shape pattern associated with the forecast point M to search for the shape patterns corresponding to the air quality data structure in the data belonging to the correlated air pollution monitoring station (step 722 For each detected shape pattern, the mechanism for a very short-term air pollution forecast calculates a similarity Smi (step 724 The mechanism for a very short-term air pollution forecast subtracts the percentage difference from a perfect 100 percent match (step ). 726 ) and determines whether the calculated similarity Smi is greater than a given similarity threshold SmT (step 728 ).

[0060] If in step 728If the similarity Smi is greater than a predefined similarity threshold SmT, the mechanism for very short-term air pollution prediction recognizes the air pollution monitoring station as belonging to an area where it can be predicted that the pollution level p will be similar to the historical pollution level ph at time T. p +h is near (step 730 ). If in step 728 the calculated similarity Sm is not greater than a predefined similarity threshold SmT, or from step 730 The mechanism for a very short-term air pollution forecast determines whether another air pollution monitoring station to be analyzed is available (step 732 ). If in step 732 If no other air pollution monitoring station is available, the operation returns to step 720 back. If in step 732If no other air pollution monitoring station is available for analysis, the mechanism for a very short-term air pollution forecast provides the calculated similarity Sm of the historical pollution curve that lies above the similarity threshold SmT, the similarity Smi of each detected air pollution monitoring station in the list of correlated air pollution monitoring stations that lies above the similarity threshold SmT, and the pollution value ph at time T. p +h out (step 734 ), after which the operation ends.

[0061] Fig. Figure 8 represents the operation performed by the very short-term air pollution forecast mechanism when providing a very short-term air pollution forecast according to an illustrative embodiment, as described in step 1. 506 from Fig.5 described. At the start of the operation, the mechanism for a very short-term air pollution forecast uses the similarity Sm of the historical pollution curve that is above the similarity threshold SmT, which correlates with the detected pollution curve of the forecast point M, and the similarity Smi of each detected air pollution monitoring station in the list of correlated air pollution monitoring stations to assign a weight w j to calculate for each detected air pollution monitoring station. The mechanism for a very short-term air pollution forecast calculates the weighting w. j for a similar period Tj (step 802 ) according to the similarity Sm in the period Tj, from which Smj is obtained, and the similarity Smi in the period Tj, from which Smij is obtained, using the following equation: w j = S m j * ∏ S m i j ∑ j = 1 n S m j * ∏ S m i j .

[0062] The mechanism then provides a pollution level p for a very short-term air pollution forecast. t+h for the correlated air pollution monitoring stations at time T p +h (step 804 ) using the following equation beforehand: p t + h = ∑ j = 1 n w j p j .

[0063] The very short-term air pollution forecasting mechanism then issues the forecast to one or more companies and / or individuals so that measures can be taken to protect themselves or to reduce air pollution (step 1). 806 ), after which the operation ends.

[0064] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, processes, and computer program products according to various embodiments of the present invention. In this context, each block in the flowcharts or block diagrams can represent a module, segment, or section of instructions that includes one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions indicated in the block may occur in a different order than shown in the figures. For example, depending on the functionality included, two consecutively shown blocks may even be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order.It should also be noted that each block of the block diagrams and / or flowcharts and combinations of blocks in the block diagrams and / or flowcharts can be implemented by special hardware-based systems that perform the specified functions or operations, or by combinations of special hardware and computer instructions.

[0065] In this way, the illustrative embodiments provide mechanisms for very short-term air pollution forecasting, predicting air pollution levels for the next few hours, for example, 1 to 6 hours. Air pollution is predicted hourly using intrinsic meteorological and pollutant diffusion relationships between monitoring stations. Using current air pollution levels detected by a plurality of air pollution monitoring stations, the mechanisms utilize meteorological and pollutant diffusion relationships associated with each station to identify correlated stations. Once a set of correlated stations has been identified, the mechanisms detect air pollution patterns and, in particular, air pollution events.A fire causing an increase in air pollution, an unexpected chemical release by a company causing air pollution, or similar events. The mechanisms then provide a very short-term forecast of air pollution for the identified area and other areas that may be affected for the next few hours by detecting pollution patterns.

[0066] As noted above, it should be noted that the illustrative embodiments can be purely hardware-based, purely software-based, or a hybrid embodiment containing both hardware and software elements. In one exemplary embodiment, the mechanisms of the illustrative embodiment are implemented in software or program code, which includes, but is not limited to, firmware, resident software, microcode, etc.

[0067] A data processing system suitable for storing and / or executing program code includes at least one processor, which is directly or indirectly connected to memory elements via a system bus. These memory elements may include local memory used during the actual execution of the program code, mass storage, and cache memory, which provides temporary storage of at least part of the program code to reduce the frequency with which the code needs to be retrieved from mass storage during execution.

[0068] Input / output (I / O) units (for example, keyboards, displays, pointing devices, etc., but not limited to these) can be connected to the system either directly or through intermediary I / O control units. Network adapters can also be connected to the system in such a way that the data processing system is enabled to connect to other data processing systems or remotely located printers or storage devices through intermediary private or public networks. Modems, cable modems, and Ethernet cards are just some of the currently available types of network adapters.

[0069] The description of the present invention is provided for illustrative and descriptive purposes and is not intended to be exhaustive or limited to the invention as presented. Many modifications and variants are apparent to those skilled in the art without altering the scope and essence of the described embodiments. The embodiment was selected and described to best explain the basic concepts of the invention and its practical application, and to enable other skilled individuals to understand the invention in relation to various embodiments with different modifications suitable for the intended use.The terminology used herein has been chosen to best explain the basic ideas of the embodiments, their practical application or technical improvement over technologies available on the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein.

Claims

[1] Method in a data processing system comprising a processor and a memory for predicting air pollution, wherein the method comprises: Identifying one or more air pollution monitoring stations correlated with a forecast point from a plurality of air pollution monitoring stations by the data processing system; for the one or more air pollution monitoring stations that correlate with the forecast point, the detection of one or more forecast point patterns, historical forecast point patterns related to the one or more forecast point patterns, and one or more air pollution monitoring station patterns related to the one or more forecast point patterns, by the data processing system; and Providing a pollution forecast based on the one or more patterns of the forecast point, the historical patterns of the forecast point associated with the one or more patterns of the forecast point, and the one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the forecast point, by the data processing system. [2] Method according to claim 1, wherein the detection of the one or more air pollution monitoring stations correlated with the forecast point utilizes air quality data from a plurality of air pollution monitoring stations and the forecast point and weather data from a plurality of weather monitoring stations. [3] Method according to claim 1, comprising the detection of one or more air pollution monitoring stations correlated with the prediction point: Identifying a set of air pollution monitoring stations from the majority of air pollution monitoring stations located within a specified distance around the forecast point, by the data processing system; For each of the set of air pollution monitoring stations, detecting a diffusion rate s of a pollutant from the air pollution monitoring station M i to the forecast point M using the wind speed w s and the wind direction w d through the data processing system; Calculating an angle Θ between the monitoring station M i and the forecast point M based on the wind direction w d at the place M ithrough the data processing system; Calculating the velocity v of the pollutant using the diffusion velocity s from monitoring station M i to the prediction point M by the data processing system using: v = s + w s * cos Θ; Recognizing the degree of influence D i of the pollutant from monitoring station M i to the prediction point M by the data processing system using: D i = Q 2 π ν σ y σ z exp [ − 1 2 ( y 2 σ y 2 t + z 2 σ z 2 t ) − k 2 t ] where Q is the pollution value of M i v is the speed of motion, σ y The diffusion parameter on the y-axis (a fixed value) is σ. z The diffusion parameter on the z-axis (a fixed value) is , y is the distance between M i and M on the y-axis, z is the distance between M iand M is on the z-axis, t is the duration in hours (e.g. 1 hour, 2 hours, 3 hours ... etc.) and k is the decay factor, which may be a predefined factor; Determine whether the identified degree of influence D i greater than a threshold DT of the degree of influence by the data processing system; and in response to the fact that the degree of influence D i If the degree of influence exceeds a threshold value DT, the air pollution monitoring station M is added. i to the one or more air pollution monitoring stations that are correlated with the forecast point M, by the data processing system. [4] Method according to claim 1, wherein the recognition of the historical patterns of the prediction point, which are related to the one or more patterns of the prediction point, comprises: For the forecast point M, recognition of associated weather data and pollution data for a period T. p through the data processing system; for the period T p of the prediction point M: Recognition of one or more patterns of the prediction point by the data processing system; Extracting shape parameters from one or more patterns of the prediction point by the data processing system; Searching for historical pollution data associated with forecast point M that exhibit a similarly shaped pattern to that of one or more of the forecast point's patterns, thereby forming a set of similarly shaped patterns, by the data processing system; The data processing system calculates a similarity Sm of each similarly shaped pattern in the set of similarly shaped patterns; Determine whether the similarity Sm is greater than a predefined similarity threshold SmT, using the data processing system; and In response to the fact that the similarity Sm is greater than the specified similarity threshold SmT, a historical pollution value ph is detected at time T. p +h from the historical pollution data by the data processing system. [5] Method according to claim 4, wherein the shape parameters of one or more of a number of rises, a number of falls, a degree of rises, a degree of falls, an average amplitude, a duration and extent of change of the rise, a duration and extent of change of the fall, a detected maximum value and a detected minimum value. [6] Method according to claim 1, comprising the detection of one or more patterns of the air pollution monitoring stations associated with one or more patterns of the prediction point: For each of the one or more air pollution monitoring stations that correlate with the forecast point, recognition of associated weather data and pollution data for a period T. p through the data processing system; for the period T p of the prediction point M: Recognition of one or more patterns of the prediction point by the data processing system; Extracting shape parameters from one or more patterns of the prediction point by the data processing system; Searching for data from one or more air pollution monitoring stations that have a similarly shaped pattern to that of the one or more patterns of the prediction point, by the data processing system, thereby forming a set of similarly shaped patterns; The data processing system calculates the similarity Smi of each similarly shaped pattern in the set of similarly shaped patterns; Determine whether the similarity Smi is greater than a predefined similarity threshold SmT, using the data processing system; and In response to the fact that the similarity Smi is greater than a given similarity threshold SmT, the air pollution monitoring station is recognized as belonging to an area where it can be predicted that the pollution level p will be similar to a historical pollution level ph at time T. p+h is close, through the data processing system. [7] Method according to claim 1, comprising providing the pollution forecast based on one or more patterns of the forecast point, the historical patterns of the forecast point associated with the one or more patterns of the forecast point, and the one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the forecast point: Calculate a weighting w for each of the one or more air pollution monitoring stations j for a period Tj according to the similarity Sm in the period Tj, from which Smj results, and the similarity Smi in the period Tj, from which Smij results, by the data processing system using: w j = S m j * ∏ S m i j ∑ j = 1 n S m j * ∏ S m i j ; Predictions of a pollution level p t+hfor the one or more air pollution monitoring stations at time T p +h through the data processing system using the equation: p t + h = ∑ j = 1 n w j p j ; and The data processing system issues the pollution forecast to one or more companies or individuals so that measures can be taken to protect themselves or to reduce air pollution. [8] Computer program product comprising a computer-readable storage medium in which a computer-readable program is stored, wherein the computer-readable program, when executed on a data processing unit, causes the data processing unit to: Identifying one or more air pollution monitoring stations correlated with a forecast point from a plurality of air pollution monitoring stations; for the one or more air pollution monitoring stations that correlate with the forecast point, detection of one or more patterns of the forecast point, historical patterns of the forecast point that are related to the one or more patterns of the forecast point, and one or more patterns of the air pollution monitoring stations that are related to the one or more patterns of the forecast point; and Providing a pollution forecast based on one or more forecast point patterns, the forecast point's historical patterns associated with the one or more forecast point patterns, and the one or more air pollution monitoring station patterns associated with the one or more forecast point patterns. [9] Computer program product according to claim 8, wherein the computer program product, for detecting the one or more air pollution monitoring stations correlated with the forecast point, further causes the data processing unit to use air quality data from a plurality of air pollution monitoring stations and the forecast point and weather data from a plurality of weather monitoring stations. [10] Computer program product according to claim 8, wherein the computer program product, for detecting the one or more air pollution monitoring stations correlated with the prediction point, further causes the data processing unit to: Identifying a set of air pollution monitoring stations from the plurality of air pollution monitoring stations located within a specified distance around the forecast point; For each of the set of air pollution monitoring stations, detecting a diffusion rate s of a pollutant from the air pollution monitoring station M i to the forecast point M using the wind speed w s and the wind direction w d ; Calculating an angle Θ between the monitoring station M i and the forecast point M based on the wind direction w d at the place M i ; Calculating the velocity v of the pollutant using the diffusion velocity s from monitoring station M i to the prediction point M using: v = s + w s * cos Θ ; Recognizing the degree of influence D i of the pollutant from monitoring station M i to the prediction point M using: D i = Q 2 π ν σ y σ z exp [ − 1 2 ( y 2 σ y 2 t + z 2 σ z 2 t ) − k 2 t ] where Q is the pollution value of M iv is the speed of motion, σ y The diffusion parameter on the y-axis (a fixed value) is σ. z The diffusion parameter on the z-axis (a fixed value) is , y is the distance between M i and M on the y-axis, z is the distance between M i and M is on the z-axis, t is the duration in hours (e.g. 1 hour, 2 hours, 3 hours ... etc.) and k is the decay factor, which may be a predefined factor; Determine whether the identified degree of influence D i greater than a threshold value DT of the degree of influence; and In response to the fact that the degree of influence Di is greater than a threshold value DT of the degree of influence, the air pollution monitoring station M is added. i to the one or more air pollution monitoring stations that are correlated with the forecast point M. [11] Computer program product according to claim 8, wherein the computer program product, for recognizing the historical patterns of the prediction point that are related to the one or more patterns of the prediction point, further causes the data processing unit to: For the forecast point M, recognition of associated weather data and pollution data for a period T. p ; For the period Tp of the prediction point M, recognition of one or more patterns of the prediction point; Extracting shape parameters from one or more patterns of the prediction point; Search for historical pollution data associated with forecast point M that exhibit a similarly shaped pattern to that of one or more of the forecast point's patterns, thereby forming a set of similarly shaped patterns; Calculating a similarity Sm of each similarly shaped pattern in the set of similarly shaped patterns; Determine whether the similarity Sm is greater than a given similarity threshold SmT; and In response to the fact that the similarity Sm is greater than the specified similarity threshold SmT, a historical pollution value ph is detected at time T. p +h from historical pollution data. [12] Computer program product according to claim 11, wherein the shape parameters of one or more of a number of rises, a number of falls, a degree of rises, a degree of falls, an average amplitude, a duration and magnitude of change of the rise, a duration and magnitude of change of the fall, a detected maximum value and a detected minimum value. [13] Computer program product according to claim 8, wherein the computer program product, for recognizing one or more patterns of the air pollution monitoring stations that are associated with one or more patterns of the prediction point, further causes the data processing unit to: For each of the one or more air pollution monitoring stations that correlate with the forecast point, recognition of associated weather data and pollution data for a period T. p ; For the period Tp of the prediction point M, recognition of one or more patterns of the prediction point; Extracting shape parameters from one or more patterns of the prediction point; Search for data from one or more air pollution monitoring stations that have a similarly shaped pattern to that of the one or more patterns of the forecast point; Calculating a similarity Smi of each similarly shaped pattern in the set of similarly shaped patterns; Determine whether the similarity Smi is greater than a given similarity threshold SmT; and In response to the fact that the similarity Smi is greater than a given similarity threshold SmT, the air pollution monitoring station is recognized as belonging to an area where it can be predicted that the pollution level p will be similar to a historical pollution level ph at time T. p +h is near. [14] Computer program product according to claim 8, wherein the computer program product, for providing the pollution forecast based on one or more patterns of the forecast point, the historical patterns of the forecast point associated with the one or more patterns of the forecast point, and the one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the forecast point, further causes the data processing unit to: Calculate a weighting w for each of the one or more air pollution monitoring stations j for a period Tj according to the similarity Sm in the period Tj, from which Smj results, and the similarity Smi in the period Tj, from which Smij results, using: w j = S m j * ∏ S m i j ∑ j = 1 n S m j * ∏ S m i j ; Predictions of a pollution level p t+hfor the one or more air pollution monitoring stations at time T p +h using the equation: p t + h = ∑ j = 1 n w j p j ; and Issuing the pollution forecast to one or more companies or individuals so that measures can be taken to protect themselves or to reduce air pollution. [15] Device comprising: a processor; and a memory connected to the processor, wherein the memory contains instructions which, when executed by the processor, cause the processor to: Identifying one or more air pollution monitoring stations correlated with a forecast point from a plurality of air pollution monitoring stations; for the one or more air pollution monitoring stations that correlate with the forecast point, detection of one or more patterns of the forecast point, historical patterns of the forecast point that are related to the one or more patterns of the forecast point, and one or more patterns of the air pollution monitoring stations that are related to the one or more patterns of the forecast point; and Providing a pollution forecast based on one or more forecast point patterns, the forecast point's historical patterns associated with the one or more forecast point patterns, and the one or more air pollution monitoring station patterns associated with the one or more forecast point patterns. [16] Device according to claim 15, wherein the instructions for detecting the one or more air pollution monitoring stations correlated with the forecast point further cause the processor to use air quality data from a plurality of air pollution monitoring stations and the forecast point and weather data from a plurality of weather monitoring stations. [17] Device according to claim 15, wherein the instructions for detecting the one or more air pollution monitoring stations correlated with the prediction point further cause the processor to: Identifying a set of air pollution monitoring stations from the plurality of air pollution monitoring stations located within a specified distance around the forecast point; For each of the set of air pollution monitoring stations, detecting a diffusion rate s of a pollutant from the air pollution monitoring station M i to the forecast point M using the wind speed w s and the wind direction w d ; Calculating an angle Θ between the monitoring station M i and the forecast point M based on the wind direction w d at the place M i ; Calculating the velocity v of the pollutant using the diffusion velocity s from monitoring station M i to the prediction point M using: v = s + w s * cos Θ ; Recognizing the degree of influence D i of the pollutant from monitoring station M i to the prediction point M using: D i = Q 2 π ν σ y σ z exp [ − 1 2 ( y 2 σ y 2 t + z 2 σ z 2 t ) − k 2 t ] where Q is the pollution value of M iv is the speed of motion, σ y The diffusion parameter on the y-axis (a fixed value) is σ. z The diffusion parameter on the z-axis (a fixed value) is , y is the distance between M i and M on the y-axis, z is the distance between M i and M is on the z-axis, t is the duration in hours (e.g. 1 hour, 2 hours, 3 hours ... etc.) and k is the decay factor, which may be a predefined factor; Determine whether the identified degree of influence D i greater than a threshold value DT of the degree of influence; and In response to the fact that the degree of influence Di is greater than a threshold value DT of the degree of influence, the air pollution monitoring station M is added. i to the one or more air pollution monitoring stations that are correlated with the forecast point M. [18] Device according to claim 15, wherein the instructions for recognizing the historical patterns of the prediction point, which are associated with the one or more patterns of the prediction point, further cause the processor to: For the forecast point M, recognition of associated weather data and pollution data for a period T. p ; For the period Tp of the prediction point M, recognition of one or more patterns of the prediction point; Extracting shape parameters from one or more patterns of the prediction point; Search for historical pollution data associated with forecast point M that exhibit a similarly shaped pattern to that of one or more of the forecast point's patterns; Calculating a similarity Sm of each similarly shaped pattern in the set of similarly shaped patterns; Determine whether the similarity Sm is greater than a given similarity threshold SmT; and In response to the fact that the similarity Sm is greater than the specified similarity threshold SmT, a historical pollution value ph is detected at time T. p +h from historical pollution data. [19] Device according to claim 18, wherein the shape parameters of one or more of a number of rises, a number of falls, a degree of rises, a degree of falls, an average amplitude, a duration and extent of change of the rise, a duration and extent of change of the fall, a detected maximum value and a detected minimum value. [20] Device according to claim 15, wherein the instructions for detecting one or more patterns of the air pollution monitoring stations associated with one or more patterns of the prediction point further cause the processor to: For each of the one or more air pollution monitoring stations that correlate with the forecast point, recognition of associated weather data and pollution data for a period T. p ; For the period Tp of the prediction point M, recognition of one or more patterns of the prediction point; Extracting shape parameters from one or more patterns of the prediction point; Search for data from one or more air pollution monitoring stations that have a similarly shaped pattern to that of the one or more patterns of the forecast point; Calculating a similarity Smi of each similarly shaped pattern in the set of similarly shaped patterns; Determine whether the similarity Smi is greater than a given similarity threshold SmT; and In response to the fact that the similarity Smi is greater than a given similarity threshold SmT, the air pollution monitoring station is recognized as belonging to an area where it can be predicted that the pollution level p will be similar to a historical pollution level ph at time T. p +h is near. [21] Device according to claim 15, wherein the instructions for providing the pollution forecast based on the one or more patterns of the forecast point, the historical patterns of the forecast point associated with the one or more patterns of the forecast point, and the one or more patterns of the air pollution monitoring stations associated with the one or more patterns of the forecast point, further cause the processor to: Calculate a weighting w for each of the one or more air pollution monitoring stations j for a period Tj according to the similarity Sm in the period Tj, from which Smj results, and the similarity Smi in the period Tj, from which Smij results, using: w j = S m j * ∏ S m i j ∑ j = 1 n S m j * ∏ S m i j ; Predictions of a pollution level p t+hfor the one or more air pollution monitoring stations at time T p +h using the equation: p t + h = ∑ j = 1 n w j p j ; and Issuing the pollution forecast to one or more companies or individuals so that measures can be taken to protect themselves or to reduce air pollution.