Sample analysis method based on environmental monitoring service and environmental pollution treatment

Through dynamic sampling and multi-source data fusion technology, combined with machine learning algorithms, the error and data homogeneity problems caused by the small number of samples in environmental pollutant monitoring are solved, and more detailed and diversified pollutant data analysis is achieved, supporting more Accurate pollution prevention and control strategies.

CN119004030AActive Publication Date: 2024-11-22SHAANXI DETIAN ENERGY SAVING & ENVIRONMENTAL PROTECTION TESTING CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411086522.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-22
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

The prior art has the sampling error caused by the small number of samples in the monitoring of environmental pollutants, and the data is prone to homogeneity, lacking in detail and diversity.

Method used

Using dynamic sampling planning combined with sensor network and multi-source data fusion technology, machine learning algorithms are used to adjust sample collection strategies based on time, location and meteorological conditions to ensure data diversity and detail, reduce duplicate data, and identify abnormalities through multi-dimensional data analysis point.

Benefits of technology

It improves the representativeness and accuracy of sample analysis, reduces sampling error and data homogeneity, provides more detailed and diverse pollutant concentration data, and supports the formulation of more accurate pollution prevention and control strategies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004030A_ABST
    Figure CN119004030A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of environmental pollutant prevention and control, and discloses a sample analysis method based on environmental monitoring service and environmental pollution abatement, which comprises the following steps: step 1, environmental medium selection and pollutant determination; step 2, data acquisition and fusion; 3, dynamic data adjustment and analysis; 4, determining a detection item; step 5, independently collecting; and step 6, analyzing a result. The method helps to improve the representativeness and accuracy of sampling, reduces errors caused by a small number of samples, accurately evaluates the pollution level by using a machine learning algorithm, and achieves the beneficial effects of solving sampling errors caused by a small number of samples and not causing data homogenization.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of environmental pollutant prevention and control, and in particular to a sample analysis method based on environmental monitoring services and environmental pollution control. Background Art

[0002] my country's environmental survey and monitoring mainly relies on scientific research projects of universities and research institutes, as well as routine monitoring by national monitoring stations and other departments. The differences in the above research results are mainly due to the uneven distribution of pollutants in environmental media, which leads to certain sampling errors between different research surveys. That is, the survey results with the same survey scope and purpose only reflect the local data characteristics of the pollution status. Increasing the survey frequency and the number of survey samples is an effective way to reduce sampling errors. Aggregating data with the same survey scope and the same survey purpose is also a strategy to increase the survey frequency and the number of survey samples. This strategy also helps to improve the accurate judgment of environmental pollution concentration levels.

[0003] After searching, it was found that a method for diagnosing the concentration level of pollutants in environmental media was published with the publication number CN 110781225 B. The method includes the following steps: S1 determining the environmental media; S2 selecting the pollutants to be diagnosed; S3 analyzing and diagnosing the concentration of pollutants in the environmental media; S4 conclusion: analyzing and summarizing the results of the concentration level of pollutants in the environmental media; wherein S3 specifically includes the following operations: S3.1 setting the data acquisition range; S3.2 determining the data collection rules; S3.3 data sorting, merging, and calculation; S3.4 data sampling; S3.5 pollution level evaluation. This method aggregates data with the same survey scope and the same survey purpose, indirectly increasing the survey frequency and the number of survey samples, avoiding the sampling error caused by the small number of survey samples and the number of samples, improving the accuracy of the analysis of environmental pollution concentration levels, and helping managers to formulate pollution prevention and control strategies.

[0004] Although the above technical solution uses multiple data summaries with the same scope and purpose to supplement the number of survey samples and thus achieve the effect of reducing sampling errors, since the data are all in the same scope and for the same purpose, it is easy to cause data homogeneity and uniformity. Summary of the invention

[0005] Technical issues solved: In view of the shortcomings of the existing technology, the present invention provides a sample analysis method based on environmental monitoring services and environmental pollution control, which has the advantages of solving the sampling error caused by the small number of samples without causing data homogeneity, more detailed sample detection and no large amount of duplication of sample data, thus solving the problems of the above-mentioned technology.

[0006] Technical solution: To achieve the above object, the present invention provides the following technical solution: a sample analysis method based on environmental monitoring services and environmental pollution control, comprising the following steps: Step 1: Environmental media selection and pollutant determination: Determine the environmental media and select the pollutants to be diagnosed; Step 2: Data collection and fusion: Set the scope of data acquisition. In addition to the conventional monitoring area, different time periods and weather conditions should also be considered. A dynamic sampling plan should be formulated, including sampling rules at different times, locations and meteorological conditions. Sensor networks and remote monitoring technologies should be used to collect data in real time. Multi-source data fusion technology should be used to integrate sample data from different sources. Step 3: Dynamic data adjustment and analysis: Use dynamic sampling technology to adjust sample collection strategies based on real-time data changes and preliminary results of pollutant concentrations. Combine multi-dimensional data: time, location, and meteorological conditions, use machine learning algorithms to accurately evaluate pollution levels, and dynamically adjust sample collection and analysis strategies based on data performance under different conditions. Step 4: Determine the test items: Data items with large gaps between the sample data after dynamic data adjustment and analysis and the existing data are marked separately, and the collected samples corresponding to the marked items are determined; Step 5: Separate collection: Separately collect the samples determined in step 4, and continue to analyze the separately collected samples from step 2. If the secondary test results are consistent, proceed to the next step; Step 6. Result analysis: Analyze and summarize the results of pollutant concentration levels in environmental media, and formulate more accurate pollution prevention and control strategies based on dynamic data collection and analysis results.

[0007] Preferably, the detailed steps of step 1 are: S1.1. Collect background information, review historical monitoring data and literature, understand the environmental conditions and pollution history of the area, conduct on-site investigations, and understand the current status of environmental media and possible pollution sources; S1.2. Select representative points for monitoring based on the characteristics of the environmental media, including those near pollution sources and in different areas, and design a monitoring point layout plan to ensure coverage of different areas and pollution sources; S1.3. According to the nature of pollutants, they are divided into gaseous pollutants including sulfur dioxide and nitrogen oxides, water pollutants including heavy metals and organic matter, and soil pollutants including pesticide residues and heavy metals. Understand the main sources of different pollutants including industrial emissions, traffic emissions and agricultural activities; S1.4. Select pollutants that have a greater impact on the environment and human health, analyze the historical monitoring data of the area, and select pollutants with higher concentrations or significant changes in the historical data.

[0008] Preferably, the environmental medium expression determined in step 1 is: Eigenvector: Set each environmental medium The eigenvector of ; ; in It is an environmental medium In the The value of the feature, is the number of features; Feature weights: ; Evaluation function: ; Selection criteria: .

[0009] Preferably, the expression of the pollutant to be diagnosed selected in step 1 is: Eigenvectors: ; in It is a pollutant In the The value of the feature, is the number of features; Feature weights: ; Select priority pollutants: Evaluation function: ; Selection criteria: .

[0010] Preferably, the data acquisition range expression set in step 2 is: Determine the monitoring area: Spatial scope: Set the monitoring area , expressed as a multidimensional region: ; Time range: set monitoring time , expressed as a time interval: ; Weather conditions: Define weather conditions is a combination of multiple meteorological variables: ; in Indicates meteorological variables, including temperature, humidity, and wind speed; Dynamic Sampling Plan: ; in is the sampling rule function, which represents the sampling plan under specific conditions.

[0011] Preferably, the expression for real-time data collection in step 2 is: Sensor data: set in area Interior layout sensors, of which From 1 to Sensor in time The reading is : ; Real-time data, define real-time data sets For all sensors at time Data collection: ; Multi-source data fusion: Use the data fusion model Fusion to integrate data from different sources and set multiple data sources The fusion process is expressed as: ; Set the weight of each data source , the fusion result is: .

[0012] Preferably, the expression of step three is: Real-time data: Real-time datasets : ; Pollutant concentration, pollutant concentration In time Preliminary results ; in Indicates Pollutants in time No. measurements, is the measured quantity; Based on real-time data Pollutant concentration Adjust the sampling strategy and set the adjustment strategy function : ; Multidimensional data analysis: define a multidimensional data fusion model For time ,Place and weather conditions Combination of: ; Predictive model, using machine learning algorithms to build a pollution level prediction model , the model is based on multidimensional data : , in is the prediction function of the linear regression algorithm; Model optimization, optimize model parameters To minimize the prediction error : ; in, is the loss function: ; Dynamically adjust sampling and analysis strategies based on the prediction results of the machine learning model and the actual data performance, and set dynamic adjustment functions : .

[0013] Preferably, the expression of step 4 is: ; Indicates The sample data after adjustment; Indicates Items of existing data; The threshold value of the gap is used to determine whether the data difference is significant; Represents a collection of data items with large gaps marked.

[0014] Preferably, the pollutant concentration level in step 6 is ,in Indicates different measurement points or time points, defining the average value of the pollutant concentration level in the environmental medium for: ; in It is Pollutant concentration at a point; is the total number of measurement points; is the mean pollutant concentration level.

[0015] Preferably, the standard deviation in the environmental medium is defined in step 6 for: ; in: is the standard deviation of the pollutant concentration levels.

[0016] Compared with the prior art, the present invention provides a sample analysis method based on environmental monitoring services and environmental pollution control, which has the following beneficial effects: 1. The present invention adjusts the sampling strategy according to the preliminary results of real-time data changes and pollutant concentrations by setting a dynamic sampling plan. This helps improve the representativeness and accuracy of sampling, reduces errors caused by a small number of samples, uses machine learning algorithms to accurately evaluate pollution levels, and predicts pollution levels based on multi-dimensional data including time, location, and meteorological conditions. The machine learning model can identify patterns and trends in the data, thereby reducing errors caused by a small number of samples. Combined with multi-dimensional data such as time, location, and meteorological conditions, analysis can provide a more comprehensive understanding of the pollution situation. In this way, even if the number of samples is small, the sampling error can be reduced by integrating various data, while avoiding data homogenization, achieving the beneficial effect of solving the sampling error caused by a small number of samples without causing data homogenization.

[0017] 2. The present invention divides the sampling area into several layers according to different characteristics: geographical location and pollution source, and then performs sampling in each layer. This ensures that data at different levels are fully covered, reduces duplication, and performs sampling in different time periods to capture the dynamic characteristics of pollutant changes. In this way, even if the number of samples is limited, the diversity and details of the data are increased through time differences, and data from different data sources are fused, including sensor data and monitoring station data, etc., to increase the diversity and details of the data. Data from different sources usually have different characteristics, which can reduce repetitiveness. The anomaly detection algorithm in machine learning is used to identify abnormal data points and repeated data, thereby enhancing the uniqueness and details of the data, achieving the beneficial effect of more detailed detection samples and no large-scale duplication of sample data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] See also Figure 1 , a sample analysis method based on environmental monitoring services and environmental pollution control, comprising the following steps: Step 1: Environmental media selection and pollutant determination: Determine the environmental media and select the pollutants to be diagnosed; Step 2: Data collection and fusion: Set the scope of data acquisition. In addition to the conventional monitoring area, different time periods and weather conditions should also be considered. A dynamic sampling plan should be formulated, including sampling rules at different times, locations and meteorological conditions. Sensor networks and remote monitoring technologies should be used to collect data in real time. Multi-source data fusion technology should be used to integrate sample data from different sources. Step 3: Dynamic data adjustment and analysis: Use dynamic sampling technology to adjust sample collection strategies based on real-time data changes and preliminary results of pollutant concentrations. Combine multi-dimensional data: time, location, and meteorological conditions, use machine learning algorithms to accurately evaluate pollution levels, and dynamically adjust sample collection and analysis strategies based on data performance under different conditions. Step 4: Determine the test items: Data items with large gaps between the sample data after dynamic data adjustment and analysis and the existing data are marked separately, and the collected samples corresponding to the marked items are determined; Step 5: Separate collection: Separately collect the samples determined in step 4, and continue to analyze the separately collected samples from step 2. If the secondary test results are consistent, proceed to the next step; Step 6. Result analysis: Analyze and summarize the results of pollutant concentration levels in environmental media, and formulate more accurate pollution prevention and control strategies based on dynamic data collection and analysis results.

[0021] Dynamically adjust the strategy: By setting a dynamic sampling plan, the sampling strategy can be adjusted according to the changes in real-time data and preliminary results of pollutant concentrations. This helps improve the representativeness and accuracy of sampling and reduce errors caused by a small number of samples. For example, when real-time data shows that the pollutant concentration in certain areas or time periods is abnormal, the sampling frequency of these areas can be increased.

[0022] Multi-time and multi-location sampling: Sampling at different times and locations can provide more comprehensive data coverage, reduce the error caused by single sampling, and avoid data homogeneity.

[0023] Multi-source data fusion: Use sensor networks and remote monitoring technology to collect data in real time, and integrate data from different sources through multi-source data fusion technology. This reduces sampling errors caused by the insufficiency of a single data source, while increasing data diversity and avoiding data homogeneity.

[0024] Weighted data fusion: During the data fusion process, weights are set for different data sources, and the influence of each data source in the fusion is adjusted according to its quality and reliability to ensure the accuracy and representativeness of the integrated data.

[0025] Machine learning model: Use machine learning algorithms to accurately evaluate pollution levels and predict pollution levels based on multi-dimensional data such as time, location, and meteorological conditions. Machine learning models can identify patterns and trends in data, thereby reducing errors caused by small sample sizes.

[0026] Dynamically adjust strategies: Dynamically adjust sampling and analysis strategies based on the prediction results of the machine learning model and the actual data performance, which can effectively deal with the uncertainty caused by the small number of samples and ensure the optimization of the sampling strategy.

[0027] Multi-dimensional data fusion: Combining data from multiple dimensions such as time, location, and meteorological conditions for analysis can provide a more comprehensive understanding of the pollution situation. In this way, even if the number of samples is small, sampling errors can be reduced by integrating data from multiple aspects, while avoiding data homogeneity.

[0028] Dynamic data adjustment: Based on real-time data changes, sample collection strategies and analysis methods are adjusted to adapt to different environmental conditions and pollution levels, which effectively reduces errors and improves data reliability.

[0029] Data marking with large gaps: By comparing dynamic data with existing data, data items with large gaps are marked and sampled separately. This can identify and resolve anomalies in the data, further reducing errors caused by small sample sizes.

[0030] Preferably, the detailed steps of step 1 are: S1.1. Collect background information, review historical monitoring data and literature, understand the environmental conditions and pollution history of the area, conduct on-site investigations, and understand the current status of environmental media and possible pollution sources; S1.2. Select representative points for monitoring based on the characteristics of the environmental media, including those near pollution sources and in different areas, and design a monitoring point layout plan to ensure coverage of different areas and pollution sources; S1.3. According to the nature of pollutants, they are divided into gaseous pollutants including sulfur dioxide and nitrogen oxides, water pollutants including heavy metals and organic matter, and soil pollutants including pesticide residues and heavy metals. Understand the main sources of different pollutants including industrial emissions, traffic emissions and agricultural activities; S1.4. Select pollutants that have a greater impact on the environment and human health, analyze the historical monitoring data of the area, and select pollutants with higher concentrations or significant changes in the historical data.

[0031] Preferably, the environmental medium expression determined in step 1 is: Eigenvector: Set each environmental medium The eigenvector of ; ; in It is an environmental medium In the The value of the feature, is the number of features; Feature weights: ; Evaluation function: ; Selection criteria: .

[0032] Preferably, the expression of the pollutant to be diagnosed selected in step 1 is: Eigenvectors: ; in It is a pollutant In the The value of the feature, is the number of features; Feature weights: ; Select priority pollutants: Evaluation function: ; Selection criteria: .

[0033] Preferably, the data acquisition range expression set in step 2 is: Determine the monitoring area: Spatial scope: Set the monitoring area , expressed as a multidimensional region: ; Time range: set monitoring time , expressed as a time interval: ; Weather conditions: Define weather conditions is a combination of multiple meteorological variables: ; in Indicates meteorological variables, including temperature, humidity, and wind speed; Dynamic Sampling Plan: ; in is the sampling rule function, which represents the sampling plan under specific conditions.

[0034] Preferably, the expression for real-time data collection in step 2 is: Sensor data: set in area Interior layout sensors, of which From 1 to Sensor in time The reading is : ; Real-time data, define real-time data sets For all sensors at time Data collection: ; Multi-source data fusion: Use the data fusion model Fusion to integrate data from different sources and set multiple data sources The fusion process is expressed as: ; Set the weight of each data source , the fusion result is: .

[0035] Preferably, the expression of step three is: Real-time data: Real-time datasets : ; Pollutant concentration, pollutant concentration In time Preliminary results ; in Indicates Pollutants in time No. measurements, is the measured quantity; Based on real-time data Pollutant concentration Adjust the sampling strategy and set the adjustment strategy function : ; Multidimensional data analysis: define a multidimensional data fusion model For time ,Place and weather conditions Combination of: ; Predictive model, using machine learning algorithms to build a pollution level prediction model , the model is based on multidimensional data : , in is the prediction function of the linear regression algorithm; Model optimization, optimize model parameters To minimize the prediction error : ; in, is the loss function: ; Dynamically adjust sampling and analysis strategies based on the prediction results of the machine learning model and the actual data performance, and set dynamic adjustment functions : .

[0036] Preferably, the expression of step 4 is: ; Indicates The sample data after adjustment; Indicates Items of existing data; The threshold value of the gap is used to determine whether the data difference is significant; Represents a collection of data items with large gaps marked.

[0037] Preferably, the pollutant concentration level in step 6 is ,in Indicates different measurement points or time points, defining the average value of the pollutant concentration level in the environmental medium for: ; in It is Pollutant concentration at a point; is the total number of measurement points; is the mean pollutant concentration level.

[0038] Preferably, the standard deviation in the environmental medium is defined in step 6 for: ; in: is the standard deviation of the pollutant concentration levels.

[0039] Optimize sampling design; Stratified sampling: The sampling area is divided into several layers according to different characteristic geographical locations, pollution sources, etc., and then sampling is carried out in each layer. This ensures that data at different levels are fully covered and duplication is reduced.

[0040] Random sampling: Random sampling within each stratum can reduce duplication due to systematic bias and provide a more representative sample.

[0041] Multi-dimensional data collection; Comprehensive collection of different parameters: Collecting data on a variety of different parameters, such as pollutant concentrations, meteorological conditions, etc., can not only obtain more detailed information, but also avoid the repetitiveness of a single parameter.

[0042] Multi-period sampling: Sampling is performed over different time periods to capture the dynamic characteristics of pollutant changes. This increases the diversity and details of the data through time differences even if the number of samples is limited.

[0043] Data preprocessing and intelligent analysis; Deduplication algorithm: Deduplication algorithm is applied during the data processing stage to identify and exclude duplicate data. Common deduplication methods include similarity calculation based on data features and threshold screening.

[0044] Feature engineering: By performing feature extraction and dimensionality reduction on data, valuable features can be extracted to avoid duplication problems caused by data redundancy.

[0045] Data fusion and integration; Cross-source data fusion: Fusion of data from different data sources, such as sensor data, monitoring station data, etc., to increase data diversity and details. Data from different sources usually have different characteristics, which can reduce duplication.

[0046] Multi-method integration: Combine multiple detection methods (such as chemical analysis, physical testing) for comprehensive evaluation, so as to obtain information from multiple perspectives and reduce the repetitiveness of a single method.

[0047] High frequency dynamic monitoring; Real-time monitoring system: Use real-time monitoring equipment to collect data at a high frequency. This method captures subtle changes, ensures the detail of the data, and reduces duplication issues through the diversity of real-time data.

[0048] Dynamically adjust sampling strategies: Dynamically adjust sampling strategies according to changes in real-time data to avoid repeated sampling under the same conditions.

[0049] Machine learning and data modeling; Anomaly detection algorithms: Anomaly detection algorithms in machine learning are applied to identify abnormal data points and duplicate data, thereby enhancing the uniqueness and details of the data.

[0050] Data augmentation: Using synthetic data generation to enrich sample data, thereby increasing data diversity.

[0051] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations may be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A sample analysis method based on environmental monitoring services and environmental pollution control, characterized in that: The following steps are involved: Step 1: Environmental media selection and pollutant determination: Determine the environmental media and select the pollutants to be diagnosed; Step 2: Data collection and fusion: Set the scope of data acquisition. In addition to the conventional monitoring area, different time periods and weather conditions should also be considered. A dynamic sampling plan should be formulated, including sampling rules at different times, locations and meteorological conditions. Sensor networks and remote monitoring technologies should be used to collect data in real time. Multi-source data fusion technology should be used to integrate sample data from different sources. Step 3: Dynamic data adjustment and analysis: Use dynamic sampling technology to adjust sample collection strategies based on real-time data changes and preliminary results of pollutant concentrations. Combine multi-dimensional data: time, location, and meteorological conditions, use machine learning algorithms to accurately evaluate pollution levels, and dynamically adjust sample collection and analysis strategies based on data performance under different conditions. Step 4: Determine the test items: Data items with large gaps between the sample data after dynamic data adjustment and analysis and the existing data are marked separately, and the collected samples corresponding to the marked items are determined; Step 5: Separate collection: Separately collect the samples determined in step 4, and continue to analyze the separately collected samples from step 2. If the secondary test results are consistent, proceed to the next step; Step 6. Result analysis: Analyze and summarize the results of pollutant concentration levels in environmental media, and formulate more accurate pollution prevention and control strategies based on dynamic data collection and analysis results.

2. A sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1, characterized in that: The detailed steps of step 1 are: S1.

1. Collect background information, review historical monitoring data and literature, understand the environmental conditions and pollution history of the area, conduct on-site investigations, and understand the current status of environmental media and possible pollution sources; S1.

2. Select representative points for monitoring based on the characteristics of the environmental media, including near pollution sources and different areas, and design a monitoring point layout plan to ensure coverage of different areas and pollution sources; S1.

3. According to the nature of pollutants, they are divided into gaseous pollutants including sulfur dioxide and nitrogen oxides, water pollutants including heavy metals and organic matter, and soil pollutants including pesticide residues and heavy metals. Understand the main sources of different pollutants including industrial emissions, traffic emissions and agricultural activities; S1.

4. Select pollutants that have a greater impact on the environment and human health, analyze the historical monitoring data of the area, and select pollutants with higher concentrations or significant changes in the historical data.

3. A sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1, characterized in that: The environmental medium expression determined in step 1 is: Eigenvector: Set each environmental medium The eigenvector of ; ;in It is an environmental medium In the The value of the feature, is the number of features; Feature weights: ; Evaluation function: ; Selection criteria: .

4. A sample analysis method based on environmental monitoring services and environmental pollution control according to claim 3, characterized in that: The expression of the pollutant to be diagnosed selected in step 1 is: Eigenvectors: ;in It is a pollutant In the The value of the feature, is the number of features; Feature weights: ; Select priority pollutants: Evaluation function: ; Selection criteria: .

5. The sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1 is characterized in that: In step 2, the data acquisition range expression is set as: Determine the monitoring area: Spatial scope: Set the monitoring area , expressed as a multidimensional region: ; Time range: set monitoring time , expressed as a time interval: ; Weather conditions: Define weather conditions is a combination of multiple meteorological variables: ;in Indicates meteorological variables, including temperature, humidity, and wind speed; Dynamic Sampling Plan: ; in is the sampling rule function, which represents the sampling plan under specific conditions.

6. A sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1, characterized in that: The expression of real-time data collection in step 2 is: Sensor data: set in area Interior layout sensors, of which From 1 to Sensor in time The reading is : ; Real-time data, define real-time data sets For all sensors at time Data collection: ; Multi-source data fusion: Use the data fusion model Fusion to integrate data from different sources and set multiple data sources The fusion process is expressed as: ; Set the weight of each data source , the fusion result is: .

7. The sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1 is characterized in that: The expression of step three is: Real-time data: Real-time datasets : ; Pollutant concentration, pollutant concentration In time Preliminary results ; in Indicates Pollutants in time No. measurements, is the measured quantity; Based on real-time data Pollutant concentration Adjust the sampling strategy and set the adjustment strategy function : ; Multidimensional data analysis: define a multidimensional data fusion model For time ,Place and weather conditions Combination of: ; Predictive model, using machine learning algorithms to build a pollution level prediction model , the model is based on multidimensional data : , in is the prediction function of the linear regression algorithm; Model optimization, optimize model parameters To minimize the prediction error : ; in, is the loss function: ; Dynamically adjust sampling and analysis strategies based on the prediction results of the machine learning model and the actual data performance, and set dynamic adjustment functions : 。 8. The sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1 is characterized in that: The expression of step 4 is: ; Indicates The sample data after adjustment; Indicates Items of existing data; The threshold value of the gap is used to determine whether the data difference is significant; Represents a collection of data items with large gaps marked.

9. The sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1, characterized in that: The pollutant concentration level in step 6 ,in Indicates different measurement points or time points, defining the average value of the pollutant concentration level in the environmental medium for: ;in It is Pollutant concentration at a point; is the total number of measurement points; is the mean pollutant concentration level.

10. The sample analysis method based on environmental monitoring services and environmental pollution control according to claim 1, characterized in that: The standard deviation in the environmental medium is defined in step 6 for: ;in: is the standard deviation of the pollutant concentration levels.

Citation Information

Patent Citations

  • Method for diagnosing concentration level of environmental medium pollutants

    CN110781225A

  • Large-area soil heavy metal detection and spatial and temporal distribution characteristic analysis method and system

    CN114443982A

  • Service quality inspection method based on dynamic adaptation and storage medium

    CN115423237A

  • Gaseous pollutant positioning method

    CN118246194A

  • Application of artificial neural network for the prediction of ambient air quality criteria pollutants at local scale in kota city

    IN201911038056A