Artificial intelligence river water quality pollutant spatial form monitoring system and method

Abstract

The invention relates to the technical field of water quality monitoring, in particular to an artificial intelligence river water quality pollutant spatial form monitoring system and method, and the system comprises a concentration trend analysis module, a spatial form monitoring module, a spatial trend analysis module and a pollution early warning evaluation module. According to the method, the water quality is monitored at a plurality of river water area nodes, the pollutant concentration data can be accurately captured, the change rate of the pollutant concentration can be predicted, the understanding of the pollution trend is improved, the response speed to the pollution event is enhanced, the image monitoring data is combined, the convolutional neural network is used for analyzing the river water area image, and the accuracy of the analysis is improved. The spatial area of the pollutants is analyzed, so that the spatial distribution state of the pollutants is evaluated in detail, the severity level of the pollutants can be evaluated, managers are notified in real time, meanwhile, dynamic change information of pollutant concentration and spatial distribution is integrated, an early warning mechanism is more agile and accurate, and the early warning efficiency is improved. And the effectiveness and the accuracy of pollution early warning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring, and in particular to an artificial intelligence system and method for monitoring the spatial morphology of river water pollutants. Background Art

[0002] The field of water quality monitoring technology mainly involves systems and equipment used to detect, evaluate and manage the chemical, biological and physical properties of water. The field of water quality monitoring uses a variety of sensors and analytical equipment to determine pollutants in water, such as organic pollutants, heavy metals, nutrients and microorganisms. Developments in the technology field aim to provide real-time, high-precision water quality data in order to respond to possible pollution incidents in a timely manner and protect public health and environmental safety. Technologies include sensor development, data acquisition systems, remote monitoring technology and data processing algorithms to achieve real-time monitoring and dynamic management of water quality.

[0003] Among them, the spatial morphology monitoring system for river water quality pollutants is a system specifically used to monitor the distribution and concentration changes of pollutants in rivers. The system uses sensor technology to achieve continuous and dynamic monitoring of river water quality, and can describe the spatial distribution pattern of pollutants in detail. The main purpose of the system is to provide accurate data support for environmental protection departments and relevant management agencies, helping management agencies to make more scientific and effective choices in water resources management and pollution prevention and control decisions, and also provide the public with transparent information on water quality safety. Through this monitoring, pollution sources and pollution diffusion trends can be discovered in a timely manner, so that corresponding prevention or control measures can be taken.

[0004] Traditional monitoring systems have certain limitations in monitoring and warning pollutants, which are mainly reflected in the dynamic monitoring of changes in pollutant concentrations and spatial distribution. In the face of rapidly changing pollution events, the reaction speed and processing capabilities of traditional systems cannot keep up with the speed of environmental changes. The lack of real-time data integration and analysis capabilities makes it impossible for traditional systems to accurately assess the severity of pollutants. In addition, traditional systems are not accurate enough in identifying and analyzing the spatial morphology of pollutants, which limits the accurate assessment of the spatial distribution status of pollutants. This makes the pollution warning assessment lack the necessary data support, reduces the timeliness and effectiveness of the warning, and will lead to wrong judgments or delays in handling pollution events, affecting the health of the river ecosystem and the surrounding environment. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an artificial intelligence river water quality pollutant spatial morphology monitoring system and method.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an artificial intelligence river water quality pollutant spatial morphology monitoring system, the system comprising:

[0007] The concentration trend analysis module is based on the river water environment. Water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time, obtain pollutant concentration data at multiple nodes in the river over a period of time, predict the rate of change of river pollutant concentration, and obtain pollution concentration trend information;

[0008] The spatial morphology monitoring module is based on river water image monitoring data. It analyzes river water images through convolutional neural networks, identifies the spatial area of ​​river pollutants, and evaluates the spatial distribution state index of river pollutants by combining the pollutant concentrations of multiple nodes to obtain spatial distribution state information.

[0009] The spatial trend analysis module obtains the spatial distribution state index of river pollutants within a period of time based on the spatial distribution state information, evaluates the change trend of the spatial distribution state of pollutants, and obtains the spatial distribution state trend information;

[0010] The pollution warning assessment module analyzes the development trend of river pollutants based on the pollution concentration trend information and spatial distribution status trend information, and evaluates the severity level of pollutants in combination with the current spatial distribution status index of river pollutants and the current pollutant concentration, and promptly notifies management personnel to obtain real-time warning information.

[0011] The present invention is improved in that the steps of obtaining the pollution concentration trend information are:

[0012] Based on the river water environment, water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time, obtain pollutant concentration data at multiple nodes in the river over a period of time, and obtain a pollutant concentration data set;

[0013] Based on the pollutant concentration data set, the formula:

[0014]

[0015] Calculate the rate of change of pollutant concentration ,in, and The time points and The pollutant concentration, For time point The flow velocity influencing factor is For time point The influencing factor of river width is is the attenuation coefficient, is the rate of change of pollutant concentration, is the total number of time points, is the base of natural logarithm, is the measurement time interval;

[0016] Based on the rate of change of the pollutant concentration ,according to The value is used to evaluate the trend of pollutant concentration changes and obtain pollution concentration trend information.

[0017] The present invention is improved in that the method for identifying the spatial area of ​​river pollutants is:

[0018] Based on the river water environment, image data of the river water area is captured by an image sensor;

[0019] Based on the image data of the river water area, the river water area image is analyzed by a convolutional neural network to identify the pollutant area in the water area, and the formula is used:

[0020]

[0021] Calculate the total spatial area of ​​contaminants ,in, is the total spatial area of ​​the pollutants, is the total number of pollutant areas, For the image The number of pixels in the polluted area, is the actual area corresponding to each pixel, is the angular complexity of the pollutant shape in the image, is the shape complexity adjustment coefficient.

[0022] The present invention is improved in that the step of acquiring the spatial distribution state information is:

[0023] Based on the total spatial area of ​​the pollutants , combined with the pollutant concentration at each node, through the formula:

[0024]

[0025] Calculate the spatial distribution index of river pollutants ,in, Indicates the spatial distribution index of river pollutants, Is a node The pollutant concentration, Is a node The area of ​​the corresponding region, is the total spatial area of ​​the pollutants, is the distribution uniformity adjustment coefficient, is the total number of river monitoring nodes, is the base of natural logarithm;

[0026] Based on the spatial distribution state index of the river pollutants ,according to The size of the value is used to evaluate the spatial distribution state of pollutants and obtain the spatial distribution state information.

[0027] The present invention is improved in that the step of acquiring the spatial distribution state trend information is:

[0028] Based on the spatial distribution state information, obtain the spatial distribution state index of river pollutants within a period of time, and collect pollutant concentration and location data at corresponding time points to obtain distribution state association data;

[0029] Based on the distribution state associated data, through the formula:

[0030]

[0031] Calculate the trend value of spatial distribution status ,in, Indicates the trend value of spatial distribution status, It's time point The change in state index from the previous time point, It's time point The spatial diffusion speed of pollutants, is the average spatial diffusion velocity during the measurement period, is the weight coefficient, is the angle between the pollutant diffusion direction and the main river direction. is the total number of time points;

[0032] Based on the spatial distribution state trend value , evaluate the diffusion speed and direction changes of river pollutants, and obtain spatial distribution trend information.

[0033] The present invention is improved in that the method for analyzing the development trend of river pollutants is:

[0034] Based on the pollution concentration trend information and spatial distribution state trend information, extract the current concentration change rate and spatial distribution state trend value of river pollutants;

[0035] Based on the current concentration change rate and spatial distribution trend value of the river pollutants, the formula is:

[0036]

[0037] Calculate the trend index of river pollutants ,in, Indicates the development trend index of river pollutants, is the rate of change of pollutant concentration, is the trend value of spatial distribution state, , and is the adjustment parameter, is the base of natural logarithm;

[0038] Based on the trend index of the river pollutants , evaluate the development direction and extent of pollutants in rivers, and obtain information on pollution development trends.

[0039] The present invention is improved in that the step of obtaining the real-time warning information is:

[0040] Based on the trend index of the river pollutants , obtain the current spatial distribution state index of river pollutants and the current average concentration of pollutants, and obtain warning related data;

[0041] Based on the warning related data, through the formula:

[0042]

[0043] Calculating a contaminant's severity score ,in, Rate the severity of the pollutant, is the current spatial distribution state index, is the current average concentration of pollutants, is the development trend index of river pollutants, , and is the weight coefficient;

[0044] Severity score based on the contaminant , compared with the preset warning threshold, implement corresponding warning notification, notify management personnel in time, and obtain real-time warning information.

[0045] The method for monitoring the spatial morphology of river water quality pollutants by artificial intelligence is implemented based on the above-mentioned system for monitoring the spatial morphology of river water quality pollutants by artificial intelligence, and includes the following steps:

[0046] S1: Based on the river water environment, water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time and obtain a pollutant concentration data set;

[0047] S2: Based on the pollutant concentration data set, predict the concentration change trend of the pollutant through time series analysis to obtain pollution concentration trend information;

[0048] S3: Based on the river water image monitoring data, the image is processed through a convolutional neural network to identify river pollutants, analyze the spatial area of ​​river pollutants, evaluate the spatial distribution state index of river pollutants, and obtain spatial distribution state information;

[0049] S4: Based on the spatial distribution state information, evaluating the spatial distribution state change trend of the pollutants to obtain spatial distribution state trend information;

[0050] S5: Based on the pollution concentration trend information and spatial distribution status trend information, analyze the development trend of river pollutants, identify the severity level of pollutants, set warning thresholds, implement warning mechanisms, notify management personnel, and obtain real-time warning information.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are:

[0052] In the present invention, by monitoring water quality at multiple river water nodes, pollutant concentration data can be accurately captured and the rate of change of pollutant concentration can be predicted, thereby improving the understanding of pollution trends and enhancing the response speed to pollution incidents. In combination with image monitoring data, a convolutional neural network is used to analyze river water images and the spatial area of ​​pollutants, so that the spatial distribution status of pollutants is evaluated in detail, providing comprehensive data support, being able to evaluate the severity of pollutants and notify management personnel in real time, and integrating dynamic change information of pollutant concentration and spatial distribution, making the early warning mechanism more agile and accurate, improving the effectiveness and accuracy of pollution early warnings, and enabling management personnel to make quick and effective response measures based on real-time data. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a system flow chart of the present invention;

[0054] Figure 2 A flow chart for obtaining pollution concentration trend information for the present invention;

[0055] Figure 3 Flow chart for identifying the spatial area of ​​river pollutants for the present invention;

[0056] Figure 4 A flow chart of obtaining spatial distribution status information of the present invention;

[0057] Figure 5 A flow chart for obtaining spatial distribution status trend information of the present invention;

[0058] Figure 6 A flow chart for analyzing the development trend of river pollutants for the present invention;

[0059] Figure 7 The present invention is a flow chart for obtaining real-time warning information. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0062] Example

[0063] See also Figure 1 The present invention provides a technical solution: an artificial intelligence river water quality pollutant spatial morphology monitoring system, the system comprising:

[0064] The concentration trend analysis module is based on the river water environment. Water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time, obtain pollutant concentration data at multiple nodes in the river over a period of time, predict the rate of change of river pollutant concentration, and obtain pollution concentration trend information;

[0065] The spatial morphology monitoring module is based on river water image monitoring data. It analyzes river water images through convolutional neural networks, identifies the spatial area of ​​river pollutants, and evaluates the spatial distribution state index of river pollutants by combining the pollutant concentrations of multiple nodes to obtain spatial distribution state information.

[0066] The spatial trend analysis module obtains the spatial distribution state index of river pollutants within a period of time based on the spatial distribution state information, evaluates the changing trend of the spatial distribution state of pollutants, and obtains the spatial distribution state trend information;

[0067] The pollution warning assessment module analyzes the development trend of river pollutants based on the pollution concentration trend information and spatial distribution status trend information, and evaluates the severity level of pollutants by combining the current spatial distribution status index of river pollutants and the current pollutant concentration, so as to promptly notify management personnel and obtain real-time warning information.

[0068] Pollution concentration trend information includes the pollutant concentration increase and decrease ratio and concentration change pattern of the monitoring nodes. Spatial distribution status information includes the spatial diffusion range of pollutants, the area percentage of the affected area and the spatial distribution of pollutant concentrations. Spatial distribution status trend information includes the pollutant diffusion rate, directional changes and changes in pollution degree. Real-time warning information includes pollution level classification and emergency response level.

[0069] See also Figure 2 , the steps to obtain pollution concentration trend information are:

[0070] Based on the river water environment, water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time, obtain pollutant concentration data at multiple nodes in the river over a period of time, and obtain a pollutant concentration data set;

[0071] Based on the pollutant concentration data set, the formula is:

[0072]

[0073] Calculate the rate of change of pollutant concentration ,in, and The time points and The pollutant concentration, For time point The flow velocity influencing factor is For time point The influencing factor of river width is is the attenuation coefficient, is the rate of change of pollutant concentration, is the total number of time points, is the base of natural logarithm, is the measurement time interval;

[0074] Based on the rate of change of pollutant concentration ,according to The value is used to evaluate the trend of pollutant concentration changes and obtain pollution concentration trend information.

[0075] formula:

[0076]

[0077] Parameter details and how to obtain them:

[0078] and : Indicates a time point and The pollutant concentration is measured in real time by water quality monitoring sensors.

[0079] : Time point The velocity influence factor is calculated based on the velocity data at that time point. The velocity data is usually obtained by a flow meter, and the influence factor can be obtained by standardizing the velocity value to ensure that its contribution to the formula is moderate.

[0080] : Time point The river width influence factor is obtained by measuring the width of the river at that point in time and performing corresponding data transformation (such as standardization) in order to evaluate the impact of width on pollutant diffusion.

[0081] : Attenuation coefficient, which describes the attenuation of pollutants with distance, is usually determined based on environmental science research literature or experimental data.

[0082] : The total number of time points is determined based on actual monitoring data.

[0083] : Time interval is the time difference between two measurements and is usually determined by the settings of the monitoring equipment.

[0084] Calculation Example

[0085] Assume that At a time point, given the following data:

[0086] mg / L, mg / L, mg / L;

[0087] , , ;

[0088] , , ;

[0089] ;

[0090] Hour;

[0091] The calculation process of the pollutant concentration change rate is as follows:

[0092]

[0093] Calculate the exponential parts:

[0094]

[0095]

[0096] Substituting the values:

[0097]

[0098]

[0099]

[0100] Pollutant concentration change rate for , indicating that within one hour, considering the velocity and width of the river, the pollutant concentration increases by an average of about 10.3407 mg / L. The value can be used to support environmental management decisions and guide the adjustment of pollution prevention and control measures.

[0101] See also Figure 3 , the method to identify the spatial area of ​​river pollutants is:

[0102] Based on the river water environment, image data of the river water area is captured by an image sensor;

[0103] Based on the image data of river waters, the convolutional neural network is used to analyze the river water images, identify the pollutant areas in the waters, and use the formula:

[0104]

[0105] Calculate the total spatial area of ​​contaminants ,in, is the total spatial area of ​​the pollutants, is the total number of pollutant areas, For the image The number of pixels in the polluted area, is the actual area corresponding to each pixel, is the angular complexity of the pollutant shape in the image, is the shape complexity adjustment coefficient.

[0106] formula:

[0107]

[0108] Parameter details and how to obtain them:

[0109] : The total number of polluted areas identified in the image is obtained by counting the polluted areas identified by image analysis software using a convolutional neural network.

[0110] : The first The number of pixels in each pollutant area is obtained by counting the number of pixels in each area using image processing software.

[0111] : The actual area corresponding to each pixel is calculated based on the height and angle of the camera and the actual scale of the ground. For example, if the camera setting height and angle indicate that each pixel represents a ground area of ​​0.01 square meters, then It is 0.01.

[0112] : The angular complexity of the contaminant’s shape in the image, usually assessed by calculating the geometric boundaries and angles of the shape using image analysis software.

[0113] : The shape complexity adjustment coefficient is an adjustment factor set according to the variability of pollutant shapes. It is often set to a constant determined based on experience and is used to adjust the impact of irregular shapes on area calculations.

[0114] Calculation Example

[0115] Assume that the The specific numbers of polluted areas are as follows:

[0116] pixels, pixels, pixels, m², , , , .

[0117] Calculate the area of ​​each region as follows:

[0118] Region 1:

[0119]

[0120] Region 2:

[0121]

[0122] Region 3:

[0123]

[0124] Total spatial area of ​​pollutants Calculated as:

[0125] m²

[0126] The results showed that the three polluted areas identified in the image covered a total area of ​​5.11 square meters. This calculation provides accurate data support for environmental monitoring and helps environmental protection agencies assess and respond to river pollution problems.

[0127] See also Figure 4 , the steps to obtain spatial distribution status information are:

[0128] Total spatial area based on pollutants , combined with the pollutant concentration at each node, through the formula:

[0129]

[0130] Calculate the spatial distribution index of river pollutants ,in, Indicates the spatial distribution index of river pollutants, Is a node The pollutant concentration, Is a node The area of ​​the corresponding region, is the total spatial area of ​​the pollutants, is the distribution uniformity adjustment coefficient, is the total number of river monitoring nodes, is the base of natural logarithm;

[0131] Spatial distribution state index based on river pollutants ,according to The size of the value is used to evaluate the spatial distribution state of pollutants and obtain the spatial distribution state information.

[0132] formula:

[0133]

[0134] Parameter details and how to obtain them:

[0135] : Spatial distribution status index of river pollutants, which indicates the uniformity and concentration of the overall pollution distribution. It is used to evaluate the uniformity of pollutant distribution in the river. A lower index value indicates that the pollutant distribution is more uniform, and a higher index value indicates that some areas are seriously polluted.

[0136] :node The pollutant concentration is usually measured in real time by water quality monitoring sensors.

[0137] :node For the area part of the corresponding region, the area of ​​each node is determined based on the image analysis results of the polluted area.

[0138] : The total spatial area of ​​the pollutant, calculated by the previous step.

[0139] :The adjustment coefficient that affects the distribution uniformity is set according to the needs of environmental analysis to adjust the influence of the spatial area ratio.

[0140] : The total number of river monitoring nodes, that is, the number of nodes involved in the analysis.

[0141] Calculation example:

[0142] Assuming there are 3 monitoring nodes, the following are the specific settings and calculation processes:

[0143] Node data: ppm, m², ppm, m², ppm, m², total spatial area of ​​pollutants m², total number of nodes , adjustment coefficient .

[0144] Calculation steps:

[0145] For each node, calculate the area share and adjusted concentration impact:

[0146]

[0147]

[0148]

[0149] Summary calculation:

[0150]

[0151] Calculated spatial distribution state index This reflects the uniformity and concentration of pollutants in the river. A high value indicates that the concentration of pollutants in some areas is significantly higher than in other areas, indicating the presence of possible pollution points.

[0152] See also Figure 5 , the steps to obtain spatial distribution status trend information are:

[0153] Based on the spatial distribution state information, the spatial distribution state index of river pollutants within a period of time is obtained, and the pollutant concentration and location data at the corresponding time point are collected to obtain the distribution state correlation data;

[0154] Based on the distribution state associated data, through the formula:

[0155]

[0156] Calculate the trend value of spatial distribution status ,in, Indicates the trend value of spatial distribution status, It's time point The change in state index from the previous time point, It's time point The spatial diffusion speed of pollutants, is the average spatial diffusion velocity during the measurement period, is the weight coefficient, is the angle between the pollutant diffusion direction and the main river direction. is the total number of time points;

[0157] Based on the trend value of spatial distribution status , evaluate the diffusion speed and direction changes of river pollutants, and obtain spatial distribution trend information.

[0158] formula:

[0159]

[0160] Parameter details and how to obtain them:

[0161] : State index at consecutive time points The change in spatial distribution state index at different time points is calculated The difference is obtained.

[0162] : Time point The spatial diffusion rate of pollutants is usually estimated based on image analysis and sensor data to estimate the movement speed of pollutants in water bodies.

[0163] : The average spatial diffusion velocity during the measurement period, calculated for all The average value of .

[0164] : Weight coefficient, used to adjust the impact of speed on trend analysis, usually set based on previous research or experimental data.

[0165] : The angle between the pollutant diffusion direction and the main river direction, obtained through analysis of geographic information system and related software.

[0166] : The total number of measured time points, representing the number of time points included in the analysis.

[0167] Calculation example:

[0168] Assuming that data at three time points are monitored, the specific settings and calculations are as follows:

[0169] Time point data: , m / s, , , m / s, , , m / s, , average speed m / s, weight coefficient .

[0170] Calculation steps:

[0171] For each time point, calculate the trend contribution:

[0172]

[0173]

[0174]

[0175] Trend value calculation:

[0176]

[0177] Calculated spatial distribution trend value It means that during the observation period, the spatial distribution trend of pollutants showed a certain diffusion pattern, reflecting the dynamic changes in the diffusion speed and direction of pollutants. The values ​​indicate that the diffusion speed and direction of pollutants in the river change relatively slowly, without any dramatic diffusion or migration events.

[0178] See also Figure 6 , the method to analyze the development trend of river pollutants is:

[0179] Based on the pollution concentration trend information and spatial distribution state trend information, the current concentration change rate and spatial distribution state trend value of river pollutants are extracted;

[0180] Based on the current concentration change rate and spatial distribution trend of river pollutants, the formula is:

[0181]

[0182] Calculate the trend index of river pollutants ,in, Indicates the development trend index of river pollutants, is the rate of change of pollutant concentration, is the trend value of spatial distribution state, , and is the adjustment parameter, is the base of natural logarithm;

[0183] Based on the trend index of river pollutants , evaluate the development direction and extent of pollutants in rivers, and obtain information on pollution development trends.

[0184] formula:

[0185]

[0186] Parameter details and how to obtain them:

[0187] : The rate of change of pollutant concentration, calculated by the previous step.

[0188] : Trend value of spatial distribution state, calculated through the previous steps.

[0189] , and : Adjustment coefficients are set based on the experience of environmental scientists or engineers and previous research to adjust the weight of each measurement in the trend index. Parameters can be derived through experiments or historical data analysis to ensure that the model output is consistent with actual observations.

[0190] Calculation example:

[0191] Assume that the specific measurement data are as follows:

[0192] ppm / hour (rate of change of pollutant concentration)

[0193] (Spatial distribution status trend value)

[0194] (Adjustment coefficient)

[0195] Calculation steps:

[0196] Calculate the square of the rate of change of pollutant concentration:

[0197] ppm² / hour².

[0198] Compute the logarithmic term:

[0199]

[0200] Calculate the trend index:

[0201]

[0202] The development trend index The value is 4.38, which reflects the comprehensive development trend of pollutants in the river, taking into account the trend of concentration change rate and spatial distribution. Values ​​indicate that pollutants may be spreading at an accelerated rate or accumulating in a specific area, and appropriate management measures are needed to address possible environmental risks.

[0203] See also Figure 7 , the steps to obtain real-time warning information are:

[0204] Based on the trend index of river pollutants , obtain the current spatial distribution state index of river pollutants and the current average concentration of pollutants, and obtain warning related data;

[0205] Based on the warning related data, through the formula:

[0206]

[0207] Calculating a contaminant's severity score ,in, Score the severity of the pollutant, is the current spatial distribution state index, is the current average concentration of pollutants, is the development trend index of river pollutants, , and is the weight coefficient;

[0208] Severity score based on contaminants , compared with the preset warning threshold, implement corresponding warning notification, notify management personnel in time, and obtain real-time warning information.

[0209] formula:

[0210]

[0211] Parameter details and how to obtain them:

[0212] : Current spatial distribution state index, calculated by the previous steps.

[0213] : The current average concentration of pollutants is calculated by averaging the pollution data from each monitoring point in the river.

[0214] : The development trend index of river pollutants, calculated by the previous steps.

[0215] , and : Weight coefficients, which weight the impact of spatial state index, pollutant concentration and development trend index respectively. The parameters are set based on historical data and expert experience to ensure that the relative importance of each indicator in the score is appropriately reflected.

[0216] Calculation Example

[0217] Assume the following specific values:

[0218] (Spatial distribution state index)

[0219] ppm (current average concentration)

[0220] (River Pollutant Trend Index)

[0221] Weight coefficient: , , .

[0222] Calculation process:

[0223] Compute the logarithmic part of the state index:

[0224]

[0225] Calculate the square root portion of the mean concentration:

[0226]

[0227] Calculate the fractional part of the Development Trend Index:

[0228]

[0229] calculate :

[0230]

[0231] Severity Rating Indicates the severity of the current environmental pollution situation. Higher values ​​indicate that immediate environmental protection measures need to be taken to reduce the impact of pollution. The score helps managers quickly understand the pollution situation and develop appropriate response strategies.

[0232] The artificial intelligence-based spatial morphology monitoring method for river water quality pollutants includes the following steps:

[0233] S1: Based on the river water environment, water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time and obtain a pollutant concentration data set;

[0234] S2: Based on the pollutant concentration data set, through time series analysis, the concentration change trend of pollutants is predicted to obtain pollution concentration trend information;

[0235] S3: Based on the river water image monitoring data, the image is processed through a convolutional neural network to identify river pollutants, analyze the spatial area of ​​river pollutants, evaluate the spatial distribution state index of river pollutants, and obtain spatial distribution state information;

[0236] S4: Based on the spatial distribution state information, evaluate the change trend of the spatial distribution state of pollutants to obtain the spatial distribution state trend information;

[0237] S5: Based on the pollution concentration trend information and spatial distribution status trend information, analyze the development trend of river pollutants, identify the severity level of pollutants, set warning thresholds, implement warning mechanisms, notify management personnel, and obtain real-time warning information.

[0238] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. Artificial intelligence river water quality pollutant spatial morphology monitoring system, characterized by: The system comprises: The concentration trend analysis module is based on the river water environment. Water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time, obtain pollutant concentration data at multiple nodes in the river over a period of time, predict the rate of change of river pollutant concentration, and obtain pollution concentration trend information; The spatial morphology monitoring module is based on river water image monitoring data. It analyzes river water images through convolutional neural networks, identifies the spatial area of ​​river pollutants, and evaluates the spatial distribution state index of river pollutants by combining the pollutant concentrations of multiple nodes to obtain spatial distribution state information. The spatial trend analysis module obtains the spatial distribution state index of river pollutants within a period of time based on the spatial distribution state information, evaluates the change trend of the spatial distribution state of pollutants, and obtains the spatial distribution state trend information; The pollution warning assessment module analyzes the development trend of river pollutants based on the pollution concentration trend information and spatial distribution status trend information, and evaluates the severity level of pollutants in combination with the current spatial distribution status index of river pollutants and the current pollutant concentration, and promptly notifies management personnel to obtain real-time warning information.

2. The artificial intelligence river water quality pollutant spatial morphology monitoring system according to claim 1 is characterized in that: The steps for obtaining the pollution concentration trend information are as follows: Based on the river water environment, water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time, obtain pollutant concentration data at multiple nodes in the river over a period of time, and obtain a pollutant concentration data set; Based on the pollutant concentration data set, the formula: Calculate the rate of change of pollutant concentration ,in, and The time points and The pollutant concentration, For time point The flow velocity influencing factor is For time point The river width influencing factor is is the attenuation coefficient, is the rate of change of pollutant concentration, is the total number of time points, is the base of natural logarithm, is the measurement time interval; Based on the rate of change of the pollutant concentration ,according to The value is used to evaluate the trend of pollutant concentration changes and obtain pollution concentration trend information.

3. The artificial intelligence river water quality pollutant spatial morphology monitoring system according to claim 1 is characterized in that: The method for identifying the spatial area of ​​river pollutants is: Based on the river water environment, image data of the river water area is captured by an image sensor; Based on the image data of the river water area, the river water area image is analyzed by a convolutional neural network to identify the pollutant area in the water area, and the formula is used: Calculate the total spatial area of ​​contaminants ,in, is the total spatial area of ​​the pollutants, is the total number of pollutant areas, For the image The number of pixels in the polluted area, is the actual area corresponding to each pixel, is the angular complexity of the pollutant shape in the image, is the shape complexity adjustment coefficient.

4. The artificial intelligence river water quality pollutant spatial morphology monitoring system according to claim 3 is characterized in that: The steps for acquiring the spatial distribution state information are: Based on the total spatial area of ​​the pollutants , combined with the pollutant concentration at each node, through the formula: Calculate the spatial distribution index of river pollutants ,in, Indicates the spatial distribution index of river pollutants, Is a node The pollutant concentration, Is a node The area of ​​the corresponding region, is the total spatial area of ​​the pollutants, is the distribution uniformity adjustment coefficient, is the total number of river monitoring nodes, is the base of natural logarithm; Based on the spatial distribution state index of the river pollutants ,according to The size of the value is used to evaluate the spatial distribution state of pollutants and obtain the spatial distribution state information.

5. The artificial intelligence river water quality pollutant spatial morphology monitoring system according to claim 1 is characterized in that: The steps for acquiring the spatial distribution state trend information are as follows: Based on the spatial distribution state information, obtain the spatial distribution state index of river pollutants within a period of time, and collect pollutant concentration and location data at corresponding time points to obtain distribution state association data; Based on the distribution state associated data, through the formula: Calculate the trend value of spatial distribution status ,in, Indicates the trend value of spatial distribution status, It's time point The change in state index from the previous time point, It's time point The spatial diffusion speed of pollutants, is the average spatial diffusion velocity during the measurement period, is the weight coefficient, is the angle between the pollutant diffusion direction and the main river direction. is the total number of time points; Based on the spatial distribution state trend value , evaluate the diffusion speed and direction changes of river pollutants, and obtain spatial distribution trend information.

6. The artificial intelligence river water quality pollutant spatial morphology monitoring system according to claim 1 is characterized in that: The method for analyzing the development trend of river pollutants is: Based on the pollution concentration trend information and spatial distribution state trend information, extract the current concentration change rate and spatial distribution state trend value of river pollutants; Based on the current concentration change rate and spatial distribution trend value of the river pollutants, the formula is: Calculate the trend index of river pollutants ,in, Indicates the development trend index of river pollutants, is the rate of change of pollutant concentration, is the trend value of spatial distribution state, , and is the adjustment parameter, is the base of natural logarithm; Based on the trend index of the river pollutants , evaluate the development direction and extent of pollutants in rivers, and obtain information on pollution development trends.

7. The artificial intelligence river water quality pollutant spatial morphology monitoring system according to claim 6 is characterized in that: The steps for obtaining the real-time warning information are: Based on the trend index of the river pollutants , obtain the current spatial distribution state index of river pollutants and the current average concentration of pollutants, and obtain warning related data; Based on the warning related data, through the formula: Calculating a contaminant's severity score ,in, Score the severity of the pollutant, is the current spatial distribution state index, is the current average concentration of pollutants, is the development trend index of river pollutants, , and is the weight coefficient; Severity score based on the contaminant , compared with the preset warning threshold, implement corresponding warning notification, notify management personnel in time, and obtain real-time warning information.

8. An artificial intelligence-based spatial morphology monitoring method for river water quality pollutants, characterized in that: The artificial intelligence river water quality pollutant spatial morphology monitoring system according to any one of claims 1 to 7 is implemented, comprising the following steps: Based on the river water environment, water quality monitoring sensors are arranged at multiple nodes in the river water area to monitor the river water quality in real time and obtain a pollutant concentration data set; Based on the pollutant concentration data set, predict the concentration change trend of the pollutant through time series analysis to obtain pollution concentration trend information; Based on the river water image monitoring data, the image is processed through a convolutional neural network to identify river pollutants, analyze the spatial area of ​​river pollutants, evaluate the spatial distribution state index of river pollutants, and obtain spatial distribution state information; Based on the spatial distribution state information, evaluating the spatial distribution state change trend of pollutants to obtain spatial distribution state trend information; Based on the pollution concentration trend information and spatial distribution status trend information, the development trend of river pollutants is analyzed, the severity level of pollutants is identified, warning thresholds are set, warning mechanisms are implemented, management personnel are notified, and real-time warning information is obtained.

Images