Water quality intelligent evaluation and processing system fusing multi-dimensional space-time data

Abstract

The application provides a water quality intelligent evaluation and processing system for fusing multi-dimensional space-time data, and relates to the technical field of data analysis, wherein the system comprises: obtaining water quality detection data and land type data of a target water area, analyzing the water quality detection data, performing correlation analysis on the water quality analysis result and the land type data, extracting algal biological index data, and performing coupling analysis with the water quality analysis result, using a multi-level progressive judgment path to determine and analyze the correlation analysis result and the water body health state characteristics, and managing the target water area based on the target water quality grade. The technical problem of low water quality evaluation accuracy and early warning lag caused by isolated water quality evaluation dimension in the prior art is solved. Through multi-dimensional fusion of water area space-time water quality data, land type data and algal biological indexes, accurate grading diagnosis of water quality is realized, the overall accuracy of water quality evaluation is improved, and the technical effect of early warning lag is improved.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically to a water quality intelligent assessment and treatment system that integrates multidimensional spatiotemporal data. Background Technology

[0002] Traditional water quality assessment methods typically rely on the regular collection and laboratory analysis of water samples from various monitoring sections to obtain conventional physicochemical indicators such as dissolved oxygen, chemical oxygen demand, ammonia nitrogen, and total phosphorus. These indicators are then compared item by item with surface water environmental quality standards, and the water quality category is determined based on the exceedance of standards. However, existing assessment systems do not analyze land use types in the catchment area, making it impossible to identify the direction and intensity of the impact of different land use types on water quality indicators at the source. Furthermore, existing assessment methods rely excessively on the compliance determination of chemical indicators, neglecting the actual health status of the aquatic ecosystem. For example, when conventional indicators such as dissolved oxygen and ammonia nitrogen have not yet exceeded standards, the algal community structure may have already undergone significant changes due to the continuous input of nutrients. These early degradation signals at the ecological level are completely missing in traditional assessment systems, resulting in a serious lag in early warning of water quality deterioration.

[0003] Existing technologies suffer from isolated dimensions in water quality assessment, leading to low accuracy and delayed early warning. Summary of the Invention

[0004] The purpose of this application is to provide a water quality intelligent assessment and processing system that integrates multi-dimensional spatiotemporal data, in order to solve the technical problems of isolated water quality assessment dimensions in existing technologies, which leads to low accuracy of water quality assessment and delayed early warning.

[0005] In view of the above problems, this application provides a water quality intelligent assessment and processing system that integrates multi-dimensional spatiotemporal data. The system includes: a data acquisition module for acquiring water quality detection data from multiple monitoring sections of a target water area and corresponding land type data of the catchment area; a data parsing module for retrieving water quality parsing strategies to parse the water quality detection data and obtain water quality parsing results; a correlation analysis module for performing correlation analysis on any indicator parameter corresponding to any water quality indicator in the water quality parsing results and any area ratio corresponding to any use type in the land type data to obtain correlation analysis results; a coupling analysis module for extracting algal biometric data from the water quality detection data and performing coupling analysis with the water quality parsing results to obtain the water health status characteristics of the target water area during periods of water quality deterioration; a judgment analysis module for using a multi-level progressive judgment path to perform judgment analysis on the correlation analysis results and the water health status characteristics to obtain a target water quality level; and a water area management module for managing the target water area based on the target water quality level.

[0006] Optionally, the raw data acquisition unit is used to acquire raw detection data of the target water area at the multiple monitoring sections; the raw data processing unit is used to transmit the raw detection data to the cloud, and use cloud computing power to perform noise reduction and calibration processing on the raw detection data to generate calibrated detection data, which is recorded as the water quality detection data.

[0007] Optionally, the first processing result acquisition subunit is used to smooth the original detection data using a sliding window filter to obtain a first processing result; the second processing result acquisition subunit is used to remove interference from the first processing result using a median filter to obtain a second processing result; and the water quality detection data acquisition subunit is used to perform reverse compensation on the second processing result using the target response curve of the target sensor in a standard water environment to obtain the water quality detection data.

[0008] Optionally, the time-series analysis result acquisition unit is used to extract time-dimensional data from the water quality testing data, perform time-series trend analysis on the time-dimensional data, and obtain time-series analysis results for predetermined water quality indicators; the spatial analysis result acquisition unit is used to extract spatial-dimensional data from the water quality testing data, and perform horizontal comparison of the spatial-dimensional data according to the upstream, midstream, and downstream zones of the target water area, and identify the spatial analysis results corresponding to each zone in the upstream, midstream, and downstream areas; the water quality analysis result acquisition unit is used to combine the time-series analysis results and the spatial analysis results to form the water quality analysis result.

[0009] Optionally, the predetermined water quality indicators include at least dissolved oxygen, chemical oxygen demand, ammonia nitrogen, and total phosphorus.

[0010] Optionally, the first utilization type acquisition unit is used to acquire a first utilization type from the land type data, wherein the first utilization type corresponds to a first area ratio; the first indicator parameter acquisition unit is used to acquire a first indicator parameter corresponding to a first water quality indicator in the water quality analysis results; the correlation coefficient calculation unit is used to calculate the Pearson correlation coefficient between the first area ratio and the first indicator parameter to obtain a first correlation coefficient; the positive effect type marking unit is used to mark the first utilization type as a positive effect type if the first correlation coefficient is positive and its absolute value exceeds a first correlation threshold; and the negative effect type marking unit is used to mark the first utilization type as a negative effect type if the first correlation coefficient is negative and its absolute value exceeds the first correlation threshold.

[0011] Optionally, the indicator data extraction unit is used to extract the chlorophyll a concentration and algal density from the algal biological indicator data; the ratio calculation unit is used to calculate the ratio of the chlorophyll a concentration to the algal density to obtain the chlorophyll index per unit algal mass; the first time period acquisition unit is used to acquire the first time period corresponding to the water quality deterioration period in the water quality analysis results, and extract the first mean value of the chlorophyll index per unit algal mass within the first time period; the second time period acquisition unit is used to acquire the second time period corresponding to the water quality good period, and extract the second mean value of the chlorophyll index per unit algal mass within the second time period; the deviation amplitude calculation unit is used to compare the first mean value with the second mean value to obtain the deviation amplitude, and if the deviation amplitude exceeds a first predetermined threshold, the water health status characteristics are obtained.

[0012] Optionally, the indicator data analysis unit is used to analyze the algal biological indicator data to obtain algal species composition data, the algal species composition data including multiple algal species concentrations corresponding to each of the multiple algal species; the logarithmic transformation unit is used to perform a logarithmic transformation on the first algal species concentration among the multiple algal species concentrations to obtain a first logarithmic concentration; the algal species dominance acquisition unit is used to record the ratio of the first logarithmic concentration to the sum of the logarithmic concentrations of the multiple algal species as the first algal species dominance; the difference calculation unit is used to calculate the difference between the first time period mean of the first algal species dominance during the water quality deterioration period and the second time period mean of the first algal species dominance during the water quality good period in the water quality analysis results, and if the difference exceeds a second predetermined threshold, the health status characteristic is obtained.

[0013] Optionally, the system includes a turbidity and chromaticity data acquisition unit for acquiring turbidity and chromaticity data from the water quality testing data; a first-level water quality grade output unit for outputting a first-level water quality grade if the turbidity data is lower than a first turbidity threshold and the chromaticity data is lower than a first chromaticity threshold; a turbidity and chromaticity data judgment unit for acquiring chemical oxygen demand (COD) and ammonia nitrogen (AM) data from the water quality testing data if the turbidity data is not lower than the first turbidity threshold or the chromaticity data is not lower than the first chromaticity threshold; and a second-level water quality grade output unit for outputting a second-level water quality grade if the COD data is lower than the first COD threshold and the AM nitrogen data is lower than the first COD threshold. The system outputs a secondary water quality level based on a first ammonia nitrogen threshold. A type acquisition unit is used to acquire the positive and negative effect types in the correlation analysis results if the chemical oxygen demand (COD) data is not lower than the first COD threshold or the ammonia nitrogen data is not lower than the first ammonia nitrogen threshold. A type ratio judgment unit is used to acquire the water body health status characteristics if the ratio of the number of positive effect types to the number of negative effect types is lower than a first ratio threshold. A tertiary water quality level output unit is used to output a tertiary water quality level if the deviation in the water body health status characteristics exceeds a third threshold or the difference exceeds a fourth threshold.

[0014] Optionally, the emission data acquisition unit is used to acquire pollution source emission data of the target water area, the pollution source emission data including multiple emission index parameters corresponding to multiple pollution sources; the pollution source contribution rate acquisition unit is used to use the positive effect type and negative effect type in the correlation analysis results as prior constraints, and combine the pollution source emission data to perform factor decomposition analysis on the water quality analysis results to obtain the contribution rate of each pollution source; the priority ranking unit is used to rank the treatment priorities of the target water area based on the contribution rate of each pollution source.

[0015] One or more technical solutions provided in this application have at least the following technical effects or advantages: The system provided in this application includes a data acquisition module for acquiring water quality monitoring data from multiple monitoring sections of a target water area and corresponding land type data of the catchment area; a data parsing module for retrieving water quality parsing strategies to parse the water quality monitoring data and obtain water quality parsing results; a correlation analysis module for performing correlation analysis on any indicator parameter corresponding to any water quality indicator in the water quality parsing results and any area ratio corresponding to any use type in the land type data to obtain correlation analysis results; a coupling analysis module for extracting algal biometric data from the water quality monitoring data and performing coupling analysis with the water quality parsing results to obtain the water health status characteristics of the target water area during the period of water quality deterioration; a judgment analysis module for using a multi-level progressive judgment path to perform judgment analysis on the correlation analysis results and the water health status characteristics to obtain the target water quality level; and a water area management module for managing the target water area based on the target water quality level. This achieves the technical effect of achieving precise water quality classification and diagnosis through multi-dimensional fusion of water quality data in time and space, land type data, and algal biometrics, improving the comprehensiveness and accuracy of water quality assessment, and reducing early warning lag.

[0016] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the structure of a water quality intelligent assessment and treatment system that integrates multi-dimensional spatiotemporal data, as provided in this application.

[0019] Figure 2 This is a schematic diagram of the data parsing module in a water quality intelligent assessment and treatment system that integrates multi-dimensional spatiotemporal data, as provided in this application.

[0020] Figure labeling: Data acquisition module 10, data parsing module 20, correlation analysis module 30, coupling analysis module 40, judgment analysis module 50, water area management module 60, time series analysis result acquisition unit 21, spatial analysis result acquisition unit 22, water quality analysis result acquisition unit 23. Detailed Implementation

[0021] This application provides a water quality intelligent assessment and processing system that integrates multi-dimensional spatiotemporal data. This system addresses the technical problems of existing technologies where isolated dimensions in water quality assessment lead to low accuracy and delayed early warnings. It achieves precise water quality grading and diagnosis through multi-dimensional fusion of spatiotemporal water quality data, land type data, and algal bioindicators, thereby improving the comprehensiveness and accuracy of water quality assessment and mitigating delayed early warnings.

[0022] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0023] like Figure 1 , Figure 2 As shown, this application provides a water quality intelligent assessment and treatment system that integrates multi-dimensional spatiotemporal data. The water quality intelligent assessment and treatment system that integrates multi-dimensional spatiotemporal data includes: The data acquisition module 10 is used to acquire water quality test data from multiple monitoring sections of the target water area and land type data of the corresponding catchment area.

[0024] Furthermore, the data acquisition module 10 includes: a raw data acquisition unit, used to acquire raw detection data of the target water area at the multiple monitoring sections; and a raw data processing unit, used to transmit the raw detection data to the cloud, and use cloud computing power to perform noise reduction and calibration processing on the raw detection data to generate calibrated detection data, which is recorded as the water quality detection data.

[0025] Specifically, based on the hydrogeographic characteristics of the target water area, such as river length, lake / reservoir area, and tributary confluence locations, multiple monitoring sections are deployed at key locations in the target water area, including upstream background sections, midstream control sections, and downstream reduction sections, in accordance with water quality monitoring standards. Online monitoring stations are configured at each of these monitoring sections. These online monitoring stations integrate various water quality sensor arrays, including but not limited to: dissolved oxygen electrochemical sensors, ammonia nitrogen ion-selective electrodes, chemical oxygen demand ultraviolet spectroscopy sensors, total phosphorus molybdenum blue colorimetric sensors, chlorophyll a fluorescence sensors, and algae counting sensors. Based on the multiple water quality sensor arrays integrated into the online monitoring stations, raw detection data of the target water area at multiple monitoring sections are collected in real time. This raw detection data is then transmitted to the cloud in real time via 4G / 5G wireless communication networks or wired fiber optic networks. The cloud server utilizes cloud computing power to perform noise reduction and calibration processing on the raw detection data. This cloud processing improves the reliability and accuracy of the collected data while reducing the power consumption and cost requirements of on-site equipment. The calibrated test data is recorded as water quality test data. The water quality test data includes at least the following: conventional physicochemical indicators such as dissolved oxygen, chemical oxygen demand, ammonia nitrogen, and total phosphorus, as well as algal biological indicators such as chlorophyll a concentration, algal density, and algal species composition, and also includes turbidity data and color data.

[0026] While acquiring water quality monitoring data from multiple monitoring sections, land type data of the target water catchment area are obtained through remote sensing imagery or land survey data. The catchment area refers to the water area above all monitoring sections of the target water where rainfall runoff ultimately flows into the water. Its boundary is determined by hydrological analysis using a digital elevation model. Land type data includes categories such as cultivated land, forest land, grassland, water area, construction land, and unused land. The proportion of each type of land area to the total area of ​​the catchment area is calculated and recorded as the area ratio.

[0027] By acquiring water quality monitoring data from multiple monitoring sections of the target water area and land type data of the corresponding catchment area, basic data in both water and land dimensions are provided for water quality assessment, thereby improving the reliability and accuracy of intelligent water quality assessment.

[0028] Furthermore, the raw data processing unit includes: a first processing result acquisition subunit, used to smooth the raw detection data using a sliding window filter to obtain a first processing result; a second processing result acquisition subunit, used to remove interference from the first processing result using a median filter to obtain a second processing result; and a water quality detection data acquisition subunit, used to perform reverse compensation on the second processing result using the target response curve of the target sensor in a standard water environment to obtain the water quality detection data.

[0029] Specifically, after the raw test data is transmitted to the cloud, the cloud server uses a sliding window filtering method to smooth various water quality indicators in the raw test data. A fixed-width sliding window is set, preferably N=3 or N=7, and is adaptively adjusted according to the degree of data fluctuation. The standard deviation σ of the data within the sliding window is calculated. If σ exceeds 15% of the historical average of the corresponding indicator, it indicates drastic water quality changes in the current period, and N is automatically reduced to 3 to retain details of rapid changes. If σ is lower than 15% of the historical average of the corresponding indicator, N is expanded to 7 to enhance the smoothing effect. Starting from the beginning of the raw test data, the sliding window is moved forward point by point. At each sliding window position, the arithmetic mean of all data points within the window is taken as the smoothed output value at the center of that sliding window, which can preserve low-frequency trends while effectively reducing noise amplitude. The first processing result is obtained through sliding window filtering.

[0030] The first processing result is then subjected to median filtering to remove pulse interference present in the field monitoring environment, such as instantaneous mechanical vibration caused by fish colliding with the sensor probe, sudden drop in light signal caused by floating objects briefly obscuring the optical window, or transient power surges induced by lightning strikes. Specifically, a sliding window of width N is used, and all data points within the window are sorted in ascending order of value. The value at the middle position of the sorted sequence is then taken as the output result at the current moment. Median filtering is then applied to obtain the interference-removed second processing result. The second processing result is then corrected by using the target response curve established during the target sensor's factory calibration or the most recent field calibration to perform reverse compensation calibration. The target response curve refers to the target response curve obtained by applying a series of standard solutions of known concentrations to the target sensor in a standard water environment (i.e., using a standard solution system of known concentrations, with the temperature controlled at 25±0.5℃, and the ionic strength uniformly adjusted by the background electrolyte), recording the output signal values ​​of the target sensor at each concentration point, and then fitting the mapping relationship between the target sensor output signal and the actual concentration using the least squares method. For example, the target response curve can be expressed as a quadratic polynomial in the form C=a·V. 2+b·V+c, where V is the target sensor output electrical signal, C is the standard concentration value, and a, b, and c are fitting coefficients. The second processed result Vmeas obtained from the current measurement is substituted into the inverse function of the target response curve to perform inversion calculation Ctrue= f -1 (Vmeas,T), where T is the current water sample temperature, used to introduce temperature compensation correction, and f is the target response curve obtained from calibration. -1 This is the inverse function of the target response curve, used to calculate the corresponding concentration value based on the current measured electrical signal. The reverse compensation step effectively eliminates the effects of individual sensor differences and time-varying drift, improving the authenticity, accuracy, and reliability of the final output water quality detection data.

[0031] For example, by calling the target response curve obtained from the calibration of the target dissolved oxygen sensor, the relationship between the dissolved oxygen concentration C and the output current I is C = 0.426·I. 2 -0.315·I+0.052, temperature compensation coefficient is 0.028 mg / L·℃ -1 Substituting the median filter output value I = 6.87 μA into the inverse function of the target response curve, and considering temperature compensation at the current water temperature of 28.6℃ (3.6℃ higher than the calibration temperature of 25℃), the dissolved oxygen solubility decreases. The compensation amount is 0.028 × 3.6 = 0.1008 mg / L. The final calculated calibrated dissolved oxygen concentration is 0.426 × (6.87) 2 -0.315×6.87+0.052-0.1008≈17.90mg / L.

[0032] By smoothing, interference removal, and reverse compensation of sensor response curves, random noise and abnormal interference in field monitoring data are effectively filtered out, sensor detection deviation and drift error are corrected, thereby improving the accuracy and stability of water quality detection data.

[0033] The data parsing module 20 is used to retrieve the water quality analysis strategy to analyze the water quality detection data and obtain the water quality analysis results.

[0034] Furthermore, the data parsing module 20 includes: a time-series parsing result acquisition unit 21, used to extract time-dimensional data from the water quality testing data, perform time-series trend analysis on the time-dimensional data, and obtain time-series parsing results for predetermined water quality indicators; a spatial parsing result acquisition unit 22, used to extract spatial-dimensional data from the water quality testing data, and perform horizontal comparison of the spatial-dimensional data according to the upstream, midstream, and downstream zones of the target water area, and identify the spatial parsing results for each zone corresponding to the upstream, midstream, and downstream; and a water quality parsing result acquisition unit 23, used to combine the time-series parsing results and the spatial parsing results to form the water quality parsing result.

[0035] Furthermore, the predetermined water quality indicators include at least dissolved oxygen, chemical oxygen demand, ammonia nitrogen, and total phosphorus.

[0036] Specifically, time-dimensional data of predetermined water quality indicators are extracted from water quality testing data. This refers to the concentration sequence of predetermined water quality indicators recorded at different sampling time points at each monitoring section. The predetermined water quality indicators include at least dissolved oxygen, chemical oxygen demand (COD), ammonia nitrogen, and total phosphorus. Dissolved oxygen refers to the molecular oxygen content dissolved in water, measured in mg / L. It is a key parameter characterizing the self-purification capacity of water bodies and the living conditions of aerobic organisms. Chemical oxygen demand (COD) refers to the amount of oxidant consumed when treating water samples with strong oxidants, such as potassium dichromate, under certain conditions, measured in mg / L. It is used to reflect the degree of pollution of reducing substances in water bodies. Ammonia nitrogen refers to the nitrogen content existing in the form of free ammonia and ammonium ions, measured in mg / L. It mainly comes from the decomposition of nitrogen-containing organic matter in domestic sewage and industrial wastewater. Total phosphorus refers to the total concentration of phosphorus in various forms in water bodies, measured in mg / L. It is an important indicator for measuring the degree of eutrophication of water bodies.

[0037] The time series decomposition method is used to perform time series trend analysis on the concentration sequence of each predetermined water quality indicator within a historical window. For example, the historical window is the past 30 days, with a total of 180 sampling time points, one every 4 hours. The concentration sequence of each predetermined water quality indicator is used as input, and it is additively decomposed into trend component, seasonal component, and residual component using the STL algorithm. The trend component is extracted by smoothing the concentration sequence of the predetermined water quality indicator through local weighted regression, reflecting the overall trend of the water quality indicator on a longer time scale, such as a continuous increase in ammonia nitrogen concentration or a continuous decrease in dissolved oxygen. The seasonal component is extracted by calculating the phase of the same period, such as the 24-hour daily period, i.e., the mean of 6 sampling points in each period, and smoothing it, reflecting the regular fluctuation of water quality on the daily scale, such as the increase of dissolved oxygen due to photosynthesis during the day and the decrease due to respiration at night. The residual component is the random fluctuation part remaining after removing the trend and seasonal components from the original sequence. Linear regression fitting is performed on the trend components over a continuous time window, such as six consecutive time points (i.e., 24 hours), and the slope k of the change is calculated. For pollution indicators such as ammonia nitrogen, chemical oxygen demand, and total phosphorus, if k is positive, or if k is negative for positive indicators such as dissolved oxygen, and the cumulative change of the trend, i.e., the concentration difference from the start to the end, exceeds 20% of the historical average threshold of the predetermined water quality indicator, then the continuous period is marked as a period of water quality deterioration. Conversely, if the trend components of all predetermined water quality indicators do not fluctuate by more than ±10% of the historical average within a continuous 48-hour period, and the seasonal components within the same period are within the normal fluctuation range, i.e., do not exceed 1.5 times the standard deviation of the seasonal components in the same historical period, then the period is marked as a period of good water quality. The final output time series analysis results include the deterioration / good period label for each indicator, the trend slope k value, the cumulative change magnitude, and the start and end timestamps.

[0038] Spatial dimension data is extracted from water quality monitoring data. This spatial dimension data refers to the concentration values ​​of water quality indicators simultaneously measured at monitoring sections upstream, midstream, and downstream of the target water body at the same sampling time point. Upstream refers to the background section closest to the source and least affected by human activities within the target water body, typically located at the inflow boundary of the catchment area or the river section before the confluence of large tributaries. Midstream refers to the control section in the midstream of the target water body that passes through densely populated urban or agricultural areas and has the most complex pollution input. Downstream refers to the reduction section near the outlet or confluence with the next level of water body within the target water body. Then, the predetermined water quality indicators of each zone at the same time point are compared horizontally, and the longitudinal difference index (LDI) is used to quantify the degree of water quality change between adjacent zones: LDI = |C| i -C i-1 | / C i-1 ×100%, where C i For the current partition, such as the midstream or downstream indicator concentration value, C i-1 For adjacent upstream zones, such as upstream or midstream, the LDI (Liquidity Distribution Index) is used to determine the concentration values ​​of the indicator. If the LDI between a zone and its upstream neighbor exceeds 30%, that zone is marked as a zone of significant water quality change. The spatial characteristics of this change, such as an increase or decrease in concentration, are recorded to obtain spatial analysis results. The temporal analysis results are combined with the spatial analysis results to form the overall water quality analysis result, which includes both temporal and spatial analysis results of the water quality monitoring data.

[0039] For example, from 00:00 on July 20, 2025 to July 22, 2025, data was collected every 4 hours, resulting in 18 data points for the ammonia nitrogen concentration sequence over 72 hours. The temporal trend of the ammonia nitrogen concentration sequence is as follows: From 00:00 on July 20 to 08:00 on July 21, the ammonia nitrogen concentration gradually increased from 0.51 mg / L to 0.92 mg / L, showing a monotonically increasing trend for 8 consecutive time points, with a cumulative increase of 80.4%, exceeding the 20% threshold of the historical average of 0.65 mg / L, i.e., an increase exceeding 0.13 mg / L. Based on this, this time window is marked as the water quality deterioration period, starting at 00:00 on July 20, 2025 and ending at 08:00 on July 21, 2025, with a peak concentration of 0.92 mg / L and a slope of +0.0128 mg / L·h. -1From 00:00 to 24:00 on July 22, dissolved oxygen remained stable between 7.6 and 7.8 mg / L, chemical oxygen demand (COD) between 12 and 13 mg / L, ammonia nitrogen between 0.31 and 0.34 mg / L, and total phosphorus between 0.08 and 0.10 mg / L. The concentration fluctuations of these four indicators did not exceed ±10% of their respective historical averages, and all met the surface water standard limits, namely dissolved oxygen ≥ 5 mg / L, COD ≤ 20 mg / L, ammonia nitrogen ≤ 1.0 mg / L, and total phosphorus ≤ 0.2 mg / L. Therefore, this 24-hour window was marked as a period of excellent water quality.

[0040] Spatial data were extracted at 06:00 on July 21, 2025. The ammonia nitrogen concentration at the upstream section was 0.55 mg / L, the concentration at the midstream section surged to 0.92 mg / L, and the concentration at the downstream section was 0.88 mg / L. The longitudinal difference index (LDI) was calculated. 中游-上游 =|0.92-0.55| / 0.55×100%=67.3%, which is greater than the 30% threshold. Therefore, the midstream section is marked as a zone of significant water quality change, with the direction being upward, indicating increased pollution. The temporal and spatial analysis results are then combined to form the final water quality analysis result.

[0041] By analyzing water quality testing data from both temporal and spatial dimensions, we can comprehensively reflect the dynamic changes in water quality, avoid the one-sidedness of traditional static single-point evaluation, effectively determine the temporal evolution characteristics of water quality and the differences in upstream and downstream spatial distribution, and improve the comprehensiveness and accuracy of water quality analysis.

[0042] The correlation analysis module 30 is used to perform correlation analysis on any indicator parameter corresponding to any water quality indicator in the water quality analysis results and any area ratio corresponding to any use type in the land type data, and obtain the correlation analysis results.

[0043] Furthermore, the correlation analysis module 30 includes: a first utilization type acquisition unit, used to acquire a first utilization type in the land type data, the first utilization type corresponding to a first area ratio; a first indicator parameter acquisition unit, used to acquire a first indicator parameter corresponding to a first water quality indicator in the water quality analysis results; a correlation coefficient calculation unit, used to calculate the Pearson correlation coefficient between the first area ratio and the first indicator parameter to obtain a first correlation coefficient; a positive effect type marking unit, used to mark the first utilization type as a positive effect type if the first correlation coefficient is positive and its absolute value exceeds a first correlation threshold; and a negative effect type marking unit, used to mark the first utilization type as a negative effect type if the first correlation coefficient is negative and its absolute value exceeds the first correlation threshold.

[0044] Specifically, any land use type is selected from the land type data as the first use type, and the corresponding first area ratio is obtained. An arbitrary predetermined water quality indicator, such as ammonia nitrogen, is obtained from the water quality analysis results as the first water quality indicator, and the corresponding first indicator parameter is obtained, such as the average ammonia nitrogen data of each monitoring section. It should be noted that the term "first" in the above terminology is used to distinguish similar objects. Then, the Pearson correlation coefficient formula is used to calculate the first area ratio and the first indicator parameter. The expression for the Pearson correlation coefficient r is: Where n is the actual number of monitoring sections deployed within the target water area, and x i Let x̄ be the area ratio of this land use type within the catchment area of ​​the i-th monitoring section, x̄ be the mean of the area ratios of all monitoring sections, and ȳ be the mean of the area ratios of all monitoring sections. i Let denoted as the mean of the water quality index at the i-th monitoring section, and ȳ as the mean of the mean of the index across all monitoring sections. The Pearson correlation coefficient ranges from -1 to 1, with positive values ​​indicating a positive correlation between the area ratio and the index parameter, and negative values ​​indicating a negative correlation. The closer the absolute value is to 1, the stronger the linear correlation. By pairwise combining any predetermined water quality index from the water quality analysis results with any land use type from the land type data, the correlation coefficient for each combination is calculated using the method described above.

[0045] A first correlation threshold is set to determine whether a significant correlation exists. For example, a first correlation threshold of 0.6 corresponds to the critical correlation coefficient at the statistical significance level of r < 0.05, ensuring the statistical reliability of the correlation results. The effect type is determined based on the first correlation coefficient: if the first correlation coefficient is positive and its absolute value is greater than the first correlation threshold, the first land use type is marked as a positive effect type, indicating that this land use type has a positive effect on water quality improvement. If the first correlation coefficient is negative and its absolute value is greater than the first correlation threshold, the first land use type is marked as a negative effect type, indicating that this land use type has a negative effect on water quality deterioration. For example, construction land, due to its large impermeable area, leads to increased concentrations of ammonia nitrogen and chemical oxygen demand in downstream water bodies. If the absolute value of the correlation coefficient for a combination does not exceed 0.6, the land use type corresponding to that combination is not marked as any effect type and is considered to have no significant statistical association with water quality.

[0046] By calculating the Pearson correlation coefficient by pairwise combining the index parameters corresponding to any water quality index in the water quality analysis results with the area ratio corresponding to any land use type in the land type data, a quantitative analysis of the correlation between all land use types and all water quality indicators is achieved. Based on this, each land use type is marked as a positive effect type or a negative effect type, which improves the scientific objectivity of pollution source tracing and provides a basis for decision-making for the treatment targets.

[0047] The coupling analysis module 40 is used to extract algal bioindicator data from the water quality detection data and perform coupling analysis with the water quality analysis results to obtain the water health status characteristics of the target water area during the period of water quality deterioration.

[0048] Furthermore, the coupling analysis module 40 includes: an indicator data extraction unit, used to extract chlorophyll a concentration and algal density from the algal biological indicator data; a ratio calculation unit, used to calculate the ratio of the chlorophyll a concentration to the algal density to obtain the chlorophyll index per unit algal mass; a first time period acquisition unit, used to acquire the first time period corresponding to the water quality deterioration period in the water quality analysis results, and extract the first mean value of the chlorophyll index per unit algal mass within the first time period; a second time period acquisition unit, used to acquire the second time period corresponding to the water quality good period, and extract the second mean value of the chlorophyll index per unit algal mass within the second time period; and a deviation amplitude calculation unit, used to compare the first mean value with the second mean value to obtain the deviation amplitude, and if the deviation amplitude exceeds a first predetermined threshold, to acquire the water health status characteristics.

[0049] Specifically, two core algal biometrics were extracted from water quality testing data: chlorophyll a concentration and algal density. Chlorophyll a concentration, measured in μg / L, refers to the mass concentration of chlorophyll a in phytoplankton within the water body, determined by fluorescence or spectrophotometry, and characterizes the total algal biomass. Algal density, measured in cells / mL, refers to the total number of algal cells per unit volume of water, obtained by flow cytometry or microscopic counting. The extracted chlorophyll a concentration and algal density were then compared to obtain the chlorophyll index per unit algal mass: chlorophyll index per unit algal mass = chlorophyll a concentration / algal density, representing the average mass of chlorophyll a carried by each algal cell.

[0050] The time boundaries of water quality deterioration periods are obtained from the water quality analysis results and marked as the first time period. The chlorophyll index per unit algal mass is extracted for all sampling times within this first time period, and its arithmetic mean is calculated as the first mean. Similarly, the time boundaries of water quality good periods are obtained from the water quality analysis results and marked as the second time period. The chlorophyll index per unit algal mass is extracted for all sampling times within this second time period, and its arithmetic mean is calculated as the second mean. Then, the first mean and the second mean are compared and analyzed to calculate the deviation range. The deviation range = (first mean - second mean) / second mean × 100%, that is, using the mean chlorophyll index per unit algal mass during water quality good periods as a benchmark, the relative deviation of the mean chlorophyll index per unit algal mass during water quality deterioration periods is quantified. Based on statistical analysis of extensive historical monitoring data, the first predetermined threshold is set as ±25% of the average chlorophyll index per unit algal mass during periods of good water quality. Within normal water quality fluctuations, natural variations in the algal community structure typically do not cause the chlorophyll index per unit algal mass to deviate from the baseline value during periods of good water quality by more than 25%. Once this first predetermined threshold is exceeded, it indicates that the algal community structure has undergone significant changes, and the water body is in an unhealthy ecological stress state. The deviation is compared with the first predetermined threshold. If the absolute value of the deviation is greater than the first predetermined threshold, it is determined that the target water area has a significant water health risk during periods of water quality deterioration. The water health status characteristics are acquired and output, including the deviation magnitude and direction.

[0051] By extracting chlorophyll a concentration and algal density from algal bioindicator data and calculating their ratio, the chlorophyll index per unit algal mass is obtained. Then, the mean value of this index is extracted during periods of water quality deterioration and good water quality, and the deviation is compared to obtain the deviation range. This enables ecological cross-validation and health diagnosis of water quality deterioration from the perspective of changes in the physiological state of algal communities, improves the ecological sensitivity and early warning capability of water quality assessment, and avoids the risk of missed judgments when physicochemical indicators meet the standards but the ecosystem has already degraded.

[0052] Furthermore, the coupling analysis module 40 further includes: an indicator data analysis unit, used to analyze the algal biological indicator data to obtain algal species composition data, the algal species composition data including multiple algal species concentrations corresponding to each of the multiple algal species; a logarithmic transformation unit, used to perform a logarithmic transformation on the first algal species concentration among the multiple algal species concentrations to obtain a first logarithmic concentration; an algal species dominance acquisition unit, used to record the ratio of the first logarithmic concentration to the sum of the logarithmic concentrations of the multiple algal species as the first algal species dominance; and a difference calculation unit, used to calculate the difference between the first time period mean of the first algal species dominance during the water quality deterioration period and the second time period mean of the first algal species dominance during the water quality good period in the water quality analysis results, and if the difference exceeds a second predetermined threshold, the health status characteristic is obtained.

[0053] Specifically, species analysis is performed on algal biometric data in water quality testing data to obtain algal species composition data. The algal species composition data refers to the classification data obtained after identifying the species and measuring the concentration of various algae in the target water area by using flow cytometry combined with fluorescence labeling technology or by microscopic morphological identification and counting methods. It includes multiple algal species, such as Microcystis and Anabaena in the cyanobacteria, Chlorella and Scenedesmus in the chlorophyll, Cyclophyta and Synechocera in the diatoms, as well as Euglena and Cryptophyta, and the corresponding concentration values ​​of each algal species, in cells / mL, reflecting the species diversity structure of the phytoplankton community in the water body and the relative richness of each species.

[0054] Then, logarithmic transformations are performed on the concentrations of multiple algal species. For example, the natural logarithm of the concentration of the first algal species is calculated to obtain the first logarithmic concentration of that species. In actual calculations, to avoid the logarithmic operation tending towards negative infinity due to extremely low concentrations, such as algal species concentrations close to zero, a very small constant, such as 1, is added to the original concentration data for offset processing. After obtaining multiple logarithmic concentrations by performing logarithmic transformations on the concentrations of multiple algal species, these multiple logarithmic concentrations are summed to obtain the sum of the logarithmic concentrations of multiple algal species. Then, the ratio of the first logarithmic concentration to the sum of the logarithmic concentrations of multiple algal species is calculated as the dominance of the first algal species. This value reflects the relative importance of a particular first algal species in the entire algal community. The larger the dominance value, the higher the proportion of the algal species in the community and the more dominant its ecological niche.

[0055] The time boundaries of the water quality deterioration period (i.e., the first time period) and the water quality good period (i.e., the second time period) are determined. The dominance of the first algal species at all sampling time points within the first time period is extracted, and their arithmetic mean is calculated as the mean for the first time period. Simultaneously, the dominance of the first algal species at all sampling time points within the second time period is extracted, and their arithmetic mean is calculated as the mean for the second time period. The difference between the mean for the first time period and the mean for the second time period is then calculated and compared with a second predetermined threshold. Under natural conditions, the normal fluctuation of species dominance in the algal community of the same water body between seasons or years usually does not exceed 10 percentage points. Once the difference in dominance of a certain algal species between the deterioration period and the good period exceeds 15 percentage points, it indicates a significant statistically and ecologically significant jump in the relative abundance of that algal species, signifying that the community structure has been substantially disturbed by water quality deterioration. Therefore, the second predetermined threshold is preferably set to 0.15. If the difference between the average value of the first time period and the average value of the second time period is greater than the second predetermined threshold, it is determined that there is a significant algal community structure succession in the target water area during the period of water quality deterioration. The water health status characteristics are obtained and output. The water health status characteristics include at least the dominance change value, the name of the specific algal species whose dominance increases, the average dominance value of the deterioration period and the good period, and the water quality indication meaning based on the ecological habits of the algal species. For example, a significant increase in the dominance of cyanobacteria indicates that the eutrophication of the water body is aggravated and there is a risk of cyanobacterial bloom. The water quality indication meaning is determined based on the corresponding ecological and physiological characteristics and water environment indication characteristics of each algal species.

[0056] Logarithmic transformation eliminates the calculation bias caused by the difference in absolute concentration between different algal species, making the dominance calculation truly reflect the changes in the proportion structure within the community. This enables the accurate identification of key biomarker species that lead to water quality deterioration and their magnitude of change, further improving the accuracy and reliability of water quality deterioration cause diagnosis and ecological early warning.

[0057] The judgment analysis module 50 is used to perform judgment analysis on the correlation analysis results and the water health status characteristics using a multi-level progressive judgment path to obtain the target water quality level.

[0058] Furthermore, the judgment and analysis module 50 includes: a turbidity and color data acquisition unit, used to acquire turbidity data and color data from the water quality testing data; a first-level water quality grade output unit, used to output a first-level water quality grade if the turbidity data is lower than a first turbidity threshold and the color data is lower than a first color threshold; a turbidity and color data judgment unit, used to acquire chemical oxygen demand (COD) data and ammonia nitrogen data from the water quality testing data if the turbidity data is not lower than the first turbidity threshold or the color data is not lower than the first color threshold; and a second-level water quality grade output unit, used to acquire chemical oxygen demand (COD) data and ammonia nitrogen data if the COD data is lower than a first COD threshold and the... If the ammonia nitrogen data is lower than the first ammonia nitrogen threshold, a secondary water quality level is output; a type acquisition unit is used to acquire the positive and negative effect types in the correlation analysis results if the chemical oxygen demand data is not lower than the first chemical oxygen demand threshold or the ammonia nitrogen data is not lower than the first ammonia nitrogen threshold; a type ratio judgment unit is used to acquire the water body health status characteristics if the ratio of the number of positive effect types to the number of negative effect types is lower than the first ratio threshold; a tertiary water quality level output unit is used to output a tertiary water quality level if the deviation amplitude in the water body health status characteristics exceeds the third threshold or the difference exceeds the fourth threshold.

[0059] Specifically, turbidity and color data of the target water area are extracted from water quality testing data. Turbidity refers to the scattering and absorption effect of suspended particulate matter in water when light passes through it, measured in NTU. It is determined using a turbidity sensor based on the 90° scattering light turbidimetric method, reflecting the clarity and suspended solids content of the water. Color refers to the depth of color in water, measured using the platinum-cobalt standard colorimetric method, reflecting the content of dissolved colored substances in the water. The extracted turbidity data is compared with a preset first turbidity threshold, and the color data is also compared with a first color threshold. The first turbidity threshold is preferably set to 5 NTU, corresponding to the turbidity limit for Class II water in the Surface Water Environmental Quality Standard. The first color threshold is preferably set to 15 degrees, corresponding to the upper limit of color in the Drinking Water Source Quality Standard. When the turbidity data is less than 5 NTU and the color data is less than 15 degrees, it indicates that the water has excellent sensory properties and extremely low levels of inorganic suspended solids and colored dissolved substances, resulting in a Class I water quality rating, which corresponds to excellent water quality.

[0060] When the turbidity data is greater than or equal to 5 NTU or the color data is greater than or equal to 15 degrees, the second-level judgment process is initiated. The chemical oxygen demand (COD) and ammonia nitrogen (AM) data from the water quality test data are obtained, and the COD data is compared with the first COD threshold and the AM data is compared with the first AM threshold. According to the Class III water limit in the Surface Water Environmental Quality Standard, the first COD threshold is preferably set to 20 mg / L and the first AM threshold is set to 1.0 mg / L. When the COD data is lower than the first COD threshold and the AM data is lower than the first AM threshold, a Class II water quality grade is output, indicating that although the water body has slight turbidity or color, the degree of organic pollution is still within the acceptable Class III water quality standard range, and a Class II water quality grade is output.

[0061] When the chemical oxygen demand is not less than 20 mg / L or the ammonia nitrogen is not less than 1.0 mg / L, that is, the organic pollution index has exceeded the Class III water standard limit, the third-level judgment process is initiated. The positive and negative effect types that have been marked are obtained from the output results of the correlation analysis module 30. The ratio of the positive and negative effect types is calculated and compared with the first ratio threshold. The first ratio threshold is set to 1 for example. If the number of positive effect types is greater than or equal to the number of negative effect types, that is, the ratio calculation result is greater than or equal to 1, it indicates that the land use structure of the catchment area generally has the capacity for self-purification and pollution buffering. Conversely, if the ratio of the number of positive effect types to the number of negative effect types is less than 1, it indicates that the land use types that have a deteriorating effect on water quality are dominant in terms of both quantity and scope of influence. The water health status characteristics are obtained from the output of the coupling analysis module 40. The deviation of the chlorophyll index per unit algal mass is compared with the third threshold. If the difference of the time-period average value of the dominance of a specific algal species is compared with the fourth threshold, the third threshold corresponds to the judgment threshold of the deviation amplitude, which is set to 25%. The fourth threshold is used to judge the difference of algal species dominance, which is set to 0.15. When the deviation amplitude is greater than the third threshold or the difference is greater than the fourth threshold, it indicates that the water body not only exceeds the standards in terms of physicochemical indicators, but also shows significant changes in the algal community structure or abnormal deviations in the physiological state at the ecological level. The third-level water quality grade is output, indicating that the target water area has poor water quality and obvious signs of ecological degradation.

[0062] By using a multi-level progressive judgment path to classify the correlation analysis results of the target water area with the characteristics of the water health status in a hierarchical manner, a comprehensive water quality grade assessment of the entire chain is realized, from apparent quality to the degree of organic pollution, then to the structure of pollution causes, and finally to the state of ecological response. This improves the judgment efficiency and the comprehensiveness and reliability of water quality assessment.

[0063] The water area management module 60 is used to manage the target water area based on the target water quality level.

[0064] Furthermore, the water area management module 60 includes: an emission data acquisition unit, used to acquire pollution source emission data of the target water area, the pollution source emission data including multiple emission index parameters corresponding to multiple pollution sources; a pollution source contribution rate acquisition unit, used to use the positive effect type and negative effect type in the correlation analysis results as prior constraints, and combine the pollution source emission data to perform factor decomposition analysis on the water quality analysis results to obtain the contribution rate of each pollution source; and a priority ranking unit, used to rank the treatment priorities of the target water area based on the contribution rates of each pollution source.

[0065] Specifically, when the target water area is classified as Class III water quality and requires remediation measures, pollution source emission data for the target water area is obtained from external data sources, such as the pollution source census database of the ecological and environmental departments, the online monitoring system of key polluting units, and the agricultural non-point source pollution survey ledger. This pollution source emission data refers to quantitative information on pollutants discharged into the water body by various types of pollution sources within the catchment area, such as chemical oxygen demand (COD), ammonia nitrogen, total phosphorus, and total nitrogen. Specifically, it includes multiple emission index parameters corresponding to each pollution source. Then, the positive and negative effect types from the correlation analysis results are used as prior constraints. Combined with the aforementioned pollution source emission data, factor decomposition analysis is performed on the water quality analysis results. This factor decomposition analysis can employ an improved source apportionment method based on the chemical mass balance (CMB) receptor model. Its basic principle is to consider the pollutant concentrations observed at each monitoring section as a linear superposition of contributions from multiple pollution sources. By establishing a source-receptor response relationship matrix, the contribution share of each pollution source to the receptor point, i.e., the monitoring section, is inferred. Specifically, the emission load per unit area is obtained by dividing the annual emission of the pollution source by the area of ​​its catchment area, and a pollution source emission fingerprint matrix E=[e s,p ], where e s,p This represents the emission index parameter of the p-th pollutant from the s-th pollution source. Simultaneously, a mapping relationship is established between each pollution source and each land use type. For example, the ratio of cultivated land area is mainly associated with agricultural runoff non-point source pollution, the ratio of construction land area is mainly associated with urban surface runoff and sewage discharge, and the ratio of forest land area is associated with its positive effects of pollutant interception and reduction.

[0066] The positive and negative effect types identified in the correlation analysis results are used as prior constraints, including sign and weight constraints. Positive contribution coefficients are assigned to pollution sources associated with land use types with negative effects, indicating that such land use leads to increased water quality index concentrations. Conversely, negative contribution coefficients are assigned to ecological purification processes associated with land use types with positive effects, indicating that such land use helps reduce pollutant concentrations. For land use types marked as strongly correlated (correlation coefficient absolute value ≥ 0.8), the contribution rate of their associated pollution sources is assigned a higher prior weight during iterative optimization, making the calculation results more focused on pollution sources with statistically significant impact. Under the combined effect of sign and weight constraints, the non-negative constraint least squares method is used to solve for the minimization objective function: Where Q is the optimization objective to be minimized. To monitor the measured concentration of pollutant p at the cross-section, G s,p Let ΣG be the source contribution coefficient of the s-th pollution source to the p-th pollutant. s,p This represents the summation over all pollution sources, from the 1st to the Sth. s,p σ represents the emission index parameter of the p-th pollutant from the s-th pollution source. p Let G be the standard deviation of the measurement error for the p-th pollutant. The solution process satisfies the constraint: G s,p ≥0, and a sign constraint consistent with the positive / negative effect type label. The objective function is solved iteratively using non-negative constrained least squares, which starts from G. s,p Starting from the zero vector where = 0, the contamination sources that minimize the prediction residual are gradually added to the active set. The contribution coefficients of each source in the active set are repeatedly adjusted until the residual gradient approaches zero. The final output is G. s,p The value represents the contribution rate of each pollution source to a specific water quality indicator. The larger the contribution rate, the more significant the impact of the pollution source on the increase of the indicator's concentration. The contribution rates of the same pollution source to different pollutants are comprehensively weighted, and the weighting coefficients can be dynamically adjusted according to the key controlled pollutant types corresponding to the target water quality level to obtain the comprehensive contribution rate of the pollution source. The sum of the contribution rates of all pollution sources is normalized to 100%.

[0067] Based on the overall contribution rate of each pollution source, all pollution sources within the target water area are ranked from highest to lowest contribution rate to form a priority sequence for remediation. The ranking rule is: the higher the overall contribution rate, the higher the remediation priority. The output remediation priority ranking results are presented in list form, including but not limited to the name of each pollution source, its overall contribution rate, the land use types involved with negative effects, and the suggested remediation measures, for management departments to formulate specific remediation plans, such as reducing fertilizer application, constructing ecological buffer zones, and upgrading sewage treatment facilities.

[0068] By using the positive and negative effect types from the correlation analysis results as prior constraints for factor decomposition analysis, and combining them with pollution source emission data to quantify the source contribution rate of water quality analysis results, and then prioritizing treatment based on the comprehensive contribution rate of each pollution source, a complete decision-making closed loop from water quality level determination to precise pollution source location and treatment resource allocation is achieved. At the same time, it can identify potential risks of eutrophication in water bodies in advance, effectively improve early warning lag, enhance the scientific nature of treatment decisions and the targeting of resource allocation, and thus improve the effectiveness and reliability of target water area treatment.

[0069] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0070] Obviously, those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A water quality intelligent assessment and treatment system integrating multi-dimensional spatiotemporal data, characterized in that, include: The data acquisition module is used to acquire water quality monitoring data from multiple monitoring sections of the target water area and land type data of the corresponding catchment area; The data parsing module is used to retrieve the water quality analysis strategy to analyze the water quality detection data and obtain the water quality analysis results; The correlation analysis module is used to perform correlation analysis between any indicator parameter corresponding to any water quality indicator in the water quality analysis results and any area ratio corresponding to any use type in the land type data, and obtain the correlation analysis results. The coupling analysis module is used to extract algal bioindicator data from the water quality detection data and perform coupling analysis with the water quality analysis results to obtain the water health status characteristics of the target water area during the period of water quality deterioration. The judgment and analysis module is used to perform judgment and analysis on the correlation analysis results and the water health status characteristics using a multi-level progressive judgment path to obtain the target water quality level. The water area management module is used to manage the target water area based on the target water quality level.

2. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 1, characterized in that, The data acquisition module includes: The raw data acquisition unit is used to acquire raw detection data of the target water area at the multiple monitoring sections; The raw data processing unit is used to transmit the raw detection data to the cloud and use cloud computing power to perform noise reduction and calibration processing on the raw detection data to generate calibrated detection data, which is recorded as the water quality detection data.

3. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 2, characterized in that, The raw data processing unit includes: The first processing result obtaining subunit is used to smooth the original detection data using a sliding window filter to obtain the first processing result; The second processing result acquisition subunit is used to remove interference from the first processing result using median filtering to obtain the second processing result. The water quality testing data acquisition subunit is used to perform reverse compensation on the second processing result using the target response curve of the target sensor in a standard water environment to obtain the water quality testing data.

4. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 1, characterized in that, The data parsing module includes: The time series analysis result acquisition unit is used to extract the time dimension data from the water quality detection data, perform time series trend analysis on the time dimension data, and obtain the time series analysis results of the predetermined water quality indicators. The spatial resolution result acquisition unit is used to extract spatial dimension data from the water quality detection data, and to perform horizontal comparison of the spatial dimension data according to the upstream, midstream and downstream partitions of the target water area to identify the spatial resolution results of each partition corresponding to the upstream, midstream and downstream areas. A water quality analysis result acquisition unit is used to combine the time-series analysis result and the spatial analysis result to form the water quality analysis result.

5. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 4, characterized in that, The predetermined water quality indicators include at least dissolved oxygen, chemical oxygen demand, ammonia nitrogen, and total phosphorus.

6. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 1, characterized in that, The correlation analysis module includes: The first utilization type acquisition unit is used to acquire the first utilization type in the land type data, wherein the first utilization type corresponds to the first area ratio; The first indicator parameter acquisition unit is used to acquire the first indicator parameter corresponding to the first water quality indicator in the water quality analysis results. The correlation coefficient calculation unit is used to calculate the Pearson correlation coefficient between the first area ratio and the first index parameter to obtain the first correlation coefficient; A positive effect type marking unit is used to mark the first utilization type as a positive effect type if the first correlation coefficient is positive and its absolute value exceeds the first correlation threshold; A negative effect type marking unit is used to mark the first utilization type as a negative effect type if the first correlation coefficient is negative and its absolute value exceeds the first correlation threshold.

7. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 1, characterized in that, The coupling analysis module includes: The indicator data extraction unit is used to extract the chlorophyll a concentration and algal density from the algal bioindicator data. The ratio calculation unit is used to calculate the ratio of the chlorophyll a concentration to the algal density to obtain the chlorophyll index per unit algal mass. The first time period acquisition unit is used to acquire the first time period corresponding to the water quality deterioration period in the water quality analysis results, and extract the first mean value of the unit algal mass chlorophyll index within the first time period. The second time period acquisition unit is used to acquire the second time period corresponding to the period with excellent water quality, and extract the second mean value of the unit algal mass chlorophyll index within the second time period; The deviation calculation unit is used to compare the first mean with the second mean to obtain the deviation. If the deviation exceeds a first predetermined threshold, the water health status characteristics are obtained.

8. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 7, characterized in that, The coupling analysis module further includes: The indicator data analysis unit is used to analyze the algal biological indicator data to obtain algal species composition data, which includes multiple algal species concentrations corresponding to each of the multiple algal species. The logarithmic transformation unit is used to perform a logarithmic transformation on the concentration of the first algal species among the multiple algal species concentrations to obtain the first logarithmic concentration. The algal species dominance acquisition unit is used to record the ratio of the first logarithmic concentration to the sum of the logarithmic concentrations of the plurality of algal species as the first algal species dominance. The difference calculation unit is used to calculate the difference between the first time period mean of the dominance of the first algae species during the water quality deterioration period and the second time period mean of the dominance of the first algae species during the water quality good period in the water quality analysis results. If the difference exceeds a second predetermined threshold, the health status feature is obtained.

9. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 8, characterized in that, The determination and analysis module includes: The turbidity and color data acquisition unit is used to acquire turbidity data and color data from the water quality test data; A first-level water quality grade output unit is used to output a first-level water quality grade if the turbidity data is lower than a first turbidity threshold and the chromaticity data is lower than a first chromaticity threshold. A turbidity and colorimetric data determination unit is used to obtain chemical oxygen demand (COD) data and ammonia nitrogen data from the water quality detection data if the turbidity data is not lower than the first turbidity threshold or the colorimetric data is not lower than the first colorimetric threshold. The secondary water quality grade output unit is used to output a secondary water quality grade if the chemical oxygen demand data is lower than the first chemical oxygen demand threshold and the ammonia nitrogen data is lower than the first ammonia nitrogen threshold. A type acquisition unit is used to acquire the positive effect type and negative effect type in the correlation analysis results if the chemical oxygen demand data is not lower than the first chemical oxygen demand threshold or the ammonia nitrogen data is not lower than the first ammonia nitrogen threshold. A type ratio judgment unit is used to obtain the water health status characteristics if the ratio of the number of positive effect types to the number of negative effect types is lower than a first ratio threshold. The three-level water quality grade output unit is used to output a three-level water quality grade if the deviation of the water body health status characteristics exceeds a third threshold or the difference exceeds a fourth threshold.

10. The intelligent water quality assessment and treatment system integrating multi-dimensional spatiotemporal data according to claim 9, characterized in that, The water management module includes: The emission data acquisition unit is used to acquire the pollution source emission data of the target water area, wherein the pollution source emission data includes multiple emission index parameters corresponding to each of the multiple pollution sources; The pollution source contribution rate acquisition unit is used to take the positive effect type and negative effect type in the correlation analysis results as prior constraints, and combine the pollution source emission data to perform factor decomposition analysis on the water quality analysis results to obtain the contribution rate of each pollution source. The priority ranking unit is used to rank the target water area for treatment priority based on the contribution rate of each pollution source.

Images