Environment-friendly environment monitoring system

Abstract

The invention relates to the technical field of environment monitoring, and discloses an environment-friendly environment monitoring system, which collects static and dynamic data through a fixed monitoring station and a mobile device, realizes frequency adaptive calibration by adopting a linear interpolation or spline interpolation algorithm, and constructs a fusion data matrix of time-space alignment; matching an optimal environment evaluation model based on an optimization algorithm (such as an eagle algorithm), and dynamically selecting a prediction algorithm in combination with pollution characteristics; a differential response strategy is triggered through a multi-stage early warning mechanism (yellow / orange / red), a pollution source positioning map and an emergency scheme are synchronously generated, and'monitoring-analysis-disposal 'closed-loop management is realized. The method can be applied to the scenes of urban atmosphere, river water quality, industrial area multi-parameter pollution and the like, the monitoring precision (the omission ratio is reduced by more than or equal to 25%), the response speed (the early warning push is less than or equal to 8 seconds) and the resource utilization efficiency (the energy consumption is reduced by 20-35%) are effectively improved, and a high-reliability solution is provided for intelligent environmental protection.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to an environmentally friendly environmental monitoring system. Background Art

[0002] With the rapid development of urbanization and industrialization, environmental quality issues (such as air pollution, water pollution, and excessive noise) have become a global focus. Traditional environmental monitoring systems rely on fixed monitoring stations or single sensor networks, which have the following technical bottlenecks:

[0003] The data dimension is single and the monitoring blind spots are significant: Existing systems typically use statically deployed sensors (such as fixed air quality monitoring stations), which have limited spatial coverage and struggle to capture the dynamic diffusion patterns of pollution sources. For example, real-time monitoring of mobile pollution sources (such as transport vehicles) or sudden pollution incidents (such as industrial leaks) is subject to lags, resulting in insufficient data integrity and missed detection rates exceeding 30%.

[0004] Heterogeneous data fusion is difficult: Due to the difference in sampling frequencies, achieving spatiotemporal alignment between static monitoring equipment (low sampling frequency, high data stability) and dynamic mobile monitoring equipment (high sampling frequency, large data fluctuations) is difficult. Traditional interpolation algorithms (such as the nearest neighbor method) are prone to introducing high-frequency noise, which distorts the fused data and further affects the accuracy of pollution assessment models.

[0005] The evaluation algorithm is poorly adapted to the scenario: Existing environmental quality assessments often rely on fixed algorithms (such as linear regression and static threshold methods), which are unable to dynamically adjust model parameters based on pollution type and regional characteristics. For example, pollution factor weights differ significantly between industrial and residential areas, but traditional systems lack intelligent algorithm matching mechanisms, resulting in an increased misjudgment rate (approximately 15%-20%).

[0006] Delayed early warning response and lack of closed-loop management: Most systems only offer a single threshold alarm function, lacking a tiered warning and emergency response mechanism. When a pollution incident occurs, managers must manually analyze data, locate the source, and develop a plan, taking hours and making it difficult to meet the demand for rapid response.

[0007] Inadequate energy efficiency and sustainability: Existing monitoring equipment often operates continuously in high-power consumption mode, especially in remote areas with power supply difficulties. The system's endurance is limited, which is contrary to the goal of green environmental protection.

[0008] Industry improvement attempts: In recent years, some technologies have attempted to introduce mobile monitoring equipment or Internet of Things technology, but they still face problems such as low efficiency of data fusion algorithms and insufficient dynamic calibration accuracy. Therefore, an environmentally friendly environmental monitoring system is needed that can integrate multi-source data, dynamically calibrate frequency, intelligent matching algorithm and realize closed-loop early warning response, so as to break through the existing technical bottleneck and improve the efficiency of environmental governance. Summary of the Invention

[0009] (0) Technical problems solved In view of the deficiencies of the prior art, the present invention provides an environmentally friendly environment monitoring system that solves the problems raised in the above background technology.

[0010] (2) Technical solution To achieve the above objectives, the present invention provides the following technical solutions: an environmentally friendly environment monitoring system, the method comprising the following steps: S1. Collect environmental static monitoring data and environmental dynamic monitoring data; S2. Measure and process the sampling frequencies of the environmental static monitoring data and dynamic monitoring data to generate static frequency data and dynamic frequency data; S3, determine the consistency of static and dynamic frequencies and generate frequency consistency determination data; if they are consistent, execute S5; if they are inconsistent, execute S4; S4. Adjust the sampling frequency of the static monitoring data to generate static adjustment data; S5. Combine static and dynamic monitoring data to construct environmental parameter fusion data; S6. Match the environmental quality assessment algorithm type and generate target algorithm type feature data; S7. Perform environmental quality calibration based on the fused data and target algorithm, and generate an environmental quality calibration report.

[0011] Preferably, the S1 includes: S11. Collect environmental parameters at preset time intervals through fixed monitoring stations to generate static monitoring data; S12. Collect environmental dynamic parameters in real time through mobile monitoring equipment to generate dynamic monitoring data.

[0012] Preferably, the S2 includes: S21. Import the static and dynamic monitoring data into the environmental management platform, and use a bidirectional search algorithm to extract their sampling frequencies, which are marked as static frequency (f_s) and dynamic frequency (f_d), respectively, in Hertz.

[0013] Preferably, the S3 includes: S31. Compare the values ​​of f_s and f_d; if the difference is within a preset threshold, determine that they are consistent; otherwise, determine that they are inconsistent.

[0014] Preferably, the S4 includes: S41. Use a linear interpolation algorithm to adjust the sampling frequency of the static monitoring data according to f_d to generate static adjustment data.

[0015] Preferably, the S5 includes: S51. Align the static adjustment data and the dynamic monitoring data along the time axis to construct spatiotemporal fusion environmental parameter fusion data.

[0016] Preferably, the S6 includes: S61. Establish a standard parameter fusion data matrix corresponding to different environmental assessment algorithms; S62: Match the environmental parameter fusion data with the standard matrix and search for the best matching evaluation algorithm type through an optimization algorithm. The specific steps are as follows: S621, initialize optimization algorithm parameters and randomly generate candidate algorithm populations; S622, exploration phase: the simulation algorithm population searches for the best matching position in the solution space and updates the candidate positions; S623, development phase: evaluate the objective function value of the candidate position and update the optimal algorithm type; S624. After iteration until convergence, output target algorithm type feature data.

[0017] Preferably, the S7 includes: S71. Call the target algorithm to calibrate abnormal parameters in the fused data and generate a calibrated environmental quality report; S72. Compare the calibration result with the environmental standard and trigger an early warning signal.

[0018] Preferably, the system comprises: Environmental parameter acquisition module, data processing and fusion module, algorithm matching engine, calibration and early warning execution module.

[0019] Preferably, the calibration and warning execution module includes: A multi-level dynamic early warning unit, which adaptively divides the early warning levels based on the degree to which the parameters in the environmental quality calibration report deviate from the standard values; The warning levels include mild warning (yellow mark), moderate warning (orange mark) and severe warning (red mark), and are associated with different response strategy databases; When a severe warning is triggered, a pollution source location map and emergency treatment plan are generated simultaneously and pushed to the terminal.

[0020] (3) Beneficial effects Compared with the prior art, the present invention provides an environmentally friendly environment monitoring system with the following beneficial effects: 1. Multi-source data fusion improves monitoring accuracy By integrating the multi-dimensional environmental parameters of fixed monitoring stations (static data) and mobile devices (dynamic data), we overcome the limitations of a single data source and build a high-precision environmental quality model based on spatiotemporal characteristics, significantly improving the comprehensiveness and accuracy of pollution monitoring and reducing the missed detection rate by ≥25%.

[0021] 2. Dynamic frequency adaptive calibration technology A linear interpolation algorithm is used to intelligently match the sampling frequencies of static and dynamic data, solving the problem of data synchronization between heterogeneous devices, ensuring the time consistency of monitoring data, and reducing errors caused by frequency differences by more than 30%.

[0022] 3. Intelligent algorithm matching optimizes evaluation efficiency Based on optimization algorithms (such as the Osprey algorithm), the optimal environmental assessment model is dynamically matched to achieve precise adaptation of the algorithm and data features, which increases the efficiency of parameter analysis in complex environments by 40% while reducing the cost of manual intervention.

[0023] 4. Multi-level early warning and closed-loop response mechanism By linking dynamic graded warnings (yellow / orange / red) with pollution source location maps, a closed-loop management process from "monitoring-warning-disposal" is achieved. Once a severe warning is triggered, the system generates an emergency plan within 5 seconds and pushes it to the terminal, increasing response speed by 60% compared to traditional methods and effectively controlling the risk of pollution spread.

[0024] 5. Resource optimization and sustainability improvement The system can automatically call differentiated governance strategies according to the warning level (such as starting energy-saving mode for a mild warning and activating full-power purification for a severe warning), reducing energy consumption by 20%-35%, in line with the green and low-carbon goals of environmental monitoring.

[0025] 6. Enhanced visualization and operability Through geographic information mapping technology, pollution data is overlaid on maps to support managers in quickly locating pollution sources and formulating treatment paths, improving decision-making efficiency by 50%. It is suitable for real-time supervision in complex scenarios such as cities and industrial areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the overall system architecture of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0028] The environmental monitoring system comprises the following steps: S1. Collect environmental static monitoring data and environmental dynamic monitoring data; S2. Measure and process the sampling frequencies of the environmental static monitoring data and dynamic monitoring data to generate static frequency data and dynamic frequency data; S3, determine the consistency of static and dynamic frequencies and generate frequency consistency determination data; if they are consistent, execute S5; if they are inconsistent, execute S4; S4. Adjust the sampling frequency of the static monitoring data to generate static adjustment data; S5. Combine static and dynamic monitoring data to construct environmental parameter fusion data; S6. Match the environmental quality assessment algorithm type and generate target algorithm type feature data; S7. Perform environmental quality calibration based on the fusion data and target algorithm, and generate an environmental quality calibration report; Said S1 comprises: S11. Collect environmental parameters at preset time intervals through fixed monitoring stations to generate static monitoring data; S12. Collecting environmental dynamic parameters in real time through mobile monitoring equipment to generate dynamic monitoring data; The S2 includes: S21. Import the static and dynamic monitoring data into the environmental management platform and use a bidirectional search algorithm to extract their sampling frequencies, which are marked as static frequency (f_s) and dynamic frequency (f_d), respectively, in Hertz; The S3 includes: S31, compare the values ​​of f_s and f_d; if the difference is within a preset threshold, determine that they are consistent; otherwise, determine that they are inconsistent; The S4 includes: S41, using a linear interpolation algorithm to adjust the sampling frequency of the static monitoring data according to f_d to generate static adjustment data; The S5 includes: S51, aligning the static adjustment data and the dynamic monitoring data according to the time axis to construct spatiotemporal fusion environmental parameter fusion data; The S6 includes: S61. Establish a standard parameter fusion data matrix corresponding to different environmental assessment algorithms; S62: Match the environmental parameter fusion data with the standard matrix and search for the best matching evaluation algorithm type through an optimization algorithm. The specific steps are as follows: S621, initialize optimization algorithm parameters and randomly generate candidate algorithm populations; S622, exploration phase: the simulation algorithm population searches for the best matching position in the solution space and updates the candidate positions; S623, development phase: evaluate the objective function value of the candidate position and update the optimal algorithm type; S624, after iteration until convergence, output target algorithm type characteristic data; The S7 includes: S71. Call the target algorithm to calibrate abnormal parameters in the fused data and generate a calibrated environmental quality report; S72. Compare the calibration result with the environmental standard and trigger an early warning signal. Specific embodiments Example 1: Urban Air Pollution Monitoring and Early Warning System 1. System hardware configuration Fixed monitoring stations: Deployed in core urban areas (such as transportation hubs and industrial park boundaries), equipped with high-precision PM2.5, SO2, and NOx sensors, with a sampling frequency of 1 time / minute (static data).

[0030] Mobile monitoring equipment: installed on drones and sanitation vehicles, equipped with portable gas sensors (VOCs, O3) and GPS modules, with a sampling frequency of 1 time / 10 seconds (dynamic data).

[0031] Central processing platform: uses cloud computing server, built-in data fusion engine, algorithm matching module and early warning decision unit, and supports 5G communication protocol.

[0032] 2. Implementation Process Step 1: Multi-source data acquisition and frequency calibration Fixed stations and mobile devices collect data synchronously, and static data (f_s=1 / 60Hz) and dynamic data (f_d=1 / 10 Hz) are obtained through the environmental management platform.

[0033] Frequency consistency judgment: When the platform detects f_s ≠ f_d (the static frequency is lower than the dynamic frequency), it triggers the linear interpolation algorithm to upconvert the static data to generate static adjustment data aligned with the dynamic data (f_s' = 1 / 10 Hz).

[0034] Step 2: Spatiotemporal data fusion Align the adjusted static data (PM2.5, SO2) with the dynamic data (VOCs, O3) according to the timestamp, and construct a spatio-temporal fusion matrix in combination with GPS coordinates. For example:

[0035] Timestamp: 2023-10-01 14:00:00 Location: Longitude X, Latitude Y Static parameters: PM2.5 = 45 μg / m³, SO2 = 0.08 ppm Dynamic parameters: VOCs = 1.2 ppm, O3 = 0.05 ppm Step 3: Intelligent algorithm matching Optimization algorithm search: Use the improved Osprey Optimization Algorithm (OOA) to match the best evaluation model in the standard algorithm library (including random forest, LSTM, support vector machine).

[0036] Input: Feature vectors of the fusion data matrix (such as pollutant concentration change rate, spatial gradient).

[0037] Output: The matching result is the LSTM model (suitable for time-series pollution prediction), and its weight parameters are loaded.

[0038] Step 4: Pollution assessment and graded warning Model prediction: The LSTM model predicts that the PM2.5 concentration will rise to 75 μg / m³ in the next hour (exceeding the national standard of 50 μg / m³).

[0039] Dynamic graded warning: Minor warning (yellow): PM2.5 ≤ 60 μg / m³, trigger an internal warning on the platform and start the energy-saving mode of the fixed station (sampling frequency reduced to 1 time / 5 minutes).

[0040] Medium warning (orange): 60 μg / m³ < PM2.5 ≤ 70 μg / m³, send a text message notification to the urban management department and mark the suspicious pollution area.

[0041] Severe warning (red): PM2.5 > 70 μg / m³ (triggered in this example), perform the following operations: Pollution source location: Based on the spatio-temporal hotspot analysis of dynamic data, lock the pollution source as a certain industrial park (coordinates X + 500m, Y + 300m).

[0042] Emergency plan generation: Call the database to generate instructions of "stop production for investigation + sprinkle water to reduce dust", and push them to the park management terminal.

[0043] Visualization map: Overlay the pollution concentration heat map and source point markers on the platform interface.

[0044] 3. Test Results Monitoring accuracy: After data integration, the PM2.5 missed detection rate dropped from 32% to 7%.

[0045] Response speed: From data collection to warning push, it takes ≤8 seconds (traditional system ≥20 seconds).

[0046] Energy consumption optimization: Fixed station power consumption is reduced by 28% under mild warning conditions.

[0047] Example 2: Abnormal river water quality monitoring and closed-loop treatment 1. Scenario Description Abnormal water turbidity suddenly occurred in the lower reaches of a river. The system coordinated detection through fixed buoy stations (static pH and COD monitoring) and unmanned boats (dynamic turbidity and temperature monitoring).

[0048] 2. Key Operations Frequency calibration: The frequency of static data (1 time / 30 minutes) is adjusted to be consistent with the dynamic data (1 time / 5 minutes) through cubic spline interpolation.

[0049] Algorithm matching: The Osprey algorithm was matched to the support vector machine (SVM) model, identifying the anomaly as industrial wastewater discharge (92% confidence level).

[0050] Closed-loop response: Trigger a red alert and generate a pollution source tracing path map.

[0051] Automatically link to the environmental law enforcement database, retrieve the list of suspected polluting enterprises and issue inspection tasks.

[0052] The unmanned boat activated the emergency sampling mode to preserve water sample evidence.

[0053] 3. Effect Verification The time required to handle pollution incidents has been shortened from 4 hours to 40 minutes.

[0054] The dynamic interpolation error is reduced by 41% compared with the traditional nearest neighbor method.

[0055] Example 3: Real-time monitoring and collaborative governance system for multi-parameter pollution in industrial areas 1. Scenario and Hardware Configuration Monitoring target: Multi-parameter pollution monitoring of volatile organic compounds (VOCs), heavy metals (such as lead and cadmium) and noise in a chemical park.

[0056] Fixed monitoring points: Fixed multi-parameter sensor stations are deployed around the factory boundary to monitor VOCs (PID sensor), heavy metals (XRF spectrometer) and noise (decibel meter), with a sampling frequency of 1 time / 5 minutes (static data).

[0057] Mobile Monitoring Unit: Inspection robot: Equipped with a portable VOCs detector, an acoustic camera, and a laser radar (LiDAR), it patrols along a preset path with a sampling frequency of 1 time / 30 seconds (dynamic data).

[0058] Vehicle-mounted mobile station: Installed on campus security vehicles, it collects PM10 and sulfur dioxide (SO2) data in real time with a sampling frequency of 1 time / 15 seconds.

[0059] Edge computing nodes: Deployed in the campus control center, they integrate data preprocessing, local algorithm matching, and real-time decision-making functions, and provide redundant backup with the cloud platform.

[0060] 2. Implementation Process Step 1: Heterogeneous Data Collection and Frequency Alignment Static data: VOCs uploaded by the fixed station = 2.5ppm (1.5 times the standard), noise = 72dB (daytime limit 65dB).

[0061] Dynamic data: The inspection robot detected an instantaneous VOCs peak of 4.0ppm in a certain tank area, and the acoustic camera captured the source of abnormal mechanical noise.

[0062] Frequency calibration: The static data frequency (1 / 300 Hz) was upscaled to the dynamic data frequency (1 / 30 Hz) by cubic spline interpolation to ensure time axis alignment.

[0063] The SO2 data (1 / 15 Hz) from the vehicle-mounted mobile station is processed by downsampling and filtering to match the data frequency of the inspection robot.

[0064] Step 2: Multimodal Data Fusion and Contamination Modeling Construct a spatiotemporal-parameter multidimensional matrix to correlate VOCs, noise, SO2, and location information: Location: Tank area A3 coordinates (X:123.45, Y:67.89) Parameter Set: - Static: VOCs=2.5ppm, Noise=72dB - Dynamic (Robot): VOCs = 4.0ppm, Noise Hotspot = 85dB - Dynamic (on-board): SO2=0.3ppm The data fusion engine extracts feature vectors: VOCs concentration gradient, noise spectrum main frequency, and SO2 diffusion rate.

[0065] Step 3: Optimize algorithm matching and pollution tracing Osprey Algorithm (OOA) Search: The input feature vector is matched with a standard algorithm library (including convolutional neural network CNN, gradient boosting tree GBDT, and physical diffusion model).

[0066] The optimal output model is the physical diffusion model (suitable for VOCs leakage tracing), with a confidence level of 88%.

[0067] Pollution source location: The model reversely deduced the VOCs diffusion path and, combined with LiDAR point cloud data, identified the leak source as valve A3-5 in the tank area (coordinate accuracy ±0.5m).

[0068] The acoustic camera analyzed the noise spectrum and identified the abnormal source as a damaged fan (characteristic frequency 1.2kHz).

[0069] Step 4: Tiered response and multi-departmental coordination Warning trigger: Red alert (VOCs>3.0ppm): The central screen of the park triggers the sound and light alarm for the entire area, and the emergency broadcast is activated.

[0070] Orange warning (noise > 75dB): Push a work order to the equipment maintenance department and mark the fan fault point.

[0071] Closed-loop response: Automatic isolation: The system remotely closes the inlet and outlet valves of the A3 tank area and activates the explosion-proof ventilation system.

[0072] Emergency team dispatch: The robot navigates to the leak point and transmits video and gas concentration in real time; Security vehicles blocked the surrounding roads, and the onboard mobile station continuously monitored the SO2 concentration downwind.

[0073] Governance plan generation: Call the database to match the "VOCs Leakage Disposal Plan" and push the steps: a. Cover the leak area with inert gas; b. Maintenance personnel wear Class A protective clothing to valves A3-5; c. Start the perimeter sprinkler system to reduce the vapor concentration.

[0074] Pollution diffusion simulation: Based on real-time meteorological data (wind speed and direction), the model predicts the pollution impact range in the next 30 minutes and pushes it to the surrounding community emergency platform.

[0075] 3. Test Results Monitoring efficiency: The time required to locate pollution sources has been reduced from an average of 45 minutes during manual inspections to 3 minutes; After multi-parameter data fusion, the VOCs monitoring blind area was reduced by 90%.

[0076] Treatment effect: The entire leak incident response process took 8 minutes (traditional process ≥40 minutes); After the emergency plan was implemented, the VOCs concentration dropped to the safety threshold (0.5ppm) within 15 minutes.

[0077] Resource optimization: Through graded warnings, fixed stations in non-leakage areas enter sleep mode, reducing overall energy consumption by 35%.

[0078] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0079] While 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 variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring environmental quality based on dynamic fusion of multi-source environmental parameters, characterized in that: The method comprises the following steps: S1. Collect environmental static monitoring data and environmental dynamic monitoring data; S2. Measure and process the sampling frequencies of the environmental static monitoring data and dynamic monitoring data to generate static frequency data and dynamic frequency data; S3, determine the consistency of static and dynamic frequencies and generate frequency consistency determination data; if they are consistent, execute S5; if they are inconsistent, execute S4; S4. Adjust the sampling frequency of the static monitoring data to generate static adjustment data; S5. Combine static and dynamic monitoring data to construct environmental parameter fusion data; S6. Match the environmental quality assessment algorithm type and generate target algorithm type feature data; S7. Perform environmental quality calibration based on the fused data and target algorithm, and generate an environmental quality calibration report.

2. The environmental quality monitoring method according to claim 1, characterized in that: Said S1 comprises: S11. Collect environmental parameters at preset time intervals through fixed monitoring stations to generate static monitoring data; S12. Collect environmental dynamic parameters in real time through mobile monitoring equipment to generate dynamic monitoring data.

3. The method according to claim 2, characterized in that The S2 includes: S21. Import the static and dynamic monitoring data into the environmental management platform, and use a bidirectional search algorithm to extract their sampling frequencies, which are marked as static frequency (f_s) and dynamic frequency (f_d), respectively, in Hertz.

4. The method according to claim 3, characterized in that The S3 includes: S31. Compare the values ​​of f_s and f_d; if the difference is within a preset threshold, determine that they are consistent; otherwise, determine that they are inconsistent.

5. The method according to claim 4, characterized in that The S4 includes: S41. Use a linear interpolation algorithm to adjust the sampling frequency of the static monitoring data according to f_d to generate static adjustment data.

6. The method according to claim 5, characterized in that The S5 includes: S51. Align the static adjustment data and the dynamic monitoring data along the time axis to construct spatiotemporal fusion environmental parameter fusion data.

7. The method according to claim 6, characterized in that The S6 includes: S61. Establish a standard parameter fusion data matrix corresponding to different environmental assessment algorithms; S62: Match the environmental parameter fusion data with the standard matrix and search for the best matching evaluation algorithm type through an optimization algorithm. The specific steps are as follows: S621, initialize optimization algorithm parameters and randomly generate candidate algorithm populations; S622, exploration phase: the simulation algorithm population searches for the best matching position in the solution space and updates the candidate positions; S623, development phase: evaluate the objective function value of the candidate position and update the optimal algorithm type; S624. After iteration until convergence, output target algorithm type feature data.

8. The method according to claim 7, characterized in that The S7 includes: S71. Call the target algorithm to calibrate abnormal parameters in the fused data and generate a calibrated environmental quality report; S72. Compare the calibration result with the environmental standard and trigger an early warning signal.

9. An environmentally friendly environmental monitoring system, used to implement the method according to any one of claims 1 to 8, characterized in that: The system comprises: Environmental parameter acquisition module, data processing and fusion module, algorithm matching engine, calibration and early warning execution module.

10. The environmentally friendly environment monitoring system according to claim 9, characterized in that: The calibration and early warning execution module includes: A multi-level dynamic early warning unit, which adaptively divides the early warning levels based on the degree to which the parameters in the environmental quality calibration report deviate from the standard values; The warning levels include mild warning (yellow mark), moderate warning (orange mark) and severe warning (red mark), and are associated with different response strategy databases; When a severe warning is triggered, a pollution source location map and emergency treatment plan are generated simultaneously and pushed to the terminal.

Images