Method, device and readable storage medium for improving environmental monitoring accuracy

Abstract

The present invention provides a method, device and readable storage medium for improving the accuracy of environmental monitoring, which belongs to the field of atmospheric environment detection quality control technology. The method includes: obtaining environmental monitoring data of a target area, wherein the environmental monitoring data includes concentration monitoring data of a monitored object; determining a probability distribution function of the relationship between the corresponding concentration and probability based on the acquired concentration monitoring data; using a local linear regression method, based on the probability distribution function, predicting the probability density function value of a preset range of a preset breakpoint, and determining the function approximation value on both sides of the preset breakpoint. The present invention utilizes precise determination of breakpoints and reasonable division of discrete intervals; and with the help of local linear regression, accurately predicts the probability density function and determines the function approximation value; by calculating the difference in probability density on both sides of the breakpoint, effectively judges the continuity of the data, ensures the quality and reliability of the data, and improves the accuracy of environmental monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of atmospheric environment detection quality control, and in particular to a method, device and readable storage medium for improving the accuracy of environmental monitoring. Background Art

[0002] In order to accurately grasp the degree of air pollution and formulate scientific treatment plans, a large number of automatic ambient air monitoring stations have been deployed across the country to carry out high-frequency monitoring of pollution factors such as particulate matter (PM2.5 and PM10) and gaseous pollutants (such as SO2, NO2, O3, CO, etc.). Among them, five-minute value data, as an important basis for real-time monitoring, can reflect the short-term fluctuation characteristics of pollution factors and provide support for pollution source analysis and refined management and control. In the field of environmental monitoring, accurately obtaining and analyzing environmental monitoring data is crucial for assessing environmental conditions. Currently, the accuracy and reliability of environmental monitoring data face many challenges.

[0003] Existing environmental monitoring data often contains invalid data, such as those exceeding instrument ranges or missing values, which compromises data integrity and the accuracy of analytical results. Furthermore, traditional methods have limitations in accurately assessing the characteristics of environmental monitoring data, such as identifying data breakpoints and analyzing data continuity. Furthermore, existing environmental monitoring methods struggle to accurately and effectively analyze environmental monitoring data, failing to provide a reliable basis for environmental monitoring, thus hindering accurate assessments of the target area's environment. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method for improving the accuracy of environmental monitoring, which is dedicated to solving many problems existing in the current environmental monitoring process to achieve more accurate and reliable environmental monitoring.

[0005] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a method for improving the accuracy of environmental monitoring, the method comprising: obtaining environmental monitoring data of a target area, the environmental monitoring data including concentration monitoring data of a monitored object; determining a probability distribution function of the relationship between the corresponding concentration and probability based on the acquired concentration monitoring data; using a local linear regression method, based on the probability distribution function, predicting the probability density function value of a preset range of a preset breakpoint, and determining the function approximation value on both sides of the preset breakpoint to calculate the difference in probability density on both sides of the preset breakpoint; judging the continuity of the environmental monitoring data based on the difference in probability density on both sides of the preset breakpoint to improve the accuracy of environmental monitoring of the target area.

[0006] Optionally, obtaining environmental monitoring data of the target area includes: obtaining concentration monitoring data with timestamps; recording the obtained concentration monitoring data with timestamps as a time series; eliminating invalid data in the time series, and determining the eliminated invalid data as missing points; and calculating a supplementary value based on the linear relationship between the preceding and following adjacent data of the missing point through a linear interpolation algorithm.

[0007] Optionally, determining the probability distribution function of the relationship between the corresponding concentration and probability based on the acquired concentration monitoring data includes: dividing the environmental monitoring data according to the preset breakpoints to obtain discrete intervals; and obtaining the probability distribution function based on the discrete intervals.

[0008] On the basis of the above scheme, before dividing the environmental monitoring data according to the preset breakpoints, the method also includes: determining the preset breakpoints based on the distribution characteristics of the concentration monitoring data of the monitored object, and the preset breakpoints are used to indicate the critical value of the environmental pollution of the monitored object.

[0009] Optionally, the timestamp of the concentration monitoring data is a preset time interval.

[0010] Optionally, dividing the environmental monitoring data according to the preset breakpoints to obtain discrete intervals includes: dividing the environmental monitoring data into equally spaced intervals according to the concentration of the monitored object according to the preset breakpoints to obtain the discrete intervals; and calculating the concentration of the monitored object after the equally spaced intervals are calculated using the following formula:

[0011]

[0012] Among them, g(R i ) represents the concentration of the monitored object after the concentration is divided into equal intervals, R i is the concentration of the monitored object in the discrete interval, b represents the width of the divided concentration interval, and c is the pollutant concentration at the preset breakpoint. express The largest integer;

[0013] Use the following formula to solve for the concentration interval width:

[0014]

[0015] Where x i represents the concentration point, μ represents x i The mean concentration of n represents the number of concentration points.

[0016] Optionally, the calculation of the probability density difference on both sides of the preset breakpoint includes: using the McCrary test method, and based on the function approximation values ​​on both sides of the preset breakpoint, determining the probability density estimation values ​​on both sides of the preset breakpoint; performing logarithmic calculation on the determined probability density estimation values ​​on both sides of the preset breakpoint to obtain the logarithmic difference of the probability density on both sides of the preset breakpoint.

[0017] Optionally, the determination of the continuity of the preset breakpoint includes: determining whether there is discontinuity at the preset breakpoint based on the size of the logarithmic difference of the probability density on both sides in combination with a one-sided test method.

[0018] Optionally, the determining whether there is a discontinuity in the preset breakpoint includes: comparing the obtained logarithmic difference with a preset first threshold and a second threshold, and performing the following steps based on the comparison result: if the logarithmic difference is less than the first threshold, determining that there is a discontinuity in the preset breakpoint; if the first threshold is less than the logarithmic difference and less than the second threshold, marking the determination result; if the second threshold is less than the logarithmic difference, determining that there is no discontinuity in the preset breakpoint.

[0019] On the other hand, the present invention provides a control device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for improving the accuracy of environmental monitoring as described above.

[0020] On the other hand, the present invention provides a readable storage medium having instructions stored thereon, wherein the instructions enable a machine to execute the above-mentioned method for improving the accuracy of environmental monitoring.

[0021] The present invention provides a method for improving the accuracy of environmental monitoring, which can scientifically and accurately determine preset breakpoints, reasonably divide discrete intervals, accurately predict probability density functions and determine function approximation values ​​with the help of local linear regression, effectively judge data continuity by calculating logarithmic differences, ensure data quality and reliability, and thus improve the accuracy of environmental monitoring.

[0022] The method of the present invention is highly versatile, simple to operate and easy to promote. It can serve different environmental monitoring scenarios, provide a basis for environmental decision-making, assist in refined environmental management, and comprehensively improve the accuracy and effectiveness of environmental monitoring.

[0023] This method innovatively uses local linear regression to construct probability density function estimates of monitoring data at pre-set breakpoints. This approach preserves the local characteristics of the data while avoiding potential misjudgments caused by global trend models, thereby improving the accuracy of data distribution estimates. By performing regression analysis on the probability density functions to the left and right of the pre-set breakpoint, potential discontinuities in the data at the pre-set breakpoint can be captured in greater detail.

[0024] Secondly, based on the McCrary test, this method quantitatively determines the continuity of monitoring data at a predetermined breakpoint by calculating the logarithmic difference between the regression values ​​on either side of the breakpoint. Compared to traditional anomaly detection methods such as mean or variance analysis, this method is more suitable for processing non-normally distributed data and can directly identify the specific locations where data manipulation or anomalies may occur, significantly improving the sensitivity and robustness of detection.

[0025] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0027] Figure 1 The present invention is a flowchart of a method for improving the accuracy of environmental monitoring.

[0028] Figure 2 Schematic diagram of breakpoint continuity testing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0030] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. In the embodiments of this application, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use such solutions.

[0031] Figure 1 This is a flow chart of a method for improving the accuracy of environmental monitoring according to an embodiment of the present invention. Figure 1 As shown, the method for improving the accuracy of environmental monitoring may include the following steps:

[0032] Step S100: Acquire environmental monitoring data of a target area, where the environmental monitoring data includes concentration monitoring data of monitored objects.

[0033] In embodiments of the present invention, environmental monitoring data may include concentration monitoring data of monitored objects. The monitored objects may include pollution factors that affect the environment, such as particulate matter (PM2.5 and PM10), gaseous pollutants (such as SO2, NO2, O3, CO, etc.). It should be noted that the embodiments of the present invention use PM2.5 as an example of a monitored object for illustration, and are not intended to limit the embodiments of the present invention.

[0034] The preferred breakpoint of the environmental monitoring data in the embodiment of the present invention may be a critical value of a high-pollution area of ​​the monitored object.

[0035] For example, the analysis breakpoint c is determined based on the ambient air quality standard of PM2.5 and the distribution characteristics of the monitoring data. In this embodiment, c is set to 75 μg / m 3 is the breakpoint, i.e. the critical value of the high pollution area.

[0036] In a preferred embodiment of the present invention, step S100 may include:

[0037] Acquire concentration monitoring data with timestamps; record the acquired concentration monitoring data with timestamps as a time series; eliminate invalid data in the time series, and determine the eliminated invalid data as missing points; calculate the supplementary value according to the linear relationship between the preceding and following adjacent data of the missing point through a linear interpolation algorithm.

[0038] In an embodiment of the present invention, the timestamp of the concentration monitoring data may be a preset time interval, for example, the preset time interval may be 3 minutes, 5 minutes or 8 minutes. For example, five minutes of PM2.5 concentration monitoring data with a timestamp is obtained from an environmental monitoring device and recorded as a time series {X t}, where X t is the PM2.5 concentration at time t. Invalid data outside the instrument's range is eliminated, and missing data is supplemented using linear interpolation. For example, a linear interpolation algorithm calculates supplementary values ​​based on the linear relationship between the adjacent data before and after the missing point, thus ensuring the integrity of the time series data.

[0039] Step S200: Determine a probability distribution function of the relationship between the corresponding concentration and probability based on the acquired concentration monitoring data.

[0040] In a preferred embodiment of the present invention, step S200 may include: dividing the environmental monitoring data according to preset breakpoints to obtain discrete intervals; and obtaining a probability distribution function based on the discrete intervals.

[0041] Preferably, before dividing the environmental monitoring data according to preset breakpoints, the method further includes: determining preset breakpoints according to distribution characteristics of the concentration monitoring data of the monitored object, and the preset breakpoints are used to indicate critical values ​​of environmental pollution of the monitored object.

[0042] Since the probability density function of PM2.5 at each concentration is relatively discrete, in order to better perform the next step of local linear regression, PM2.5 can be first divided according to the concentration range and the discrete intervals can be obtained.

[0043] Specifically, the environmental monitoring data is divided according to the preset breakpoints to obtain discrete intervals, including: dividing the discrete intervals by equal intervals according to the concentration of the monitored object according to the preset breakpoints; and calculating the corresponding concentration of the monitored object after the concentration is divided by equal intervals using the following formula:

[0044]

[0045] Among them, g(R i ) represents the concentration of the monitored object after the concentration is divided into equal intervals, R i is the concentration of the monitored object in the discrete interval, b represents the width of the divided concentration interval, and c is the pollutant concentration at the preset breakpoint. express The maximum integer.

[0046] In order to minimize the influence of human factors, the following formula is used to solve the concentration interval width:

[0047]

[0048] Where x i represents the concentration point, μ represents x i The mean concentration of n represents the number of concentration points.

[0049] Then, define equidistant grid points X1,X2,…,X J are points with a spacing of b, which covers the entire concentration range. Then the frequency distribution of the jth interval is:

[0050]

[0051] Its probability distribution can be expressed as (X j ,Y j ) in the form of a scatter plot.

[0052] Step S300: Using the local linear regression method, based on the probability distribution function, predict the probability density function value of the preset range of the preset breakpoint, and determine the function approximation values ​​on both sides of the preset breakpoint to calculate the difference in probability density on both sides of the preset breakpoint.

[0053] In a preferred embodiment of the present invention, step S300 may include: using a local linear regression method to estimate the probability density function near the breakpoint. The density estimate at point x is in Obtained by minimizing the objective function.

[0054] Minimize the objective function:

[0055]

[0056] Where L(φ1,φ2,x) is the objective function about point x, φ1,φ2 are the parameters to be solved;

[0057] Where K(·) is the Gaussian kernel function, expressed as:

[0058]

[0059] For example, h=15b, where h is the bandwidth.

[0060] For example, by solving the minimum value of the above objective function, the function approximation values ​​on the left and right sides of the point x = c are:

[0061]

[0062] in:

[0063]

[0064] Where, f - (c) and f + (c) is the function approximation value on both sides of the target point x=c, is the local polynomial kernel function estimate of degree k on the left side of x = c, is an estimate of a local polynomial kernel function of degree k to the right of x=c, where k is the degree of the local polynomial kernel function, for example, k=1,2.

[0065] Step S400: judging the continuity of the environmental monitoring data based on the difference in probability density on both sides of the preset breakpoint, so as to improve the accuracy of environmental monitoring of the target area.

[0066] In a preferred embodiment of the present invention, step S400 may include:

[0067] S410. Using the McCrary test method, based on the function approximation values ​​on both sides of the breakpoint, obtain the probability density estimates on both sides of the breakpoint. For example, the McCrary test method is used to verify whether the data distribution at breakpoint c is continuous. The McCrary test method tests whether there is discontinuity in the data by calculating the logarithmic difference of the probability density on both sides of the breakpoint. The test formula is:

[0068]

[0069] in and are the probability density estimates on the left and right sides of the breakpoint c, respectively.

[0070] S420 , performing a logarithmic operation on the obtained probability density estimates on both sides of the breakpoint to obtain a logarithmic difference in the probability density on both sides of the breakpoint.

[0071] For example, the determination of the continuity of a breakpoint includes: judging whether there is a significant discontinuity at the breakpoint based on the size of the logarithmic difference in the probability density on both sides, combined with a one-sided test method.

[0072] Determining whether a discontinuity exists at a breakpoint includes: comparing the obtained logarithmic difference with a preset first threshold and a second threshold, and performing the following steps based on the comparison result: if the logarithmic difference is less than the first threshold, determining that a discontinuity exists at the breakpoint; if the first threshold is less than the logarithmic difference and less than the second threshold, marking the determination result, and subsequently determining whether a discontinuity exists at the breakpoint through expert judgment, or determining whether a discontinuity exists at the breakpoint by setting a third threshold and comparing the logarithmic difference with the third threshold; if the second threshold is less than the logarithmic difference, determining that no discontinuity exists at the breakpoint.

[0073] like Figure 2 As shown in Figure 2, the size of the logarithmic difference Δ is used to determine whether there is a significant discontinuity at the breakpoint. Since the PM2.5 concentration test breakpoint c = 75 μg / m 3 It is usually located on the right side of the normal distribution peak and can be tested using a one-sided t-test.

[0074] For example, if Δ<-2, it is considered that there is a high possibility of a breakpoint, that is, there is a high possibility of human manipulation;

[0075] If -2<Δ<-1.64, it is considered that there may be a distribution breakpoint, but the probability is low and further manual identification is required;

[0076] If Δ>-1.64, it is considered that there is no breakpoint in the data distribution, that is, there is no possibility of human manipulation.

[0077] The present invention innovatively uses local linear regression to construct a probability density function estimate of the monitoring data at the breakpoint. This method can avoid the misjudgment that may be caused by the overall trend model while maintaining the local characteristics of the data, thereby improving the accuracy of the data distribution estimate. By performing regression analysis on the probability density functions on the left and right sides of the breakpoint, the potential discontinuity of the data at the breakpoint can be captured more carefully. Secondly, based on the McCrary test method, the present invention quantitatively judges the monitoring data at a specified breakpoint (such as 35μg / m 3 and 75 μg / m 3 ) at the location of the data. Compared with traditional anomaly detection methods such as mean or variance analysis, this method is more suitable for processing non-normally distributed data and can directly reflect the specific locations where the data may be manipulated or abnormal, significantly improving the sensitivity and robustness of detection. By eliminating invalid data and optimizing the breakpoint selection process, the present invention can adapt to the characteristics of monitoring points in different regions, improving the operability of the algorithm in large-scale point applications.

[0078] The present invention provides a control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the above-mentioned method for improving the accuracy of environmental monitoring.

[0079] An embodiment of the present invention provides a readable storage medium having instructions stored thereon, wherein the instructions enable a machine to execute the above-mentioned method for improving the accuracy of environmental monitoring.

[0080] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0082] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0084] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0085] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0086] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0088] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the present application.

Claims

1. A method for improving the accuracy of environmental monitoring, characterized in that: The method includes: Acquiring environmental monitoring data of a target area, wherein the environmental monitoring data includes concentration monitoring data of a monitored object; Determining a probability distribution function of a relationship between a corresponding concentration and a probability based on the acquired concentration monitoring data, including: dividing the environmental monitoring data according to preset breakpoints to obtain discrete intervals; and obtaining the probability distribution function based on the discrete intervals; Dividing the environmental monitoring data to obtain discrete intervals includes: dividing the discrete intervals by equal intervals according to the preset breakpoints and the concentration of the monitored object; and calculating the concentration of the monitored object after the concentration is divided by equal intervals by the following formula: Among them, g(R i ) represents the concentration of the monitored object after the concentration is divided into equal intervals, R i is the concentration of the monitored object in the discrete interval, b represents the width of the divided concentration interval, and c is the pollutant concentration at the preset breakpoint. express The largest integer; Use the following formula to solve for the concentration interval width: Where x i represents the concentration point, μ represents x i The mean concentration of , n represents the number of concentration points; Using a local linear regression method, based on the probability distribution function, a probability density function value within a preset range of a preset breakpoint is predicted, and function approximation values ​​on both sides of the preset breakpoint are determined to calculate the difference in probability density on both sides of the preset breakpoint; The continuity of the environmental monitoring data is determined based on the difference in probability density on both sides of the preset breakpoint, so as to improve the accuracy of environmental monitoring of the target area.

2. The method according to claim 1, characterized in that The obtaining of environmental monitoring data of the target area includes: Obtain concentration monitoring data with time stamps; The acquired concentration monitoring data with time stamps are recorded as time series; Eliminating invalid data in the time series, and determining the eliminated invalid data as missing points; The supplementary value is calculated by a linear interpolation algorithm according to the linear relationship between the preceding and following adjacent data of the missing point.

3. The method according to claim 1, characterized in that Before dividing the environmental monitoring data according to the preset breakpoints, the method further includes: The preset breakpoint is determined according to the distribution characteristics of the concentration monitoring data of the monitored object, and the preset breakpoint is used to indicate the critical value of the environmental pollution of the monitored object.

4. The method according to claim 1, wherein The calculation of the probability density difference on both sides of the preset breakpoint includes: Using the McCrary test method, and based on the function approximation values ​​on both sides of the preset breakpoint, determining the probability density estimate values ​​on both sides of the preset breakpoint; Performing a logarithmic calculation on the probability density estimates on both sides of the predetermined breakpoint to obtain a logarithmic difference in the probability density on both sides of the predetermined breakpoint.

5. The method according to claim 4, characterized in that The determination of the continuity of the preset breakpoints includes: According to the size of the logarithm difference of the probability density on both sides, combined with the one-sided test method, it is determined whether the preset breakpoint has discontinuity.

6. The method according to claim 5, characterized in that The determining whether the preset breakpoint has discontinuity includes: Compare the logarithmic difference obtained with the preset first and second thresholds, and perform the following steps based on the comparison results: If the logarithmic difference is less than the first threshold, it is determined that the preset breakpoint has discontinuity; If the first threshold value is less than the logarithmic difference and less than the second threshold value, the determination result is marked; If the second threshold is less than the logarithmic difference, it is determined that there is no discontinuity at the preset breakpoint.

7. A control device, characterized in that: The control device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for improving the accuracy of environmental monitoring according to any one of claims 1 to 6.

8. A readable storage medium, characterized in that: The readable storage medium stores instructions, which enable a machine to execute the method for improving the accuracy of environmental monitoring according to any one of claims 1-6.

Images