Water quality analysis and detection method and system based on sponge city engineering

Abstract

The invention relates to the technical field of data processing, in particular to a hydrology and water quality analysis and detection method and system based on sponge city engineering, and the method comprises the steps: respectively obtaining monitoring data of each hydrology monitoring index and water quality monitoring index at each monitoring point of the sponge city engineering in a preset time period before the current moment; predicting normal water quality data of each water quality monitoring index at the target monitoring point at the current moment according to the data change synchronism of each hydrological monitoring index between each other monitoring point and the target monitoring point and the data change association degree of each water quality monitoring index; obtaining a final predicted value of each water quality monitoring index at the current moment; according to the difference between the actual monitoring data of each water quality monitoring index at the target monitoring point at the current moment and the final predicted value, the water quality abnormal condition of the target monitoring point at the current moment is detected, and the accuracy of detecting the water quality abnormal condition of the sponge city project is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a water quality analysis and testing method and system based on sponge city engineering. Background Technology

[0002] Sponge city engineering is a comprehensive urban water system project that uses a series of ecological management methods to achieve functions such as the storage, infiltration, and purification of natural rainwater. Water quality analysis and testing are crucial to ensuring the operational status and efficiency of sponge city projects. Water quality testing mainly measures the "quality and composition of water," and is used for drinking water safety, pollution early warning, and water treatment effect evaluation. Real-time monitoring and evaluation of water quality provide data support for the optimization of sponge city facilities and water safety management.

[0003] Existing water quality testing methods primarily rely on setting thresholds for each monitoring data point and triggering alarms for data exceeding these thresholds. However, actual hydrological conditions often significantly impact water quality data. For instance, increased runoff due to heavy rainfall can alter pollutant migration patterns. Traditional testing methods struggle to distinguish between water quality anomalies caused by changes in hydrological conditions and those resulting from actual pollution events, and they also overlook this pollutant migration, leading to a high false alarm rate.

[0004] Therefore, improving the accuracy of detecting abnormal water quality in sponge city projects has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a water quality analysis and detection method and system based on sponge city projects, in order to solve the problem of how to improve the accuracy of detecting abnormal water quality conditions in sponge city projects.

[0006] In a first aspect, embodiments of the present invention provide a water quality analysis and testing method based on sponge city engineering, the method comprising the following steps: At at least two monitoring points in the sponge city project, monitoring data for each hydrological and water quality indicator were acquired at each time point within a preset time period prior to the current time. Any monitoring point is designated as the target monitoring point. Based on the synchronicity of the data changes of various hydrological monitoring indicators between each other monitoring point and the target monitoring point within the preset time period, and the correlation between the data changes of various water quality monitoring indicators between each other monitoring point and the target monitoring point within the preset time period, the water quality response degree of various water quality monitoring indicators at the target monitoring point is obtained. Based on the monitoring data of any water quality monitoring indicator at the target monitoring point at each non-pollution time within the preset time period, and the water quality response degree of any water quality monitoring indicator at the target monitoring point, the normal water quality data of any water quality monitoring indicator at the target monitoring point at the current time is predicted to obtain the final predicted value. Based on the difference between the actual monitoring data and the final predicted value of any water quality monitoring indicator at the target monitoring point at the current moment, the degree of abnormality of any water quality monitoring indicator at the target monitoring point at the current moment is obtained. Based on the degree of abnormality of each water quality monitoring indicator at each monitoring point at the current moment, the water quality abnormality at each monitoring point at the current moment is detected.

[0007] Secondly, embodiments of the present invention also provide a water quality analysis and testing system based on sponge city engineering, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements a water quality analysis and testing method based on sponge city engineering as described in the first aspect.

[0008] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: This invention analyzes the flow relationship between monitoring points other than the target monitoring point and the target monitoring point by synchronizing the data changes of various hydrological monitoring indicators between the two points. This improves the influence of water quality data between monitoring points with flow relationships. Furthermore, by combining the correlation of data changes of various water quality monitoring indicators between each monitoring point and the target monitoring point, the water quality response of various water quality monitoring indicators at the target monitoring point is obtained, thereby improving the accuracy of predicting the normal water quality data of various water quality monitoring indicators at the target monitoring point at the current moment. Based on the monitoring data of various water quality monitoring indicators at the target monitoring point at each non-pollution time within the preset time period, and the water quality response of various water quality monitoring indicators at the target monitoring point, the normal water quality data of various water quality monitoring indicators at the target monitoring point at the current moment is predicted. Then, based on the difference between the predicted results and the actual monitoring values, the water quality anomaly situation at the target monitoring point at the current moment is assessed. This can effectively distinguish water quality anomalies caused by changes in hydrological conditions, reduce the possibility of water quality anomalies being misidentified as water quality anomalies caused by real pollution events, and greatly improve the accuracy of detecting the real water quality anomalies at each monitoring point. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart of a water quality analysis and testing method based on sponge city engineering provided in Embodiment 1 of the present invention. Detailed Implementation

[0011] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0012] It should be noted that the terms "first," "second," etc., used in this disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure.

[0013] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0014] See Figure 1 This is a flowchart of a water quality analysis and testing method based on sponge city engineering provided in Embodiment 1 of the present invention, as shown below. Figure 1 As shown, the method may include: Step S101: At at least two monitoring points in the sponge city project, acquire monitoring data for each hydrological monitoring indicator and each water quality monitoring indicator at each time point within a preset time period prior to the current time.

[0015] Following the hydrological and water quality transmission path of sponge city projects, monitoring points are set up at key nodes such as upstream river channels or stormwater pipe network inlets, inlets and outlets of various facilities (such as reservoirs), and downstream discharge outlets. At each monitoring point, level gauges, flow meters, and velocity meters are installed to monitor water level, runoff flow rate, and runoff velocity (hydrological data), respectively. Multi-parameter online water quality monitoring instruments, online COD analyzers, online ammonia nitrogen analyzers, and online total phosphorus analyzers are used to monitor pH, dissolved oxygen, turbidity, COD, ammonia nitrogen, and total phosphorus data (water quality data), respectively. All monitoring equipment performs monitoring every 5 minutes. The hydrological monitoring indicators are set as water level, runoff flow rate, and runoff velocity, and the water quality monitoring indicators are set as pH, dissolved oxygen, turbidity, COD, ammonia nitrogen, and total phosphorus data. There are no restrictions here; implementers can set the water quality and hydrological monitoring indicators, as well as the monitoring frequency, according to the specific scenario.

[0016] To avoid interference from seasonal fluctuations, based on the monitoring frequency, the data of each hydrological and water quality monitoring indicator at each monitoring point within the previous 7 days (excluding the current time) are analyzed as historical data at each moment to detect water quality anomalies at each monitoring point at the current moment. There are no restrictions on this; implementers can set it according to specific scenarios. To avoid interference from pollution events, data from the time of pollution are removed from the historical data used (i.e., historical data of each hydrological and water quality monitoring indicator at each monitoring point within the previous 7 days). To avoid the problem of insufficient data volume after removing data from the pollution time, which could lead to random results, data needs to be supplemented backwards after data removal. The time period consisting of all historical data is recorded as the historical time period. For example, assuming the times before the current time are (10:00, 10:05, 10:10, 10:15, 10:20, 10:25, 10:30), and a monitoring point experiences pollution at 10:20 and 10:25, then the historical data for all hydrological and water quality monitoring indicators at that monitoring point at 10:20 and 10:25 are removed. The data is then supplemented using the historical data for the same hydrological and water quality monitoring indicators at 09:50 and 09:55. The time period corresponding to all historical data is recorded as the historical time period, i.e., 09:50-10:30. Considering that historical data with excessively long time intervals has low reference value, the historical data should not exceed 30 days.

[0017] It is worth noting that due to the different geographical locations of different monitoring points, the pollution time within the 7 days prior to the current moment varies, as does the duration of the pollution event. Consequently, the length of the corresponding historical periods at different monitoring points also varies. To facilitate subsequent analysis, the longest historical period is used as the standard, i.e., the longest historical period is used as the preset period. Historical data of each hydrological and water quality monitoring indicator at each monitoring point at each moment within the longest historical period are obtained. The obtained historical data are then normalized to obtain the monitoring data of each hydrological and water quality monitoring indicator at each monitoring point at each moment within the preset period.

[0018] Step S102: Record any monitoring point as the target monitoring point. Based on the synchronicity of the data changes of various hydrological monitoring indicators between each other monitoring point and the target monitoring point within the preset time period, and the correlation between the data changes of various water quality monitoring indicators between each other monitoring point and the target monitoring point within the preset time period, obtain the water quality response degree of various water quality monitoring indicators at the target monitoring point.

[0019] In the transmission path of sponge cities, pollutants are mainly transported along the direction of water flow. This means that water quality data only have an impact when there is a flow relationship between different monitoring points. The flow between different monitoring points is mainly reflected in the synchronicity of changes in hydrological data. That is, if hydrological data such as runoff flow rate and runoff velocity change at one monitoring point, and the corresponding hydrological data at another monitoring point also changes similarly, then there is a flow relationship between these two monitoring points, meaning that the water quality at one monitoring point will have a significant impact on the other. Therefore, in this embodiment of the invention, any monitoring point is designated as the target monitoring point, and all other monitoring points are designated as other monitoring points. First, based on the synchronicity of changes in various hydrological monitoring indicators between each other monitoring point and the target monitoring point, the degree of influence of each other monitoring point on the water quality at the target monitoring point is obtained. This quantifies the flow between each other monitoring point and the target monitoring point. Then, based on the flow between each other monitoring point and the target monitoring point, the possibility of the target monitoring point being affected by water quality anomalies at the current moment is analyzed, and further, the possibility of a real pollution event occurring at the target monitoring point at the current moment is analyzed.

[0020] Taking the d-th other monitoring point as an example, the steps to obtain the degree of influence of the d-th other monitoring point on the water quality of the target monitoring point are as follows: (1) Based on the consistency of the data changes of each hydrological monitoring indicator between each other monitoring point and the target monitoring point within the preset time period, obtain the influence weight of each hydrological monitoring indicator.

[0021] Since there are multiple hydrological monitoring indicators, and different hydrological monitoring indicators have different degrees of responsiveness to the flow between monitoring points, it is first necessary to obtain the influence weight of each hydrological monitoring indicator based on the consistency of the data changes of each other monitoring point and the target monitoring point within the preset time period, so as to quantify the degree of responsiveness of each hydrological monitoring indicator to the flow between monitoring points.

[0022] Specifically: Taking the hydrological monitoring indicator a as an example, if there is a pollution moment at the target monitoring point within the preset time period, then based on the monitoring data of the hydrological monitoring indicator a at the target monitoring point at each non-pollution moment within the preset time period, the spline interpolation method is used to obtain the fitted data of the hydrological monitoring indicator a at the target monitoring point at each pollution moment within the preset time period. The monitoring data of the hydrological monitoring indicator a at the target monitoring point at each non-pollution moment within the preset time period and the fitted data at the pollution moment are combined to form a hydrological data sequence. The spline interpolation method is an existing technology and will not be elaborated here. If there is no pollution moment at the target monitoring point within the preset time period, then the monitoring data of the hydrological monitoring indicator a at the target monitoring point at each moment within the preset time period are combined to form a hydrological data sequence. If the hydrological data sequence of the a-th hydrological monitoring indicator at the d-th other monitoring point is obtained within the preset time period, then the formula for calculating the consistency of the data change of the a-th hydrological monitoring indicator between the d-th other monitoring point and the target monitoring point is: in, This indicates the degree of consistency between the data changes of the a-th hydrological monitoring indicator at the d-th other monitoring point and the target monitoring point. This indicates the number of all data points in a hydrological data series. This represents the difference between the i-th data point and the (i-1)-th data point in the hydrological data sequence corresponding to the a-th hydrological monitoring indicator at the target monitoring point. This represents the difference between the i-th data point and the (i-1)-th data point in the hydrological data sequence corresponding to the a-th hydrological monitoring indicator at the d-th other monitoring point. This represents a preset constant used to ensure that the fraction is meaningful. In this embodiment of the invention, it is set... There are no restrictions here; implementers can set it according to the proposed scenario. Represents a linear normalization function; It should be noted that, The larger the value, the more synchronized the data changes of the hydrological monitoring index a at the d-th other monitoring point and the target monitoring point are within the preset time period (increasing or decreasing simultaneously), and thus... The larger the value, the more obvious the transmissibility of the hydrological monitoring indicator a between the dth other monitoring point and the target monitoring point.

[0023] Similarly, to obtain the consistency of data changes in the hydrological monitoring indicator a between each other monitoring point and the target monitoring point, since some other monitoring points have no flow relationship with the target monitoring point, to avoid the influence of these other monitoring points on the analysis results, based on the characteristics that the similarity of the consistency of data changes in the hydrological monitoring indicator a between monitoring points with flow relationships is high, while the randomness of the consistency of data changes in the hydrological monitoring indicator a between monitoring points without flow relationships is strong, the DBSCAN clustering algorithm is used to cluster all data change consistency levels, obtaining at least one cluster. The cluster with the largest number of members is selected. If only one cluster with the largest number of members exists, the average value of the data change consistency levels in all data change consistency levels in the cluster with the largest number of members is calculated. This average value of the data change consistency levels in all data change consistency levels in the cluster with the largest number of members yields the data performance level of the hydrological monitoring indicator a, denoted as . If there are at least two clusters with the largest number of members, then calculate the average of the consistency of data variation in each cluster with the largest number of members. Select the maximum value of the average value corresponding to each cluster with the largest number of members as the data performance degree of the hydrological monitoring indicator a, denoted as . The DBSCAN clustering algorithm is an existing technology and will not be described in detail here. For each monitoring point, the standard deviation of the monitoring data for the a-th hydrological monitoring index at all non-pollution times within the preset time period is obtained. The average of the standard deviations corresponding to the a-th hydrological monitoring index at all monitoring points is calculated. The average of all standard deviations is normalized using the norm function to obtain the fluctuation degree of the a-th hydrological monitoring index, denoted as [missing information]. ; The influence weight of the hydrological monitoring indicator a is obtained by calculating the product of its fluctuation level and its data performance level, denoted as [missing information]. ,Right now The more significant the fluctuation in the data of hydrological monitoring indicator a within the preset time period, that is... The larger the value, the more consistent the changes in the hydrological monitoring index a between other monitoring points and the target monitoring point, i.e. This indicates that the hydrological monitoring indicator a is better able to reflect the flow between monitoring points.

[0024] (2) Taking the dth other monitoring point as an example, based on the similarity of the fluctuation trends of various hydrological monitoring indicators between the dth other monitoring point and the target monitoring point in the preset time period, and the influence weight of each hydrological monitoring indicator, the degree of influence of the dth other monitoring point on the water quality at the target monitoring point is obtained.

[0025] Considering that the more similar the fluctuation trends of hydrological data at other monitoring points are to the target monitoring point, the greater the influence of other monitoring points on the water quality at the target monitoring point, in this embodiment of the invention, taking the d-th other monitoring point as an example, the degree of influence of the d-th other monitoring point on the water quality at the target monitoring point is obtained based on the similarity of the fluctuation trends of various hydrological monitoring indicators between the d-th other monitoring point and the target monitoring point within the preset time period, and the influence weight of each hydrological monitoring indicator.

[0026] Specifically: The monitoring data of various hydrological monitoring indicators of the target monitoring point at each time point within the preset time period are combined into multidimensional hydrological data. The multidimensional hydrological data at all times are combined into a multidimensional data sequence according to the time sequence, which is denoted as the target multidimensional data sequence. The multidimensional data sequence corresponding to the d-th other monitoring point is obtained and denoted as the multidimensional data sequence to be analyzed. The index of each multidimensional hydrological data is obtained according to the position of each multidimensional hydrological data in the target multidimensional data sequence and the multidimensional data sequence to be analyzed. Because different monitoring points have different geographical locations, the impact of other monitoring points on the target monitoring point has a lag. Therefore, it is necessary to shift the multidimensional data sequence to be analyzed forward to align with the target multidimensional data sequence, and analyze the similarity of the fluctuation trends of various hydrological monitoring indicators between the d-th other monitoring point and the target monitoring point at each alignment. The specific implementation process is as follows: Obtain a preset lag data sequence. The minimum value in the preset lag data sequence is 0, and the maximum value is the number of all times in the preset time period minus 1, that is, the number of all data in the target multidimensional data sequence or the multidimensional data sequence to be analyzed minus 1. For example, assuming there are 5 times in the preset time period, the preset lag data sequence is (0, 1, 2, 3, 4). For any lag data in the lag time sequence, subtract the index of each multidimensional hydrological data in the multidimensional data sequence to be analyzed from the index of any lag data to obtain the index of each multidimensional hydrological data in the multidimensional data sequence to be analyzed. A new index is used for hydrological data to shift the multidimensional data sequence to be analyzed forward. Based on the influence weights of various hydrological monitoring indicators, the new index of each multidimensional hydrological data point in the multidimensional data sequence to be analyzed, and the index of each multidimensional hydrological data point in the target multidimensional data sequence, the weighted Euclidean distance in multidimensional space is calculated between any two multidimensional hydrological data points with the same index and corresponding non-pollution times. Taking index j as an example: if the time corresponding to the multidimensional hydrological data point with index j in the target multidimensional data sequence is the non-pollution time of the target monitoring point, and the time corresponding to the multidimensional hydrological data point with index j in the multidimensional data sequence to be analyzed is the non-pollution time of the d-th other monitoring point, then based on the influence weights of various hydrological monitoring indicators, the weighted Euclidean distance between the multidimensional hydrological data point with index j in the target multidimensional data sequence and the multidimensional hydrological data point with index j in the multidimensional data sequence to be analyzed is calculated, denoted as […]. ,Right now Where n represents the number of hydrological monitoring indicators, This represents the monitoring data of the a-th hydrological monitoring indicator in the multidimensional hydrological data with index j in the target multidimensional data sequence. This represents the monitoring data of the a-th hydrological monitoring indicator in the multidimensional hydrological data with new index j, within the multidimensional data sequence to be analyzed at the d-th other monitoring point. This indicates the influence weight of the hydrological monitoring indicator a; Calculate the average of all weighted Euclidean distances to obtain the degree of data difference between the d-th other monitoring point and the target monitoring point under any given lag data; The degree of data difference between the target monitoring point and the d-th other monitoring point under each lag data point in the lag data sequence is obtained, and the minimum value of all data difference degrees is obtained, denoted as . Using the negative of the minimum value as the independent variable of an exponential function with the natural constant as the base, we obtain the degree of influence of the d-th other monitoring point on the water quality at the target monitoring point, denoted as... ,Right now Where exp() represents an exponential function with base to the natural constant. The smaller the value, the more similar the fluctuation trends of various hydrological monitoring indicators are between the d-th other monitoring point and the target monitoring point, and thus... The larger the value, the greater the impact of the d-th other monitoring point on the water quality at the target monitoring point.

[0027] Thus, the influence of the d-th other monitoring point on the water quality at the target monitoring point is obtained, which is used to quantify the flow between the d-th other monitoring point and the target monitoring point. Similarly, the influence of each other monitoring point on the water quality at the target monitoring point is obtained.

[0028] Furthermore, considering that the impact of other monitoring points on the water quality of the target monitoring point is mainly through the transfer of pollutants, and that the speed and amount of pollutant transfer will vary under different hydrological conditions such as flow rate, velocity, and propagation distance, the degree of impact on the target monitoring point will also vary when the same water quality is transferred from different monitoring points to the target monitoring point. In other words, the "amount of pollutants" received by the target monitoring point will differ, or the "pollution contribution" of different monitoring points to the target monitoring point will be different. Therefore, it is necessary to combine the correlation of changes in water quality data between the dth other monitoring point and the target monitoring point to further analyze the influence relationship of the dth other monitoring point on the water quality data of the target monitoring point, and obtain the degree of water quality contribution of the dth other monitoring point to the various water quality monitoring indicators at the target monitoring point and the lag time of water quality impact.

[0029] Specifically: The monitoring data of various hydrological monitoring indicators at the dth other monitoring point at each non-pollution time within the preset time period are used to form multidimensional hydrological data. The K-means clustering algorithm is used to perform multidimensional clustering on all multidimensional hydrological data to obtain at least one cluster. Since the water quality of the target monitoring point at the current time is affected by the water quality of other monitoring points in the previous time period, the cluster in which the current time was located in the previous time period is recorded as the target cluster. The K value in the K-means clustering algorithm is determined by the elbow method. The K-means clustering algorithm and the elbow method are existing technologies and will not be described in detail here. If any moment within the target cluster is a non-contaminated moment at the target monitoring point, then that moment is recorded as the target moment, all target moments within the target cluster are obtained, and at least two consecutive target moments are combined into a time period to be analyzed. For any analysis period, taking the b-th water quality monitoring indicator as an example, the monitoring data of the b-th water quality monitoring indicator at the target monitoring point at each moment in any analysis period are used to form a water quality data sequence. Because the water quality monitoring indicator may undergo some sedimentation and dilution during the propagation process between different monitoring points, and the basic values ​​of each monitoring point are not completely consistent, the water quality influence relationship between different monitoring points is more reflected in the amount of data change. Therefore, the first-order difference sequence of the water quality data sequence is obtained and denoted as the difference sequence of the b-th water quality monitoring indicator at the target monitoring point in any analysis period. The difference sequence of the b-th water quality monitoring indicator at the d-th other monitoring point in any analysis period is also obtained. Map the difference sequences corresponding to the target monitoring point and the d-th other monitoring point to a two-dimensional coordinate system to obtain waveforms corresponding to the target monitoring point and the d-th other monitoring point. The horizontal axis of the two-dimensional coordinate system represents time, and the vertical axis represents the data in the difference sequence. Similar to the above method of obtaining the preset lag data sequence, a preset lag time sequence is obtained. The difference between any two data points in the preset lag time sequence is the time represented by the unit length of the horizontal axis in the two-dimensional coordinate system. The maximum value in the preset lag time sequence is the duration of any time period to be analyzed. Assuming the horizontal axis... The target unit length represents 5 minutes of time. The duration of any time period to be analyzed is 20. The preset lag time series is (0, 5, 10, 15, 20). For any lag time in the preset lag time series, the waveform corresponding to the d-th other monitoring point is shifted in the opposite direction of the horizontal axis by the lag time. The Pearson correlation coefficient between the two waveforms corresponding to the overlapping part of the horizontal axis in the two-dimensional coordinate system is calculated to obtain the correlation degree between the d-th other monitoring point and the target monitoring point for the b-th water quality monitoring indicator at any lag time. Obtain the correlation degree corresponding to each lag time in the preset lag time series, select the maximum value among all correlation degrees, and use it as the correlation feature value of the b-th water quality monitoring indicator between the d-th other monitoring point and the target monitoring point in any analysis period. Record the lag time corresponding to the correlation feature value as the delay time of the b-th water quality monitoring indicator between the d-th other monitoring point and the target monitoring point in any analysis period. Obtain the associated feature value and delay time corresponding to each of the time periods to be analyzed, calculate the average value of all associated feature values, and obtain the water quality contribution of the d-th other monitoring point to the b-th water quality monitoring indicator at the target monitoring point, denoted as . Calculate the average of all delay times to obtain the lag time of the water quality impact of the d-th other monitoring point on the b-th water quality monitoring indicator at the target monitoring point, denoted as . .

[0030] Thus, we have obtained the water quality contribution of the dth other monitoring point to the bth water quality monitoring indicator at the target monitoring point and the water quality impact lag time. Similarly, we have obtained the water quality contribution of each other monitoring point to each water quality monitoring indicator at the target monitoring point and the water quality impact lag time.

[0031] Furthermore, based on the degree of influence of each other monitoring point on the water quality at the target monitoring point, as well as the contribution of each other monitoring point to the water quality of various water quality monitoring indicators at the target monitoring point and the lag time of water quality impact, the water quality response degree of each water quality monitoring indicator at the target monitoring point is obtained. This is used to quantify how much the monitoring data of each water quality monitoring indicator at the target monitoring point is affected by other monitoring points at the current moment. Specifically: Taking the b-th water quality monitoring indicator and the d-th other monitoring point as an example, the product of the contribution of the d-th other monitoring point to the b-th water quality monitoring indicator at the target monitoring point and the influence of the d-th other monitoring point on the water quality status at the target monitoring point is calculated. This product yields the influence weight of the d-th other monitoring point on the b-th water quality monitoring indicator at the target monitoring point, denoted as […]. ,Right now ,in, This indicates the degree of contribution of the d-th other monitoring point to the water quality of the b-th water quality monitoring indicator at the target monitoring point. This indicates the degree of influence of the d-th other monitoring point on the water quality at the target monitoring point. The larger the value, the greater the connectivity between the d-th other monitoring point and the target monitoring point, and the more likely the water quality status of the d-th other monitoring point is to be transmitted to the target monitoring point. The larger the value, the more data of water quality indicator b from the d-th other monitoring point is transmitted to the target monitoring point; that is, the greater the contribution of the d-th other monitoring point to water quality indicator b at the target monitoring point. The larger, and The larger the value, the greater the influence of the d-th other monitoring point on the water quality of the target monitoring point, and thus... The larger; Based on the lag time of the impact of the dth other monitoring point on the bth water quality monitoring indicator at the target monitoring point, the current time is subtracted from the lag time of the impact of the dth other monitoring point on the bth water quality monitoring indicator at the target monitoring point to obtain the water quality impact time. For example, assuming the current time is 10:00 and the lag time is 10 minutes, the water quality impact time is 09:50. When pollution or other situations occur at other monitoring points, data fluctuations at those points will propagate to the current monitoring point with the water flow. When the water quality data at other monitoring points are normal and stable, they will not have an abnormal impact on the current monitoring point. Therefore, the change in the water quality data of the bth water quality monitoring indicator at the dth other monitoring point at the water quality impact time is subtracted from the monitoring data at the time preceding the water quality impact time. This change is denoted as _____. ; Similarly, obtain the influence weight of each other monitoring point on the b-th water quality monitoring indicator at the target monitoring point, and the change in water quality data of the b-th water quality monitoring indicator at each other monitoring point at the time of the water quality influence. Based on the weight corresponding to each other monitoring point, perform a weighted summation of the change in water quality data corresponding to each other monitoring point to obtain the water quality response degree of the b-th water quality monitoring indicator at the target monitoring point.

[0032] In one embodiment, the formula for calculating the water quality response degree of the b-th water quality monitoring indicator at the target monitoring point is: in, This represents the water quality response level of the b-th water quality monitoring indicator at the target monitoring point, and N represents the number of other monitoring points. This represents the influence weight of the d-th other monitoring point on the b-th water quality monitoring indicator at the target monitoring point. This represents the change in water quality data for the b-th water quality monitoring indicator at the d-th other monitoring point at the time of water quality impact.

[0033] It should be noted that, The larger the value, the greater the influence of the d-th other monitoring point on the water quality of the target monitoring point. The larger the value, the more significant the change in the monitoring data of the b-th water quality indicator at the d-th other monitoring point at the time of water quality impact. The larger, and The larger the value, the greater the likelihood that the water quality monitoring indicator b at the target monitoring point will undergo a similarly large change in the monitoring data at the current moment, and thus... The larger the value, the greater the influence of water quality on the b-th water quality monitoring indicator at the target monitoring point at the current moment. In other words, the change of the b-th water quality monitoring indicator at the target monitoring point at the current moment is more consistent with the changes of other monitoring points at their corresponding water quality influence moments.

[0034] Thus, the water quality response level of the b-th water quality monitoring indicator at the target monitoring point was obtained. Similarly, the water quality response level of each water quality monitoring indicator at the target monitoring point was obtained.

[0035] Step S103: Based on the monitoring data of any water quality monitoring indicator at the target monitoring point during non-pollution times before the current time, and the water quality response degree of the water quality monitoring indicator at the target monitoring point, predict the normal water quality data of the water quality monitoring indicator at the target monitoring point at the current time, and obtain the final predicted value. Based on the monitoring data of various water quality monitoring indicators at the target monitoring point during non-pollution times prior to the current moment, and the water quality response degree of various water quality monitoring indicators at the target monitoring point obtained in step S103, the normal water quality data of various water quality monitoring indicators at the target monitoring point at the current moment is predicted, and the final predicted value of various water quality monitoring indicators at the target monitoring point at the current moment is obtained. Based on the difference between the final predicted value and the monitoring data of various water quality monitoring indicators at the target monitoring point at the current moment, the abnormal water quality situation at the target monitoring point at the current moment is detected.

[0036] Taking the b-th water quality monitoring indicator as an example, the final predicted value of the b-th water quality monitoring indicator at the target monitoring point at the current time is obtained as follows: If there is a pollution moment at the target monitoring point within the preset time period, then based on the monitoring data of the b-th water quality monitoring index at the target monitoring point at each non-pollution moment within the preset time period, the spline interpolation method is used to obtain the fitted data of the b-th water quality monitoring index at the target monitoring point at each pollution moment within the preset time period. The monitoring data of the b-th water quality monitoring index at the target monitoring point at each non-pollution moment within the preset time period and the fitted data at the pollution moment are combined to form the normal water quality data sequence of the b-th water quality monitoring index at the target monitoring point within the preset time period. If there is no pollution moment at the target monitoring point within the preset time period, then the monitoring data of the b-th water quality monitoring index at the target monitoring point at each moment within the preset time period are combined to form the normal water quality data sequence. Based on the normal water quality data sequence, a preset prediction algorithm is used to predict the normal water quality data of the b-th water quality monitoring index at the target monitoring point at the current time to obtain the initial prediction value. In this embodiment of the invention, the preset prediction algorithm is set to the LSTM algorithm. There is no limitation here. The implementer can set the prediction algorithm according to the scenario. The LSTM algorithm is existing technology and will not be described in detail here. If the water quality at the target monitoring point is affected by other monitoring points rather than by a pollution event occurring at the target monitoring point itself, the initial predicted value should be supplemented based on the degree of influence of the target monitoring point on the water quality of other monitoring points. That is, the sum of the water quality response degree of the b-th water quality monitoring indicator at the target monitoring point and the initial predicted value should be calculated to obtain the final predicted value of the b-th water quality monitoring indicator at the target monitoring point at the current moment.

[0037] In one embodiment, the formula for calculating the final predicted value of the b-th water quality monitoring indicator at the target monitoring point at the current time is: in, This represents the final predicted value of the b-th water quality monitoring indicator at the target monitoring point at the current moment. This represents the initial predicted value of the b-th water quality monitoring indicator at the target monitoring point at the current time. This indicates the water quality response level of the b-th water quality monitoring indicator at the target monitoring point.

[0038] It should be noted that, The larger the value, the greater the influence of other monitoring points on the water quality monitoring index b at the target monitoring point at the current moment. The more consistent the change in the water quality monitoring index b at the target monitoring point at the current moment is with the changes at other monitoring points at their corresponding times of influence. Therefore, using... The initial predicted value of water quality monitoring indicator b at the target monitoring point is adjusted at the current moment to more accurately reflect the water quality status of the target monitoring point at the current moment. The larger.

[0039] Step S104: Based on the difference between the actual monitoring data of any water quality monitoring indicator at the target monitoring point and the final predicted value at the current moment, obtain the degree of abnormality of any water quality monitoring indicator at the target monitoring point at the current moment; and detect the water quality abnormality at each monitoring point at the current moment based on the degree of abnormality of each water quality monitoring indicator at each monitoring point at the current moment.

[0040] Since the final predicted value of the b-th water quality monitoring indicator at the target monitoring point obtained in step S103 is based on monitoring data from a non-polluted time, the greater the difference between the actual monitoring data and the final predicted value, the greater the possibility of water quality anomalies at the target monitoring point. Therefore, the absolute value of the difference between the actual monitoring data and the final predicted value of the b-th water quality monitoring indicator at the target monitoring point at the current time is calculated to obtain the degree of anomaly of the b-th water quality monitoring indicator at the target monitoring point at the current time.

[0041] In one embodiment, the formula for calculating the degree of anomaly of the b-th water quality monitoring indicator at the target monitoring point at the current time is: in, This indicates the degree of anomaly of the b-th water quality monitoring indicator at the target monitoring point at the current time. This represents the actual monitoring data of the b-th water quality monitoring indicator at the target monitoring point at the current time. This represents the final predicted value of the b-th water quality monitoring indicator at the target monitoring point at the current moment. Represents the absolute value symbol.

[0042] It should be noted that, When it is large, if It is also relatively large, that is The smaller the value, the greater the influence of other monitoring points on the data anomaly of the b-th water quality monitoring indicator at the target monitoring point, and the less likely a real pollution event has occurred at the target monitoring point; conversely, if... Smaller, i.e. The larger the value, the less the data anomaly of the b-th monitoring indicator at the target monitoring point is affected by other monitoring points, and the greater the probability that an actual pollution event will occur at the target monitoring point at the current moment. In other words, the greater the probability that a real water quality anomaly will occur at the target monitoring point at the current moment. The larger.

[0043] Similarly, the historical anomaly level of the b-th water quality monitoring indicator at each monitoring point is obtained at each non-pollution time within the preset time period. Based on all historical anomaly levels, the normal range of the b-th water quality monitoring indicator is obtained using the 3sigma principle. The 3sigma principle is existing technology and will not be elaborated here. If the anomaly level of the b-th water quality monitoring indicator at the target monitoring point is not within the normal range at the current time, it indicates that a pollution event has occurred at the target monitoring point, and an anomaly alarm is triggered for the b-th water quality monitoring indicator at the target monitoring point.

[0044] Similarly, by obtaining the degree of abnormality of various water quality monitoring indicators at each monitoring point along the hydrological and water quality transmission path of the sponge city project at the current moment, we can detect the water quality abnormality of various water quality monitoring indicators at each monitoring point at the current moment, which is to detect the possibility of pollution events at each monitoring point.

[0045] Based on the same inventive concept as the above method, this embodiment of the invention also provides a water quality analysis and testing system based on sponge city engineering, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described water quality analysis and testing methods based on sponge city engineering.

[0046] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A water quality analysis and testing method based on sponge city engineering, characterized in that, The water quality analysis and testing method based on sponge city engineering includes: At at least two monitoring points in the sponge city project, monitoring data for each hydrological and water quality indicator were acquired at each time point within a preset time period prior to the current time. Any monitoring point is designated as the target monitoring point. Based on the synchronicity of the data changes of various hydrological monitoring indicators between each other monitoring point and the target monitoring point within the preset time period, and the correlation between the data changes of various water quality monitoring indicators between each other monitoring point and the target monitoring point within the preset time period, the water quality response degree of various water quality monitoring indicators at the target monitoring point is obtained. Based on the monitoring data of any water quality monitoring indicator at the target monitoring point at each non-pollution time within the preset time period, and the water quality response degree of any water quality monitoring indicator at the target monitoring point, the normal water quality data of any water quality monitoring indicator at the target monitoring point at the current time is predicted to obtain the final predicted value. Based on the difference between the actual monitoring data and the final predicted value of any water quality monitoring indicator at the target monitoring point at the current moment, the degree of abnormality of any water quality monitoring indicator at the target monitoring point at the current moment is obtained. Based on the degree of abnormality of each water quality monitoring indicator at each monitoring point at the current moment, the water quality abnormality at each monitoring point at the current moment is detected.

2. The water quality analysis and testing method based on sponge city engineering according to claim 1, characterized in that, The water quality response level of each water quality monitoring indicator at the target monitoring point includes: For any other monitoring point, based on the synchronicity of the data changes of various hydrological monitoring indicators between the other monitoring point and the target monitoring point within the preset time period, the degree of influence of the other monitoring point on the water quality at the target monitoring point is obtained. Based on the correlation between the data changes of various water quality monitoring indicators between any other monitoring point and the target monitoring point within the preset time period, the water quality contribution of any other monitoring point to the water quality monitoring indicators at the target monitoring point and the water quality impact lag time are obtained respectively. The degree of influence of each other monitoring point on the water quality of the target monitoring point, the contribution of each other monitoring point to the water quality of each water quality monitoring indicator at the target monitoring point, and the lag time of the water quality impact are obtained. Based on the degree of influence of each other monitoring point on the water quality of the target monitoring point, the contribution of each other monitoring point to the water quality of each water quality monitoring indicator at the target monitoring point, and the lag time of the water quality impact, the water quality response degree of each water quality monitoring indicator at the target monitoring point is obtained.

3. The water quality analysis and testing method based on sponge city engineering according to claim 2, characterized in that, The step of obtaining the degree of influence of any other monitoring point on the water quality at the target monitoring point based on the synchronicity of data changes of various hydrological monitoring indicators between any other monitoring point and the target monitoring point within the preset time period includes: Based on the degree of consistency of data changes of various hydrological monitoring indicators between each other monitoring point and the target monitoring point within the preset time period, the influence weight of each hydrological monitoring indicator is obtained. The monitoring data of each hydrological monitoring indicator of the target monitoring point at each moment within the preset time period are combined into multidimensional hydrological data. The multidimensional hydrological data at all moments are combined into a multidimensional data sequence according to time sequence, which is denoted as the target multidimensional data sequence. The multidimensional data sequence corresponding to any other monitoring point is obtained and denoted as the multidimensional data sequence to be analyzed. The index of each multidimensional hydrological data is obtained according to the position of each multidimensional hydrological data in the target multidimensional data sequence and the multidimensional data sequence to be analyzed. A preset lag data sequence is obtained, where the minimum value in the preset lag data sequence is 0. For any lag data in the lag time sequence, the index of each multidimensional hydrological data in the multidimensional data sequence to be analyzed is subtracted from the index of any lag data to obtain a new index of each multidimensional hydrological data in the multidimensional data sequence to be analyzed. Based on the influence weight of each hydrological monitoring indicator, the new index of each multidimensional hydrological data in the multidimensional data sequence to be analyzed, and the index of each multidimensional hydrological data in the target multidimensional data sequence, the weighted Euclidean distance in the multidimensional space is calculated between each pair of multidimensional hydrological data with the same index and corresponding non-pollution times. The average value of all weighted Euclidean distances is calculated to obtain the degree of data difference between any other monitoring point and the target monitoring point under any lag data. The degree of data difference between any other monitoring point and the target monitoring point is obtained under each lag data in the lag data sequence. The minimum value of all data difference degrees is obtained. The negative of the minimum value is used as the independent variable of an exponential function with the natural constant as the base, so as to obtain the degree of influence of any other monitoring point on the water quality at the target monitoring point.

4. The water quality analysis and testing method based on sponge city engineering according to claim 3, characterized in that, The step of obtaining the influence weight of each hydrological monitoring indicator based on the consistency of data changes of each other monitoring point and the target monitoring point within the preset time period includes: For any hydrological monitoring indicator, if there is a pollution moment at the target monitoring point within the preset time period, then based on the monitoring data of the hydrological monitoring indicator at the target monitoring point at each non-pollution moment within the preset time period, the spline interpolation method is used to obtain the fitted data of the hydrological monitoring indicator at the target monitoring point at each pollution moment within the preset time period. The monitoring data of the hydrological monitoring indicator at the target monitoring point at each non-pollution moment within the preset time period and the fitted data at the pollution moment are combined to form a hydrological data sequence. If there is no pollution moment at the target monitoring point within the preset time period, then the monitoring data of the hydrological monitoring indicator at the target monitoring point at each moment within the preset time period are combined to form a hydrological data sequence. If the hydrological data sequence of any hydrological monitoring indicator at any other monitoring point is obtained within the preset time period, then the formula for calculating the consistency of the data changes of any hydrological monitoring indicator between the target monitoring point and the other monitoring point is as follows: ； in, d represents any one of the hydrological monitoring indicators, and d represents any other monitoring point. This indicates the degree of consistency in the data changes of any hydrological monitoring indicator between any other monitoring point and the target monitoring point. This indicates the number of all data points in a hydrological data series. This represents the difference between the i-th data point and the (i-1)-th data point in the hydrological data sequence corresponding to any of the aforementioned hydrological monitoring indicators at the target monitoring point. This represents the difference between the i-th data point and the (i-1)-th data point in the hydrological data sequence corresponding to any hydrological monitoring indicator at any other monitoring point. This represents a preset constant. Represents a linear normalization function; The consistency of data change of any hydrological monitoring indicator between each other monitoring point and the target monitoring point is obtained. All data consistency is clustered to obtain at least one cluster. The cluster with the most members is obtained. If there is only one cluster with the most members, the average of all data consistency in the cluster with the most members is calculated to obtain the data performance of any hydrological monitoring indicator. If there are at least two clusters with the most members, the average of all data consistency in the cluster with the most members is calculated for each cluster. The maximum value of the average value corresponding to each cluster with the most members is selected as the data performance of any hydrological monitoring indicator. The standard deviation of the monitoring data of any hydrological monitoring index at each monitoring point under all non-pollution times within the preset time period is obtained. The average of all standard deviations is normalized to obtain the fluctuation degree of any hydrological monitoring index. The influence weight of any hydrological monitoring indicator is obtained by calculating the product between the degree of fluctuation and the degree of data performance of each hydrological monitoring indicator.

5. The water quality analysis and testing method based on sponge city engineering according to claim 2, characterized in that, The step of obtaining the water quality contribution of any other monitoring point to the water quality monitoring indicators at the target monitoring point and the water quality impact lag time based on the correlation between the data changes of various water quality monitoring indicators between any other monitoring point and the target monitoring point within the preset time period includes: The monitoring data of various hydrological monitoring indicators at any other monitoring point within the preset time period at each non-pollution time are used to form multidimensional hydrological data. Multidimensional clustering is performed on all multidimensional hydrological data to obtain at least one cluster. The cluster containing the previous time of the current time is recorded as the target cluster. If any time in the target cluster is a non-pollution time at the target monitoring point, then that time is recorded as the target time. All target times in the target cluster are obtained, and at least two consecutive target times are used to form the time period to be analyzed. For any time period to be analyzed, the monitoring data of any water quality monitoring indicator at the target monitoring point at each time point in any time period to be analyzed are combined into a water quality data sequence. The first-order difference sequence of the water quality data sequence is obtained and recorded as the difference sequence of any water quality monitoring indicator at the target monitoring point in any time period to be analyzed. The difference sequence of any water quality monitoring indicator at any other monitoring point in any time period to be analyzed is also obtained. Map the difference sequences corresponding to the target monitoring point and any other monitoring point to a two-dimensional coordinate system to obtain waveforms corresponding to the target monitoring point and any other monitoring point, respectively. The horizontal axis of the two-dimensional coordinate system represents time, and the vertical axis represents the data in the difference sequence. Obtain a preset lag time series. For any lag time in the preset lag time series, shift the waveform corresponding to any other monitoring point in the opposite direction of the horizontal axis by any lag time. Calculate the Pearson correlation coefficient between the two waveforms corresponding to the overlapping part of the horizontal axis in the two-dimensional coordinate system to obtain the degree of correlation between any other monitoring point and the target monitoring point for any water quality monitoring indicator at any lag time. Obtain the correlation degree corresponding to each lag time in the preset lag time series, select the maximum value among all correlation degrees, and use it as the correlation feature value of any water quality monitoring indicator between any other monitoring point and the target monitoring point in any analysis period. Record the lag time corresponding to the correlation feature value as the delay time of any water quality monitoring indicator between any other monitoring point and the target monitoring point in any analysis period. Obtain the associated feature value and delay time corresponding to each of the time periods to be analyzed, calculate the average value of all associated feature values, obtain the water quality contribution of any other monitoring point to any water quality monitoring indicator at the target monitoring point, calculate the average value of all delay times, and obtain the water quality impact lag time of any other monitoring point to any water quality monitoring indicator at the target monitoring point.

6. The water quality analysis and testing method based on sponge city engineering according to claim 2, characterized in that, The process of obtaining the water quality response level of each water quality monitoring indicator at the target monitoring point based on the degree of influence of each other monitoring point on the water quality status at the target monitoring point, the degree of contribution of each other monitoring point to the water quality of each water quality monitoring indicator at the target monitoring point, and the water quality impact lag time includes: For any water quality monitoring indicator, calculate the product between the contribution of any other monitoring point to the water quality of the target monitoring point and the influence of any other monitoring point on the water quality status of the target monitoring point, and obtain the influence weight of any other monitoring point on the water quality monitoring indicator of the target monitoring point. Based on the lag time of the water quality impact of any other monitoring point on any water quality monitoring indicator at the target monitoring point, the current time is subtracted from the lag time of the water quality impact of any other monitoring point on any water quality monitoring indicator at the target monitoring point to obtain the water quality impact time. The monitoring data of any other water quality monitoring indicator at the water quality impact time is subtracted from the monitoring data at the time before the water quality impact time to obtain the change in water quality data of any other water quality monitoring indicator at the water quality impact time. Obtain the influence weight of each other monitoring point on any water quality monitoring indicator at the target monitoring point, and the change in water quality data of any water quality monitoring indicator at each other monitoring point at the time of water quality influence. Based on the weight corresponding to each other monitoring point, perform a weighted summation of the change in water quality data corresponding to each other monitoring point to obtain the water quality response degree of any water quality monitoring indicator at the target monitoring point.

7. The water quality analysis and testing method based on sponge city engineering according to claim 1, characterized in that, The step involves predicting the normal water quality data of any water quality monitoring indicator at the target monitoring point at the current time based on the monitoring data of any water quality monitoring indicator at the target monitoring point during each non-pollution time within the preset time period, and the water quality response degree of any water quality monitoring indicator at the target monitoring point, to obtain the final predicted value, including: If there is a pollution moment at the target monitoring point within the preset time period, then based on the monitoring data of any water quality monitoring indicator at the target monitoring point at each non-pollution moment within the preset time period, the spline interpolation method is used to obtain the fitted data of any water quality monitoring indicator at the target monitoring point at each pollution moment within the preset time period. The monitoring data of any water quality monitoring indicator at the target monitoring point at each non-pollution moment within the preset time period and the fitted data at the pollution moment are combined to form a normal water quality data sequence of any water quality monitoring indicator at the target monitoring point within the preset time period. If there is no pollution moment at the target monitoring point within the preset time period, then the monitoring data of any water quality monitoring indicator at the target monitoring point at each moment within the preset time period are combined to form a normal water quality data sequence. Based on the normal water quality data sequence, a preset prediction algorithm is used to predict the normal water quality data of any one of the water quality monitoring indicators at the target monitoring point at the current time, and an initial prediction value is obtained. The final predicted value is obtained by summing the water quality response level of any water quality monitoring indicator at the target monitoring point with the initial predicted value.

8. The water quality analysis and testing method based on sponge city engineering according to claim 1, characterized in that, The step of obtaining the degree of abnormality of any water quality monitoring indicator at the target monitoring point at the current moment based on the difference between the actual monitoring data and the final predicted value of any water quality monitoring indicator at the current moment includes: The absolute value of the difference between the actual monitoring data of any water quality monitoring indicator at the target monitoring point at the current moment and the final predicted value is calculated to obtain the degree of abnormality of any water quality monitoring indicator at the target monitoring point at the current moment.

9. The water quality analysis and testing method based on sponge city engineering according to claim 1, characterized in that, The process of detecting water quality anomalies at each monitoring point based on the degree of anomaly of various water quality monitoring indicators at the current moment includes: For any water quality monitoring indicator, the historical abnormality level of the water quality monitoring indicator at each monitoring point is obtained at each non-pollution time within the preset time period. Based on all historical abnormality levels, the normal range of the water quality monitoring indicator is obtained using the 3sigma principle. If the abnormality level of the water quality monitoring indicator at any monitoring point at the current time is not within the normal range, an abnormal alarm is triggered for the water quality monitoring indicator at any monitoring point.

10. A water quality analysis and testing system based on sponge city engineering, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the water quality analysis and testing method based on sponge city engineering as described in any one of claims 1-9.

Images