A river water quality exceeding standard grade prediction method based on multi-source data and interval estimation

Abstract

The application discloses a river water quality exceeding standard grade prediction method based on multi-source data and interval estimation, which comprises the following steps: collecting historical water quality data and historical rainfall condition data corresponding to the historical water quality data; screening water quality exceeding standard data in the historical water quality data, and classifying water quality grades; performing prediction interval calculation and analysis to obtain the mean upper and lower limit ranges of rainfall conditions corresponding to different water quality grades under a certain guarantee level, i.e., prediction intervals; performing normalization processing on the rainfall condition prediction intervals corresponding to each water quality grade; obtaining rainfall condition data of the next few days through weather forecasting, judging the prediction interval range to which the rainfall and the maximum rainfall intensity belong, and thus predicting the water quality exceeding standard grade corresponding to the rainfall condition under a specific guarantee level. The application is suitable for different river water body conditions, the analysis and prediction results are based on actual duration water quality monitoring data and rainfall condition data, and the application has the advantages of strong adaptability and easy operation.

Description

Technical Field

[0001] This invention belongs to the field of urban river flood season water environment prevention and control, and relates to river water quality prediction technology, specifically a method for predicting the level of river water quality exceeding standards based on multi-source data and interval estimation. Background Technology

[0002] The impact of flood season rainfall on water quality is an important research topic in urban river management. Although my country has achieved significant results in urban river management, and black and odorous water bodies have been largely successfully treated, flood season rainfall often leads to a large amount of rainwater runoff entering the rivers. This runoff typically carries pollutants from urban surfaces, including heavy metals, pesticides, household waste, and oil spills, resulting in the recurrence of blackening and foul odors in urban rivers after rain. Under heavy rainfall conditions, these pollutants can rapidly enter the river system, leading to significant deterioration of water quality.

[0003] Studies have shown that stormwater runoff is one of the main causes of urban river water quality exceeding standards. For example, research found that during rainfall events in Wuqing District, Tianjin, pollutant concentrations in rivers increased significantly, with a maximum decrease of approximately 67% (Yang et al., 2021). Similarly, in a study of the Nilwala River in Sri Lanka, rainfall significantly affected water quality indices, with total alkalinity being the most affected parameter (Garusinghe & Premarathn, 2024). The increased pollution following stormwater runoff not only threatens the ecological environment but also poses risks to human health. Under high flow conditions, the levels of microbial pollutants in river water increase significantly. Summary of the Invention

[0004] Purpose of the invention: In order to overcome the shortcomings of the existing technology, this invention provides a method for predicting the level of water quality exceeding standards in rivers based on multi-source data and interval estimation. It is applicable to different river water conditions. The analysis and prediction results are based on actual historical water quality monitoring data and rainfall conditions. It has the advantages of strong adaptability and easy operation, and has important guiding significance for ensuring the water environment quality of urban rivers during rainy days.

[0005] Technical Solution: To achieve the above objectives, this invention provides a method for predicting river water quality exceedance levels based on multi-source data and interval estimation, comprising the following steps:

[0006] S1: Collect historical water quality data and the corresponding historical rainfall conditions;

[0007] S2: Filter out water quality data that exceeds standards from historical water quality data and classify the water quality levels;

[0008] S3: Based on the water quality data processed in step S2 and the corresponding rainfall conditions data, perform prediction interval calculation and analysis to obtain the upper and lower limits of the average rainfall conditions corresponding to different water quality levels under a certain guarantee level, i.e., the prediction interval.

[0009] S4: Standardize the rainfall condition prediction intervals corresponding to each water quality level (Class III-IV, Class IV-V, and worse than Class V) to ensure the continuity and independence of the prediction intervals for each level.

[0010] S5: Obtain rainfall data for the next few days through weather forecasts, determine the predicted range of rainfall amount and maximum rainfall intensity, and thus predict the water quality exceedance level corresponding to the rainfall conditions under a specific guarantee level.

[0011] Furthermore, the historical water quality data in step S1 includes dissolved oxygen (DO), total phosphorus (TP), ammonia nitrogen (NH3-N), and permanganate index (COD). Mn The water quality data are taken as the maximum or minimum values ​​from the start to the end of the rainfall (dissolved oxygen is taken as the minimum value) within 24 hours.

[0012] Historical rainfall data includes rainfall amount and maximum rainfall intensity.

[0013] Furthermore, in step S2, the water quality levels are divided into Class III to IV, Class IV to V, and worse than Class V. The dissolved oxygen, total phosphorus, ammonia nitrogen, and permanganate index are assigned to the standard values ​​of Class III to IV, Class IV to V, and worse than Class V to determine the class to which the dissolved oxygen, total phosphorus, ammonia nitrogen, and permanganate index belong.

[0014] After filtering out the data that meets the range criteria, the monitoring data is changed to the corresponding water quality level. For example, if the ammonia nitrogen index belongs to Class III or IV and its value is 1.23, then it is changed to Class III or IV, and so on.

[0015] Furthermore, the calculation principle and method of the prediction interval in step S3 include:

[0016] Principle: When analyzing and calculating the prediction interval, the upper and lower limits of the mean within a certain prediction interval are given. This prediction interval provides an estimated range for the mean, telling us the possible range of the true population mean under a specific guarantee level. Common guarantee levels are 90%, 95%, and 99%, and the specific prediction interval range depends on the actual application requirements. Taking a 95% guarantee level as an example, the prediction interval for the mean consists of two parts: a lower limit and an upper limit. These two boundaries define a range, meaning that there is a 95% probability that the true population mean will fall within this range.

[0017] Calculation methods: Common formulas for calculating prediction intervals involve the sample mean, sample standard deviation, sample size, and critical values ​​for the t-distribution or z-distribution, depending on the sample size and whether the population standard deviation is known. Below are the formulas for the two most common scenarios:

[0018] When the population standard deviation is unknown and the sample size n < 30, use the interval formula for the t-distribution:

[0019]

[0020] In the formula, It is the sample mean; t * is the critical value of the t-distribution, which depends on the chosen guarantee level (e.g., 95%) and degrees of freedom n-1; s is the sample standard deviation; n is the sample size; 1 is the standard error (SE); PI is the prediction interval range.

[0021] When the population standard deviation is known or the sample size n ≥ 30, use the interval formula for the z-distribution:

[0022]

[0023] In the formula, It is the sample mean; z * σ is the critical value of the z-distribution; σ is the population standard deviation; n is the sample size. PI is the standard error (SE) and the prediction interval range.

[0024] Furthermore, the critical value t of the t-distribution involved in the calculation of the prediction interval in step S3... * Obtain it using the following formula:

[0025] t α / 2，df =T -1 (1-α / 2,df) (3)

[0026] Among them, T -1 It is the inverse cumulative distribution function of the t-distribution; α is the significance level; df is the degrees of freedom;

[0027] To implement formula (3), the critical value t is obtained using the following Python code. * :

[0028] import scipy.stats as st

[0029] #Guarantee Level

[0030] assurance_level = 0.95

[0031] #Degrees of freedom (sample size - 1)

[0032] degrees_of_freedom = 19

[0033] # Corresponding t value

[0034] t_value=st.t.ppf((1+assurance_level) / 2,degrees_of_freedom)

[0035] print(f"For the assurance level {assurance_level*100}% and the degrees of freedom {degrees_of_freedom}, the value of t is: {t_value:.4f}");

[0036] Among them, the assurance level can be replaced with other (0, 1) values ​​according to the usage requirements;

[0037] The critical z-distribution involved * Use the following formula to obtain:

[0038] z α / 2 =Φ -1 (1-α / 2) (4)

[0039] Where, Φ -1 It is the inverse cumulative distribution function of the standard normal distribution; α is the significance level; z α / 2 It is the critical value of the Z-distribution;

[0040] To implement formula (4), the critical z is obtained using the following Python code. * :

[0041] import scipy.stats as st

[0042] #Guarantee Level

[0043] assurance_level = 0.95

[0044] # Corresponding z value

[0045] z_value=st.norm.ppf((1+assurance_level) / 2)

[0046] print(f"For the assurance level {assurance_level*100}%, the z value is: {z_value:.4f}")

[0047] The assurance level can be replaced with other values ​​(0, 1) as needed.

[0048] Furthermore, the method for normalizing the prediction interval in step S4 is as follows:

[0049] 1) Based on the prediction interval formula, three intervals (Class III to IV, Class IV to V, and Class V worse) are calculated. Each interval contains two numbers, representing the start and end values ​​of the range;

[0050] 2) Extract all values ​​within the range and compile them into a separate list, while adjusting the results of the prediction interval calculation that are negative to 0;

[0051] 3) Remove outliers (such as 0), and sort the extracted values ​​to ensure they are arranged in ascending order;

[0052] 4) Based on the sorted points, redistribute continuous and non-overlapping ranges;

[0053] 5) The final output range is adjusted to ensure that it is continuous and does not overlap.

[0054] Furthermore, steps 3) to 5) can be quickly implemented using the following Python code:

[0055] ① If there are three sets of prediction intervals to process, use the following code:

[0056]

[0057] During code execution, [(27.8,51.7),(28.2,107.3),(0,147.0)] can be replaced with any three desired prediction interval ranges;

[0058] ② If the prediction interval to be processed has only two sets, then use the following code:

[0059]

[0060] During code execution, [(10.4,19.4),(6.8,24.0)] can be replaced with any two desired prediction interval ranges.

[0061] ③ If there is only one set of prediction intervals to be processed, then no normalization processing is required.

[0062] Furthermore, in step S5, when predicting the water quality level based on rainfall or maximum rainfall intensity, a lookup table should be created based on the predicted range obtained from the analysis, and the smallest predicted range should be selected. If the water quality level is below this predicted range, there is no risk of exceeding the standard.

[0063] Furthermore, in step S5, when predicting the water quality level based on rainfall or maximum rainfall intensity, if the water quality levels predicted by the rainfall and maximum rainfall intensity data are different, the predicted worse water quality level should be used.

[0064] Furthermore, in step S5, when predicting the water quality level based on rainfall or maximum rainfall intensity, if the rainfall or maximum rainfall intensity exceeds the upper limit of all prediction intervals, the water quality warning level is set to the water quality warning level corresponding to the maximum rainfall or rainfall intensity within the given prediction interval.

[0065] Beneficial effects: Most existing water quality prediction methods focus on monitoring techniques, machine learning, or deep learning methods, but do not fully consider the impact of rainy days during the flood season on river water quality, nor do they consider the risk of water quality exceeding standards under predicted rainfall conditions. This invention utilizes statistical analysis principles to combine the calculation and analysis of prediction intervals with historical monitoring data, and provides Python code to execute data calculation and processing. It supplements a water quality prediction method under rainfall conditions, achieving accurate prediction of water quality under rainfall conditions, and has strong adaptability and operability. It can be widely applied to the flood season water quality prediction work of different types of rivers. Attached Figure Description

[0066] Figure 1 This is a flowchart illustrating the method of the present invention. Detailed Implementation

[0067] The present invention will be further illustrated below with reference to the accompanying drawings and specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. After reading this invention, any modifications of the invention in various equivalent forms by those skilled in the art will fall within the scope defined by the appended claims.

[0068] like Figure 1 As shown, this invention provides a method for predicting the level of river water quality exceeding standards based on multi-source data and interval estimation, comprising the following steps:

[0069] S1: Collect historical water quality data and the corresponding historical rainfall conditions;

[0070] Historical water quality data include dissolved oxygen (DO), total phosphorus (TP), ammonia nitrogen (NH3-N), and permanganate index (COD). Mn The water quality data are taken as the maximum or minimum values ​​from the start to the end of the rainfall (dissolved oxygen is taken as the minimum value) within 24 hours.

[0071] The collected water quality and rainfall data were organized in the following format:

[0072]

[0073] S2: Filter out water quality data that exceeds standards from historical water quality data and classify the water quality levels;

[0074] Screening for dissolved oxygen (DO), total phosphorus (TP), ammonia nitrogen (NH3-N), and permanganate index (COD) respectively. Mn This applies to situations where the water quality falls into different levels (Class III-IV, Class IV-V, and worse than Class V). The screening criteria refer to the Surface Water Environmental Quality Standard GB3838-2002, and the standard range involved in the operational procedures includes:

[0075]

[0076]

[0077] After filtering out the data that meets the range criteria, the monitoring data is changed to the corresponding water quality level. For example, if the ammonia nitrogen index belongs to Class III or IV and its value is 1.23, then it is changed to Class III or IV, and so on.

[0078] S3: Based on the water quality data processed in step S2 and the corresponding rainfall conditions data, perform prediction interval calculation and analysis to obtain the upper and lower limits of the average rainfall conditions corresponding to different water quality levels under a certain guarantee level, i.e., the prediction interval.

[0079] The calculation principles and methods for the prediction interval include:

[0080] Principle: When analyzing and calculating the prediction interval, the upper and lower limits of the mean within a certain prediction interval are given. This prediction interval provides an estimated range for the mean, indicating the possible range of the true population mean at a specific guarantee level. Common guarantee levels are 90%, 95%, and 99%. The specific prediction interval range depends on the actual application requirements and is determined by the user based on the actual situation. Taking a 95% guarantee level as an example, the prediction interval for the mean consists of two parts: a lower limit and an upper limit. These two boundaries define a range, meaning that there is a 95% probability that the true population mean will fall within this range.

[0081] Calculation methods: Common formulas for calculating prediction intervals involve the sample mean, sample standard deviation, sample size, and the critical value of the t-distribution or z-distribution, depending on the sample size and whether the population standard deviation is known. The following are formulas for two scenarios:

[0082] When the population standard deviation is unknown and the sample size n < 30, use the interval formula for the t-distribution:

[0083]

[0084] In the formula, It is the sample mean; t* is the critical value of the t-distribution, which depends on the chosen guarantee level (e.g., 95%) and degrees of freedom n-1; s is the sample standard deviation; n is the sample size; 1 is the standard error (SE); PI is the prediction interval range.

[0085] When the population standard deviation is known or the sample size n ≥ 30, use the interval formula for the z-distribution:

[0086]

[0087] In the formula, It is the sample mean; z * σ is the critical value of the z-distribution; σ is the population standard deviation; n is the sample size. PI is the standard error, and PI is the prediction interval range.

[0088] The calculation of the prediction interval involves the critical value t of the t-distribution. * It can be obtained using the following formula:

[0089] t α / 2，df =T -1 (1-α / 2,df) (3)

[0090] Among them, T -1 It is the inverse cumulative distribution function (or PPF, Percent Point Function) of the t-distribution.

[0091] α is the significance level (e.g., for a 95% confidence level, α = 1 - 0.95 = 0.05).

[0092] df is the degree of freedom, usually calculated as n-1, where n is the sample size.

[0093] Based on formula (3), for ease of operation, the critical value t of the t-distribution involved in the calculation of the prediction interval is... * Alternatively, it can be obtained using the following Python code:

[0094] import scipy.stats as st

[0095] #Guarantee Level

[0096] assurance_level = 0.95

[0097] #Degrees of freedom (sample size - 1)

[0098] degrees_of_freedom = 19

[0099] # Corresponding t value

[0100] t_value=st.t.ppf((1+assurance_level) / 2,degrees_of_freedom)

[0101] print(f"For the assurance level {assurance_level*100}% and the degrees of freedom {degrees_of_freedom}, the value of t is: {t_value:.4f}");

[0102] During the use of the code, the degrees of freedom need to be modified according to the sample size n. In the example code, the sample size is 20, so the degrees of freedom is 19. The assurance level can be replaced with other (0, 1) values ​​as needed.

[0103] The critical z-distribution involved * Use the following formula to obtain:

[0104] z α / 2 =Φ -1 (1-α / 2) (4)

[0105] Where, Φ -1 It is the inverse cumulative distribution function (PPF) of the standard normal distribution.

[0106] α is the significance level (e.g., for a 95% confidence level, α = 1 - 0.95 = 0.05).

[0107] z α / 2 It is the critical value of the Z-distribution, used to calculate confidence intervals, etc.

[0108] Based on formula (4), for ease of operation, the critical z-distribution involved is... * This can be obtained through the following Python code:

[0109] import scipy.stats as st

[0110] #Guarantee Level

[0111] assurance_level = 0.95

[0112] # Corresponding z value

[0113] z_value=st.norm.ppf((1+assurance_level) / 2)

[0114] print(f"For the assurance level {assurance_level*100}%, the z value is: {z_value:.4f}")

[0115] The assurance level can be replaced with other values ​​(0, 1) as needed.

[0116] S4: Standardize the rainfall forecast intervals corresponding to each water quality level (Class III-IV, Class IV-V, and worse than Class V) to ensure the continuity and independence of the forecast intervals for each level. Specifically, this includes:

[0117] 1) Based on the prediction interval formula, three intervals (Class III to IV, Class IV to V, and Class V worse) are calculated. Each interval contains two numbers, representing the start and end values ​​of the range;

[0118] 2) Extract all values ​​within the range and compile them into a separate list, while adjusting the results of the prediction interval calculation that are negative to 0;

[0119] 3) Remove outliers (such as 0), and sort the extracted values ​​to ensure they are arranged in ascending order;

[0120] 4) Based on the sorted points, redistribute continuous and non-overlapping ranges;

[0121] 5) The final output range is adjusted to ensure that it is continuous and does not overlap.

[0122] Steps 3) to 5) can be quickly implemented using the following Python code:

[0123] ① If there are three sets of prediction intervals to process, use the following code:

[0124]

[0125]

[0126] During code execution, [(27.8,51.7),(28.2,107.3),(0,147.0)] can be replaced with any three desired prediction interval ranges;

[0127] ② If the prediction interval to be processed has only two sets, then use the following code:

[0128]

[0129]

[0130] During code execution, [(10.4,19.4),(6.8,24.0)] can be replaced with any two desired prediction interval ranges.

[0131] ③ If there is only one set of prediction intervals to be processed, then no normalization processing is required.

[0132] S5: Obtain rainfall data for the next few days through weather forecasts, determine the predicted range of rainfall amount and maximum rainfall intensity, and thus predict the water quality exceedance level corresponding to the rainfall conditions under a specific guarantee level.

[0133] When predicting water quality levels based on rainfall or maximum rainfall intensity, a lookup table should be created based on the prediction interval obtained from the analysis, as follows:

[0134]

[0135] Select the smallest prediction range; anything below this range is considered to have no risk of exceeding the limit.

[0136] When predicting water quality levels based on rainfall or maximum rainfall intensity, there may be situations where the water quality level determined based on rainfall data differs from that determined based on maximum rainfall intensity data. In such cases, the worst-case scenario, i.e., the scenario where the water quality level is determined to be worse, should be prioritized. In short, if the water quality levels predicted by rainfall and maximum rainfall intensity data differ, the predicted worse water quality level should be taken as the standard.

[0137] When predicting water quality levels based on rainfall or maximum rainfall intensity, if the rainfall or maximum rainfall intensity exceeds the upper limit of all prediction intervals, the water quality warning level for this prediction will be set to the level corresponding to the maximum rainfall or rainfall intensity within the given prediction interval.

[0138] Based on the above, in order to verify the effectiveness and effect of the method of the present invention, this embodiment applies the method of the present invention to an example, specifically including the following steps:

[0139] Step 1: The research object of this embodiment is a national monitoring section of a river in Nanjing. Dissolved oxygen (DO) monitoring data of the automatic monitoring station of this section from January 1, 2021 to September 1, 2023 were collected, where dissolved oxygen (DO) was the minimum value within 24 hours from the start to the end of rainfall;

[0140] Step 2: Collect rainfall and maximum rainfall intensity data from the meteorological station from January 1, 2021 to September 1, 2023, and compile them with water quality data into Table 1;

[0141] Table 1 Historical Rainfall and Water Quality Data for National Monitoring Sections

[0142]

[0143] Step 3: Data screening and processing. Screening was performed to identify water quality indicators falling into different water quality levels (Class III-IV, Class IV-V, and worse than Class V), and all dissolved oxygen (DO) monitoring values ​​were adjusted to the corresponding water quality levels, as shown in Table 2;

[0144] Table 2 Dissolved Oxygen (DO) Water Quality Levels

[0145]

[0146] Step 4: Calculate the prediction intervals corresponding to different water quality levels according to Table 2. In this case, we expect to obtain the water quality exceedance risk level with an 80% probability. Therefore, we ensure that the level is 80% during the calculation process and obtain the mean upper and lower limits of the rainfall conditions corresponding to different water quality levels, i.e., the prediction intervals. The results are summarized in Table 3.

[0147] Table 3. Prediction Interval Analysis Results

[0148]

[0149] Step 5: Prediction Interval Normalization. The prediction intervals for rainfall conditions corresponding to the water quality levels (Class III-IV, Class IV-V, and worse than Class V) in Table 3 are normalized to ensure the continuity and independence of the prediction intervals for each level. This process is implemented using Python code, and the results are shown in Table 4.

[0150] Table 4. Normalization results of prediction intervals

[0151]

[0152] Step 6: Forecasting. Obtain rainfall data for the next 7 days through weather forecasts, determine the predicted range of rainfall amount and maximum rainfall intensity, and thus predict the water quality level under 80% of the rainfall conditions. See Table 5 for specific implementation details. In the forecasting process, Day 4 is judged based on rainfall amount. According to Table 4, it should be classified as Class IV to V. However, if judged based on maximum rainfall intensity, it belongs to Class III to IV water quality. Considering the worst-case scenario as excellent, it is comprehensively judged as Class IV to V. The judgment logic for Day 5 is the same.

[0153] Table 5 Water Quality Prediction Results

[0154]

Claims

1. A method for predicting the level of exceedance of river water quality standards based on multi-source data and interval estimation, characterized in that, Includes the following steps: S1: Collect historical water quality data and the corresponding historical rainfall conditions; S2: Filter out water quality data that exceeds standards from historical water quality data and classify the water quality levels; S3: Based on the water quality data processed in step S2 and the corresponding rainfall conditions data, perform prediction interval calculation and analysis to obtain the mean upper and lower limits of rainfall conditions corresponding to different water quality levels under a 95% guarantee level, i.e., the prediction interval. S4: Standardize the rainfall forecast intervals corresponding to each water quality level to ensure the continuity and independence of the forecast intervals for each level. S5: Obtain rainfall data for the next few days through weather forecasts, determine the predicted range of rainfall amount and maximum rainfall intensity, and thus predict the water quality exceedance level corresponding to the rainfall conditions under an 80% guarantee level. The historical water quality data in step S1 includes dissolved oxygen, total phosphorus, ammonia nitrogen and permanganate index. The total phosphorus, ammonia nitrogen and permanganate index are taken as the maximum or minimum values ​​from the start to the end of the rainfall 24 hours, and the dissolved oxygen is taken as the minimum value. Historical rainfall data includes rainfall amount and maximum rainfall intensity; The method for normalizing the prediction interval in step S4 is as follows: 1) Based on the prediction interval formula, three intervals are calculated, namely Class III to IV, Class IV to V, and Class V (worst). Each interval contains two numbers, representing the start and end values ​​of the range. 2) Extract all values ​​within the range and compile them into a separate list, while adjusting the results of the prediction interval calculation that are negative to 0; 3) Remove outliers and sort the extracted values ​​to ensure they are arranged in ascending order; 4) Based on the sorted points, redistribute continuous and non-overlapping ranges; 5) The final output range is adjusted to ensure that it is continuous and does not overlap.

2. The method for predicting river water quality exceedance levels based on multi-source data and interval estimation according to claim 1, characterized in that, In step S2, the water quality levels are divided into Class III to IV, Class IV to V, and worse than Class V. The standard values ​​of dissolved oxygen, total phosphorus, ammonia nitrogen, and permanganate index are assigned to the ranges of Class III to IV, Class IV to V, and worse than Class V to determine the class to which dissolved oxygen, total phosphorus, ammonia nitrogen, and permanganate index belong.

3. The method for predicting river water quality exceedance levels based on multi-source data and interval estimation according to claim 1, characterized in that, The method for calculating the prediction interval in step S3 includes: When the population standard deviation is unknown and the sample size n < 30, use the interval formula for the t-distribution: PI= (1); In the formula, It is the sample mean; This is the critical value of the t-distribution; n is the sample standard deviation; n is the sample size. Standard error; PI is the prediction interval range; When the population standard deviation is known or the sample size n ≥ 30, use the interval formula for the z-distribution: PI= (2); In the formula, It is the sample mean; For the critical z-distribution; n is the population standard deviation; n is the sample size. PI is the standard error, and PI is the prediction interval range.

4. The method for predicting river water quality exceedance levels based on multi-source data and interval estimation according to claim 3, characterized in that, The critical value of the t-distribution involved in the calculation of the prediction interval in step S3. Obtain it using the following formula: ； in, It is the inverse cumulative distribution function of the t-distribution; It is the significance level; It refers to degrees of freedom; obtained through calculation. That is, the critical value. ; The critical value of the z-distribution involved Use the following formula to obtain: (4)； in, It is the inverse cumulative distribution function of the standard normal distribution; It is the significance level; It is the critical value of the Z-distribution, that is, the critical value. .

5. The method for predicting river water quality exceedance levels based on multi-source data and interval estimation according to claim 1, characterized in that, In step S5, when predicting the water quality level based on rainfall or maximum rainfall intensity, a lookup table is created based on the predicted range obtained from the analysis. The smallest predicted range is selected, and anything below this predicted range is considered to have no risk of exceeding the standard.

6. The method for predicting river water quality exceedance levels based on multi-source data and interval estimation according to claim 1, characterized in that, In step S5, when predicting the water quality level based on rainfall or maximum rainfall intensity, if the water quality levels predicted by the rainfall and maximum rainfall intensity data are different, the worse predicted water quality level shall prevail.

7. The method for predicting river water quality exceedance levels based on multi-source data and interval estimation according to claim 1, characterized in that, In step S5, when predicting the water quality level based on rainfall or maximum rainfall intensity, if the rainfall or maximum rainfall intensity exceeds the upper limit of all prediction intervals, the water quality warning level is set to the water quality warning level corresponding to the maximum rainfall or rainfall intensity in the given prediction interval.

Images