A method for detecting environmental quality
The environmental quality detection method, which uses multi-source data acquisition and dynamic weight calculation, solves the problems of single data dimension, monitoring error and assessment lag, and achieves efficient, accurate and real-time assessment of environmental quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA TOWER CO LTD GUANGXI ZHUANG AUTONOMOUS REGION BRANCH
- Filing Date
- 2026-03-06
- Publication Date
- 2026-06-05
AI Technical Summary
Existing environmental quality monitoring methods suffer from problems such as limited data dimensions, insufficient elimination of monitoring errors during data processing, fixed weights for assessment indicators that cannot adapt to the differentiated needs of different pollution types and regions, and delayed feedback of assessment results.
By employing multi-source data acquisition, combining the improved 3σ criterion with the LOWESS algorithm to remove outliers, performing data standardization, dynamically calculating subjective and objective weights, and calculating the comprehensive environmental quality index through the improved Nemerow index method, the entire process of automated detection is achieved.
It improves data reliability and the accuracy of assessment results, adapts to the needs of different pollution types and regions, and enables real-time environmental quality assessment and control.
Smart Images
Figure FT_1 
Figure QLYQS_1 
Figure QLYQS_6
Abstract
Description
Technical Field
[0001] This invention belongs to the field of environmental monitoring technology, and specifically relates to an environmental quality monitoring method. Background Technology
[0002] Existing environmental quality monitoring methods mostly employ a single monitoring indicator (such as PM2.5 concentration, COD value, etc.) or a multi-indicator evaluation model with fixed weights, which has the following drawbacks: 1) The data has only one dimension and cannot fully reflect the overall environmental quality; 2) Monitoring errors (such as outliers caused by instrument drift or environmental interference) were not adequately eliminated during data processing, affecting the accuracy of the assessment; 3) The fixed weights of the evaluation indicators cannot adapt to the differentiated needs of different pollution types (such as air pollution and water pollution) and different regions (such as industrial areas and residential areas); 4) The feedback of assessment results is delayed, making it difficult to support real-time environmental management decisions.
[0003] Therefore, this application provides an environmental quality testing method to solve the above problems.
[0004] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention
[0005] The purpose of this invention is to provide an environmental quality detection method to solve the problems of existing technologies, such as single data dimension, insufficient elimination of monitoring errors during data processing, fixed weights of evaluation indicators, and delayed feedback of evaluation results.
[0006] To achieve the above objectives, the present invention provides the following technical solution: An environmental quality testing method includes the following steps: S1. Collect data from multiple sources; S2. Preprocess the collected multi-source data, specifically including the following steps: S21. Remove outliers from the collected multi-source data to obtain the removed multi-source data. S22. Standardize the removed multi-source data to obtain standardized multi-source data; S3. Perform testing on the standardized multi-source data to obtain the test results.
[0007] As a preferred option, the multi-source data collected in S1 includes physical indicators, chemical indicators, biological indicators, and meteorological / hydrological auxiliary indicators, and is uniformly stored as structured data in the format of "indicator type-collection time-collection location-value".
[0008] As a preferred embodiment, S21 involves removing outliers from the collected multi-source data, specifically including the following steps: S211. Calculate the mean μ and standard deviation σ of each collected data; S212. Determine whether the collected data is within the range of [μ-3σ, μ+3σ]. If so, use the collected data as the processed multi-source data. If not, determine whether the collected data is real abnormal data or reasonable extreme value data. If so, remove the collected data. If not, use the collected data as the processed multi-source data. S213. Use linear interpolation to fill in the processed multi-source data to obtain the removed multi-source data.
[0009] As a preferred option, S22 performs standardization processing on the removed multi-source data, specifically including the following steps: S221. Standardize the removed physical indicators and the removed meteorological / hydrological auxiliary indicators to obtain standardized data, as shown in the following formula: ; in, For the data after removal, For standardized data, The mean, Standard deviation; S222. Standardize the removed chemical and biological indicators to obtain standardized data, as shown in the following formula: ; in, For the data after removal, For standardized data, The minimum value after removing data. The maximum value of the data after removal is the standardized data range of [0,1].
[0010] As a preferred method, S3 performs detection on the standardized multi-source data, specifically including the following steps: S31. Subjective weighting is determined for the standardized multi-source data; S32. Objectively determine the weights of the standardized multi-source data; S33. The subjective weights and objective weights are merged to obtain the merged weights; S34. Calculate the sub-indices of each environmental element by combining the weighted and standardized multi-source data. S35. Calculate the comprehensive environmental quality index; S36. Based on the comprehensive environmental quality index Environmental quality is divided into 5 levels, with the specific standards as follows: Excellent: Q∈[0,0.2], meets the national Class I standard, with no obvious pollution; Good: Q∈(0.2,0.4], meets the national Class II standard, slight pollution; Qualified: Q∈(0.4,0.6], meets the national Class III standard, moderate pollution; Unqualified: Q∈(0.6,0.8], exceeding the national Class III standard, indicating severe pollution; Severe pollution: Q∈(0.8,1.0], significantly exceeding national standards, requiring urgent control measures; Use this standard as the test result.
[0011] As a preferred option, S31 involves subjectively determining the weights of the standardized multi-source data, specifically including the following steps: S311. Construct a three-level hierarchical structure for environmental quality assessment - assessment of environmental elements such as air, water, and soil - assessment of monitoring indicators; S312. Evaluate the standardized multi-source data according to the environmental quality assessment rules to obtain the first weight; S313. Evaluate the standardized multi-source data according to the environmental factor assessment rules to obtain the second weight; S314. Evaluate the standardized multi-source data according to the monitoring indicator evaluation rules to obtain the third weight; S315. Add the three weights together to obtain the subjective weight. .
[0012] As a preferred option, S32 involves objectively determining the weights of the standardized multi-source data, specifically including the following steps: S321. Calculate the information entropy of each indicator from the standardized multi-source data, using the following formula: ; in, , For the standardized multi-source data of the i-th sample and the j-th indicator, The normalized weight of the j-th indicator for the i-th sample; S322. Calculate the difference coefficient for the information entropy of each indicator to obtain the difference coefficient for each indicator. The formula is as follows: ; Among them, the larger the difference coefficient, the greater the impact of the indicator on the evaluation result; S323. Calculate the objective weights of the difference coefficients of each indicator to obtain the objective weights. The formula is as follows: .
[0013] As a preferred option, S33 integrates subjective and objective weights, using the following formula: ; in, This is the scene adaptation coefficient, set according to the monitoring scene.
[0014] As a preferred method, in S34, the fused weights and standardized multi-source data are calculated using the following formula: .
[0015] As a preferred option, the formula for calculating the comprehensive environmental quality index in S35 is as follows: ; in, The value range is [0,1].
[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) The environmental quality detection method of the present invention improves the reliability of data by combining the improved 3σ criterion with the LOWESS algorithm in the data preprocessing stage, effectively eliminating outliers and retaining reasonable extreme values.
[0017] (2) The environmental quality detection method of the present invention realizes the scenario-based adaptation of the evaluation index weights and pollution response through dynamic weight calculation, and solves the problem that fixed weights cannot take into account differentiated needs.
[0018] (3) The environmental quality detection method of the present invention takes into account both the average level and extreme values of the index by improving the Nemerow index method, so that the evaluation results are more in line with the actual environmental quality status.
[0019] (4) The environmental quality detection method of the present invention automates the entire process of data collection, processing, evaluation and feedback, improves evaluation efficiency, and significantly improves the accuracy of results compared with traditional methods. It can be widely applied to urban environmental monitoring, industrial park pollution control, ecological protection zone environmental assessment and other scenarios. Attached Figure Description
[0020] Figure 1 This is a schematic diagram of the method steps in an embodiment of the present invention. Detailed Implementation
[0021] The technical solution of this invention patent will be clearly and completely described below. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.
[0022] In the description of this invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention.
[0023] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.
[0024] See attached document Figure 1 An environmental quality testing method includes the following steps: S1: Collection of multi-source data; The collected data include: physical indicators (such as atmospheric particulate matter concentration and water turbidity), chemical indicators (such as SO2, NOx, and heavy metal content), biological indicators (such as water microbial content and soil enzyme activity), and meteorological / hydrological auxiliary indicators (such as temperature, humidity, and water flow velocity). Data collection methods: Combining fixed monitoring stations (real-time online monitoring), mobile monitoring equipment (drones, monitoring vehicles), and manual sampling and testing to ensure the spatiotemporal coverage of data; Data format: uniformly stored as structured data in the format of "indicator type-collection time-collection location-value", and the sampling frequency is set from 1 time / hour to 1 time / 24 hours according to the monitoring scenario; S2: Preprocess the collected multi-source data, specifically including the following steps: S21: Remove outliers from the collected multi-source data to obtain the removed multi-source data, specifically: S211: Calculate the mean μ and standard deviation σ of each collected data; S212: Determine whether the collected data is within the range of [μ-3σ, μ+3σ]. If so, use the collected data as processed multi-source data. If not, further determine whether the collected data is real abnormal data or reasonable extreme value data. If so, discard the collected data. If not, use the collected data as processed multi-source data. Specifically, for data exceeding the range of [μ-3σ, μ+3σ], use the LOWESS algorithm to fit the local data trend and determine whether the data is a real anomaly (such as a sudden value caused by instrument failure) or a reasonable extreme value (such as a sudden pollution event). S213: Use linear interpolation to fill in the processed multi-source data to obtain the removed multi-source data. Specifically, after removing the real outliers, use linear interpolation to fill in the data gaps to ensure data continuity. S22: Standardize the removed multi-source data to obtain standardized multi-source data. This includes the following steps: S221: Standardize the removed physical indicators and the removed meteorological / hydrological auxiliary indicators to obtain standardized data, as shown in the following formula: ; in, For the data after removal, For standardized data, The mean, Standard deviation; S222: Standardize the removed chemical and biological indicators to obtain standardized data, as shown in the following formula: ; in, For the data after removal, For standardized data, The minimum value after removing data. To determine the maximum value of the data after removal, the standardized data range is uniformly set to [0,1]. S3: Perform detection on the standardized multi-source data to obtain the detection results. The specific steps are as follows: S31: Subjective weighting is performed on the standardized multi-source data, specifically as follows: S311: Construct a three-level hierarchical structure for environmental quality assessment - assessment of environmental elements such as air, water, and soil - assessment of monitoring indicators; S312: Evaluate the standardized multi-source data according to the environmental quality assessment rules to obtain the first weight; S313: Evaluate the standardized multi-source data according to the environmental factor assessment rules to obtain the second weight; S314: Evaluate the standardized multi-source data according to the monitoring indicator evaluation rules to obtain the third weight; S315: Add the three weights together to obtain the subjective weight. ; S32: Objective weighting is determined for the standardized multi-source data, specifically as follows: S321: Calculate the information entropy of each indicator from the standardized multi-source data, using the following formula: ; in, , For the standardized multi-source data of the i-th sample and the j-th indicator, The normalized weight of the j-th indicator for the i-th sample; S322: Calculate the difference coefficient for the information entropy of each indicator to obtain the difference coefficient for each indicator. The formula is as follows: ; Among them, the larger the difference coefficient, the greater the impact of the indicator on the evaluation result; S323: Calculate the objective weights for the difference coefficients of each indicator to obtain the objective weights. The formula is as follows: ; S33: Merge the subjective weights and objective weights to obtain the merged weights. The formula is as follows: ; in, The scene adaptation coefficient is set according to the monitoring scene, such as: industrial area. ,live If the value of a certain type of pollution indicator (such as PM2.5) in the real-time monitoring data significantly exceeds the standard (more than twice the national standard), the weight of that type of indicator will be automatically increased by 20%, realizing dynamic response of the weight. S34: Calculate the sub-indices of each environmental element by combining the weighted and standardized multi-source data. The formula is as follows: ; S35: Calculate the comprehensive environmental quality index The formula is as follows: , in, The value range is [0,1]; S36: Based on the comprehensive environmental quality index Environmental quality is divided into 5 levels, with the specific standards as follows: Excellent: Q∈[0,0.2], meets the national Class I standard, with no obvious pollution; Good: Q∈(0.2,0.4], meets the national Class II standard, slight pollution; Qualified: Q∈(0.4,0.6], meets the national Class III standard, moderate pollution; Unqualified: Q∈(0.6,0.8], exceeding the national Class III standard, indicating severe pollution; Severe pollution: Q∈(0.8,1.0], significantly exceeding national standards, requiring urgent control measures; Use this standard as the test result.
[0025] In this embodiment, five fixed monitoring stations and two mobile monitoring vehicles were selected in a city to collect PM2.5, PM10, SO2, and NO. X The system collects six atmospheric indicators, including O3 and CO, and simultaneously collects three auxiliary indicators, including temperature, humidity and wind speed, at a sampling frequency of once per hour for 72 consecutive hours. Three outliers (caused by instrument malfunction) in the PM2.5 index were removed using the improved 3σ criterion and supplemented by linear interpolation; Z-score standardization was applied to the six atmospheric indicators and extreme value standardization was applied to the three auxiliary indicators. The scene adaptation coefficient α was set to 0.4 (urban residential area). Subjective weights were obtained by AHP method (PM2.5 has the highest weight, 0.3), and objective weights were obtained by entropy weight method (O3 has the highest weight, 0.25). After fusion, the final weight of PM2.5 was 0.28 and that of O3 was 0.26. The calculated range of the comprehensive environmental quality index Q over 72 hours is [0.18, 0.52], with 36 hours classified as "good" and 12 hours as "qualified" (during morning and evening traffic peaks), and no "unqualified" or higher levels. Results feedback: The top three contributors to pollution output were PM2.5, O3, and NO. X It is speculated that the pollution sources are vehicle exhaust and industrial emissions, and it is recommended to strengthen road dust control during peak traffic hours.
[0026] The environmental quality detection method of this invention solves the problems of outlier interference and inconsistent data dimensions in traditional methods through improved preprocessing methods; it breaks through the limitations of traditional fixed weights through improved weight calculation methods; and it effectively removes outliers and retains reasonable extreme values by detecting multi-source data, thereby improving data reliability and solving the problem that fixed weights cannot take into account differentiated needs. It takes into account both the average level and extreme values of indicators, making the assessment results more consistent with the actual environmental quality situation.
[0027] The foregoing description of specific exemplary embodiments of the invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of the invention, as well as various different choices and variations. The scope of the invention is intended to be defined by the claims and their equivalents.
Claims
1. An environmental quality testing method, characterized in that, Includes the following steps: S1. Collect data from multiple sources; S2. Preprocess the collected multi-source data, specifically including the following steps: S21. Remove outliers from the collected multi-source data to obtain the removed multi-source data. S22. Standardize the removed multi-source data to obtain standardized multi-source data; S3. Perform testing on the standardized multi-source data to obtain the test results.
2. The environmental quality testing method according to claim 1, characterized in that, The multi-source data collected in S1 includes physical indicators, chemical indicators, biological indicators, and meteorological / hydrological auxiliary indicators, and is uniformly stored as structured data in the format of "indicator type-collection time-collection location-value".
3. The environmental quality testing method according to claim 1, characterized in that, S21 involves removing outliers from the collected multi-source data, specifically including the following steps: S211. Calculate the mean μ and standard deviation σ of each collected data; S212. Determine whether the collected data is within the range of [μ-3σ, μ+3σ]. If so, use the collected data as the processed multi-source data. If not, determine whether the collected data is real abnormal data or reasonable extreme value data. If so, remove the collected data. If not, use the collected data as the processed multi-source data. S213. Use linear interpolation to fill in the processed multi-source data to obtain the removed multi-source data.
4. The environmental quality testing method according to claim 1, characterized in that, S22 standardizes the removed multi-source data, specifically including the following steps: S221. Standardize the removed physical indicators and the removed meteorological / hydrological auxiliary indicators to obtain standardized data, as shown in the following formula: ； in, For the data after removal, For standardized data, The mean, Standard deviation; S222. Standardize the removed chemical and biological indicators to obtain standardized data, as shown in the following formula: ； in, For the data after removal, For standardized data, The minimum value after removing data. The maximum value of the data after removal is the standardized data range of [0,1].
5. The environmental quality testing method according to claim 1, characterized in that, S3 performs inspection on standardized multi-source data, specifically including the following steps: S31. Subjective weighting is determined for the standardized multi-source data; S32. Objectively determine the weights of the standardized multi-source data; S33. The subjective weights and objective weights are merged to obtain the merged weights; S34. Calculate the sub-indices of each environmental element by combining the weighted and standardized multi-source data. S35. Calculate the comprehensive environmental quality index; S36. Based on the comprehensive environmental quality index Environmental quality is divided into 5 levels, with the specific standards as follows: Excellent: Q∈[0,0.2], meets the national Class I standard, with no obvious pollution; Good: Q∈(0.2,0.4], meets the national Class II standard, slight pollution; Qualified: Q∈(0.4,0.6], meets the national Class III standard, moderate pollution; Unqualified: Q∈(0.6,0.8], exceeding the national Class III standard, indicating severe pollution; Severe pollution: Q∈(0.8,1.0], significantly exceeding national standards, requiring urgent control measures; Use this standard as the test result.
6. The environmental quality testing method according to claim 5, characterized in that, S31 involves subjective weighting of standardized multi-source data, specifically including the following steps: S311. Construct a three-level hierarchical structure for environmental quality assessment - assessment of environmental elements such as air, water, and soil - assessment of monitoring indicators; S312. Evaluate the standardized multi-source data according to the environmental quality assessment rules to obtain the first weight; S313. Evaluate the standardized multi-source data according to the environmental factor assessment rules to obtain the second weight; S314. Evaluate the standardized multi-source data according to the monitoring indicator evaluation rules to obtain the third weight; S315. Add the three weights together to obtain the subjective weight. .
7. The environmental quality testing method according to claim 6, characterized in that, S32 involves determining the objective weights of standardized multi-source data, specifically including the following steps: S321. Calculate the information entropy of each indicator from the standardized multi-source data, using the following formula: ； in, , For the standardized multi-source data of the i-th sample and the j-th indicator, The normalized weight of the j-th indicator for the i-th sample; S322. Calculate the difference coefficient for the information entropy of each indicator to obtain the difference coefficient for each indicator. The formula is as follows: ； Among them, the larger the difference coefficient, the greater the impact of the indicator on the evaluation result; S323. Calculate the objective weights of the difference coefficients of each indicator to obtain the objective weights. The formula is as follows: 。 8. The environmental quality testing method according to claim 7, characterized in that, S33 integrates subjective and objective weights using the following formula: ； in, This is the scene adaptation coefficient, set according to the monitoring scene.
9. The environmental quality testing method according to claim 8, characterized in that, In S34, the fused weights and standardized multi-source data are calculated using the following formula: 。 10. The environmental quality testing method according to claim 9, characterized in that, The formula for calculating the comprehensive environmental quality index in S35 is as follows: ； in, The value range is [0,1].