Method, system, medium and electronic device for monitoring and collecting agricultural effluent

Abstract

The application provides an agricultural wastewater monitoring and collecting method, system, medium and electronic equipment. The agricultural wastewater monitoring and collecting method comprises the following steps: acquiring a monitoring site; measuring the carbon content concentration of dissolved organic matter and the tryptophan fluorescence intensity at the monitoring site; corresponding labeling the carbon content concentration of dissolved organic matter and the tryptophan fluorescence intensity at the same time to obtain tryptophan fluorescence intensity real-time monitoring data; based on the tryptophan fluorescence intensity real-time monitoring data, using a gradient boosting machine model for prediction to obtain carbon content concentration prediction data of dissolved organic matter in agricultural wastewater; dynamically adjusting the critical value of the carbon content concentration of dissolved organic matter according to the tryptophan fluorescence intensity real-time monitoring data and the carbon content concentration prediction data of dissolved organic matter, and obtaining agricultural wastewater after quality separation and flow separation according to the adjusted critical value.

Description

Technical Field

[0001] This application belongs to the field of agricultural wastewater treatment technology, and relates to a method, system, medium and electronic equipment for monitoring and collecting agricultural wastewater. Background Technology

[0002] While agricultural production activities promote increased grain yields and rural economic development, they inevitably lead to agricultural non-point source pollution. Agricultural wastewater mainly originates from fertilizer application, pesticide spraying, livestock and poultry breeding wastewater, and irrigation runoff during agricultural production. It typically contains pollutants such as nitrogen, phosphorus, pesticide residues, organic matter, and pathogenic microorganisms. Therefore, high-concentration wastewater in agricultural drainage ditches has become a significant factor affecting the quality of surface water and groundwater.

[0003] Compared to industrial and urban wastewater, agricultural wastewater is characterized by its dispersed discharge, significant spatial and temporal variations, complex composition, and susceptibility to climate influences. Therefore, the monitoring and collection of agricultural wastewater presents different technical challenges than point source pollution. Existing traditional water quality monitoring methods typically rely on fixed testing standards and chemical reagents, resulting in long testing cycles, slow response times, and high costs, making it difficult to effectively monitor and collect high-concentration agricultural wastewater in real time.

[0004] Meanwhile, agricultural wastewater collection systems also face numerous technical bottlenecks. Traditional drainage ditches and underground pipe systems are primarily designed for drainage, lacking effective pollutant interception and monitoring capabilities. In recent years, although agricultural non-point source pollution control measures such as constructed wetlands, ecological ditches, and drainage storage ponds have emerged, these methods are typically aimed at remediation and have not yet formed an efficient and coordinated wastewater collection and real-time monitoring system. Therefore, providing an efficient and accurate system for collecting high-concentration agricultural wastewater has become one of the most pressing issues to be addressed. Summary of the Invention

[0005] The purpose of this application is to provide a method for monitoring and collecting agricultural wastewater, which can be used to efficiently and accurately collect high-concentration agricultural wastewater.

[0006] In a first aspect, this application provides a method for monitoring and collecting agricultural wastewater, characterized in that the method includes: acquiring monitoring sites; measuring the carbon content concentration of dissolved organic matter and the tryptophan fluorescence intensity at the monitoring sites; marking the carbon content concentration of dissolved organic matter and the tryptophan fluorescence intensity at the same time to obtain real-time monitoring data of tryptophan fluorescence intensity; using a gradient lifter model to predict the carbon content concentration of dissolved organic matter in the agricultural wastewater based on the real-time monitoring data of tryptophan fluorescence intensity to obtain predicted data of carbon content concentration of dissolved organic matter in the agricultural wastewater; dynamically adjusting the critical value of carbon content concentration of dissolved organic matter according to the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter, and obtaining the separated agricultural wastewater according to the adjusted critical value.

[0007] In one implementation of the first aspect, obtaining monitoring sites includes: dividing agricultural catchment areas using a hydrological analysis process to obtain the flow direction of agricultural sewage ditches and sewage dumping points; and conducting on-site surveys and calibrations of the flow direction of the agricultural sewage ditches and the sewage dumping points to obtain the monitoring sites.

[0008] In one implementation of the first aspect, the training process of the gradient booster model includes: processing the sample dataset according to the carbon content concentration of the dissolved organic matter and the tryptophan fluorescence intensity; and training the gradient booster model based on the sample dataset to obtain the gradient booster model.

[0009] In one implementation of the first aspect, the process of using a gradient booster model to predict the carbon content concentration of dissolved organic matter in agricultural wastewater includes: using a gradient booster model to construct a mapping relationship between the tryptophan fluorescence intensity and the carbon content concentration of the dissolved organic matter.

[0010] In one implementation of the first aspect, the process of using the gradient booster model to make predictions to obtain predicted data on the carbon content concentration of dissolved organic matter in agricultural wastewater further includes: inputting the real-time monitoring data of tryptophan fluorescence intensity into the gradient booster model for prediction to obtain prediction results; and obtaining predicted data on the carbon content concentration of dissolved organic matter in the agricultural wastewater based on the prediction results.

[0011] In one implementation of the first aspect, the process of dynamically adjusting the critical value of the carbon content concentration of dissolved organic matter based on the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter includes: saving the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter to a time series database according to a time series; and dynamically adjusting the critical value of the carbon content concentration of dissolved organic matter based on the data in different time periods in the time series database.

[0012] In one implementation of the first aspect, the process of obtaining agricultural wastewater after separation and diversion includes: collecting agricultural wastewater in which the predicted carbon concentration of dissolved organic matter is greater than or equal to a critical value of the carbon concentration of dissolved organic matter; and discharging agricultural wastewater in which the predicted carbon concentration of dissolved organic matter is less than the critical value of the carbon concentration of dissolved organic matter.

[0013] Secondly, this application provides a monitoring and collection system for agricultural wastewater, comprising: a monitoring site acquisition module for acquiring monitoring sites; a data acquisition module for measuring the carbon content concentration of dissolved organic matter and the tryptophan fluorescence intensity at the monitoring sites; a data processing module for correspondingly labeling the carbon content concentration of dissolved organic matter and the tryptophan fluorescence intensity at the same time to obtain real-time monitoring data of tryptophan fluorescence intensity; a concentration prediction module for predicting the carbon content concentration of dissolved organic matter in agricultural wastewater using a gradient lifter model based on the real-time monitoring data of tryptophan fluorescence intensity; and a wastewater diversion module for dynamically adjusting the critical value of the carbon content concentration of dissolved organic matter according to the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of the carbon content concentration of dissolved organic matter, and obtaining the diverted agricultural wastewater according to the adjusted critical value.

[0014] Thirdly, this application provides an electronic device, the electronic device comprising: a memory storing a computer program thereon; and a processor communicatively connected to the memory for executing the computer program to implement the above-described method for monitoring and collecting agricultural wastewater.

[0015] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the above-described method for monitoring and collecting agricultural wastewater.

[0016] As described above, the monitoring and collection method, system, medium, and electronic equipment for agricultural wastewater described in this application have the following beneficial effects:

[0017] The agricultural wastewater monitoring and collection method provided in this application can measure the tryptophan fluorescence intensity at monitoring sites in real time, and correlate the carbon concentration of dissolved organic matter with the tryptophan fluorescence intensity at the same time. Based on the real-time monitoring data of tryptophan fluorescence intensity, a gradient lifter model is used to predict the carbon concentration of dissolved organic matter. The critical value of the carbon concentration of dissolved organic matter is dynamically adjusted by combining the real-time monitoring data and the prediction results of the gradient lifter model to achieve separation and diversion of pollutants. By using tryptophan as the monitoring target and the gradient lifter model to dynamically adjust the critical value of the carbon concentration of dissolved organic matter, highly polluted agricultural wastewater can be intercepted. This achieves efficient and accurate monitoring and separation of agricultural wastewater, thereby achieving the purpose of preliminary separation and centralized guidance of pollutants, optimizing the resource utilization of agricultural wastewater, and providing basic data support and sample guarantee for subsequent treatment processes or resource utilization. Attached Figure Description

[0018] Figure 1 The diagram shows an application scenario of the monitoring and collection method for agricultural wastewater described in this application embodiment.

[0019] Figure 2 The diagram shows a process schematic of the monitoring and collection method for agricultural wastewater as described in the embodiments of this application.

[0020] Figure 3 The diagram shown is a flowchart illustrating the method for monitoring and collecting agricultural wastewater as described in an embodiment of this application.

[0021] Figure 4 The diagram shown is a schematic representation of the test results of the gradient booster model described in the embodiments of this application.

[0022] Figure 5 The diagram shown is a structural schematic of the agricultural wastewater monitoring and collection system described in an embodiment of this application.

[0023] Figure 6 The diagram shown is a structural schematic of the fluorescence detection box described in an embodiment of this application.

[0024] Figure 7 The diagram shown is a structural schematic of the transition water tank described in an embodiment of this application.

[0025] Figure 8 The diagram shown is a structural schematic of the multi-element water storage tank described in an embodiment of this application.

[0026] Figure 9 The diagram shown is a structural schematic of the electronic device described in an embodiment of this application.

[0027] Component designation explanation

[0028] 11. Fluorescence Detection Box

[0029] 111 Water Quality Detection Fluorometer

[0030] 1111 Fluorescence Probe

[0031] 112 Slowing Board 1

[0032] 113 Fluorescence Detection Room

[0033] 12 Transition Water Tank

[0034] 121 Front lift-type water baffle

[0035] 1211 slow water outlet

[0036] 122 Rear lift-type water baffle

[0037] 123 Water level detection lifting rod

[0038] 1231 Lifting Rope

[0039] 1232 Lifting Slide Rail

[0040] 124 booster pump

[0041] 1241 Water Inlet Pipe

[0042] 125 lift

[0043] 13 Multi-element water storage tank

[0044] 131 Solar Panel

[0045] 134 Slowing Board

[0046] 135 External water treatment equipment

[0047] 100 Agricultural wastewater monitoring and collection system

[0048] 101 Monitoring Site Acquisition Module

[0049] 102 Data Acquisition Module

[0050] 103 Data Processing Module

[0051] 104 Concentration Prediction Module

[0052] 105 Wastewater Diversion Module

[0053] 2 Electronic devices

[0054] 21. Memory

[0055] 22 processors

[0056] 23 Monitors

[0057] Steps S11 to S15 Detailed Implementation

[0058] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0059] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0060] While agricultural production activities promote increased grain yields and rural economic development, they inevitably lead to agricultural non-point source pollution. Agricultural wastewater mainly originates from fertilizer application, pesticide spraying, livestock and poultry breeding wastewater, and irrigation runoff during agricultural production. It typically contains pollutants such as nitrogen, phosphorus, pesticide residues, organic matter, and pathogenic microorganisms. Therefore, high-concentration wastewater in agricultural drainage ditches has become a significant factor affecting the quality of surface water and groundwater.

[0061] Compared to industrial and urban wastewater, agricultural wastewater is characterized by its dispersed discharge, significant spatial and temporal variations, complex composition, and susceptibility to climate influences. Therefore, the monitoring and collection of agricultural wastewater presents different technical challenges than point source pollution. Existing traditional water quality monitoring methods typically rely on fixed testing standards and chemical reagents, resulting in long testing cycles, slow response times, and high costs, making it difficult to effectively monitor and collect high-concentration agricultural wastewater in real time.

[0062] Some technical solutions employ sampling devices for agricultural non-point source pollution monitoring to collect water samples at different heights, but these cannot achieve real-time on-site monitoring of water samples, resulting in poor data timeliness and high labor costs. Other technical solutions use portable sensors or water quality analysis instruments to automatically detect multiple pollutants in agricultural wastewater, but these cannot achieve branching, diversion, and efficient collection of highly polluted agricultural wastewater, and the phenomenon of high-concentration wastewater from agricultural drainage ditches being directly discharged into nearby rivers still exists.

[0063] Meanwhile, agricultural wastewater collection systems also face numerous technical bottlenecks. Traditional drainage ditches and underground pipe systems are primarily designed for drainage, lacking effective pollutant interception and monitoring capabilities. In recent years, although agricultural non-point source pollution control measures such as constructed wetlands, ecological ditches, and drainage storage ponds have emerged, these methods are typically aimed at remediation and have not yet formed an efficient and coordinated wastewater collection and real-time monitoring system. At least to address the above problems, the following embodiments of this application provide a method for monitoring and collecting agricultural wastewater.

[0064] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0065] Figure 1 This diagram illustrates an application scenario according to an embodiment of this application. For example... Figure 1 As shown, an agricultural wastewater monitoring device and an agricultural wastewater collection device are installed at the agricultural drainage ditch. The agricultural wastewater monitoring device includes a fluorescence detection box 11, a transition water tank 12, and a multi-element water storage tank 13, arranged along the water flow direction. The fluorescence detection box 11 contains a water quality fluorometer 111. The transition water tank 12 includes a front lifting baffle 121, a rear lifting baffle 122, a water level detection lifting rod 123, a booster pump 124, and a lift 125. The booster pump 124 contains an inlet pipe 1241. The multi-element water storage tank 13 includes a solar panel 131 and a battery 132. The water level detection lifting rod 123 is connected to the lift 125 via a lifting rope 1231. The battery 132 is connected to the multi-element water storage tank 13 via a wire 1321, and the booster pump 124 is connected to the lift 125 via a wire 1321. The fluorescent detection box monitors pollutants in agricultural wastewater in real time, and sends the real-time monitoring data to the cloud data system for processing and analysis. Based on the analysis results, the cloud data system sends signals to the agricultural wastewater collection device to collect and discharge the agricultural wastewater.

[0066] Figure 2 This diagram illustrates a process for monitoring and collecting agricultural wastewater according to an embodiment of this application. Figure 2 As shown, the method for monitoring and collecting agricultural wastewater includes the following steps S11 to S15:

[0067] Step S11: Obtain monitoring sites. Monitoring sites can represent the water quality status of the entire wastewater basin or a specific area. Monitoring sites are located at the main channels or collection points of wastewater flow, in relatively safe locations, and in areas where water quality changes are relatively stable.

[0068] Step S12: Measure the carbon concentration of dissolved organic matter and the fluorescence intensity of tryptophan at the monitoring site.

[0069] Dissolved organic carbon (DOC) is the carbon content of organic matter dissolved in water. The concentration of DOC reflects the amount of organic matter in water, thus assessing the degree of organic pollution in the water body.

[0070] Tryptophan fluorescence intensity refers to the fluorescence intensity emitted by amino acids such as tryptophan after being irradiated with excitation light under specific conditions. Monitoring tryptophan fluorescence intensity can be used to assess the content and properties of dissolved organic matter in agricultural wastewater.

[0071] Specifically, the fluorescence signal of tryptophan in agricultural wastewater is collected in real time using a fluorescence sensor.

[0072] Step S13: The carbon content concentration of dissolved organic matter and the fluorescence intensity of tryptophan at the same time are marked accordingly to obtain real-time monitoring data of tryptophan fluorescence intensity.

[0073] There is a certain correlation between tryptophan fluorescence intensity and DOC concentration; as DOC concentration increases, tryptophan fluorescence intensity also increases accordingly. By labeling the carbon content concentration of dissolved organic matter and the tryptophan fluorescence intensity at the same time point, and monitoring the tryptophan fluorescence intensity in real time, we can further understand the changes in DOC concentration in wastewater.

[0074] Step S14: Based on the real-time monitoring data of tryptophan fluorescence intensity, a gradient booster model is used to make predictions to obtain predicted data on the carbon content concentration of dissolved organic matter in agricultural wastewater.

[0075] By using the Gradient Boosting Machine (GBM) machine learning algorithm, a predictive model between tryptophan fluorescence intensity and DOC concentration is established. Based on real-time monitoring data of tryptophan fluorescence intensity, the DOC concentration is calculated using the predictive model, enabling real-time monitoring and early warning of agricultural wastewater discharge.

[0076] Step S15: Based on the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of dissolved organic matter carbon concentration, the critical value of dissolved organic matter carbon concentration is dynamically adjusted, and the agricultural wastewater after separation and diversion is obtained based on the adjusted critical value. Dynamically adjusting the DOC critical value based on the prediction results of the gradient lift model allows for the interception of highly polluted agricultural wastewater, optimizing the treatment effect of agricultural wastewater.

[0077] As described above, the agricultural wastewater monitoring and collection method provided in this application can measure the tryptophan fluorescence intensity at monitoring sites in real time, and correlate the carbon concentration of dissolved organic matter with the tryptophan fluorescence intensity at the same time. Based on the real-time monitoring data of tryptophan fluorescence intensity, a gradient lifter model is used to predict the carbon concentration of dissolved organic matter. The critical value of the carbon concentration of dissolved organic matter is dynamically adjusted through real-time monitoring data and the prediction results of the gradient lifter model to achieve separation of pollutants. By using tryptophan as the monitoring target and utilizing the prediction of the gradient lifter model to dynamically adjust the critical value of the carbon concentration of dissolved organic matter, highly polluted agricultural wastewater can be intercepted, achieving efficient and accurate monitoring of agricultural wastewater and optimizing the resource utilization of agricultural wastewater.

[0078] In one embodiment of this application, obtaining the monitoring site includes the following steps S21 to S22:

[0079] Step S21: Use hydrological analysis to divide the agricultural catchment area to obtain the flow direction of agricultural sewage ditches and sewage dumping points.

[0080] Specifically, hydrological analysis processes such as flow direction analysis, alluvial deposition analysis, and river network extraction in Geographic Information System (GIS) are used to delineate topographically based agricultural catchment areas, and the flow direction of agricultural sewage ditches and sewage dumping points are determined by analyzing the river network and catchment area boundaries.

[0081] Step S22: Conduct a site survey and calibration of the flow direction of the agricultural sewage ditch and the sewage dumping point to obtain the monitoring sites.

[0082] Specifically, based on the predicted approximate range of the flow direction of the above-mentioned agricultural sewage drainage ditches and the sewage dumping points, on-site surveys and calibrations are conducted to determine the outlet of the agricultural pollution source. The outlet of the agricultural pollution source is the monitoring site.

[0083] In one embodiment of this application, the training process of the gradient boosting machine model includes the following steps S31 to S32:

[0084] Step S31: Process the sample dataset according to the carbon content concentration of the dissolved organic matter and the fluorescence intensity of tryptophan.

[0085] Specifically, a subset of samples was randomly selected based on data on tryptophan fluorescence intensity and dissolved organic carbon concentration in agricultural wastewater, and this sample data was used as the training dataset. This training dataset includes samples of water quality and pollution levels from various agricultural sources within the study area.

[0086] Step S32: Train the gradient booster model based on the sample dataset to obtain the gradient booster model.

[0087] Specifically, the gradient boosting machine model is trained using a training dataset. The predictive ability of the model is optimized through the gradient boosting algorithm, and the model's hyperparameters are used for learning. Errors are reduced by iteratively learning each decision tree to obtain the optimal gradient boosting machine model. The model's hyperparameters include the number of decision trees, the maximum depth of the decision trees, and the learning rate.

[0088] In one embodiment of this application, the process of using a gradient booster model to predict the carbon content concentration of dissolved organic matter in agricultural wastewater includes: using a gradient booster model to construct a mapping relationship between the tryptophan fluorescence intensity and the carbon content concentration of dissolved organic matter.

[0089] Specifically, during the gradient booster training process, the mapping relationship between tryptophan fluorescence intensity and dissolved organic matter carbon concentration is established through iterative learning of hyperparameter tuning for each decision tree.

[0090] Furthermore, the process of training the gradient boosting machine model based on the sample dataset includes the following steps S321 to S322:

[0091] Step S321: Obtain the optimal splitting features and the optimal splitting point.

[0092] Specifically, the sample dataset is used as input features for data segmentation to construct a decision tree. At each node, some features are randomly selected, the split gain of each feature is calculated, the feature with the largest split gain is taken as the best split feature, and its corresponding split point is taken as the best split point.

[0093] Step S322: Perform recursive splitting based on the optimal splitting features and the optimal splitting points to obtain a decision tree.

[0094] Specifically, based on the best splitting features and the best splitting point, the above splitting operation is continued for each child node until the stopping condition is met, thereby obtaining the decision tree after recursive splitting.

[0095] For example, stopping conditions include the maximum depth of the decision tree, the minimum number of samples in a leaf node, and a split gain less than a preset threshold.

[0096] By constructing a decision tree, the gradient booster model can obtain the correlation between tryptophan fluorescence intensity and the carbon content concentration of dissolved organic matter. Overfitting can be effectively avoided through random feature selection and recursive node splitting, further improving the model's generalization ability.

[0097] Furthermore, the monitoring and collection method for agricultural wastewater also includes evaluating a gradient booster model. The evaluation process for the gradient booster model includes: obtaining a test dataset, which is derived from the original agricultural wastewater sample data; and based on the test dataset, evaluating the gradient booster model using the root mean square error (RMSE) and the coefficient of determination (R²). 2 The prediction accuracy and generalization ability of the gradient booster model were verified. The prediction error for the carbon concentration of dissolved organic matter was determined using the root mean square error (RMSE); a smaller RMS error indicates better prediction performance of the gradient booster model. The goodness of fit of the gradient booster model was determined using the coefficient of determination (COD), which ranges from 0 to 1; a COD closer to 1 indicates a better fit.

[0098] In some embodiments, a prediction model is established using a gradient booster based on real-time monitoring data of tryptophan fluorescence intensity, and a model is constructed to establish the relationship between tryptophan fluorescence intensity and dissolved organic matter carbon concentration in agricultural wastewater. The process is as follows: data on tryptophan fluorescence intensity and dissolved organic matter carbon concentration are obtained from agricultural wastewater, and sample data containing water quality and pollution levels of various agricultural sources in the study area are randomly selected from these two data as training datasets. The gradient booster model is trained using 60 sets of selected training datasets, and the trained gradient booster model is tested and verified using 20 sets of new agricultural wastewater sample data, thereby ensuring that the gradient booster model establishes an effective mapping relationship between tryptophan fluorescence intensity and dissolved organic matter carbon concentration.

[0099] In one embodiment of this application, the process of using the gradient booster model to make predictions to obtain predicted data on the carbon content concentration of dissolved organic matter in agricultural wastewater further includes the following steps S41 to S42:

[0100] Step S41: Input the real-time monitoring data of tryptophan fluorescence intensity into the gradient booster model for prediction to obtain the prediction result.

[0101] Specifically, each decision tree independently predicts the real-time monitoring data of tryptophan fluorescence intensity and outputs an estimated value of the carbon content concentration of dissolved organic matter. Each decision tree produces different prediction results due to randomly selected features and node splitting.

[0102] Step S42: Obtain the predicted carbon content concentration data of dissolved organic matter in the agricultural wastewater based on the prediction results.

[0103] Specifically, a weighted average is applied to the prediction results of different decision trees to output the final predicted value of DOC concentration and the predicted data of carbon content in dissolved organic matter in agricultural wastewater.

[0104] In one embodiment of this application, the process of dynamically adjusting the critical value of the carbon content concentration of dissolved organic matter based on the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter includes the following steps S51 to S52:

[0105] Step S51: Save the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter into a time series database according to the time series.

[0106] Step S52: Dynamically adjust the critical value of the carbon content concentration of the dissolved organic matter based on data from different time periods in the time series database.

[0107] In one embodiment of this application, agricultural wastewater is separated and diverted in real time according to a critical value of the dissolved organic matter carbon concentration. The process of obtaining the separated agricultural wastewater includes: collecting agricultural wastewater with a predicted dissolved organic matter carbon concentration greater than or equal to the critical value; and discharging agricultural wastewater with a predicted dissolved organic matter carbon concentration less than the critical value. By collecting agricultural wastewater with a dissolved organic matter carbon concentration greater than or equal to the critical value and discharging agricultural wastewater with a concentration less than the critical value, the separation and diversion of agricultural wastewater is achieved.

[0108] The following section will provide a detailed description of the agricultural wastewater monitoring and collection method provided in this application through a specific example. It should be noted that the content of this example is only for explaining and illustrating the agricultural wastewater monitoring and collection method provided in this application, and is not intended to limit the scope of protection of this application in any way. In specific applications, appropriate steps can be added or deleted based on this example according to actual needs. Figure 3 This is a flowchart illustrating the monitoring and collection method for agricultural wastewater in this example. Figure 3 As shown, the monitoring and collection method for agricultural wastewater in this example includes the following steps.

[0109] Step 1: Identify monitoring points that reflect agricultural non-point source pollution and effectively detect the DOC concentration and tryptophan fluorescence intensity of agricultural wastewater. Using ArcGIS software, a hydrological analysis process is employed to delineate topographically based agricultural catchment areas, determine the flow direction of agricultural wastewater ditches, and identify wastewater discharge points. Subsequently, based on the approximate range predicted by water level analysis, on-site surveys and calibrations are conducted at the wastewater ditch locations to determine the outlets of agricultural pollution sources.

[0110] Step 2: Data acquisition. Measure the DOC concentration and tryptophan fluorescence intensity at the monitoring points. Use the DOC concentration and tryptophan fluorescence intensity data as the training and testing datasets for the gradient booster model prediction.

[0111] Step 3: Data processing. The DOC concentration and tryptophan fluorescence intensity values ​​at the same time are marked accordingly and used as input features into the gradient booster model for prediction.

[0112] Step 4: Based on real-time monitoring data of tryptophan fluorescence intensity, a prediction model was established using a gradient booster (GBM) to model the relationship between tryptophan fluorescence intensity and DOC concentration in agricultural wastewater. A subset of sample data was randomly selected from the tryptophan fluorescence intensity and DOC concentration data in agricultural wastewater as the training set to ensure representativeness and diversity. This dataset includes samples of water quality and pollution levels from various agricultural sources within the study area, ensuring broad adaptability of the model. Subsequently, the gradient booster model was trained using the selected training dataset (60 sets), and tested using 20 sets of data. The test results are shown below. Figure 4 As shown, the results indicate that the gradient booster model performs well and can effectively establish the mapping relationship between tryptophan fluorescence intensity and DOC concentration.

[0113] Step 5: Use a gradient boosting machine model to predict the DOC concentration in agricultural wastewater in real time. Input the real-time monitored tryptophan fluorescence intensity data into the trained gradient boosting machine model, and calculate the DOC concentration in agricultural wastewater in real time based on the prediction results.

[0114] Step 6: Dynamically adjust the DOC threshold. Real-time monitored tryptophan fluorescence intensity data and predicted DOC concentration data are saved to a time-series database, and data statistics are performed. The threshold is then dynamically adjusted based on data from different time periods.

[0115] Step 7: Feedback the DOC threshold value to the agricultural wastewater collection equipment to perform real-time branching and diversion of agricultural wastewater. Agricultural wastewater with a predicted DOC concentration value ≥ the DOC threshold value is collected and then treated, while agricultural wastewater with a predicted DOC concentration value < the DOC threshold value is discharged.

[0116] In summary, the agricultural wastewater monitoring and collection method provided in this application can collect the fluorescence signal of tryptophan in agricultural wastewater in real time using a fluorescence sensor, and use a gradient lift model to predict the DOC concentration in agricultural wastewater in real time. The method dynamically adjusts the critical DOC concentration value to intercept highly polluted agricultural wastewater. Then, the high-DOC-concentration agricultural wastewater is automatically collected by equipment. This agricultural wastewater monitoring and collection method achieves efficient and accurate monitoring and management of agricultural wastewater, optimizing its resource utilization.

[0117] The scope of protection for the monitoring and collection method for agricultural wastewater described in this application is not limited to the order of steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0118] This application also provides an agricultural wastewater monitoring and collection system, which can implement the agricultural wastewater monitoring and collection method described in this application. However, the implementation device of the agricultural wastewater monitoring and collection method described in this application includes, but is not limited to, the structure of the agricultural wastewater monitoring and collection system listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0119] Figure 5 The diagram shown is a structural schematic of an agricultural wastewater monitoring and collection system according to an embodiment of this application. Figure 5 As shown, the agricultural wastewater monitoring and collection system 100 includes: a monitoring site acquisition module 101, a data acquisition module 102, a data processing module 103, a concentration prediction module 104, and a wastewater diversion module 105. The monitoring site acquisition module 101 is used to acquire monitoring sites. The data acquisition module 102 is used to measure the carbon concentration of dissolved organic matter and the tryptophan fluorescence intensity at the monitoring sites. The data processing module 103 is used to mark the carbon concentration of dissolved organic matter and the tryptophan fluorescence intensity at the same time to obtain real-time monitoring data of tryptophan fluorescence intensity. The concentration prediction module 104 is used to predict the carbon concentration of dissolved organic matter in agricultural wastewater using a gradient lifter model based on the real-time monitoring data of tryptophan fluorescence intensity to obtain predicted data of carbon concentration of dissolved organic matter. The wastewater diversion module 105 is used to dynamically adjust the critical value of carbon concentration of dissolved organic matter according to the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon concentration of dissolved organic matter, and obtain the diverted agricultural wastewater according to the adjusted critical value.

[0120] It should be noted that, Figure 5 The modules in the agricultural wastewater monitoring and collection system 100 shown are related to... Figure 2 The steps in the method for monitoring and collecting agricultural wastewater correspond one-to-one, and will not be elaborated here.

[0121] In one embodiment of this application, the data acquisition module includes an initial detection unit and a real-time fluorescence detection unit. The initial detection unit is used to detect DOC concentration and tryptophan fluorescence intensity in water samples collected from agricultural wastewater monitoring points before equipment deployment, and uses the DOC concentration and tryptophan fluorescence intensity detection data as the proposed initial critical value and training dataset for the gradient booster model. Three days prior to equipment installation, agricultural wastewater samples from 80 different time points are collected and sampled for DOC concentration and tryptophan fluorescence intensity detection.

[0122] The real-time fluorescence detection unit is used to detect the fluorescence intensity of tryptophan using a portable water quality fluorometer, and uploads the tryptophan fluorescence intensity data from the detection results to the cloud data system in real time. The tryptophan fluorescence detection range is: excitation wavelength 260–290 nm, emission wavelength 320–380 nm.

[0123] In one embodiment of this application, the data processing module includes a historical data storage device and a threshold dynamic adjuster. The historical data storage device is used to store the predicted data of tryptophan fluorescence intensity and DOC concentration at corresponding times. The concentration prediction module predicts the carbon content concentration of dissolved organic matter at corresponding times using a gradient booster model and preprocessed real-time monitoring data of tryptophan fluorescence intensity, and saves the predicted carbon content concentration data of dissolved organic matter to the historical data storage device.

[0124] The threshold dynamic adjuster is used to dynamically adjust the threshold based on data in the historical data storage. The dynamic adjustment method uses the mean and standard deviation of a certain time period as the base values, and the threshold dynamic adjustment formula is as follows:

[0125]

[0126] in, The critical DOC concentration for time period a to b is expressed in mg / L. The predicted mean DOC concentration for time period a to b is given in mg / L. The standard deviation of DOC concentration is given for time period a to b, in mg / L.

[0127] In one embodiment of this application, the agricultural wastewater collection device is used to automatically separate and efficiently collect substandard wastewater in response to changes in the water quality of agricultural wastewater. Please refer to [link / reference]. Figure 6-8The agricultural wastewater collection equipment includes a fluorescent detection box 11, a transition water tank, and a multi-functional water storage tank, wherein the multi-functional water storage tank can be connected to external water treatment equipment for diversified integration.

[0128] Furthermore, the fluorescence detection box is used to house the water quality detection fluorometer 111 and the fluorescence probe 1111. The fluorescence detection chamber 113 and the slow-flow plate 112 can provide a darker working environment with a lower flow rate for fluorescence detection, thereby improving the accuracy of tryptophan fluorescence intensity detection.

[0129] Furthermore, the transition water tank 12 is positioned behind the fluorescence detection box 11, with a distance of 50cm between them. A water level detection lifting rod 123 is mounted on top of the transition water tank 12 for real-time water level monitoring. The water level detection lifting rod 123 is externally connected to a lifting rope 1231, which is driven by a lifting mechanism to raise the front lifting baffle 121 and the rear lifting baffle 122. Both the front lifting baffle 121 and the rear lifting baffle 122 are positioned on lifting slide rails 1232. The front lifting baffle 121 is equipped with several 5cm diameter slow-flow inlets 1211 to allow wastewater to enter the transition water tank 11 at a low flow rate.

[0130] Furthermore, the elevator is equipped with a built-in signal receiver to receive signals sent by the sewage diversion module in the cloud data system. Specifically, when the predicted DOC concentration is less than the critical DOC value, the elevator raises the water level detection lifting rod via a lifting rope. The water level detection lifting rod causes the front and rear lifting baffles to slide upwards on the lifting rail and remain at the top. At this time, the water flows downstream through the transition tank. Conversely, when the elevator is stopped, the front and rear lifting baffles slide downwards on the lifting rail under gravity and remain at the bottom. At this time, the water flows into the transition tank.

[0131] Furthermore, the water level detection lifting rod is equipped with a water level detector. When the wastewater level in the transition water tank reaches three-fifths of the height of the transition water tank, it is lifted to the multi-element water storage tank by a lift pump.

[0132] Furthermore, the multi-element water storage tank 13 is placed on the shore, with a solar panel 131 on top to power the battery. The battery powers the elevator and the lift pump. The upper part of the left frame is the water inlet, and the water outlet is located on the upper part of the right frame. The water outlet is lower than the water inlet, with a height difference of 10cm. The water outlet can be connected to an external water treatment device 135 to further utilize or treat high-concentration DOC wastewater from agricultural sewage. The water flow slowing plate is located in the middle area of ​​the multi-element water storage tank, with a length of three-fifths of the height of the multi-element water storage tank, to make the water flow gentle.

[0133] In some embodiments, the wastewater diversion module sends a collection signal to the agricultural wastewater collection equipment based on a critical value response mechanism to collect a portion of the wastewater in the agricultural wastewater with a DOC concentration value ≥ the critical value. When the predicted DOC concentration value in the agricultural wastewater is ≥ the critical value, the wastewater diversion module sends a termination signal to the elevator, i.e., the front and rear lifting baffles slide downwards on the lifting rails under gravity and remain at the bottom. At this time, the water flow converges into the transition tank. When the wastewater level in the transition tank reaches three-fifths of the tank's height, the lift pump starts working, lifting the wastewater in the transition tank to the multi-element storage tank. When the predicted DOC concentration value in the agricultural wastewater is < the DOC critical value, the wastewater diversion module sends a working signal to the elevator, i.e., the elevator raises the water level detection lifting rod via a lifting rope. The water level detection lifting rod drives the front and rear lifting baffles to slide upwards on the lifting rails and remain at the top. At this time, the water flow flows downstream through the transition tank.

[0134] In summary, the agricultural wastewater monitoring and collection system of this application combines real-time monitoring with wastewater collection, solving the problems of slow response, data dispersion, inaccurate pollutant identification, and limited collection methods in existing agricultural wastewater technologies, and achieving the following beneficial effects:

[0135] (1) By collecting the intensity of tryptophan fluorescence signals in wastewater in real time through a fluorescence sensor, and utilizing its correlation with dissolved organic matter (especially protein pollutants), it is possible to achieve rapid real-time perception and dynamic monitoring of pollutants without the need for complex chemical treatment, thereby improving the timeliness and sensitivity of pollutant concentration monitoring.

[0136] (2) The gradient booster model was used to train the nonlinear mapping relationship between tryptophan fluorescence signal and dissolved organic carbon (DOC) concentration in wastewater, overcoming the problem of insufficient applicability of traditional linear fitting model in complex agricultural wastewater system, realizing higher accuracy of pollutant concentration estimation, and providing a data basis for subsequent real-time updating of pollutant thresholds.

[0137] (3) Based on the monitoring results of pollutants in agricultural wastewater, the pollutant threshold linkage control is triggered, which guides the collection device to divert and collect wastewater with high pollution load in real time. This effectively prevents high concentrations of pollutants from spreading with runoff, improves the effect and efficiency of subsequent treatment or resource utilization, and has the synergistic benefits of pollution prevention and control and resource recovery.

[0138] (4) The modular design of the monitoring and collection system of this application is suitable for deployment in various application scenarios such as farmland drainage ditches, sewage outlets of breeding farms and agricultural irrigation return flow. It has the characteristics of easy on-site installation, low operation and maintenance costs and strong environmental adaptability. It can meet the management needs of diversified and non-standardized discharge of agricultural sewage, improve the level of information management, and respond to seasonal emission changes.

[0139] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0140] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0141] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0142] This application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, this computer program implements the agricultural wastewater monitoring and collection method provided in this application. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state hard disk, magnetic tape, floppy disk, optical disk, and any combination thereof. The above storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0143] This application embodiment may also provide an electronic device. Figure 9 The diagram shown is a structural schematic of electronic device 2 in one embodiment of this application. Figure 9 As shown, in this embodiment, the electronic device 2 includes a memory 21 and a processor 22.

[0144] The memory 21 is used to store computer programs. In some possible implementations, the memory 21 may include various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0145] In this embodiment, memory 21 may include a computer system readable medium in the form of volatile memory, such as RAM and / or cache memory. Electronic device 2 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 21 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0146] The processor 22 is connected to the memory 21 and is used to execute the computer program stored in the memory 21 so that the electronic device 2 performs the monitoring and collection method for agricultural wastewater.

[0147] For example, processor 22 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. In other embodiments, processor 22 may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0148] In some implementations, the electronic device 2 provided in this application embodiment may further include a display 23. The display 23 is communicatively connected to the memory 21 and the processor 22, and is used to display a graphical user interface (GUI) related to the monitoring and collection method of agricultural wastewater.

[0149] In this embodiment, the display 23 may include a display screen (display panel). In some implementations, the display panel may be configured using a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Alternatively, the display 23 may also be a touch panel (touchscreen, touch screen), which may include a display screen and a touch-sensitive surface. When the touch-sensitive surface detects a touch operation on or near it, it transmits the information to the processor 22 to determine the type of touch event. Subsequently, the processor 22 provides corresponding visual output on the display device based on the type of touch event.

[0150] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0151] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for monitoring and collecting agricultural wastewater, characterized in that, The methods for monitoring and collecting agricultural wastewater include: Obtain monitoring sites; The carbon concentration of dissolved organic matter and the tryptophan fluorescence intensity at the monitoring sites were measured. The carbon content concentration of dissolved organic matter and the fluorescence intensity of tryptophan at the same time point were labeled accordingly to obtain real-time monitoring data of tryptophan fluorescence intensity. Based on the real-time monitoring data of tryptophan fluorescence intensity, a gradient lifter model is used to make predictions to obtain predicted data on the carbon content concentration of dissolved organic matter in agricultural wastewater. The process of using a gradient booster model to predict the carbon content concentration of dissolved organic matter in agricultural wastewater includes: using a gradient booster model to construct a mapping relationship between the tryptophan fluorescence intensity and the carbon content concentration of dissolved organic matter; The critical value of the carbon content concentration of dissolved organic matter is dynamically adjusted based on the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter, and the agricultural wastewater after separation and diversion is obtained based on the adjusted critical value. The process of dynamically adjusting the critical value of the carbon content concentration of dissolved organic matter based on the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter includes: saving the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of carbon content concentration of dissolved organic matter to a time series database according to the time series; and dynamically adjusting the critical value of the carbon content concentration of dissolved organic matter based on the data in different time periods in the time series database. The formula for dynamically adjusting the critical value is as follows: in, The critical DOC concentration for time period a to b is expressed in mg / L. The predicted mean DOC concentration for time period a to b is given in mg / L. The standard deviation of DOC concentration is given for time period a to b, in mg / L.

2. The method for monitoring and collecting agricultural wastewater according to claim 1, characterized in that, The monitoring sites obtained include: The agricultural catchment area is divided using a hydrological analysis process to obtain the flow direction of agricultural sewage ditches and sewage dumping points; the flow direction of the agricultural sewage ditches and the sewage dumping points are then surveyed and calibrated to obtain the monitoring sites.

3. The method for monitoring and collecting agricultural wastewater according to claim 1, characterized in that, The training process of the gradient boosting machine model includes: The sample dataset is obtained by processing the dissolved organic matter's carbon content concentration and the tryptophan fluorescence intensity; the gradient booster model is trained based on the sample dataset to obtain the gradient booster model.

4. The method for monitoring and collecting agricultural wastewater according to claim 1, characterized in that, The process of using the gradient booster model to predict the carbon concentration of dissolved organic matter in agricultural wastewater further includes: The real-time monitoring data of tryptophan fluorescence intensity is input into the gradient booster model for prediction to obtain the prediction results. Based on the prediction results, the predicted carbon content concentration of dissolved organic matter in the agricultural wastewater is obtained.

5. The method for monitoring and collecting agricultural wastewater according to claim 1, characterized in that, The process of obtaining the separated agricultural wastewater based on the adjusted critical value includes: Agricultural wastewater with a predicted carbon concentration of dissolved organic matter that is greater than or equal to the critical value of the carbon concentration of dissolved organic matter is collected. Agricultural wastewater that is predicted to have a carbon concentration of dissolved organic matter that is less than the critical value of the carbon concentration of dissolved organic matter is discharged.

6. A monitoring and collection system for agricultural wastewater, configured to perform the method according to any one of claims 1 to 5, characterized in that, The monitoring and collection system for agricultural wastewater includes: The monitoring site acquisition module is used to acquire monitoring sites; The data acquisition module is used to measure the carbon concentration of dissolved organic matter and the fluorescence intensity of tryptophan at the monitoring site; The data processing module is used to label the carbon content concentration of dissolved organic matter and the fluorescence intensity of tryptophan at the same time to obtain real-time monitoring data of tryptophan fluorescence intensity. The concentration prediction module is used to predict the carbon content concentration of dissolved organic matter in agricultural wastewater by using a gradient booster model based on the real-time monitoring data of tryptophan fluorescence intensity. The process of using the gradient booster model to predict the carbon content concentration of dissolved organic matter in agricultural wastewater includes: using the gradient booster model to construct a mapping relationship between the tryptophan fluorescence intensity and the carbon content concentration of dissolved organic matter. The wastewater diversion module is used to dynamically adjust the critical value of dissolved organic matter carbon concentration based on real-time monitoring data of tryptophan fluorescence intensity and predicted data of dissolved organic matter carbon concentration, and to obtain the agricultural wastewater after diversion based on the adjusted critical value. The process of dynamically adjusting the critical value of dissolved organic matter carbon concentration based on real-time monitoring data of tryptophan fluorescence intensity and predicted data of dissolved organic matter carbon concentration includes: saving the real-time monitoring data of tryptophan fluorescence intensity and the predicted data of dissolved organic matter carbon concentration to a time series database according to a time series; and dynamically adjusting the critical value of dissolved organic matter carbon concentration based on data from different time periods in the time series database. The formula for dynamically adjusting the critical value is as follows: in, The critical DOC concentration for time period a to b is expressed in mg / L. The predicted mean DOC concentration for time period a to b is given in mg / L. The standard deviation of DOC concentration is given for time period a to b, in mg / L.

7. An electronic device, characterized in that, The electronic device includes: A memory on which computer programs are stored; A processor, communicatively connected to the memory, is used to execute the computer program to implement the method for monitoring and collecting agricultural wastewater according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by an electronic device, the program implements the method for monitoring and collecting agricultural wastewater as described in any one of claims 1 to 5.

Images